{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 1. KBO 타자 OPS 예측\n",
    "## 1.2. 탐색적 데이터 분석"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 필요 라이브러리 로드\n",
    "from matplotlib import font_manager, rc\n",
    "import matplotlib\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import platform\n",
    "\n",
    "if platform.system() == 'Windows': # 윈도우인 경우 맑은 고딕 폰트 이용\n",
    "    font_name = font_manager.FontProperties(fname=\"c:/Windows/Fonts/malgun.ttf\").get_name()\n",
    "    rc('font', family=font_name)\n",
    "else: # Mac 인 경우   \n",
    "    rc('font', family='AppleGothic')\n",
    "\n",
    "#그래프에서 마이너스 기호가 표시되게 하는 설정입니다.\n",
    "matplotlib.rcParams['axes.unicode_minus'] = False"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1.2.1. 프리시즌 데이터 분석"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1393, 29)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_id</th>\n",
       "      <th>batter_name</th>\n",
       "      <th>year</th>\n",
       "      <th>team</th>\n",
       "      <th>avg</th>\n",
       "      <th>G</th>\n",
       "      <th>AB</th>\n",
       "      <th>R</th>\n",
       "      <th>H</th>\n",
       "      <th>2B</th>\n",
       "      <th>...</th>\n",
       "      <th>GDP</th>\n",
       "      <th>SLG</th>\n",
       "      <th>OBP</th>\n",
       "      <th>E</th>\n",
       "      <th>height/weight</th>\n",
       "      <th>year_born</th>\n",
       "      <th>position</th>\n",
       "      <th>career</th>\n",
       "      <th>starting_salary</th>\n",
       "      <th>OPS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>가르시아</td>\n",
       "      <td>2018</td>\n",
       "      <td>LG</td>\n",
       "      <td>0.350</td>\n",
       "      <td>7</td>\n",
       "      <td>20</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0.550</td>\n",
       "      <td>0.409</td>\n",
       "      <td>1</td>\n",
       "      <td>177cm/93kg</td>\n",
       "      <td>1985년 04월 12일</td>\n",
       "      <td>내야수(우투우타)</td>\n",
       "      <td>쿠바 Ciego de Avila Maximo Gomez Baez(대)</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.959</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2011</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.000</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.500</td>\n",
       "      <td>0</td>\n",
       "      <td>180cm/72kg</td>\n",
       "      <td>1992년 08월 11일</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000만원</td>\n",
       "      <td>0.500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2014</td>\n",
       "      <td>한화</td>\n",
       "      <td>-</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>180cm/72kg</td>\n",
       "      <td>1992년 08월 11일</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000만원</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2015</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.130</td>\n",
       "      <td>10</td>\n",
       "      <td>23</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.130</td>\n",
       "      <td>0.286</td>\n",
       "      <td>2</td>\n",
       "      <td>180cm/72kg</td>\n",
       "      <td>1992년 08월 11일</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000만원</td>\n",
       "      <td>0.416</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2016</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.188</td>\n",
       "      <td>14</td>\n",
       "      <td>32</td>\n",
       "      <td>4</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.281</td>\n",
       "      <td>0.212</td>\n",
       "      <td>0</td>\n",
       "      <td>180cm/72kg</td>\n",
       "      <td>1992년 08월 11일</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000만원</td>\n",
       "      <td>0.493</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 29 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   batter_id batter_name  year team    avg   G  AB  R  H  2B  ...  GDP    SLG  \\\n",
       "0          0        가르시아  2018   LG  0.350   7  20  1  7   1  ...    1  0.550   \n",
       "1          1         강경학  2011   한화  0.000   4   2  2  0   0  ...    0  0.000   \n",
       "2          1         강경학  2014   한화      -   4   0  2  0   0  ...    0    NaN   \n",
       "3          1         강경학  2015   한화  0.130  10  23  3  3   0  ...    0  0.130   \n",
       "4          1         강경학  2016   한화  0.188  14  32  4  6   1  ...    0  0.281   \n",
       "\n",
       "     OBP  E  height/weight      year_born   position  \\\n",
       "0  0.409  1     177cm/93kg  1985년 04월 12일  내야수(우투우타)   \n",
       "1  0.500  0     180cm/72kg  1992년 08월 11일  내야수(우투좌타)   \n",
       "2    NaN  0     180cm/72kg  1992년 08월 11일  내야수(우투좌타)   \n",
       "3  0.286  2     180cm/72kg  1992년 08월 11일  내야수(우투좌타)   \n",
       "4  0.212  0     180cm/72kg  1992년 08월 11일  내야수(우투좌타)   \n",
       "\n",
       "                                   career  starting_salary    OPS  \n",
       "0  쿠바 Ciego de Avila Maximo Gomez Baez(대)              NaN  0.959  \n",
       "1                       광주대성초-광주동성중-광주동성고          10000만원  0.500  \n",
       "2                       광주대성초-광주동성중-광주동성고          10000만원    NaN  \n",
       "3                       광주대성초-광주동성중-광주동성고          10000만원  0.416  \n",
       "4                       광주대성초-광주동성중-광주동성고          10000만원  0.493  \n",
       "\n",
       "[5 rows x 29 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 프리시즌 데이터 로드\n",
    "preseason_df = pd.read_csv(\"./input/Pre_Season_Batter.csv\")\n",
    "# 정규시즌 데이터 로드\n",
    "regular_season_df = pd.read_csv(\"./input/Regular_Season_Batter.csv\")\n",
    "# 데이터 크기 확인\n",
    "print(preseason_df.shape)\n",
    "# 데이터 상단 출력\n",
    "display(preseason_df.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_id</th>\n",
       "      <th>year</th>\n",
       "      <th>G</th>\n",
       "      <th>AB</th>\n",
       "      <th>R</th>\n",
       "      <th>H</th>\n",
       "      <th>2B</th>\n",
       "      <th>3B</th>\n",
       "      <th>HR</th>\n",
       "      <th>TB</th>\n",
       "      <th>...</th>\n",
       "      <th>SB</th>\n",
       "      <th>CS</th>\n",
       "      <th>BB</th>\n",
       "      <th>HBP</th>\n",
       "      <th>SO</th>\n",
       "      <th>GDP</th>\n",
       "      <th>SLG</th>\n",
       "      <th>OBP</th>\n",
       "      <th>E</th>\n",
       "      <th>OPS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1393.000000</td>\n",
       "      <td>1393.000000</td>\n",
       "      <td>1393.000000</td>\n",
       "      <td>1393.000000</td>\n",
       "      <td>1393.000000</td>\n",
       "      <td>1393.000000</td>\n",
       "      <td>1393.000000</td>\n",
       "      <td>1393.000000</td>\n",
       "      <td>1393.000000</td>\n",
       "      <td>1393.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1393.000000</td>\n",
       "      <td>1393.000000</td>\n",
       "      <td>1393.000000</td>\n",
       "      <td>1393.000000</td>\n",
       "      <td>1393.000000</td>\n",
       "      <td>1393.000000</td>\n",
       "      <td>1364.000000</td>\n",
       "      <td>1368.000000</td>\n",
       "      <td>1393.000000</td>\n",
       "      <td>1364.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>173.434314</td>\n",
       "      <td>2013.014358</td>\n",
       "      <td>8.705671</td>\n",
       "      <td>19.201723</td>\n",
       "      <td>2.679828</td>\n",
       "      <td>5.021536</td>\n",
       "      <td>0.954774</td>\n",
       "      <td>0.119885</td>\n",
       "      <td>0.391960</td>\n",
       "      <td>7.391960</td>\n",
       "      <td>...</td>\n",
       "      <td>0.629576</td>\n",
       "      <td>0.291457</td>\n",
       "      <td>1.877961</td>\n",
       "      <td>0.330223</td>\n",
       "      <td>3.714286</td>\n",
       "      <td>0.447236</td>\n",
       "      <td>0.361012</td>\n",
       "      <td>0.317912</td>\n",
       "      <td>0.381910</td>\n",
       "      <td>0.676924</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>94.716851</td>\n",
       "      <td>4.166757</td>\n",
       "      <td>5.562686</td>\n",
       "      <td>13.395946</td>\n",
       "      <td>2.637212</td>\n",
       "      <td>4.232584</td>\n",
       "      <td>1.196904</td>\n",
       "      <td>0.379976</td>\n",
       "      <td>0.748557</td>\n",
       "      <td>6.538787</td>\n",
       "      <td>...</td>\n",
       "      <td>1.146854</td>\n",
       "      <td>0.595522</td>\n",
       "      <td>2.053392</td>\n",
       "      <td>0.642204</td>\n",
       "      <td>3.180884</td>\n",
       "      <td>0.723364</td>\n",
       "      <td>0.269892</td>\n",
       "      <td>0.151489</td>\n",
       "      <td>0.729521</td>\n",
       "      <td>0.386933</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>2002.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>99.000000</td>\n",
       "      <td>2010.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>9.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.217000</td>\n",
       "      <td>0.250000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.472000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>178.000000</td>\n",
       "      <td>2014.000000</td>\n",
       "      <td>9.000000</td>\n",
       "      <td>18.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.344500</td>\n",
       "      <td>0.333000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.675000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>254.000000</td>\n",
       "      <td>2017.000000</td>\n",
       "      <td>11.000000</td>\n",
       "      <td>28.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>11.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.478000</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.867000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>344.000000</td>\n",
       "      <td>2018.000000</td>\n",
       "      <td>119.000000</td>\n",
       "      <td>183.000000</td>\n",
       "      <td>35.000000</td>\n",
       "      <td>51.000000</td>\n",
       "      <td>11.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>68.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>9.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>21.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>36.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>5.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 21 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         batter_id         year            G           AB            R  \\\n",
       "count  1393.000000  1393.000000  1393.000000  1393.000000  1393.000000   \n",
       "mean    173.434314  2013.014358     8.705671    19.201723     2.679828   \n",
       "std      94.716851     4.166757     5.562686    13.395946     2.637212   \n",
       "min       0.000000  2002.000000     1.000000     0.000000     0.000000   \n",
       "25%      99.000000  2010.000000     6.000000     9.000000     1.000000   \n",
       "50%     178.000000  2014.000000     9.000000    18.000000     2.000000   \n",
       "75%     254.000000  2017.000000    11.000000    28.000000     4.000000   \n",
       "max     344.000000  2018.000000   119.000000   183.000000    35.000000   \n",
       "\n",
       "                 H           2B           3B           HR           TB  ...  \\\n",
       "count  1393.000000  1393.000000  1393.000000  1393.000000  1393.000000  ...   \n",
       "mean      5.021536     0.954774     0.119885     0.391960     7.391960  ...   \n",
       "std       4.232584     1.196904     0.379976     0.748557     6.538787  ...   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000  ...   \n",
       "25%       2.000000     0.000000     0.000000     0.000000     2.000000  ...   \n",
       "50%       4.000000     1.000000     0.000000     0.000000     6.000000  ...   \n",
       "75%       8.000000     2.000000     0.000000     1.000000    11.000000  ...   \n",
       "max      51.000000    11.000000     4.000000     5.000000    68.000000  ...   \n",
       "\n",
       "                SB           CS           BB          HBP           SO  \\\n",
       "count  1393.000000  1393.000000  1393.000000  1393.000000  1393.000000   \n",
       "mean      0.629576     0.291457     1.877961     0.330223     3.714286   \n",
       "std       1.146854     0.595522     2.053392     0.642204     3.180884   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "25%       0.000000     0.000000     0.000000     0.000000     1.000000   \n",
       "50%       0.000000     0.000000     1.000000     0.000000     3.000000   \n",
       "75%       1.000000     0.000000     3.000000     1.000000     5.000000   \n",
       "max       9.000000     4.000000    21.000000     4.000000    36.000000   \n",
       "\n",
       "               GDP          SLG          OBP            E          OPS  \n",
       "count  1393.000000  1364.000000  1368.000000  1393.000000  1364.000000  \n",
       "mean      0.447236     0.361012     0.317912     0.381910     0.676924  \n",
       "std       0.723364     0.269892     0.151489     0.729521     0.386933  \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000  \n",
       "25%       0.000000     0.217000     0.250000     0.000000     0.472000  \n",
       "50%       0.000000     0.344500     0.333000     0.000000     0.675000  \n",
       "75%       1.000000     0.478000     0.400000     1.000000     0.867000  \n",
       "max       5.000000     4.000000     1.000000     5.000000     5.000000  \n",
       "\n",
       "[8 rows x 21 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 데이터 기초통계량 확인\n",
    "display(preseason_df.describe())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "ename": "AttributeError",
     "evalue": "'AxesSubplot' object has no attribute 'rowNum'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "\u001b[1;32m~\\AppData\\Local\\Temp\\ipykernel_4060\\1923514572.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[1;31m# 데이터 시각화\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[0mpreseason_df\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mhist\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfigsize\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m10\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;36m9\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      3\u001b[0m \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtight_layout\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;31m# 그래프 간격 설정\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      4\u001b[0m \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshow\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\pandas\\plotting\\_core.py\u001b[0m in \u001b[0;36mhist_frame\u001b[1;34m(data, column, by, grid, xlabelsize, xrot, ylabelsize, yrot, ax, sharex, sharey, figsize, layout, bins, **kwds)\u001b[0m\n\u001b[0;32m    197\u001b[0m         \u001b[0mlayout\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mlayout\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    198\u001b[0m         \u001b[0mbins\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mbins\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 199\u001b[1;33m         \u001b[1;33m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    200\u001b[0m     )\n\u001b[0;32m    201\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\pandas\\plotting\\_matplotlib\\hist.py\u001b[0m in \u001b[0;36mhist_frame\u001b[1;34m(data, column, by, grid, xlabelsize, xrot, ylabelsize, yrot, ax, sharex, sharey, figsize, layout, bins, **kwds)\u001b[0m\n\u001b[0;32m    404\u001b[0m         \u001b[0msharey\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0msharey\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    405\u001b[0m         \u001b[0mfigsize\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mfigsize\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 406\u001b[1;33m         \u001b[0mlayout\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mlayout\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    407\u001b[0m     )\n\u001b[0;32m    408\u001b[0m     \u001b[0m_axes\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_flatten\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0maxes\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\pandas\\plotting\\_matplotlib\\tools.py\u001b[0m in \u001b[0;36m_subplots\u001b[1;34m(naxes, sharex, sharey, squeeze, subplot_kw, ax, layout, layout_type, **fig_kw)\u001b[0m\n\u001b[0;32m    261\u001b[0m             \u001b[0max\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mset_visible\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    262\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 263\u001b[1;33m     \u001b[0m_handle_shared_axes\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0maxarr\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnplots\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnaxes\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnrows\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mncols\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msharex\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msharey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    264\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    265\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0msqueeze\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\pandas\\plotting\\_matplotlib\\tools.py\u001b[0m in \u001b[0;36m_handle_shared_axes\u001b[1;34m(axarr, nplots, naxes, nrows, ncols, sharex, sharey)\u001b[0m\n\u001b[0;32m    305\u001b[0m                 \u001b[0mlayout\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mzeros\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnrows\u001b[0m \u001b[1;33m+\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mncols\u001b[0m \u001b[1;33m+\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbool\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    306\u001b[0m                 \u001b[1;32mfor\u001b[0m \u001b[0max\u001b[0m \u001b[1;32min\u001b[0m \u001b[0maxarr\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 307\u001b[1;33m                     \u001b[0mlayout\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0max\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrowNum\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0max\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcolNum\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0max\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_visible\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    308\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    309\u001b[0m                 \u001b[1;32mfor\u001b[0m \u001b[0max\u001b[0m \u001b[1;32min\u001b[0m \u001b[0maxarr\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mAttributeError\u001b[0m: 'AxesSubplot' object has no attribute 'rowNum'"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x648 with 25 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 데이터 시각화\n",
    "preseason_df.hist(figsize=(10,9))\n",
    "plt.tight_layout() # 그래프 간격 설정\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>year</th>\n",
       "      <th>2002</th>\n",
       "      <th>2003</th>\n",
       "      <th>2004</th>\n",
       "      <th>2005</th>\n",
       "      <th>2006</th>\n",
       "      <th>2007</th>\n",
       "      <th>2008</th>\n",
       "      <th>2009</th>\n",
       "      <th>2010</th>\n",
       "      <th>2011</th>\n",
       "      <th>2012</th>\n",
       "      <th>2013</th>\n",
       "      <th>2014</th>\n",
       "      <th>2015</th>\n",
       "      <th>2016</th>\n",
       "      <th>2017</th>\n",
       "      <th>2018</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>regular</th>\n",
       "      <td>43.00</td>\n",
       "      <td>54.00</td>\n",
       "      <td>68.00</td>\n",
       "      <td>73.00</td>\n",
       "      <td>85.00</td>\n",
       "      <td>98.00</td>\n",
       "      <td>115.00</td>\n",
       "      <td>124.00</td>\n",
       "      <td>130.00</td>\n",
       "      <td>151.0</td>\n",
       "      <td>174.0</td>\n",
       "      <td>194.00</td>\n",
       "      <td>186.00</td>\n",
       "      <td>207.00</td>\n",
       "      <td>213.00</td>\n",
       "      <td>217.00</td>\n",
       "      <td>227.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>preseason</th>\n",
       "      <td>12.00</td>\n",
       "      <td>19.00</td>\n",
       "      <td>28.00</td>\n",
       "      <td>37.00</td>\n",
       "      <td>36.00</td>\n",
       "      <td>43.00</td>\n",
       "      <td>61.00</td>\n",
       "      <td>66.00</td>\n",
       "      <td>72.00</td>\n",
       "      <td>75.0</td>\n",
       "      <td>87.0</td>\n",
       "      <td>104.00</td>\n",
       "      <td>117.00</td>\n",
       "      <td>134.00</td>\n",
       "      <td>153.00</td>\n",
       "      <td>167.00</td>\n",
       "      <td>182.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ratio</th>\n",
       "      <td>0.28</td>\n",
       "      <td>0.35</td>\n",
       "      <td>0.41</td>\n",
       "      <td>0.51</td>\n",
       "      <td>0.42</td>\n",
       "      <td>0.44</td>\n",
       "      <td>0.53</td>\n",
       "      <td>0.53</td>\n",
       "      <td>0.55</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.54</td>\n",
       "      <td>0.63</td>\n",
       "      <td>0.65</td>\n",
       "      <td>0.72</td>\n",
       "      <td>0.77</td>\n",
       "      <td>0.8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "year        2002   2003   2004   2005   2006   2007    2008    2009    2010  \\\n",
       "regular    43.00  54.00  68.00  73.00  85.00  98.00  115.00  124.00  130.00   \n",
       "preseason  12.00  19.00  28.00  37.00  36.00  43.00   61.00   66.00   72.00   \n",
       "ratio       0.28   0.35   0.41   0.51   0.42   0.44    0.53    0.53    0.55   \n",
       "\n",
       "year        2011   2012    2013    2014    2015    2016    2017   2018  \n",
       "regular    151.0  174.0  194.00  186.00  207.00  213.00  217.00  227.0  \n",
       "preseason   75.0   87.0  104.00  117.00  134.00  153.00  167.00  182.0  \n",
       "ratio        0.5    0.5    0.54    0.63    0.65    0.72    0.77    0.8  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 정규시즌 데이터에서 2002년 이후의 연도별 기록된 선수의 수\n",
    "regular_count = regular_season_df.groupby('year')['batter_id'].count().rename('regular')\n",
    "\n",
    "# 프리시즌 데이터에서 연도별 기록된 선수의 수\n",
    "preseason_count = preseason_df.groupby('year')['batter_id'].count().rename('preseason')\n",
    "\n",
    "pd.concat([regular_count, preseason_count, np.round(preseason_count/regular_count, 2).rename('ratio')],\n",
    "          axis = 1).transpose().loc[:,2002:] # 2002년부터 봅니다."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0       가르시아2018\n",
       "1        강경학2011\n",
       "2        강경학2014\n",
       "3        강경학2015\n",
       "4        강경학2016\n",
       "          ...   \n",
       "1388     황재균2014\n",
       "1389     황재균2015\n",
       "1390     황재균2016\n",
       "1391     황재균2018\n",
       "1392     황진수2014\n",
       "Name: new_idx, Length: 1393, dtype: object"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 타자의 이름과 연도를 이용해 새로운 인덱스를 생성\n",
    "regular_season_df['new_idx'] = regular_season_df['batter_name'] + regular_season_df['year'].apply(str)\n",
    "preseason_df['new_idx'] = preseason_df['batter_name'] + preseason_df['year'].apply(str)\n",
    "preseason_df['new_idx']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1358, 30) (1358, 30)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "1358"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 새로운 인덱스의 교집합\n",
    "intersection_idx = list(set(regular_season_df['new_idx']).intersection(preseason_df['new_idx']))\n",
    "\n",
    "# 교집합에 존재하는 데이터만 불러오기\n",
    "regular_season_new = regular_season_df.loc[regular_season_df['new_idx'].apply(lambda x: x in intersection_idx)].copy()\n",
    "regular_season_new = regular_season_new.sort_values(by = 'new_idx').reset_index(drop=True) \n",
    "\n",
    "preseason_new = preseason_df.loc[preseason_df['new_idx'].apply(lambda x: x in intersection_idx)].copy()\n",
    "preseason_new = preseason_new.sort_values(by = 'new_idx').reset_index(drop=True)\n",
    "\n",
    "# 검정 코드\n",
    "print(regular_season_new.shape, preseason_new.shape)\n",
    "sum(regular_season_new['new_idx'] == preseason_new['new_idx'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\HOME\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\seaborn\\_decorators.py:43: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
      "  FutureWarning\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 정규시즌과 프리시즌의 상관관계 계산\n",
    "correlation = regular_season_new['OPS'].corr(preseason_new['OPS'])\n",
    "sns.scatterplot(regular_season_new['OPS'], preseason_new['OPS'])\n",
    "plt.title('correlation(상관계수): '+str(np.round(correlation,2)), fontsize=20)\n",
    "plt.xlabel(\"정규시즌 OPS\",fontsize=12)\n",
    "plt.ylabel(\"프리시즌 OPS\",fontsize=12)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1.2.2. 정규시즌 데이터 분석"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2454, 29)"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_id</th>\n",
       "      <th>batter_name</th>\n",
       "      <th>year</th>\n",
       "      <th>team</th>\n",
       "      <th>avg</th>\n",
       "      <th>G</th>\n",
       "      <th>AB</th>\n",
       "      <th>R</th>\n",
       "      <th>H</th>\n",
       "      <th>2B</th>\n",
       "      <th>...</th>\n",
       "      <th>GDP</th>\n",
       "      <th>SLG</th>\n",
       "      <th>OBP</th>\n",
       "      <th>E</th>\n",
       "      <th>height/weight</th>\n",
       "      <th>year_born</th>\n",
       "      <th>position</th>\n",
       "      <th>career</th>\n",
       "      <th>starting_salary</th>\n",
       "      <th>OPS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>가르시아</td>\n",
       "      <td>2018</td>\n",
       "      <td>LG</td>\n",
       "      <td>0.339</td>\n",
       "      <td>50</td>\n",
       "      <td>183</td>\n",
       "      <td>27</td>\n",
       "      <td>62</td>\n",
       "      <td>9</td>\n",
       "      <td>...</td>\n",
       "      <td>3</td>\n",
       "      <td>0.519</td>\n",
       "      <td>0.383</td>\n",
       "      <td>9</td>\n",
       "      <td>177cm/93kg</td>\n",
       "      <td>1985년 04월 12일</td>\n",
       "      <td>내야수(우투우타)</td>\n",
       "      <td>쿠바 Ciego de Avila Maximo Gomez Baez(대)</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.902</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2011</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1</td>\n",
       "      <td>180cm/72kg</td>\n",
       "      <td>1992년 08월 11일</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000만원</td>\n",
       "      <td>0.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2014</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.221</td>\n",
       "      <td>41</td>\n",
       "      <td>86</td>\n",
       "      <td>11</td>\n",
       "      <td>19</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0.349</td>\n",
       "      <td>0.337</td>\n",
       "      <td>6</td>\n",
       "      <td>180cm/72kg</td>\n",
       "      <td>1992년 08월 11일</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000만원</td>\n",
       "      <td>0.686</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2015</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.257</td>\n",
       "      <td>120</td>\n",
       "      <td>311</td>\n",
       "      <td>50</td>\n",
       "      <td>80</td>\n",
       "      <td>7</td>\n",
       "      <td>...</td>\n",
       "      <td>3</td>\n",
       "      <td>0.325</td>\n",
       "      <td>0.348</td>\n",
       "      <td>15</td>\n",
       "      <td>180cm/72kg</td>\n",
       "      <td>1992년 08월 11일</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000만원</td>\n",
       "      <td>0.673</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2016</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.158</td>\n",
       "      <td>46</td>\n",
       "      <td>101</td>\n",
       "      <td>16</td>\n",
       "      <td>16</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>5</td>\n",
       "      <td>0.257</td>\n",
       "      <td>0.232</td>\n",
       "      <td>7</td>\n",
       "      <td>180cm/72kg</td>\n",
       "      <td>1992년 08월 11일</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000만원</td>\n",
       "      <td>0.489</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 29 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   batter_id batter_name  year team    avg    G   AB   R   H  2B  ...  GDP  \\\n",
       "0          0        가르시아  2018   LG  0.339   50  183  27  62   9  ...    3   \n",
       "1          1         강경학  2011   한화  0.000    2    1   0   0   0  ...    0   \n",
       "2          1         강경학  2014   한화  0.221   41   86  11  19   2  ...    1   \n",
       "3          1         강경학  2015   한화  0.257  120  311  50  80   7  ...    3   \n",
       "4          1         강경학  2016   한화  0.158   46  101  16  16   3  ...    5   \n",
       "\n",
       "     SLG    OBP   E  height/weight      year_born   position  \\\n",
       "0  0.519  0.383   9     177cm/93kg  1985년 04월 12일  내야수(우투우타)   \n",
       "1  0.000  0.000   1     180cm/72kg  1992년 08월 11일  내야수(우투좌타)   \n",
       "2  0.349  0.337   6     180cm/72kg  1992년 08월 11일  내야수(우투좌타)   \n",
       "3  0.325  0.348  15     180cm/72kg  1992년 08월 11일  내야수(우투좌타)   \n",
       "4  0.257  0.232   7     180cm/72kg  1992년 08월 11일  내야수(우투좌타)   \n",
       "\n",
       "                                   career  starting_salary    OPS  \n",
       "0  쿠바 Ciego de Avila Maximo Gomez Baez(대)              NaN  0.902  \n",
       "1                       광주대성초-광주동성중-광주동성고          10000만원  0.000  \n",
       "2                       광주대성초-광주동성중-광주동성고          10000만원  0.686  \n",
       "3                       광주대성초-광주동성중-광주동성고          10000만원  0.673  \n",
       "4                       광주대성초-광주동성중-광주동성고          10000만원  0.489  \n",
       "\n",
       "[5 rows x 29 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_id</th>\n",
       "      <th>year</th>\n",
       "      <th>avg</th>\n",
       "      <th>G</th>\n",
       "      <th>AB</th>\n",
       "      <th>R</th>\n",
       "      <th>H</th>\n",
       "      <th>2B</th>\n",
       "      <th>3B</th>\n",
       "      <th>HR</th>\n",
       "      <th>...</th>\n",
       "      <th>SB</th>\n",
       "      <th>CS</th>\n",
       "      <th>BB</th>\n",
       "      <th>HBP</th>\n",
       "      <th>SO</th>\n",
       "      <th>GDP</th>\n",
       "      <th>SLG</th>\n",
       "      <th>OBP</th>\n",
       "      <th>E</th>\n",
       "      <th>OPS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>2454.000000</td>\n",
       "      <td>2454.000000</td>\n",
       "      <td>2428.000000</td>\n",
       "      <td>2454.000000</td>\n",
       "      <td>2454.000000</td>\n",
       "      <td>2454.000000</td>\n",
       "      <td>2454.000000</td>\n",
       "      <td>2454.000000</td>\n",
       "      <td>2454.000000</td>\n",
       "      <td>2454.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>2454.000000</td>\n",
       "      <td>2454.000000</td>\n",
       "      <td>2454.000000</td>\n",
       "      <td>2454.000000</td>\n",
       "      <td>2454.000000</td>\n",
       "      <td>2454.000000</td>\n",
       "      <td>2428.000000</td>\n",
       "      <td>2430.000000</td>\n",
       "      <td>2454.000000</td>\n",
       "      <td>2428.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>178.079462</td>\n",
       "      <td>2011.614507</td>\n",
       "      <td>0.237559</td>\n",
       "      <td>72.535045</td>\n",
       "      <td>201.514670</td>\n",
       "      <td>29.912388</td>\n",
       "      <td>55.988183</td>\n",
       "      <td>9.863488</td>\n",
       "      <td>0.957620</td>\n",
       "      <td>5.504075</td>\n",
       "      <td>...</td>\n",
       "      <td>5.290139</td>\n",
       "      <td>2.335778</td>\n",
       "      <td>20.943765</td>\n",
       "      <td>3.424613</td>\n",
       "      <td>38.596985</td>\n",
       "      <td>4.603504</td>\n",
       "      <td>0.343826</td>\n",
       "      <td>0.306684</td>\n",
       "      <td>3.676447</td>\n",
       "      <td>0.649939</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>97.557947</td>\n",
       "      <td>4.992833</td>\n",
       "      <td>0.098440</td>\n",
       "      <td>45.093871</td>\n",
       "      <td>169.537029</td>\n",
       "      <td>28.778759</td>\n",
       "      <td>52.253844</td>\n",
       "      <td>9.871314</td>\n",
       "      <td>1.647193</td>\n",
       "      <td>7.989380</td>\n",
       "      <td>...</td>\n",
       "      <td>9.088580</td>\n",
       "      <td>3.194045</td>\n",
       "      <td>21.206113</td>\n",
       "      <td>4.132614</td>\n",
       "      <td>31.801466</td>\n",
       "      <td>4.713531</td>\n",
       "      <td>0.163335</td>\n",
       "      <td>0.111778</td>\n",
       "      <td>4.585248</td>\n",
       "      <td>0.261634</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>1993.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>101.250000</td>\n",
       "      <td>2008.000000</td>\n",
       "      <td>0.203000</td>\n",
       "      <td>28.000000</td>\n",
       "      <td>38.250000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.267454</td>\n",
       "      <td>0.272727</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.546000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>183.000000</td>\n",
       "      <td>2013.000000</td>\n",
       "      <td>0.255000</td>\n",
       "      <td>79.000000</td>\n",
       "      <td>163.000000</td>\n",
       "      <td>21.000000</td>\n",
       "      <td>40.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>14.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>33.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>0.360124</td>\n",
       "      <td>0.328592</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.688637</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>265.000000</td>\n",
       "      <td>2016.000000</td>\n",
       "      <td>0.291000</td>\n",
       "      <td>115.000000</td>\n",
       "      <td>357.500000</td>\n",
       "      <td>49.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>16.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>34.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>60.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>0.436000</td>\n",
       "      <td>0.367000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>0.797234</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>344.000000</td>\n",
       "      <td>2018.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>144.000000</td>\n",
       "      <td>600.000000</td>\n",
       "      <td>135.000000</td>\n",
       "      <td>201.000000</td>\n",
       "      <td>47.000000</td>\n",
       "      <td>17.000000</td>\n",
       "      <td>53.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>84.000000</td>\n",
       "      <td>21.000000</td>\n",
       "      <td>108.000000</td>\n",
       "      <td>27.000000</td>\n",
       "      <td>161.000000</td>\n",
       "      <td>24.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>30.000000</td>\n",
       "      <td>4.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 22 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         batter_id         year          avg            G           AB  \\\n",
       "count  2454.000000  2454.000000  2428.000000  2454.000000  2454.000000   \n",
       "mean    178.079462  2011.614507     0.237559    72.535045   201.514670   \n",
       "std      97.557947     4.992833     0.098440    45.093871   169.537029   \n",
       "min       0.000000  1993.000000     0.000000     1.000000     0.000000   \n",
       "25%     101.250000  2008.000000     0.203000    28.000000    38.250000   \n",
       "50%     183.000000  2013.000000     0.255000    79.000000   163.000000   \n",
       "75%     265.000000  2016.000000     0.291000   115.000000   357.500000   \n",
       "max     344.000000  2018.000000     1.000000   144.000000   600.000000   \n",
       "\n",
       "                 R            H           2B           3B           HR  ...  \\\n",
       "count  2454.000000  2454.000000  2454.000000  2454.000000  2454.000000  ...   \n",
       "mean     29.912388    55.988183     9.863488     0.957620     5.504075  ...   \n",
       "std      28.778759    52.253844     9.871314     1.647193     7.989380  ...   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000  ...   \n",
       "25%       5.000000     8.000000     1.000000     0.000000     0.000000  ...   \n",
       "50%      21.000000    40.000000     7.000000     0.000000     2.000000  ...   \n",
       "75%      49.000000   100.000000    16.000000     1.000000     8.000000  ...   \n",
       "max     135.000000   201.000000    47.000000    17.000000    53.000000  ...   \n",
       "\n",
       "                SB           CS           BB          HBP           SO  \\\n",
       "count  2454.000000  2454.000000  2454.000000  2454.000000  2454.000000   \n",
       "mean      5.290139     2.335778    20.943765     3.424613    38.596985   \n",
       "std       9.088580     3.194045    21.206113     4.132614    31.801466   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "25%       0.000000     0.000000     3.000000     0.000000    10.000000   \n",
       "50%       2.000000     1.000000    14.000000     2.000000    33.000000   \n",
       "75%       6.000000     3.000000    34.000000     5.000000    60.000000   \n",
       "max      84.000000    21.000000   108.000000    27.000000   161.000000   \n",
       "\n",
       "               GDP          SLG          OBP            E          OPS  \n",
       "count  2454.000000  2428.000000  2430.000000  2454.000000  2428.000000  \n",
       "mean      4.603504     0.343826     0.306684     3.676447     0.649939  \n",
       "std       4.713531     0.163335     0.111778     4.585248     0.261634  \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000  \n",
       "25%       1.000000     0.267454     0.272727     0.000000     0.546000  \n",
       "50%       3.000000     0.360124     0.328592     2.000000     0.688637  \n",
       "75%       7.000000     0.436000     0.367000     5.000000     0.797234  \n",
       "max      24.000000     3.000000     1.000000    30.000000     4.000000  \n",
       "\n",
       "[8 rows x 22 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "regular_season_df = pd.read_csv(\"./input/Regular_Season_Batter.csv\")\n",
    "display(regular_season_df.shape, regular_season_df.head(),regular_season_df.describe())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x648 with 25 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "regular_season_df.hist(figsize=(10,9))\n",
    "plt.tight_layout() # 그래프 간격 설정\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id='m1'>연도별 OPS 중앙값 그래프</a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x432 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(15,6)) # 그래프 크기 조정\n",
    "plt.subplot(1,2,1) # 1행 2열의 첫 번째(1행, 1열) 그래프\n",
    "g = sns.boxplot(x=\"year\", y=\"OPS\", data=regular_season_df, showfliers=False)\n",
    "g.set_title('연도별 OPS 상자그림', size = 20)\n",
    "g.set_xticklabels(g.get_xticklabels(),rotation=90)\n",
    "\n",
    "plt.subplot(1,2,2)\n",
    "plt.plot(regular_season_df.groupby('year')['OPS'].median(), marker='o')\n",
    "plt.grid(axis='y', linestyle='-', alpha=0.4)\n",
    "plt.title('연도별 OPS 중앙값', size = 20)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>year</th>\n",
       "      <th>1993</th>\n",
       "      <th>1994</th>\n",
       "      <th>1995</th>\n",
       "      <th>1996</th>\n",
       "      <th>1997</th>\n",
       "      <th>1998</th>\n",
       "      <th>1999</th>\n",
       "      <th>2000</th>\n",
       "      <th>2001</th>\n",
       "      <th>2002</th>\n",
       "      <th>...</th>\n",
       "      <th>2009</th>\n",
       "      <th>2010</th>\n",
       "      <th>2011</th>\n",
       "      <th>2012</th>\n",
       "      <th>2013</th>\n",
       "      <th>2014</th>\n",
       "      <th>2015</th>\n",
       "      <th>2016</th>\n",
       "      <th>2017</th>\n",
       "      <th>2018</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>col_0</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>8</td>\n",
       "      <td>10</td>\n",
       "      <td>14</td>\n",
       "      <td>20</td>\n",
       "      <td>32</td>\n",
       "      <td>43</td>\n",
       "      <td>...</td>\n",
       "      <td>124</td>\n",
       "      <td>130</td>\n",
       "      <td>151</td>\n",
       "      <td>174</td>\n",
       "      <td>194</td>\n",
       "      <td>186</td>\n",
       "      <td>207</td>\n",
       "      <td>213</td>\n",
       "      <td>217</td>\n",
       "      <td>227</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 26 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "year   1993  1994  1995  1996  1997  1998  1999  2000  2001  2002  ...  2009  \\\n",
       "col_0                                                              ...         \n",
       "count     1     2     1     7     8    10    14    20    32    43  ...   124   \n",
       "\n",
       "year   2010  2011  2012  2013  2014  2015  2016  2017  2018  \n",
       "col_0                                                        \n",
       "count   130   151   174   194   186   207   213   217   227  \n",
       "\n",
       "[1 rows x 26 columns]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.crosstab(regular_season_df['year'],'count').T"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id='m2'>연도별 팀 OPS</a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 연도별 팀의 OPS 중앙값 계산\n",
    "med_OPS_team = regular_season_df.pivot_table(index=['team'], columns='year',\n",
    "                                             values='OPS', aggfunc='median')\n",
    "\n",
    "# 2005년 이후에 결측치가 존재하지 않는 팀만 확인\n",
    "team_idx = med_OPS_team.loc[:,2005:].isna().sum(axis=1) <= 0\n",
    "\n",
    "plt.plot(med_OPS_team.loc[team_idx,2005:].T, marker = 'o', markersize=4)\n",
    "plt.grid(axis='y', linestyle='-', alpha=0.4)\n",
    "plt.legend(med_OPS_team.loc[team_idx,2005:].T.columns, \n",
    "           loc='center left', bbox_to_anchor=(1, 0.5)) # 그래프 범례를 그래프 밖에 위치\n",
    "plt.title('연도별 팀 OPS')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "177cm/93kg 177.0 93.0\n"
     ]
    }
   ],
   "source": [
    "import re\n",
    "\n",
    "regular_season_df['weight'] = regular_season_df['height/weight'].apply(\n",
    "    lambda x: int(re.findall('\\d+',x.split('/')[1])[0]) if pd.notnull(x) else x)\n",
    "\n",
    "regular_season_df['height'] = regular_season_df['height/weight'].apply(\n",
    "    lambda x: int(re.findall('\\d+',x.split('/')[0])[0]) if pd.notnull(x) else x)\n",
    "\n",
    "print(regular_season_df['height/weight'][0], regular_season_df['height'][0],\n",
    "      regular_season_df['weight'][0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\HOME\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\seaborn\\_decorators.py:43: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
      "  FutureWarning\n",
      "C:\\Users\\HOME\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\seaborn\\_decorators.py:43: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
      "  FutureWarning\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x360 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 몸무게/키 계산\n",
    "regular_season_df['weight_per_height'] = regular_season_df['weight'] / \\\n",
    "                                         regular_season_df['height']\n",
    "plt.figure(figsize=(15, 5)) # 그래프 크기 조정\n",
    "plt.subplot(1, 2, 1) # 1행 2열의 첫번째(1행, 1열) 그래프\n",
    "\n",
    "# 정규시즌과 프리시즌의 상관관계 계산\n",
    "correlation = regular_season_df['weight_per_height'].corr(regular_season_df['OBP'])\n",
    "sns.scatterplot(regular_season_df['weight_per_height'], regular_season_df['OBP'])\n",
    "plt.title(\"'몸무게/키'와 OBP correlation(상관관계): \" + str(np.round(correlation, 2)), \\\n",
    "          fontsize=15)\n",
    "plt.ylabel('정규시즌 OBP',fontsize=12)\n",
    "plt.xlabel('몸무게/키', fontsize=12)\n",
    "plt.subplot(1, 2, 2)\n",
    "\n",
    "# 정규시즌과 프리시즌의 상관관계 계산\n",
    "correlation = regular_season_df['weight_per_height'].corr(regular_season_df['SLG'])\n",
    "sns.scatterplot(regular_season_df['weight_per_height'], regular_season_df['SLG'])\n",
    "plt.title(\"'몸무게/키'와 SLG correlation(상관관계): \" + str(np.round(correlation, 2)), \\\n",
    "          fontsize=15)\n",
    "plt.ylabel('정규시즌 SLG', fontsize=12)\n",
    "plt.xlabel('몸무게/키', fontsize=12)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "내야수(우투우타)    643\n",
       "외야수(우투우타)    230\n",
       "외야수(좌투좌타)    201\n",
       "포수(우투우타)     189\n",
       "외야수(우투좌타)    184\n",
       "내야수(우투좌타)    141\n",
       "내야수(좌투좌타)     36\n",
       "포수(우투좌타)      14\n",
       "외야수(우투양타)      7\n",
       "내야수(우투양타)      7\n",
       "Name: position, dtype: int64"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "regular_season_df['position'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "내야수(우투우타) 내야수 우타\n"
     ]
    }
   ],
   "source": [
    "# position\n",
    "regular_season_df['pos']=regular_season_df['position'].apply(\n",
    "    lambda x: x.split('(')[0] if pd.notnull(x) else x)\n",
    "\n",
    "# 우타, 좌타, 양타\n",
    "regular_season_df['hit_way'] = regular_season_df['position'].apply(\n",
    "    lambda x: x[-3:-1] if pd.notnull(x) else x)\n",
    "print(regular_season_df['position'][0], regular_season_df['pos'][0], \n",
    "      regular_season_df['hit_way'][0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x360 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(15,5)) # 그래프 크기 조정\n",
    "plt.subplot(1,2,1) # 1행 2열의 첫번째(1행, 1열) 그래프\n",
    "ax = sns.boxplot(x='pos', y='OPS', data = regular_season_df, showfliers=False)\n",
    "\n",
    "# position 별 OPS 중앙값\n",
    "medians = regular_season_df.groupby(['pos'])['OPS'].median().to_dict()\n",
    "\n",
    "# position별 관측치 수\n",
    "nobs = regular_season_df['pos'].value_counts().to_dict()\n",
    "\n",
    "# 키 값을 'n: 값' 형식으로 변환\n",
    "for key in nobs: nobs[key] = \"n: \" + str(nobs[key])\n",
    "\n",
    "# 그래프의 Xticks text 값 얻기\n",
    "xticks_labels = [item.get_text() for item in ax.get_xticklabels()]\n",
    "\n",
    "# tick은 tick의 위치, label은 그에 해당하는 text 값\n",
    "for label in ax.get_xticklabels():\n",
    "    ax.text(xticks_labels.index(label.get_text()), \n",
    "            medians[label.get_text()] + 0.03, nobs[label.get_text()],\n",
    "            horizontalalignment='center', size='large', color='w', weight='semibold')\n",
    "    \n",
    "ax.set_title('포지션별 OPS')\n",
    "\n",
    "plt.subplot(1,2,2) # 1행 2열의 두 번째(1행, 2열) 그래프\n",
    "ax = sns.boxplot(x='hit_way', y='OPS', data = regular_season_df, showfliers=False)\n",
    "\n",
    "# 타자 방향별 OPS 중앙값\n",
    "medians = regular_season_df.groupby(['hit_way'])['OPS'].median().to_dict()\n",
    "# 타자 방향 관측치 수\n",
    "nobs = regular_season_df['hit_way'].value_counts().to_dict()\n",
    "# 키 값을 'n: 값' 형식으로 변환\n",
    "for key in nobs: nobs[key] = \"n: \" + str(nobs[key])\n",
    "\n",
    "# 그래프의 Xticks text 값 얻기\n",
    "xticks_labels = [item.get_text() for item in ax.get_xticklabels()]\n",
    "\n",
    "# tick은 tick의 위치, label은 그에 해당하는 text 값\n",
    "for label in ax.get_xticklabels():\n",
    "    ax.text(xticks_labels.index(label.get_text()), medians[label.get_text()] + 0.03,\n",
    "            nobs[label.get_text()], horizontalalignment='center', size='large',\n",
    "            color='w', weight='semibold')\n",
    "ax.set_title('타석방향별 OPS')\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    쿠바 Ciego de Avila Maximo Gomez Baez(대)\n",
       "1                         광주대성초-광주동성중-광주동성고\n",
       "2                         광주대성초-광주동성중-광주동성고\n",
       "3                         광주대성초-광주동성중-광주동성고\n",
       "4                         광주대성초-광주동성중-광주동성고\n",
       "Name: career, dtype: object"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "regular_season_df['career'].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['쿠바', '도미니카', '네덜란드', '캐나다', '미국']"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# career를 split\n",
    "foreign_country = regular_season_df['career'].apply(\n",
    "    lambda x: x.replace('-', ' ').split(' ')[0])\n",
    "\n",
    "# 외국만 추출\n",
    "foreign_country_list = list(set(foreign_country.apply(\n",
    "    lambda x: np.nan if '초' in x else x)))\n",
    "\n",
    "# 결측치 처리\n",
    "foreign_country_list = [x for x in foreign_country_list if str(x) != 'nan']\n",
    "foreign_country_list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>country</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>foreign</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   country\n",
       "0  foreign\n",
       "1   korean\n",
       "2   korean\n",
       "3   korean\n",
       "4   korean"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "regular_season_df['country'] = foreign_country\n",
    "regular_season_df['country'] = regular_season_df['country'].apply(\n",
    "    lambda x: x if pd.isnull(x)\n",
    "                 else ('foreign' if x in foreign_country_list else 'korean'))\n",
    "regular_season_df[['country']].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(15,5)) # 그래프 크기 조정\n",
    "ax = sns.boxplot(x='country', y='OPS', data = regular_season_df, showfliers=False)\n",
    "\n",
    "# 내외국인 별 OPS 중앙값 dict\n",
    "medians = regular_season_df.groupby(['country'])['OPS'].median().to_dict()\n",
    "# 내외국인 관측치 수 dict\n",
    "nobs = regular_season_df['country'].value_counts().to_dict()\n",
    "# 키 값을 'n: 값' 형식으로 변환 \n",
    "for key in nobs: nobs[key] = \"n: \" + str(nobs[key])\n",
    "\n",
    "# 그래프의 Xticks text 값 얻기\n",
    "xticks_labels = [item.get_text() for item in ax.get_xticklabels()]\n",
    "    \n",
    "for label in ax.get_xticklabels(): # tick은 tick의 위치, label은 그에 해당하는 text 값 \n",
    "    ax.text(xticks_labels.index(label.get_text()), medians[label.get_text()] + 0.03, \\\n",
    "            nobs[label.get_text()], # x 좌표, y 좌표, 해당 text\n",
    "            horizontalalignment='center', size='large', color='w', weight='semibold') \n",
    "ax.set_title('국적별 OPS')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "10000만원     177\n",
       "6000만원      117\n",
       "3000만원      105\n",
       "9000만원       97\n",
       "5000만원       91\n",
       "8000만원       89\n",
       "30000만원      74\n",
       "4000만원       62\n",
       "12000만원      62\n",
       "18000만원      54\n",
       "7000만원       53\n",
       "11000만원      49\n",
       "13000만원      48\n",
       "20000만원      46\n",
       "25000만원      45\n",
       "15000만원      41\n",
       "16000만원      28\n",
       "14000만원      26\n",
       "28000만원      20\n",
       "43000만원      17\n",
       "45000만원      16\n",
       "27000만원      15\n",
       "21000만원      13\n",
       "23000만원      12\n",
       "33000만원      10\n",
       "6500만원       10\n",
       "100000달러      4\n",
       "300000달러      3\n",
       "50000달러       2\n",
       "17000만원       1\n",
       "Name: starting_salary, dtype: int64"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "regular_season_df['starting_salary'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\HOME\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\seaborn\\distributions.py:2551: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).\n",
      "  warnings.warn(msg, FutureWarning)\n",
      "C:\\Users\\HOME\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\seaborn\\_decorators.py:43: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
      "  FutureWarning\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x360 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 결측치라면 그대로 0으로 두고 ‘만원’이 포함되어 있다면 숫자만 뽑아서 초봉으로 넣어준다. 그외 만 원 단위가 아닌 초봉은 결측치로 처리한다.\n",
    "import re\n",
    "regular_season_df['starting_salary'] = regular_season_df['starting_salary'].apply(\n",
    "    lambda x: x if pd.isnull(x)\n",
    "                 else(int(re.findall('\\d+',x)[0]) if '만원' in x else np.nan))\n",
    "\n",
    "plt.figure(figsize=(15,5)) # 그래프 크기 조정\n",
    "plt.subplot(1,2,1) # 1행 2열의 첫 번째(1행, 1열) 그래프\n",
    "b=sns.distplot(regular_season_df['starting_salary']. \\\n",
    "               loc[regular_season_df['starting_salary'].notnull()], hist=True)\n",
    "b.set_xlabel(\"starting salary\",fontsize=12)\n",
    "b.set_title('초봉의 분포', fontsize=20)\n",
    "\n",
    "plt.subplot(1,2,2) # 1행 2열의 두 번째(1행, 2열) 그래프\n",
    "\n",
    "# 정규시즌과 프리시즌의 상관관계 계산\n",
    "correlation = regular_season_df['starting_salary'].corr(regular_season_df['OPS'])\n",
    "b = sns.scatterplot(regular_season_df['starting_salary'], regular_season_df['OPS'])\n",
    "b.axes.set_title('correlation(상관계수): '+str(np.round(correlation,2)), fontsize=20)\n",
    "b.set_ylabel(\"정규시즌 OPS\",fontsize=12)\n",
    "b.set_xlabel(\"초봉\",fontsize=12)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1.2.3. 일별 데이터 분석"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(112273, 20)"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_id</th>\n",
       "      <th>batter_name</th>\n",
       "      <th>date</th>\n",
       "      <th>opposing_team</th>\n",
       "      <th>avg1</th>\n",
       "      <th>AB</th>\n",
       "      <th>R</th>\n",
       "      <th>H</th>\n",
       "      <th>2B</th>\n",
       "      <th>3B</th>\n",
       "      <th>HR</th>\n",
       "      <th>RBI</th>\n",
       "      <th>SB</th>\n",
       "      <th>CS</th>\n",
       "      <th>BB</th>\n",
       "      <th>HBP</th>\n",
       "      <th>SO</th>\n",
       "      <th>GDP</th>\n",
       "      <th>avg2</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>가르시아</td>\n",
       "      <td>3.24</td>\n",
       "      <td>NC</td>\n",
       "      <td>0.333</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0.333</td>\n",
       "      <td>2018</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>가르시아</td>\n",
       "      <td>3.25</td>\n",
       "      <td>NC</td>\n",
       "      <td>0.000</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0.143</td>\n",
       "      <td>2018</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>가르시아</td>\n",
       "      <td>3.27</td>\n",
       "      <td>넥센</td>\n",
       "      <td>0.200</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.167</td>\n",
       "      <td>2018</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>가르시아</td>\n",
       "      <td>3.28</td>\n",
       "      <td>넥센</td>\n",
       "      <td>0.200</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.176</td>\n",
       "      <td>2018</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>가르시아</td>\n",
       "      <td>3.29</td>\n",
       "      <td>넥센</td>\n",
       "      <td>0.250</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.190</td>\n",
       "      <td>2018</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   batter_id batter_name  date opposing_team   avg1  AB  R  H  2B  3B  HR  \\\n",
       "0          0        가르시아  3.24            NC  0.333   3  1  1   0   0   0   \n",
       "1          0        가르시아  3.25            NC  0.000   4  0  0   0   0   0   \n",
       "2          0        가르시아  3.27            넥센  0.200   5  0  1   0   0   0   \n",
       "3          0        가르시아  3.28            넥센  0.200   5  1  1   0   0   0   \n",
       "4          0        가르시아  3.29            넥센  0.250   4  0  1   0   0   0   \n",
       "\n",
       "   RBI  SB  CS  BB  HBP  SO  GDP   avg2  year  \n",
       "0    0   0   0   1    0   1    0  0.333  2018  \n",
       "1    0   0   0   0    0   1    0  0.143  2018  \n",
       "2    0   0   0   0    0   0    0  0.167  2018  \n",
       "3    1   0   0   0    0   0    0  0.176  2018  \n",
       "4    3   0   0   0    0   0    1  0.190  2018  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "day_by_day_df = pd.read_csv('./input/Regular_Season_Batter_Day_by_Day_b4.csv')\n",
    "display(day_by_day_df.shape, day_by_day_df.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>year</th>\n",
       "      <th>month</th>\n",
       "      <th>avg2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2001</td>\n",
       "      <td>10</td>\n",
       "      <td>0.356400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2001</td>\n",
       "      <td>4</td>\n",
       "      <td>0.205217</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2001</td>\n",
       "      <td>5</td>\n",
       "      <td>0.297157</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2001</td>\n",
       "      <td>6</td>\n",
       "      <td>0.306926</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2001</td>\n",
       "      <td>7</td>\n",
       "      <td>0.293171</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>129</th>\n",
       "      <td>2018</td>\n",
       "      <td>5</td>\n",
       "      <td>0.274083</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>130</th>\n",
       "      <td>2018</td>\n",
       "      <td>6</td>\n",
       "      <td>0.280630</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>131</th>\n",
       "      <td>2018</td>\n",
       "      <td>7</td>\n",
       "      <td>0.280817</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>132</th>\n",
       "      <td>2018</td>\n",
       "      <td>8</td>\n",
       "      <td>0.283923</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>133</th>\n",
       "      <td>2018</td>\n",
       "      <td>9</td>\n",
       "      <td>0.277841</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>134 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     year month      avg2\n",
       "0    2001    10  0.356400\n",
       "1    2001     4  0.205217\n",
       "2    2001     5  0.297157\n",
       "3    2001     6  0.306926\n",
       "4    2001     7  0.293171\n",
       "..    ...   ...       ...\n",
       "129  2018     5  0.274083\n",
       "130  2018     6  0.280630\n",
       "131  2018     7  0.280817\n",
       "132  2018     8  0.283923\n",
       "133  2018     9  0.277841\n",
       "\n",
       "[134 rows x 3 columns]"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 날짜(date)를 ‘.’을 기준으로 나누고 첫 번째 값을 월(month)로 지정 \n",
    "day_by_day_df['month'] = day_by_day_df['date'].apply(lambda x: str(x).split('.')[0])\n",
    "\n",
    "# 각 연도의 월별 평균 누적 타율(avg2) 계산\n",
    "agg_df = day_by_day_df.groupby(['year', 'month'])['avg2'].mean().reset_index()\n",
    "agg_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>year</th>\n",
       "      <th>2001</th>\n",
       "      <th>2002</th>\n",
       "      <th>2003</th>\n",
       "      <th>2004</th>\n",
       "      <th>2005</th>\n",
       "      <th>2006</th>\n",
       "      <th>2007</th>\n",
       "      <th>2008</th>\n",
       "      <th>2009</th>\n",
       "      <th>2010</th>\n",
       "      <th>2011</th>\n",
       "      <th>2012</th>\n",
       "      <th>2013</th>\n",
       "      <th>2014</th>\n",
       "      <th>2015</th>\n",
       "      <th>2016</th>\n",
       "      <th>2017</th>\n",
       "      <th>2018</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>month</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>0.356400</td>\n",
       "      <td>0.269065</td>\n",
       "      <td>0.216583</td>\n",
       "      <td>0.203636</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.260985</td>\n",
       "      <td>0.249888</td>\n",
       "      <td>0.249638</td>\n",
       "      <td>0.033333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.243526</td>\n",
       "      <td>0.246949</td>\n",
       "      <td>0.257841</td>\n",
       "      <td>0.273537</td>\n",
       "      <td>0.274042</td>\n",
       "      <td>0.282547</td>\n",
       "      <td>0.280289</td>\n",
       "      <td>0.277482</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.261714</td>\n",
       "      <td>0.261714</td>\n",
       "      <td>0.271982</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.239861</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.231236</td>\n",
       "      <td>0.210598</td>\n",
       "      <td>0.214485</td>\n",
       "      <td>0.257857</td>\n",
       "      <td>0.161979</td>\n",
       "      <td>0.238015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.205217</td>\n",
       "      <td>0.319792</td>\n",
       "      <td>0.250296</td>\n",
       "      <td>0.259663</td>\n",
       "      <td>0.235317</td>\n",
       "      <td>0.267106</td>\n",
       "      <td>0.215703</td>\n",
       "      <td>0.261531</td>\n",
       "      <td>0.252546</td>\n",
       "      <td>0.262953</td>\n",
       "      <td>0.247133</td>\n",
       "      <td>0.234199</td>\n",
       "      <td>0.267994</td>\n",
       "      <td>0.259918</td>\n",
       "      <td>0.255175</td>\n",
       "      <td>0.266711</td>\n",
       "      <td>0.259430</td>\n",
       "      <td>0.263953</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.297157</td>\n",
       "      <td>0.267990</td>\n",
       "      <td>0.241491</td>\n",
       "      <td>0.237954</td>\n",
       "      <td>0.253527</td>\n",
       "      <td>0.264283</td>\n",
       "      <td>0.237329</td>\n",
       "      <td>0.262535</td>\n",
       "      <td>0.280842</td>\n",
       "      <td>0.272934</td>\n",
       "      <td>0.250877</td>\n",
       "      <td>0.247844</td>\n",
       "      <td>0.268355</td>\n",
       "      <td>0.273899</td>\n",
       "      <td>0.261307</td>\n",
       "      <td>0.275240</td>\n",
       "      <td>0.274374</td>\n",
       "      <td>0.274083</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.306926</td>\n",
       "      <td>0.275867</td>\n",
       "      <td>0.252290</td>\n",
       "      <td>0.248800</td>\n",
       "      <td>0.249913</td>\n",
       "      <td>0.264392</td>\n",
       "      <td>0.260600</td>\n",
       "      <td>0.270766</td>\n",
       "      <td>0.278781</td>\n",
       "      <td>0.274791</td>\n",
       "      <td>0.263264</td>\n",
       "      <td>0.254577</td>\n",
       "      <td>0.270533</td>\n",
       "      <td>0.283480</td>\n",
       "      <td>0.268999</td>\n",
       "      <td>0.276307</td>\n",
       "      <td>0.279060</td>\n",
       "      <td>0.280630</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.293171</td>\n",
       "      <td>0.266650</td>\n",
       "      <td>0.244230</td>\n",
       "      <td>0.251973</td>\n",
       "      <td>0.256396</td>\n",
       "      <td>0.262464</td>\n",
       "      <td>0.259171</td>\n",
       "      <td>0.264870</td>\n",
       "      <td>0.275054</td>\n",
       "      <td>0.265501</td>\n",
       "      <td>0.264829</td>\n",
       "      <td>0.261513</td>\n",
       "      <td>0.262812</td>\n",
       "      <td>0.275677</td>\n",
       "      <td>0.272685</td>\n",
       "      <td>0.283192</td>\n",
       "      <td>0.284565</td>\n",
       "      <td>0.280817</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0.303489</td>\n",
       "      <td>0.270481</td>\n",
       "      <td>0.252319</td>\n",
       "      <td>0.249460</td>\n",
       "      <td>0.243570</td>\n",
       "      <td>0.265369</td>\n",
       "      <td>0.270258</td>\n",
       "      <td>0.265173</td>\n",
       "      <td>0.271796</td>\n",
       "      <td>0.271075</td>\n",
       "      <td>0.262048</td>\n",
       "      <td>0.258069</td>\n",
       "      <td>0.268122</td>\n",
       "      <td>0.282025</td>\n",
       "      <td>0.272377</td>\n",
       "      <td>0.283105</td>\n",
       "      <td>0.283283</td>\n",
       "      <td>0.283923</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0.308636</td>\n",
       "      <td>0.248333</td>\n",
       "      <td>0.243780</td>\n",
       "      <td>0.203953</td>\n",
       "      <td>0.237058</td>\n",
       "      <td>0.258794</td>\n",
       "      <td>0.251022</td>\n",
       "      <td>0.252942</td>\n",
       "      <td>0.264468</td>\n",
       "      <td>0.265312</td>\n",
       "      <td>0.258500</td>\n",
       "      <td>0.251232</td>\n",
       "      <td>0.260571</td>\n",
       "      <td>0.272411</td>\n",
       "      <td>0.271629</td>\n",
       "      <td>0.276513</td>\n",
       "      <td>0.273213</td>\n",
       "      <td>0.277841</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "year       2001      2002      2003      2004      2005      2006      2007  \\\n",
       "month                                                                         \n",
       "10     0.356400  0.269065  0.216583  0.203636       NaN  0.260985  0.249888   \n",
       "3           NaN       NaN       NaN       NaN       NaN  0.261714  0.261714   \n",
       "4      0.205217  0.319792  0.250296  0.259663  0.235317  0.267106  0.215703   \n",
       "5      0.297157  0.267990  0.241491  0.237954  0.253527  0.264283  0.237329   \n",
       "6      0.306926  0.275867  0.252290  0.248800  0.249913  0.264392  0.260600   \n",
       "7      0.293171  0.266650  0.244230  0.251973  0.256396  0.262464  0.259171   \n",
       "8      0.303489  0.270481  0.252319  0.249460  0.243570  0.265369  0.270258   \n",
       "9      0.308636  0.248333  0.243780  0.203953  0.237058  0.258794  0.251022   \n",
       "\n",
       "year       2008      2009      2010      2011      2012      2013      2014  \\\n",
       "month                                                                         \n",
       "10     0.249638  0.033333       NaN  0.243526  0.246949  0.257841  0.273537   \n",
       "3      0.271982       NaN  0.239861       NaN       NaN  0.231236  0.210598   \n",
       "4      0.261531  0.252546  0.262953  0.247133  0.234199  0.267994  0.259918   \n",
       "5      0.262535  0.280842  0.272934  0.250877  0.247844  0.268355  0.273899   \n",
       "6      0.270766  0.278781  0.274791  0.263264  0.254577  0.270533  0.283480   \n",
       "7      0.264870  0.275054  0.265501  0.264829  0.261513  0.262812  0.275677   \n",
       "8      0.265173  0.271796  0.271075  0.262048  0.258069  0.268122  0.282025   \n",
       "9      0.252942  0.264468  0.265312  0.258500  0.251232  0.260571  0.272411   \n",
       "\n",
       "year       2015      2016      2017      2018  \n",
       "month                                          \n",
       "10     0.274042  0.282547  0.280289  0.277482  \n",
       "3      0.214485  0.257857  0.161979  0.238015  \n",
       "4      0.255175  0.266711  0.259430  0.263953  \n",
       "5      0.261307  0.275240  0.274374  0.274083  \n",
       "6      0.268999  0.276307  0.279060  0.280630  \n",
       "7      0.272685  0.283192  0.284565  0.280817  \n",
       "8      0.272377  0.283105  0.283283  0.283923  \n",
       "9      0.271629  0.276513  0.273213  0.277841  "
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# pivot_table을 이용해 데이터 변형\n",
    "agg_df = agg_df.pivot_table(index=['month'], columns='year', values = 'avg2')\n",
    "agg_df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id='m3'>연도별 월 평균 타율</a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>year</th>\n",
       "      <th>2011</th>\n",
       "      <th>2012</th>\n",
       "      <th>2013</th>\n",
       "      <th>2014</th>\n",
       "      <th>2015</th>\n",
       "      <th>2016</th>\n",
       "      <th>2017</th>\n",
       "      <th>2018</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>month</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.247133</td>\n",
       "      <td>0.234199</td>\n",
       "      <td>0.267994</td>\n",
       "      <td>0.259918</td>\n",
       "      <td>0.255175</td>\n",
       "      <td>0.266711</td>\n",
       "      <td>0.259430</td>\n",
       "      <td>0.263953</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.250877</td>\n",
       "      <td>0.247844</td>\n",
       "      <td>0.268355</td>\n",
       "      <td>0.273899</td>\n",
       "      <td>0.261307</td>\n",
       "      <td>0.275240</td>\n",
       "      <td>0.274374</td>\n",
       "      <td>0.274083</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.263264</td>\n",
       "      <td>0.254577</td>\n",
       "      <td>0.270533</td>\n",
       "      <td>0.283480</td>\n",
       "      <td>0.268999</td>\n",
       "      <td>0.276307</td>\n",
       "      <td>0.279060</td>\n",
       "      <td>0.280630</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.264829</td>\n",
       "      <td>0.261513</td>\n",
       "      <td>0.262812</td>\n",
       "      <td>0.275677</td>\n",
       "      <td>0.272685</td>\n",
       "      <td>0.283192</td>\n",
       "      <td>0.284565</td>\n",
       "      <td>0.280817</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0.262048</td>\n",
       "      <td>0.258069</td>\n",
       "      <td>0.268122</td>\n",
       "      <td>0.282025</td>\n",
       "      <td>0.272377</td>\n",
       "      <td>0.283105</td>\n",
       "      <td>0.283283</td>\n",
       "      <td>0.283923</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0.258500</td>\n",
       "      <td>0.251232</td>\n",
       "      <td>0.260571</td>\n",
       "      <td>0.272411</td>\n",
       "      <td>0.271629</td>\n",
       "      <td>0.276513</td>\n",
       "      <td>0.273213</td>\n",
       "      <td>0.277841</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "year       2011      2012      2013      2014      2015      2016      2017  \\\n",
       "month                                                                         \n",
       "4      0.247133  0.234199  0.267994  0.259918  0.255175  0.266711  0.259430   \n",
       "5      0.250877  0.247844  0.268355  0.273899  0.261307  0.275240  0.274374   \n",
       "6      0.263264  0.254577  0.270533  0.283480  0.268999  0.276307  0.279060   \n",
       "7      0.264829  0.261513  0.262812  0.275677  0.272685  0.283192  0.284565   \n",
       "8      0.262048  0.258069  0.268122  0.282025  0.272377  0.283105  0.283283   \n",
       "9      0.258500  0.251232  0.260571  0.272411  0.271629  0.276513  0.273213   \n",
       "\n",
       "year       2018  \n",
       "month            \n",
       "4      0.263953  \n",
       "5      0.274083  \n",
       "6      0.280630  \n",
       "7      0.280817  \n",
       "8      0.283923  \n",
       "9      0.277841  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "display(agg_df.iloc[2:, 10:])\n",
    "plt.plot(agg_df.iloc[2:,10:], marker = 'o', markersize=4) # 2011~2018년 데이터만 이용\n",
    "plt.grid(axis='y', linestyle='-', alpha=0.4)\n",
    "plt.legend(agg_df.iloc[2:,10:].columns, loc='center left', bbox_to_anchor=(1, 0.5)) # 범례 그래프 밖에 위치\n",
    "plt.title('연도별 월 평균 타율')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1.3. 데이터 전처리"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_id</th>\n",
       "      <th>batter_name</th>\n",
       "      <th>year</th>\n",
       "      <th>team</th>\n",
       "      <th>avg</th>\n",
       "      <th>G</th>\n",
       "      <th>AB</th>\n",
       "      <th>R</th>\n",
       "      <th>H</th>\n",
       "      <th>2B</th>\n",
       "      <th>...</th>\n",
       "      <th>position</th>\n",
       "      <th>career</th>\n",
       "      <th>starting_salary</th>\n",
       "      <th>OPS</th>\n",
       "      <th>weight</th>\n",
       "      <th>height</th>\n",
       "      <th>weight_per_height</th>\n",
       "      <th>pos</th>\n",
       "      <th>hit_way</th>\n",
       "      <th>country</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>26</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>802</td>\n",
       "      <td>0</td>\n",
       "      <td>1076</td>\n",
       "      <td>26</td>\n",
       "      <td>802</td>\n",
       "      <td>802</td>\n",
       "      <td>802</td>\n",
       "      <td>802</td>\n",
       "      <td>802</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 35 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   batter_id  batter_name  year  team  avg  G  AB  R  H  2B  ...  position  \\\n",
       "0          0            0     0     0   26  0   0  0  0   0  ...       802   \n",
       "\n",
       "   career  starting_salary  OPS  weight  height  weight_per_height  pos  \\\n",
       "0       0             1076   26     802     802                802  802   \n",
       "\n",
       "   hit_way  country  \n",
       "0      802        0  \n",
       "\n",
       "[1 rows x 35 columns]"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame(regular_season_df.isna().sum()).transpose()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_id</th>\n",
       "      <th>year</th>\n",
       "      <th>avg</th>\n",
       "      <th>G</th>\n",
       "      <th>AB</th>\n",
       "      <th>R</th>\n",
       "      <th>H</th>\n",
       "      <th>2B</th>\n",
       "      <th>3B</th>\n",
       "      <th>HR</th>\n",
       "      <th>...</th>\n",
       "      <th>SO</th>\n",
       "      <th>GDP</th>\n",
       "      <th>SLG</th>\n",
       "      <th>OBP</th>\n",
       "      <th>E</th>\n",
       "      <th>starting_salary</th>\n",
       "      <th>OPS</th>\n",
       "      <th>weight</th>\n",
       "      <th>height</th>\n",
       "      <th>weight_per_height</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>2018</td>\n",
       "      <td>0.339</td>\n",
       "      <td>50</td>\n",
       "      <td>183</td>\n",
       "      <td>27</td>\n",
       "      <td>62</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>...</td>\n",
       "      <td>25</td>\n",
       "      <td>3</td>\n",
       "      <td>0.519000</td>\n",
       "      <td>0.383000</td>\n",
       "      <td>9</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.902000</td>\n",
       "      <td>93.0</td>\n",
       "      <td>177.0</td>\n",
       "      <td>0.525424</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>138</td>\n",
       "      <td>2005</td>\n",
       "      <td>0.127</td>\n",
       "      <td>39</td>\n",
       "      <td>63</td>\n",
       "      <td>9</td>\n",
       "      <td>8</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>15</td>\n",
       "      <td>1</td>\n",
       "      <td>0.158730</td>\n",
       "      <td>0.256757</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.415487</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>138</td>\n",
       "      <td>2006</td>\n",
       "      <td>0.139</td>\n",
       "      <td>37</td>\n",
       "      <td>36</td>\n",
       "      <td>6</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>14</td>\n",
       "      <td>0</td>\n",
       "      <td>0.194444</td>\n",
       "      <td>0.326087</td>\n",
       "      <td>4</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.520531</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>138</td>\n",
       "      <td>2007</td>\n",
       "      <td>0.000</td>\n",
       "      <td>8</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>138</td>\n",
       "      <td>2008</td>\n",
       "      <td>0.000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 26 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    batter_id  year    avg   G   AB   R   H  2B  3B  HR  ...  SO  GDP  \\\n",
       "0           0  2018  0.339  50  183  27  62   9   0   8  ...  25    3   \n",
       "12        138  2005  0.127  39   63   9   8   2   0   0  ...  15    1   \n",
       "13        138  2006  0.139  37   36   6   5   2   0   0  ...  14    0   \n",
       "14        138  2007  0.000   8    4   3   0   0   0   0  ...   2    1   \n",
       "15        138  2008  0.000   2    1   0   0   0   0   0  ...   0    0   \n",
       "\n",
       "         SLG       OBP  E  starting_salary       OPS  weight  height  \\\n",
       "0   0.519000  0.383000  9              NaN  0.902000    93.0   177.0   \n",
       "12  0.158730  0.256757  3              NaN  0.415487     NaN     NaN   \n",
       "13  0.194444  0.326087  4              NaN  0.520531     NaN     NaN   \n",
       "14  0.000000  0.000000  0              NaN  0.000000     NaN     NaN   \n",
       "15  0.000000  0.000000  0              NaN  0.000000     NaN     NaN   \n",
       "\n",
       "    weight_per_height  \n",
       "0            0.525424  \n",
       "12                NaN  \n",
       "13                NaN  \n",
       "14                NaN  \n",
       "15                NaN  \n",
       "\n",
       "[5 rows x 26 columns]"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 수치형 타입의 변수 저장\n",
    "numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64'] # 모든 numeric(수치형) 타입\n",
    "num_cols = regular_season_df.select_dtypes(include=numerics).columns\n",
    "\n",
    "# 수치형 타입 변수 중 결측치가 하나라도 존재하는 행 출력\n",
    "# isna().sum(axis=1) -> 열 기준의 결측치 개수\n",
    "# df.loc[]를 통해 결측치 0개 이상 데이터를 추출\n",
    "regular_season_df.loc[regular_season_df[num_cols].isna().sum(axis=1) > 0,num_cols].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_id</th>\n",
       "      <th>batter_name</th>\n",
       "      <th>year</th>\n",
       "      <th>team</th>\n",
       "      <th>avg</th>\n",
       "      <th>G</th>\n",
       "      <th>AB</th>\n",
       "      <th>R</th>\n",
       "      <th>H</th>\n",
       "      <th>2B</th>\n",
       "      <th>...</th>\n",
       "      <th>position</th>\n",
       "      <th>career</th>\n",
       "      <th>starting_salary</th>\n",
       "      <th>OPS</th>\n",
       "      <th>weight</th>\n",
       "      <th>height</th>\n",
       "      <th>weight_per_height</th>\n",
       "      <th>pos</th>\n",
       "      <th>hit_way</th>\n",
       "      <th>country</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>가르시아</td>\n",
       "      <td>2018</td>\n",
       "      <td>LG</td>\n",
       "      <td>0.339</td>\n",
       "      <td>50</td>\n",
       "      <td>183</td>\n",
       "      <td>27</td>\n",
       "      <td>62</td>\n",
       "      <td>9</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투우타)</td>\n",
       "      <td>쿠바 Ciego de Avila Maximo Gomez Baez(대)</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.902</td>\n",
       "      <td>93.0</td>\n",
       "      <td>177.0</td>\n",
       "      <td>0.525424</td>\n",
       "      <td>내야수</td>\n",
       "      <td>우타</td>\n",
       "      <td>foreign</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2011</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000.0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>72.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>내야수</td>\n",
       "      <td>좌타</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2014</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.221</td>\n",
       "      <td>41</td>\n",
       "      <td>86</td>\n",
       "      <td>11</td>\n",
       "      <td>19</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000.0</td>\n",
       "      <td>0.686</td>\n",
       "      <td>72.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>내야수</td>\n",
       "      <td>좌타</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2015</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.257</td>\n",
       "      <td>120</td>\n",
       "      <td>311</td>\n",
       "      <td>50</td>\n",
       "      <td>80</td>\n",
       "      <td>7</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000.0</td>\n",
       "      <td>0.673</td>\n",
       "      <td>72.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>내야수</td>\n",
       "      <td>좌타</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2016</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.158</td>\n",
       "      <td>46</td>\n",
       "      <td>101</td>\n",
       "      <td>16</td>\n",
       "      <td>16</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000.0</td>\n",
       "      <td>0.489</td>\n",
       "      <td>72.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>내야수</td>\n",
       "      <td>좌타</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2449</th>\n",
       "      <td>344</td>\n",
       "      <td>황진수</td>\n",
       "      <td>2014</td>\n",
       "      <td>롯데</td>\n",
       "      <td>0.000</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투양타)</td>\n",
       "      <td>석천초-대헌중-공주고</td>\n",
       "      <td>4000.0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>82.0</td>\n",
       "      <td>181.0</td>\n",
       "      <td>0.453039</td>\n",
       "      <td>내야수</td>\n",
       "      <td>양타</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2450</th>\n",
       "      <td>344</td>\n",
       "      <td>황진수</td>\n",
       "      <td>2015</td>\n",
       "      <td>롯데</td>\n",
       "      <td>0.000</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투양타)</td>\n",
       "      <td>석천초-대헌중-공주고</td>\n",
       "      <td>4000.0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>82.0</td>\n",
       "      <td>181.0</td>\n",
       "      <td>0.453039</td>\n",
       "      <td>내야수</td>\n",
       "      <td>양타</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2451</th>\n",
       "      <td>344</td>\n",
       "      <td>황진수</td>\n",
       "      <td>2016</td>\n",
       "      <td>롯데</td>\n",
       "      <td>0.000</td>\n",
       "      <td>11</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투양타)</td>\n",
       "      <td>석천초-대헌중-공주고</td>\n",
       "      <td>4000.0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>82.0</td>\n",
       "      <td>181.0</td>\n",
       "      <td>0.453039</td>\n",
       "      <td>내야수</td>\n",
       "      <td>양타</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2452</th>\n",
       "      <td>344</td>\n",
       "      <td>황진수</td>\n",
       "      <td>2017</td>\n",
       "      <td>롯데</td>\n",
       "      <td>0.291</td>\n",
       "      <td>60</td>\n",
       "      <td>117</td>\n",
       "      <td>18</td>\n",
       "      <td>34</td>\n",
       "      <td>6</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투양타)</td>\n",
       "      <td>석천초-대헌중-공주고</td>\n",
       "      <td>4000.0</td>\n",
       "      <td>0.761</td>\n",
       "      <td>82.0</td>\n",
       "      <td>181.0</td>\n",
       "      <td>0.453039</td>\n",
       "      <td>내야수</td>\n",
       "      <td>양타</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2453</th>\n",
       "      <td>344</td>\n",
       "      <td>황진수</td>\n",
       "      <td>2018</td>\n",
       "      <td>롯데</td>\n",
       "      <td>0.167</td>\n",
       "      <td>18</td>\n",
       "      <td>24</td>\n",
       "      <td>6</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투양타)</td>\n",
       "      <td>석천초-대헌중-공주고</td>\n",
       "      <td>4000.0</td>\n",
       "      <td>0.564</td>\n",
       "      <td>82.0</td>\n",
       "      <td>181.0</td>\n",
       "      <td>0.453039</td>\n",
       "      <td>내야수</td>\n",
       "      <td>양타</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2454 rows × 35 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      batter_id batter_name  year team    avg    G   AB   R   H  2B  ...  \\\n",
       "0             0        가르시아  2018   LG  0.339   50  183  27  62   9  ...   \n",
       "1             1         강경학  2011   한화  0.000    2    1   0   0   0  ...   \n",
       "2             1         강경학  2014   한화  0.221   41   86  11  19   2  ...   \n",
       "3             1         강경학  2015   한화  0.257  120  311  50  80   7  ...   \n",
       "4             1         강경학  2016   한화  0.158   46  101  16  16   3  ...   \n",
       "...         ...         ...   ...  ...    ...  ...  ...  ..  ..  ..  ...   \n",
       "2449        344         황진수  2014   롯데  0.000    5    5   0   0   0  ...   \n",
       "2450        344         황진수  2015   롯데  0.000    2    2   0   0   0  ...   \n",
       "2451        344         황진수  2016   롯데  0.000   11   10   2   0   0  ...   \n",
       "2452        344         황진수  2017   롯데  0.291   60  117  18  34   6  ...   \n",
       "2453        344         황진수  2018   롯데  0.167   18   24   6   4   1  ...   \n",
       "\n",
       "       position                                  career  starting_salary  \\\n",
       "0     내야수(우투우타)  쿠바 Ciego de Avila Maximo Gomez Baez(대)              0.0   \n",
       "1     내야수(우투좌타)                       광주대성초-광주동성중-광주동성고          10000.0   \n",
       "2     내야수(우투좌타)                       광주대성초-광주동성중-광주동성고          10000.0   \n",
       "3     내야수(우투좌타)                       광주대성초-광주동성중-광주동성고          10000.0   \n",
       "4     내야수(우투좌타)                       광주대성초-광주동성중-광주동성고          10000.0   \n",
       "...         ...                                     ...              ...   \n",
       "2449  내야수(우투양타)                             석천초-대헌중-공주고           4000.0   \n",
       "2450  내야수(우투양타)                             석천초-대헌중-공주고           4000.0   \n",
       "2451  내야수(우투양타)                             석천초-대헌중-공주고           4000.0   \n",
       "2452  내야수(우투양타)                             석천초-대헌중-공주고           4000.0   \n",
       "2453  내야수(우투양타)                             석천초-대헌중-공주고           4000.0   \n",
       "\n",
       "        OPS  weight  height  weight_per_height  pos  hit_way  country  \n",
       "0     0.902    93.0   177.0           0.525424  내야수       우타  foreign  \n",
       "1     0.000    72.0   180.0           0.400000  내야수       좌타   korean  \n",
       "2     0.686    72.0   180.0           0.400000  내야수       좌타   korean  \n",
       "3     0.673    72.0   180.0           0.400000  내야수       좌타   korean  \n",
       "4     0.489    72.0   180.0           0.400000  내야수       좌타   korean  \n",
       "...     ...     ...     ...                ...  ...      ...      ...  \n",
       "2449  0.000    82.0   181.0           0.453039  내야수       양타   korean  \n",
       "2450  0.000    82.0   181.0           0.453039  내야수       양타   korean  \n",
       "2451  0.000    82.0   181.0           0.453039  내야수       양타   korean  \n",
       "2452  0.761    82.0   181.0           0.453039  내야수       양타   korean  \n",
       "2453  0.564    82.0   181.0           0.453039  내야수       양타   korean  \n",
       "\n",
       "[2454 rows x 35 columns]"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 정규 시즌 데이터에서 결측치를 0으로 채우기\n",
    "regular_season_df[regular_season_df.select_dtypes(include=numerics).columns] = \\\n",
    "    regular_season_df[regular_season_df.select_dtypes(include=numerics).columns].fillna(0)\n",
    "regular_season_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_id</th>\n",
       "      <th>batter_name</th>\n",
       "      <th>date</th>\n",
       "      <th>opposing_team</th>\n",
       "      <th>avg1</th>\n",
       "      <th>AB</th>\n",
       "      <th>R</th>\n",
       "      <th>H</th>\n",
       "      <th>2B</th>\n",
       "      <th>3B</th>\n",
       "      <th>...</th>\n",
       "      <th>RBI</th>\n",
       "      <th>SB</th>\n",
       "      <th>CS</th>\n",
       "      <th>BB</th>\n",
       "      <th>HBP</th>\n",
       "      <th>SO</th>\n",
       "      <th>GDP</th>\n",
       "      <th>avg2</th>\n",
       "      <th>year</th>\n",
       "      <th>month</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>가르시아</td>\n",
       "      <td>3.24</td>\n",
       "      <td>NC</td>\n",
       "      <td>0.333</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0.333</td>\n",
       "      <td>2018</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>가르시아</td>\n",
       "      <td>3.25</td>\n",
       "      <td>NC</td>\n",
       "      <td>0.000</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0.143</td>\n",
       "      <td>2018</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>가르시아</td>\n",
       "      <td>3.27</td>\n",
       "      <td>넥센</td>\n",
       "      <td>0.200</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.167</td>\n",
       "      <td>2018</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>가르시아</td>\n",
       "      <td>3.28</td>\n",
       "      <td>넥센</td>\n",
       "      <td>0.200</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.176</td>\n",
       "      <td>2018</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>가르시아</td>\n",
       "      <td>3.29</td>\n",
       "      <td>넥센</td>\n",
       "      <td>0.250</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.190</td>\n",
       "      <td>2018</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>112268</th>\n",
       "      <td>344</td>\n",
       "      <td>황진수</td>\n",
       "      <td>6.23</td>\n",
       "      <td>LG</td>\n",
       "      <td>-</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.158</td>\n",
       "      <td>2018</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>112269</th>\n",
       "      <td>344</td>\n",
       "      <td>황진수</td>\n",
       "      <td>6.26</td>\n",
       "      <td>넥센</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0.150</td>\n",
       "      <td>2018</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>112270</th>\n",
       "      <td>344</td>\n",
       "      <td>황진수</td>\n",
       "      <td>6.27</td>\n",
       "      <td>넥센</td>\n",
       "      <td>0.500</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0.182</td>\n",
       "      <td>2018</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>112271</th>\n",
       "      <td>344</td>\n",
       "      <td>황진수</td>\n",
       "      <td>6.28</td>\n",
       "      <td>넥센</td>\n",
       "      <td>-</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.182</td>\n",
       "      <td>2018</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>112272</th>\n",
       "      <td>344</td>\n",
       "      <td>황진수</td>\n",
       "      <td>6.30</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.000</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.167</td>\n",
       "      <td>2018</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>112273 rows × 21 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        batter_id batter_name  date opposing_team   avg1  AB  R  H  2B  3B  \\\n",
       "0               0        가르시아  3.24            NC  0.333   3  1  1   0   0   \n",
       "1               0        가르시아  3.25            NC  0.000   4  0  0   0   0   \n",
       "2               0        가르시아  3.27            넥센  0.200   5  0  1   0   0   \n",
       "3               0        가르시아  3.28            넥센  0.200   5  1  1   0   0   \n",
       "4               0        가르시아  3.29            넥센  0.250   4  0  1   0   0   \n",
       "...           ...         ...   ...           ...    ...  .. .. ..  ..  ..   \n",
       "112268        344         황진수  6.23            LG      -   0  0  0   0   0   \n",
       "112269        344         황진수  6.26            넥센  0.000   1  0  0   0   0   \n",
       "112270        344         황진수  6.27            넥센  0.500   2  1  1   1   0   \n",
       "112271        344         황진수  6.28            넥센      -   0  0  0   0   0   \n",
       "112272        344         황진수  6.30            한화  0.000   2  0  0   0   0   \n",
       "\n",
       "        ...  RBI  SB  CS  BB  HBP  SO  GDP   avg2  year  month  \n",
       "0       ...    0   0   0   1    0   1    0  0.333  2018      3  \n",
       "1       ...    0   0   0   0    0   1    0  0.143  2018      3  \n",
       "2       ...    0   0   0   0    0   0    0  0.167  2018      3  \n",
       "3       ...    1   0   0   0    0   0    0  0.176  2018      3  \n",
       "4       ...    3   0   0   0    0   0    1  0.190  2018      3  \n",
       "...     ...  ...  ..  ..  ..  ...  ..  ...    ...   ...    ...  \n",
       "112268  ...    0   0   0   1    0   0    0  0.158  2018      6  \n",
       "112269  ...    0   0   0   0    0   1    0  0.150  2018      6  \n",
       "112270  ...    0   0   0   0    0   1    0  0.182  2018      6  \n",
       "112271  ...    0   0   0   0    0   0    0  0.182  2018      6  \n",
       "112272  ...    0   0   0   0    0   0    0  0.167  2018      6  \n",
       "\n",
       "[112273 rows x 21 columns]"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 일별 데이터에서 결측치를 0으로 채우기\n",
    "day_by_day_df[day_by_day_df.select_dtypes(include=numerics).columns] = \\\n",
    "    day_by_day_df[day_by_day_df.select_dtypes(include=numerics).columns].fillna(0)\n",
    "day_by_day_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_id</th>\n",
       "      <th>batter_name</th>\n",
       "      <th>year</th>\n",
       "      <th>team</th>\n",
       "      <th>avg</th>\n",
       "      <th>G</th>\n",
       "      <th>AB</th>\n",
       "      <th>R</th>\n",
       "      <th>H</th>\n",
       "      <th>2B</th>\n",
       "      <th>...</th>\n",
       "      <th>SLG</th>\n",
       "      <th>OBP</th>\n",
       "      <th>E</th>\n",
       "      <th>height/weight</th>\n",
       "      <th>year_born</th>\n",
       "      <th>position</th>\n",
       "      <th>career</th>\n",
       "      <th>starting_salary</th>\n",
       "      <th>OPS</th>\n",
       "      <th>new_idx</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>가르시아</td>\n",
       "      <td>2018</td>\n",
       "      <td>LG</td>\n",
       "      <td>0.350</td>\n",
       "      <td>7</td>\n",
       "      <td>20</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0.550</td>\n",
       "      <td>0.409</td>\n",
       "      <td>1</td>\n",
       "      <td>177cm/93kg</td>\n",
       "      <td>1985년 04월 12일</td>\n",
       "      <td>내야수(우투우타)</td>\n",
       "      <td>쿠바 Ciego de Avila Maximo Gomez Baez(대)</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.959</td>\n",
       "      <td>가르시아2018</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2011</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.000</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.500</td>\n",
       "      <td>0</td>\n",
       "      <td>180cm/72kg</td>\n",
       "      <td>1992년 08월 11일</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000만원</td>\n",
       "      <td>0.500</td>\n",
       "      <td>강경학2011</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2014</td>\n",
       "      <td>한화</td>\n",
       "      <td>-</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0</td>\n",
       "      <td>180cm/72kg</td>\n",
       "      <td>1992년 08월 11일</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000만원</td>\n",
       "      <td>0.000</td>\n",
       "      <td>강경학2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2015</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.130</td>\n",
       "      <td>10</td>\n",
       "      <td>23</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.130</td>\n",
       "      <td>0.286</td>\n",
       "      <td>2</td>\n",
       "      <td>180cm/72kg</td>\n",
       "      <td>1992년 08월 11일</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000만원</td>\n",
       "      <td>0.416</td>\n",
       "      <td>강경학2015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2016</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.188</td>\n",
       "      <td>14</td>\n",
       "      <td>32</td>\n",
       "      <td>4</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0.281</td>\n",
       "      <td>0.212</td>\n",
       "      <td>0</td>\n",
       "      <td>180cm/72kg</td>\n",
       "      <td>1992년 08월 11일</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000만원</td>\n",
       "      <td>0.493</td>\n",
       "      <td>강경학2016</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1388</th>\n",
       "      <td>342</td>\n",
       "      <td>황재균</td>\n",
       "      <td>2014</td>\n",
       "      <td>롯데</td>\n",
       "      <td>0.407</td>\n",
       "      <td>10</td>\n",
       "      <td>27</td>\n",
       "      <td>3</td>\n",
       "      <td>11</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>0.593</td>\n",
       "      <td>0.448</td>\n",
       "      <td>1</td>\n",
       "      <td>183cm/96kg</td>\n",
       "      <td>1987년 07월 28일</td>\n",
       "      <td>내야수(우투우타)</td>\n",
       "      <td>사당초-이수중-경기고-현대-우리-히어로즈-넥센-롯데-샌프란시스코</td>\n",
       "      <td>6000만원</td>\n",
       "      <td>1.041</td>\n",
       "      <td>황재균2014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1389</th>\n",
       "      <td>342</td>\n",
       "      <td>황재균</td>\n",
       "      <td>2015</td>\n",
       "      <td>롯데</td>\n",
       "      <td>0.333</td>\n",
       "      <td>11</td>\n",
       "      <td>30</td>\n",
       "      <td>8</td>\n",
       "      <td>10</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>0.433</td>\n",
       "      <td>0.389</td>\n",
       "      <td>0</td>\n",
       "      <td>183cm/96kg</td>\n",
       "      <td>1987년 07월 28일</td>\n",
       "      <td>내야수(우투우타)</td>\n",
       "      <td>사당초-이수중-경기고-현대-우리-히어로즈-넥센-롯데-샌프란시스코</td>\n",
       "      <td>6000만원</td>\n",
       "      <td>0.822</td>\n",
       "      <td>황재균2015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1390</th>\n",
       "      <td>342</td>\n",
       "      <td>황재균</td>\n",
       "      <td>2016</td>\n",
       "      <td>롯데</td>\n",
       "      <td>0.310</td>\n",
       "      <td>16</td>\n",
       "      <td>42</td>\n",
       "      <td>8</td>\n",
       "      <td>13</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>0.429</td>\n",
       "      <td>0.370</td>\n",
       "      <td>1</td>\n",
       "      <td>183cm/96kg</td>\n",
       "      <td>1987년 07월 28일</td>\n",
       "      <td>내야수(우투우타)</td>\n",
       "      <td>사당초-이수중-경기고-현대-우리-히어로즈-넥센-롯데-샌프란시스코</td>\n",
       "      <td>6000만원</td>\n",
       "      <td>0.799</td>\n",
       "      <td>황재균2016</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1391</th>\n",
       "      <td>342</td>\n",
       "      <td>황재균</td>\n",
       "      <td>2018</td>\n",
       "      <td>KT</td>\n",
       "      <td>0.250</td>\n",
       "      <td>6</td>\n",
       "      <td>16</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0.500</td>\n",
       "      <td>0.333</td>\n",
       "      <td>3</td>\n",
       "      <td>183cm/96kg</td>\n",
       "      <td>1987년 07월 28일</td>\n",
       "      <td>내야수(우투우타)</td>\n",
       "      <td>사당초-이수중-경기고-현대-우리-히어로즈-넥센-롯데-샌프란시스코</td>\n",
       "      <td>6000만원</td>\n",
       "      <td>0.833</td>\n",
       "      <td>황재균2018</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1392</th>\n",
       "      <td>344</td>\n",
       "      <td>황진수</td>\n",
       "      <td>2014</td>\n",
       "      <td>롯데</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0</td>\n",
       "      <td>181cm/82kg</td>\n",
       "      <td>1989년 02월 15일</td>\n",
       "      <td>내야수(우투양타)</td>\n",
       "      <td>석천초-대헌중-공주고</td>\n",
       "      <td>4000만원</td>\n",
       "      <td>0.000</td>\n",
       "      <td>황진수2014</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1393 rows × 30 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      batter_id batter_name  year team    avg   G  AB  R   H  2B  ...    SLG  \\\n",
       "0             0        가르시아  2018   LG  0.350   7  20  1   7   1  ...  0.550   \n",
       "1             1         강경학  2011   한화  0.000   4   2  2   0   0  ...  0.000   \n",
       "2             1         강경학  2014   한화      -   4   0  2   0   0  ...  0.000   \n",
       "3             1         강경학  2015   한화  0.130  10  23  3   3   0  ...  0.130   \n",
       "4             1         강경학  2016   한화  0.188  14  32  4   6   1  ...  0.281   \n",
       "...         ...         ...   ...  ...    ...  ..  .. ..  ..  ..  ...    ...   \n",
       "1388        342         황재균  2014   롯데  0.407  10  27  3  11   2  ...  0.593   \n",
       "1389        342         황재균  2015   롯데  0.333  11  30  8  10   3  ...  0.433   \n",
       "1390        342         황재균  2016   롯데  0.310  16  42  8  13   3  ...  0.429   \n",
       "1391        342         황재균  2018   KT  0.250   6  16  3   4   1  ...  0.500   \n",
       "1392        344         황진수  2014   롯데  0.000   1   1  1   0   0  ...  0.000   \n",
       "\n",
       "        OBP  E  height/weight      year_born   position  \\\n",
       "0     0.409  1     177cm/93kg  1985년 04월 12일  내야수(우투우타)   \n",
       "1     0.500  0     180cm/72kg  1992년 08월 11일  내야수(우투좌타)   \n",
       "2     0.000  0     180cm/72kg  1992년 08월 11일  내야수(우투좌타)   \n",
       "3     0.286  2     180cm/72kg  1992년 08월 11일  내야수(우투좌타)   \n",
       "4     0.212  0     180cm/72kg  1992년 08월 11일  내야수(우투좌타)   \n",
       "...     ... ..            ...            ...        ...   \n",
       "1388  0.448  1     183cm/96kg  1987년 07월 28일  내야수(우투우타)   \n",
       "1389  0.389  0     183cm/96kg  1987년 07월 28일  내야수(우투우타)   \n",
       "1390  0.370  1     183cm/96kg  1987년 07월 28일  내야수(우투우타)   \n",
       "1391  0.333  3     183cm/96kg  1987년 07월 28일  내야수(우투우타)   \n",
       "1392  0.000  0     181cm/82kg  1989년 02월 15일  내야수(우투양타)   \n",
       "\n",
       "                                      career  starting_salary    OPS   new_idx  \n",
       "0     쿠바 Ciego de Avila Maximo Gomez Baez(대)              NaN  0.959  가르시아2018  \n",
       "1                          광주대성초-광주동성중-광주동성고          10000만원  0.500   강경학2011  \n",
       "2                          광주대성초-광주동성중-광주동성고          10000만원  0.000   강경학2014  \n",
       "3                          광주대성초-광주동성중-광주동성고          10000만원  0.416   강경학2015  \n",
       "4                          광주대성초-광주동성중-광주동성고          10000만원  0.493   강경학2016  \n",
       "...                                      ...              ...    ...       ...  \n",
       "1388     사당초-이수중-경기고-현대-우리-히어로즈-넥센-롯데-샌프란시스코           6000만원  1.041   황재균2014  \n",
       "1389     사당초-이수중-경기고-현대-우리-히어로즈-넥센-롯데-샌프란시스코           6000만원  0.822   황재균2015  \n",
       "1390     사당초-이수중-경기고-현대-우리-히어로즈-넥센-롯데-샌프란시스코           6000만원  0.799   황재균2016  \n",
       "1391     사당초-이수중-경기고-현대-우리-히어로즈-넥센-롯데-샌프란시스코           6000만원  0.833   황재균2018  \n",
       "1392                             석천초-대헌중-공주고           4000만원  0.000   황진수2014  \n",
       "\n",
       "[1393 rows x 30 columns]"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 프리시즌 데이터에서 결측치를 0으로 채우기\n",
    "preseason_df[preseason_df.select_dtypes(include=numerics).columns] = \\\n",
    "    preseason_df[preseason_df.select_dtypes(include=numerics).columns].fillna(0)\n",
    "preseason_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_name</th>\n",
       "      <th>team</th>\n",
       "      <th>height/weight</th>\n",
       "      <th>year_born</th>\n",
       "      <th>position</th>\n",
       "      <th>career</th>\n",
       "      <th>pos</th>\n",
       "      <th>hit_way</th>\n",
       "      <th>country</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>백승룡</td>\n",
       "      <td>한화</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1982년 08월 16일</td>\n",
       "      <td>NaN</td>\n",
       "      <td>사직초(부산극동리틀)-사직중-경남상고-경성대-한화-넥센</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>백승룡</td>\n",
       "      <td>한화</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1982년 08월 16일</td>\n",
       "      <td>NaN</td>\n",
       "      <td>사직초(부산극동리틀)-사직중-경남상고-경성대-한화-넥센</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>백승룡</td>\n",
       "      <td>한화</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1982년 08월 16일</td>\n",
       "      <td>NaN</td>\n",
       "      <td>사직초(부산극동리틀)-사직중-경남상고-경성대-한화-넥센</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>백승룡</td>\n",
       "      <td>한화</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1982년 08월 16일</td>\n",
       "      <td>NaN</td>\n",
       "      <td>사직초(부산극동리틀)-사직중-경남상고-경성대-한화-넥센</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>백승룡</td>\n",
       "      <td>한화</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1982년 08월 16일</td>\n",
       "      <td>NaN</td>\n",
       "      <td>사직초(부산극동리틀)-사직중-경남상고-경성대-한화-넥센</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   batter_name team height/weight      year_born position  \\\n",
       "12         백승룡   한화           NaN  1982년 08월 16일      NaN   \n",
       "13         백승룡   한화           NaN  1982년 08월 16일      NaN   \n",
       "14         백승룡   한화           NaN  1982년 08월 16일      NaN   \n",
       "15         백승룡   한화           NaN  1982년 08월 16일      NaN   \n",
       "16         백승룡   한화           NaN  1982년 08월 16일      NaN   \n",
       "\n",
       "                            career  pos hit_way country  \n",
       "12  사직초(부산극동리틀)-사직중-경남상고-경성대-한화-넥센  NaN     NaN  korean  \n",
       "13  사직초(부산극동리틀)-사직중-경남상고-경성대-한화-넥센  NaN     NaN  korean  \n",
       "14  사직초(부산극동리틀)-사직중-경남상고-경성대-한화-넥센  NaN     NaN  korean  \n",
       "15  사직초(부산극동리틀)-사직중-경남상고-경성대-한화-넥센  NaN     NaN  korean  \n",
       "16  사직초(부산극동리틀)-사직중-경남상고-경성대-한화-넥센  NaN     NaN  korean  "
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 수치형이 아닌 변수 추출\n",
    "not_num_cols = [x for x in regular_season_df.columns if x not in num_cols]\n",
    "\n",
    "# 수치형이 아닌 변수 중 결측치가 하나라도 존재하는 행 출력\n",
    "# isna().sum(axis=1) -> 열 기준의 결측치 개수\n",
    "# df.loc[]를 통해 결측치 0개 이상 데이터를 추출\n",
    "regular_season_df.loc[regular_season_df[not_num_cols].isna().sum(axis=1) > 0, not_num_cols].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_id</th>\n",
       "      <th>batter_name</th>\n",
       "      <th>year</th>\n",
       "      <th>team</th>\n",
       "      <th>avg</th>\n",
       "      <th>G</th>\n",
       "      <th>AB</th>\n",
       "      <th>R</th>\n",
       "      <th>H</th>\n",
       "      <th>2B</th>\n",
       "      <th>...</th>\n",
       "      <th>position</th>\n",
       "      <th>career</th>\n",
       "      <th>starting_salary</th>\n",
       "      <th>OPS</th>\n",
       "      <th>weight</th>\n",
       "      <th>height</th>\n",
       "      <th>weight_per_height</th>\n",
       "      <th>pos</th>\n",
       "      <th>hit_way</th>\n",
       "      <th>country</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>가르시아</td>\n",
       "      <td>2018</td>\n",
       "      <td>LG</td>\n",
       "      <td>0.339</td>\n",
       "      <td>50</td>\n",
       "      <td>183</td>\n",
       "      <td>27</td>\n",
       "      <td>62</td>\n",
       "      <td>9</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투우타)</td>\n",
       "      <td>쿠바 Ciego de Avila Maximo Gomez Baez(대)</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.902</td>\n",
       "      <td>93.0</td>\n",
       "      <td>177.0</td>\n",
       "      <td>0.525424</td>\n",
       "      <td>내야수</td>\n",
       "      <td>우타</td>\n",
       "      <td>foreign</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2011</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.000</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000.0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>72.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>내야수</td>\n",
       "      <td>좌타</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2014</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.221</td>\n",
       "      <td>41</td>\n",
       "      <td>86</td>\n",
       "      <td>11</td>\n",
       "      <td>19</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000.0</td>\n",
       "      <td>0.686</td>\n",
       "      <td>72.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>내야수</td>\n",
       "      <td>좌타</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2015</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.257</td>\n",
       "      <td>120</td>\n",
       "      <td>311</td>\n",
       "      <td>50</td>\n",
       "      <td>80</td>\n",
       "      <td>7</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000.0</td>\n",
       "      <td>0.673</td>\n",
       "      <td>72.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>내야수</td>\n",
       "      <td>좌타</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2016</td>\n",
       "      <td>한화</td>\n",
       "      <td>0.158</td>\n",
       "      <td>46</td>\n",
       "      <td>101</td>\n",
       "      <td>16</td>\n",
       "      <td>16</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투좌타)</td>\n",
       "      <td>광주대성초-광주동성중-광주동성고</td>\n",
       "      <td>10000.0</td>\n",
       "      <td>0.489</td>\n",
       "      <td>72.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>내야수</td>\n",
       "      <td>좌타</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2442</th>\n",
       "      <td>344</td>\n",
       "      <td>황진수</td>\n",
       "      <td>2014</td>\n",
       "      <td>롯데</td>\n",
       "      <td>0.000</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투양타)</td>\n",
       "      <td>석천초-대헌중-공주고</td>\n",
       "      <td>4000.0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>82.0</td>\n",
       "      <td>181.0</td>\n",
       "      <td>0.453039</td>\n",
       "      <td>내야수</td>\n",
       "      <td>양타</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2443</th>\n",
       "      <td>344</td>\n",
       "      <td>황진수</td>\n",
       "      <td>2015</td>\n",
       "      <td>롯데</td>\n",
       "      <td>0.000</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투양타)</td>\n",
       "      <td>석천초-대헌중-공주고</td>\n",
       "      <td>4000.0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>82.0</td>\n",
       "      <td>181.0</td>\n",
       "      <td>0.453039</td>\n",
       "      <td>내야수</td>\n",
       "      <td>양타</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2444</th>\n",
       "      <td>344</td>\n",
       "      <td>황진수</td>\n",
       "      <td>2016</td>\n",
       "      <td>롯데</td>\n",
       "      <td>0.000</td>\n",
       "      <td>11</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투양타)</td>\n",
       "      <td>석천초-대헌중-공주고</td>\n",
       "      <td>4000.0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>82.0</td>\n",
       "      <td>181.0</td>\n",
       "      <td>0.453039</td>\n",
       "      <td>내야수</td>\n",
       "      <td>양타</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2445</th>\n",
       "      <td>344</td>\n",
       "      <td>황진수</td>\n",
       "      <td>2017</td>\n",
       "      <td>롯데</td>\n",
       "      <td>0.291</td>\n",
       "      <td>60</td>\n",
       "      <td>117</td>\n",
       "      <td>18</td>\n",
       "      <td>34</td>\n",
       "      <td>6</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투양타)</td>\n",
       "      <td>석천초-대헌중-공주고</td>\n",
       "      <td>4000.0</td>\n",
       "      <td>0.761</td>\n",
       "      <td>82.0</td>\n",
       "      <td>181.0</td>\n",
       "      <td>0.453039</td>\n",
       "      <td>내야수</td>\n",
       "      <td>양타</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2446</th>\n",
       "      <td>344</td>\n",
       "      <td>황진수</td>\n",
       "      <td>2018</td>\n",
       "      <td>롯데</td>\n",
       "      <td>0.167</td>\n",
       "      <td>18</td>\n",
       "      <td>24</td>\n",
       "      <td>6</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>내야수(우투양타)</td>\n",
       "      <td>석천초-대헌중-공주고</td>\n",
       "      <td>4000.0</td>\n",
       "      <td>0.564</td>\n",
       "      <td>82.0</td>\n",
       "      <td>181.0</td>\n",
       "      <td>0.453039</td>\n",
       "      <td>내야수</td>\n",
       "      <td>양타</td>\n",
       "      <td>korean</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2447 rows × 35 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      batter_id batter_name  year team    avg    G   AB   R   H  2B  ...  \\\n",
       "0             0        가르시아  2018   LG  0.339   50  183  27  62   9  ...   \n",
       "1             1         강경학  2011   한화  0.000    2    1   0   0   0  ...   \n",
       "2             1         강경학  2014   한화  0.221   41   86  11  19   2  ...   \n",
       "3             1         강경학  2015   한화  0.257  120  311  50  80   7  ...   \n",
       "4             1         강경학  2016   한화  0.158   46  101  16  16   3  ...   \n",
       "...         ...         ...   ...  ...    ...  ...  ...  ..  ..  ..  ...   \n",
       "2442        344         황진수  2014   롯데  0.000    5    5   0   0   0  ...   \n",
       "2443        344         황진수  2015   롯데  0.000    2    2   0   0   0  ...   \n",
       "2444        344         황진수  2016   롯데  0.000   11   10   2   0   0  ...   \n",
       "2445        344         황진수  2017   롯데  0.291   60  117  18  34   6  ...   \n",
       "2446        344         황진수  2018   롯데  0.167   18   24   6   4   1  ...   \n",
       "\n",
       "       position                                  career  starting_salary  \\\n",
       "0     내야수(우투우타)  쿠바 Ciego de Avila Maximo Gomez Baez(대)              0.0   \n",
       "1     내야수(우투좌타)                       광주대성초-광주동성중-광주동성고          10000.0   \n",
       "2     내야수(우투좌타)                       광주대성초-광주동성중-광주동성고          10000.0   \n",
       "3     내야수(우투좌타)                       광주대성초-광주동성중-광주동성고          10000.0   \n",
       "4     내야수(우투좌타)                       광주대성초-광주동성중-광주동성고          10000.0   \n",
       "...         ...                                     ...              ...   \n",
       "2442  내야수(우투양타)                             석천초-대헌중-공주고           4000.0   \n",
       "2443  내야수(우투양타)                             석천초-대헌중-공주고           4000.0   \n",
       "2444  내야수(우투양타)                             석천초-대헌중-공주고           4000.0   \n",
       "2445  내야수(우투양타)                             석천초-대헌중-공주고           4000.0   \n",
       "2446  내야수(우투양타)                             석천초-대헌중-공주고           4000.0   \n",
       "\n",
       "        OPS  weight  height  weight_per_height  pos  hit_way  country  \n",
       "0     0.902    93.0   177.0           0.525424  내야수       우타  foreign  \n",
       "1     0.000    72.0   180.0           0.400000  내야수       좌타   korean  \n",
       "2     0.686    72.0   180.0           0.400000  내야수       좌타   korean  \n",
       "3     0.673    72.0   180.0           0.400000  내야수       좌타   korean  \n",
       "4     0.489    72.0   180.0           0.400000  내야수       좌타   korean  \n",
       "...     ...     ...     ...                ...  ...      ...      ...  \n",
       "2442  0.000    82.0   181.0           0.453039  내야수       양타   korean  \n",
       "2443  0.000    82.0   181.0           0.453039  내야수       양타   korean  \n",
       "2444  0.000    82.0   181.0           0.453039  내야수       양타   korean  \n",
       "2445  0.761    82.0   181.0           0.453039  내야수       양타   korean  \n",
       "2446  0.564    82.0   181.0           0.453039  내야수       양타   korean  \n",
       "\n",
       "[2447 rows x 35 columns]"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 삭제할 데이터 추출\n",
    "drop_idx = regular_season_df.loc[\n",
    "    # 안타가 0개 이상이면서 장타율이 0인 경우\n",
    "    ((regular_season_df['H'] > 0) & (regular_season_df['SLG']==0)) |\n",
    "        \n",
    "    # 안타가 0개 이상 혹은 볼넷이 0개 이상 혹은 몸에 맞은 볼이 0개 이상이면서\n",
    "    # 출루율이 0인 경우\n",
    "    (((regular_season_df['H'] > 0) |\n",
    "      (regular_season_df['BB'] > 0) |\n",
    "      (regular_season_df['HBP'] > 0)) &\n",
    "     (regular_season_df['OBP'] == 0))\n",
    "].index         \n",
    "\n",
    "# 데이터 삭제\n",
    "regular_season_df = regular_season_df.drop(drop_idx).reset_index(drop=True)\n",
    "regular_season_df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1.3.2. 규정 타수 정의"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x216 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(6, 3)) # 크기 조정\n",
    "plt.plot('AB', 'OPS', data=regular_season_df, linestyle='none', marker='o', \n",
    "         markersize=2, color='blue', alpha=0.4)\n",
    "plt.xlabel('AB', fontsize=14)\n",
    "plt.ylabel('OPS', fontsize=14)\n",
    "plt.xticks(list(range(min(regular_season_df['AB']), max(regular_season_df['AB']), 30)),\n",
    "           rotation=90)\n",
    "plt.vlines(30, ymin=min(regular_season_df['OPS']), ymax=max(regular_season_df['OPS']),\n",
    "           linestyles='dashed', colors='r')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_name</th>\n",
       "      <th>AB</th>\n",
       "      <th>year</th>\n",
       "      <th>OPS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2329</th>\n",
       "      <td>테임즈</td>\n",
       "      <td>472</td>\n",
       "      <td>2015</td>\n",
       "      <td>1.293656</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>97</th>\n",
       "      <td>강정호</td>\n",
       "      <td>418</td>\n",
       "      <td>2014</td>\n",
       "      <td>1.200156</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1318</th>\n",
       "      <td>유재신</td>\n",
       "      <td>33</td>\n",
       "      <td>2018</td>\n",
       "      <td>1.192000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>416</th>\n",
       "      <td>김원섭</td>\n",
       "      <td>25</td>\n",
       "      <td>2005</td>\n",
       "      <td>0.116923</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1543</th>\n",
       "      <td>이여상</td>\n",
       "      <td>22</td>\n",
       "      <td>2013</td>\n",
       "      <td>0.090909</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>681</th>\n",
       "      <td>문규현</td>\n",
       "      <td>18</td>\n",
       "      <td>2007</td>\n",
       "      <td>0.109000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>578</th>\n",
       "      <td>김회성</td>\n",
       "      <td>17</td>\n",
       "      <td>2010</td>\n",
       "      <td>0.105000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1902</th>\n",
       "      <td>정병곤</td>\n",
       "      <td>15</td>\n",
       "      <td>2018</td>\n",
       "      <td>0.130000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1874</th>\n",
       "      <td>정경운</td>\n",
       "      <td>15</td>\n",
       "      <td>2018</td>\n",
       "      <td>0.130000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2384</th>\n",
       "      <td>현재윤</td>\n",
       "      <td>15</td>\n",
       "      <td>2014</td>\n",
       "      <td>1.229167</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     batter_name   AB  year       OPS\n",
       "2329         테임즈  472  2015  1.293656\n",
       "97           강정호  418  2014  1.200156\n",
       "1318         유재신   33  2018  1.192000\n",
       "416          김원섭   25  2005  0.116923\n",
       "1543         이여상   22  2013  0.090909\n",
       "681          문규현   18  2007  0.109000\n",
       "578          김회성   17  2010  0.105000\n",
       "1902         정병곤   15  2018  0.130000\n",
       "1874         정경운   15  2018  0.130000\n",
       "2384         현재윤   15  2014  1.229167"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# OPS 이상치 탐색을 위한 수치 정의\n",
    "Q1 = regular_season_df['OPS'].quantile(0.25)\n",
    "Q3 = regular_season_df['OPS'].quantile(0.75)\n",
    "IQR = Q3 - Q1\n",
    "\n",
    "# 실제 OPS 이상치 탐색\n",
    "regular_season_df.loc[(regular_season_df['OPS'] < (Q1 - 1.5 * IQR)) |\n",
    "                      (regular_season_df['OPS'] > (Q3 + 1.5 * IQR))].sort_values(\n",
    "    by=['AB'], axis=0, ascending=False)[['batter_name','AB','year','OPS']].head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id='m4'>7월 일별 경기수 합</a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 7.01~7.31 숫자 생성 후 반 올림\n",
    "major_ticks = list(np.round(np.linspace(7.01, 7.31, 31), 2)) \n",
    "\n",
    "july = (day_by_day_df['date'] >= 7) & (day_by_day_df['date'] < 8) # 7월만 불러오는 index\n",
    "plt.plot(major_ticks, day_by_day_df['date'].loc[july].value_counts().sort_index(), marker='o')\n",
    "plt.grid(linestyle='-', alpha=0.4)\n",
    "plt.xticks(major_ticks,rotation=90)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1.3.3. 시간 변수"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 시간 변수를 생성하는 함수 정의\n",
    "def lag_function(df, var_name, past):\n",
    "    # df = 시간변수를 생성할 데이터 프레임\n",
    "    # var_name = 시간변수 생성의 대상이 되는 변수 이름\n",
    "    # past = 몇 년 전의 성적을 생성할지 결정 (정수형)\n",
    "    df.reset_index(drop=True, inplace = True)\n",
    "    \n",
    "    #시간변수 생성\n",
    "    df['lag' + str(past) + '_' + var_name] = np.nan \n",
    "    # 'lag1_avg','lag1_G', 'AB', 'R', 'H', '2B', '3B', 'HR', 'TB', 'RBI', 'SB', 'CS', 'BB', 'HBP', 'SO', 'GDP', 'OBP', 'E', 'starting_salary']\n",
    "    df['lag' + str(past) + '_' + 'AB'] = np.nan # lag1_AB\n",
    "    \n",
    "    for col in ['AB', var_name]: # \n",
    "        for i in range(0, (max(df.index)+1)): # 행개수 \n",
    "            val = df.loc[(df['batter_name'] == df['batter_name'][i]) & (df['year'] == df['year'][i] - past), col]\n",
    "            # 과거 기록이 결측치가 아니라면 값을 넣기\n",
    "            if(len(val) != 0):\n",
    "                df.loc[i, 'lag' + str(past) + '_' + col] = val.iloc[0]\n",
    "\n",
    "    #30타수 미만 결측치 처리\n",
    "    df.loc[df['lag' + str(past) + '_' + 'AB'] < 30, 'lag' + str(past) + '_' + var_name] = np.nan\n",
    "    df.drop('lag' + str(past) + '_' + 'AB', axis = 1, inplace = True)\n",
    "\n",
    "    return df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Series([], Name: AB, dtype: int64)"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "val1 = regular_season_df.loc[(regular_season_df['batter_name'] == regular_season_df['batter_name'][0]) & (regular_season_df['year'] == regular_season_df['year'][0] - 1), 'AB']\n",
    "val1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['avg',\n",
       " 'G',\n",
       " 'AB',\n",
       " 'R',\n",
       " 'H',\n",
       " '2B',\n",
       " '3B',\n",
       " 'HR',\n",
       " 'TB',\n",
       " 'RBI',\n",
       " 'SB',\n",
       " 'CS',\n",
       " 'BB',\n",
       " 'HBP',\n",
       " 'SO',\n",
       " 'GDP',\n",
       " 'OBP',\n",
       " 'E',\n",
       " 'starting_salary',\n",
       " 'weight',\n",
       " 'height',\n",
       " 'weight_per_height']"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "numeric_cols = list(regular_season_df.select_dtypes(include=numerics).drop(['batter_id','year','OPS','SLG'], axis =1).columns)\n",
    "numeric_cols"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>avg</th>\n",
       "      <th>G</th>\n",
       "      <th>AB</th>\n",
       "      <th>R</th>\n",
       "      <th>H</th>\n",
       "      <th>2B</th>\n",
       "      <th>3B</th>\n",
       "      <th>HR</th>\n",
       "      <th>TB</th>\n",
       "      <th>RBI</th>\n",
       "      <th>...</th>\n",
       "      <th>SO</th>\n",
       "      <th>GDP</th>\n",
       "      <th>OBP</th>\n",
       "      <th>E</th>\n",
       "      <th>starting_salary</th>\n",
       "      <th>weight</th>\n",
       "      <th>height</th>\n",
       "      <th>weight_per_height</th>\n",
       "      <th>year</th>\n",
       "      <th>batter_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.339</td>\n",
       "      <td>50</td>\n",
       "      <td>183</td>\n",
       "      <td>27</td>\n",
       "      <td>62</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>95</td>\n",
       "      <td>34</td>\n",
       "      <td>...</td>\n",
       "      <td>25</td>\n",
       "      <td>3</td>\n",
       "      <td>0.383</td>\n",
       "      <td>9</td>\n",
       "      <td>0.0</td>\n",
       "      <td>93.0</td>\n",
       "      <td>177.0</td>\n",
       "      <td>0.525424</td>\n",
       "      <td>2018</td>\n",
       "      <td>가르시아</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.221</td>\n",
       "      <td>41</td>\n",
       "      <td>86</td>\n",
       "      <td>11</td>\n",
       "      <td>19</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>30</td>\n",
       "      <td>7</td>\n",
       "      <td>...</td>\n",
       "      <td>28</td>\n",
       "      <td>1</td>\n",
       "      <td>0.337</td>\n",
       "      <td>6</td>\n",
       "      <td>10000.0</td>\n",
       "      <td>72.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>2014</td>\n",
       "      <td>강경학</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.257</td>\n",
       "      <td>120</td>\n",
       "      <td>311</td>\n",
       "      <td>50</td>\n",
       "      <td>80</td>\n",
       "      <td>7</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>101</td>\n",
       "      <td>27</td>\n",
       "      <td>...</td>\n",
       "      <td>58</td>\n",
       "      <td>3</td>\n",
       "      <td>0.348</td>\n",
       "      <td>15</td>\n",
       "      <td>10000.0</td>\n",
       "      <td>72.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>2015</td>\n",
       "      <td>강경학</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.158</td>\n",
       "      <td>46</td>\n",
       "      <td>101</td>\n",
       "      <td>16</td>\n",
       "      <td>16</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>26</td>\n",
       "      <td>7</td>\n",
       "      <td>...</td>\n",
       "      <td>30</td>\n",
       "      <td>5</td>\n",
       "      <td>0.232</td>\n",
       "      <td>7</td>\n",
       "      <td>10000.0</td>\n",
       "      <td>72.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>2016</td>\n",
       "      <td>강경학</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.214</td>\n",
       "      <td>59</td>\n",
       "      <td>84</td>\n",
       "      <td>17</td>\n",
       "      <td>18</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>22</td>\n",
       "      <td>4</td>\n",
       "      <td>...</td>\n",
       "      <td>19</td>\n",
       "      <td>1</td>\n",
       "      <td>0.290</td>\n",
       "      <td>4</td>\n",
       "      <td>10000.0</td>\n",
       "      <td>72.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>2017</td>\n",
       "      <td>강경학</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 24 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     avg    G   AB   R   H  2B  3B  HR   TB  RBI  ...  SO  GDP    OBP   E  \\\n",
       "0  0.339   50  183  27  62   9   0   8   95   34  ...  25    3  0.383   9   \n",
       "2  0.221   41   86  11  19   2   3   1   30    7  ...  28    1  0.337   6   \n",
       "3  0.257  120  311  50  80   7   4   2  101   27  ...  58    3  0.348  15   \n",
       "4  0.158   46  101  16  16   3   2   1   26    7  ...  30    5  0.232   7   \n",
       "5  0.214   59   84  17  18   2   1   0   22    4  ...  19    1  0.290   4   \n",
       "\n",
       "   starting_salary  weight  height  weight_per_height  year  batter_name  \n",
       "0              0.0    93.0   177.0           0.525424  2018         가르시아  \n",
       "2          10000.0    72.0   180.0           0.400000  2014          강경학  \n",
       "3          10000.0    72.0   180.0           0.400000  2015          강경학  \n",
       "4          10000.0    72.0   180.0           0.400000  2016          강경학  \n",
       "5          10000.0    72.0   180.0           0.400000  2017          강경학  \n",
       "\n",
       "[5 rows x 24 columns]"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 상관관계를 탐색할 변수 선택\n",
    "numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64']\n",
    "numeric_cols = list(regular_season_df.select_dtypes(include=numerics).drop(['batter_id','year','OPS','SLG'], axis =1).columns)\n",
    "regular_season_temp = regular_season_df[numeric_cols + ['year', 'batter_name']].copy()\n",
    "regular_season_temp = regular_season_temp.loc[regular_season_temp['AB'] >= 30]\n",
    "regular_season_temp.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>OBP</th>\n",
       "      <th>year</th>\n",
       "      <th>batter_name</th>\n",
       "      <th>lag1_avg</th>\n",
       "      <th>lag1_G</th>\n",
       "      <th>lag1_R</th>\n",
       "      <th>lag1_H</th>\n",
       "      <th>lag1_2B</th>\n",
       "      <th>lag1_3B</th>\n",
       "      <th>lag1_HR</th>\n",
       "      <th>...</th>\n",
       "      <th>lag1_BB</th>\n",
       "      <th>lag1_HBP</th>\n",
       "      <th>lag1_SO</th>\n",
       "      <th>lag1_GDP</th>\n",
       "      <th>lag1_OBP</th>\n",
       "      <th>lag1_E</th>\n",
       "      <th>lag1_starting_salary</th>\n",
       "      <th>lag1_weight</th>\n",
       "      <th>lag1_height</th>\n",
       "      <th>lag1_weight_per_height</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.383</td>\n",
       "      <td>2018</td>\n",
       "      <td>가르시아</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.337</td>\n",
       "      <td>2014</td>\n",
       "      <td>강경학</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.348</td>\n",
       "      <td>2015</td>\n",
       "      <td>강경학</td>\n",
       "      <td>0.221</td>\n",
       "      <td>41.0</td>\n",
       "      <td>11.0</td>\n",
       "      <td>19.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>13.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>28.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.337</td>\n",
       "      <td>6.0</td>\n",
       "      <td>10000.0</td>\n",
       "      <td>72.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>0.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.232</td>\n",
       "      <td>2016</td>\n",
       "      <td>강경학</td>\n",
       "      <td>0.257</td>\n",
       "      <td>120.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>...</td>\n",
       "      <td>40.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>58.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.348</td>\n",
       "      <td>15.0</td>\n",
       "      <td>10000.0</td>\n",
       "      <td>72.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>0.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.290</td>\n",
       "      <td>2017</td>\n",
       "      <td>강경학</td>\n",
       "      <td>0.158</td>\n",
       "      <td>46.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>8.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>30.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.232</td>\n",
       "      <td>7.0</td>\n",
       "      <td>10000.0</td>\n",
       "      <td>72.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>0.4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 24 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     OBP  year batter_name  lag1_avg  lag1_G  lag1_R  lag1_H  lag1_2B  \\\n",
       "0  0.383  2018        가르시아       NaN     NaN     NaN     NaN      NaN   \n",
       "1  0.337  2014         강경학       NaN     NaN     NaN     NaN      NaN   \n",
       "2  0.348  2015         강경학     0.221    41.0    11.0    19.0      2.0   \n",
       "3  0.232  2016         강경학     0.257   120.0    50.0    80.0      7.0   \n",
       "4  0.290  2017         강경학     0.158    46.0    16.0    16.0      3.0   \n",
       "\n",
       "   lag1_3B  lag1_HR  ...  lag1_BB  lag1_HBP  lag1_SO  lag1_GDP  lag1_OBP  \\\n",
       "0      NaN      NaN  ...      NaN       NaN      NaN       NaN       NaN   \n",
       "1      NaN      NaN  ...      NaN       NaN      NaN       NaN       NaN   \n",
       "2      3.0      1.0  ...     13.0       2.0     28.0       1.0     0.337   \n",
       "3      4.0      2.0  ...     40.0       5.0     58.0       3.0     0.348   \n",
       "4      2.0      1.0  ...      8.0       2.0     30.0       5.0     0.232   \n",
       "\n",
       "   lag1_E  lag1_starting_salary  lag1_weight  lag1_height  \\\n",
       "0     NaN                   NaN          NaN          NaN   \n",
       "1     NaN                   NaN          NaN          NaN   \n",
       "2     6.0               10000.0         72.0        180.0   \n",
       "3    15.0               10000.0         72.0        180.0   \n",
       "4     7.0               10000.0         72.0        180.0   \n",
       "\n",
       "   lag1_weight_per_height  \n",
       "0                     NaN  \n",
       "1                     NaN  \n",
       "2                     0.4  \n",
       "3                     0.4  \n",
       "4                     0.4  \n",
       "\n",
       "[5 rows x 24 columns]"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 시간변수 생성 함수를 통한 지표별 1년 전 성적 추출\n",
    "for col in numeric_cols:\n",
    "    regular_season_temp = lag_function(regular_season_temp, col, 1)\n",
    "\n",
    "numeric_cols.remove('OBP')\n",
    "regular_season_temp.drop(numeric_cols, axis = 1, inplace= True)\n",
    "regular_season_temp.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Diagonal Correlation HeatMap')"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAt0AAAKmCAYAAACR0iLwAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAAsTAAALEwEAmpwYAAEAAElEQVR4nOzdd3hU1dbA4d+akt4TakBCxwZIEUGkXwvYBfXziigqKiKKCOJVAREUFSxYUBTEetWLXVERBUQQlCgivUPokECSmbQp+/tjhskEMqEOGFnv8+Rx5ux91llnz3Dvmj17zhFjDEoppZRSSqnwsZzsBJRSSimllPqn06JbKaWUUkqpMNOiWymllFJKqTDTolsppZRSSqkw06JbKaWUUkqpMNOiWymllFJKqTDTolsp9Y8nIheIyJ0nO49gIjJbRJqf7DyCichUEbnyCPdpIiLDw5SSUkr9Y2jRrZSq9ERko4j8LCI/iUimiHwtIl32txtj5hpjXj2ZOR4pEUkWkRf85/Oz/7/3/A3yShCRh/c/N8asNMaMCsNxDvpQIiKdROSzY4hZJncRyRARIyK3ldNXRGSpiDx/tMdTSqlgWnQrpf4pLjXGdDDGtASGAy+LyKUnO6mjISLJwI9ApjGmpTGmvf+83j3COFLR86OUAvQ6DnFOhvJyzwIGiciB/394NRB9QrJSSp0StOhWSv3jGGMygTvwFd+IyM37ZyxFpIGIzPDPii8WkR779xORO0TkVxH5TkQeE5F9QW0t/NtnichCEekf1DZbRO4XkekiskxEnglqe1hE5onIfBH5REQiDuMUhgH/M8a8fcB57fXHrCoi7/lz+UVEXhaRKH/bSBF5XkSmAy/4Z4eni8jbwGx/n4tE5Ef/31ciUuPABETkUhGZ6x+n+SJSX0QaAB8ADfznfPGBs88icr1/vzn+GfqOQW37RGSgiHwvIitF5NrDGIuQQp3H4ebuD5MDLAJ6HhD+QeCtoGOlisiXQe+bvv7tGf7nj/nzWCwig47lvJRS/1DGGP3TP/3Tv0r9B2wEkg7YFgHk+x/fDDzvf5wOpPkfnwEs9T8+H1gIxPqfX+r7n0gDkAisBU73P48Bfga6+Z/PBib4H0f6+57hf948KKePgJ5B+zQPcT5/7N8/RPu3wI1Bz58FRvsfjwQWAJH+552AfUAd//O6wHdAlP95L2Cy//FU4Er/4zMBu/9xf+Al/+MMYHHQsTsBn/kftwV+AxKD+q4PGm8v0Mv/uBGwo4JznI2vGJ4d9Lc46FgVncfh5p7hj9kEWBS0/TLgTcq+b5KCxjAF2A2IP4YLuNjfFgf8CZx7sv9d6J/+6d/f68+GUkr9M9nxFUMH2gFcLSJtgAb4inDwFdlvGGOcAMaYr0TE6W9rBywwxqzwtxWIyBTgYmCmv8/7/rZiEfkVqA8sB5wiMgRfgX8OMO8wco8GCstrEJEY4ExjTPBSk5fwFfSP+J9/bYwpDmrPNMZs8j++xH/e3/pXm9iA7HIOtQ3oKyLN/HnvOIy8rwReM8bkAhhjNorIz8B5wFdAMTDN37ZaRLwiEm+MyQ8R7zZjzOKgc+8E3HcY53FEuRtjVorIehG5xBjzDfAQvoK7XVCffSLSTnw/yG2Ar7hO8DdvMMZ86+/nEJFpQHvg14qOq5Q6tWjRrZT6p7oEmFXO9knAFuA1fMXZVv/2WKBkfycRsVL6v5FWfLO0wQzgCXpeFPS4BLCKSEN8Rea9+GZOB+GbHT2UTKAb8Ho5bVb/sSvK5cAiNvi5FfjAGPMwIfjXN88BxgBP4Js5vusw8j7UOBUbY4JzL/HvczTKPY9jyH0MMEFE3MBm/4eCQNEtIo8CtYAJwDr/3/7X8sAPd7HAziM+I6XUP5qu6VZK/eOIyCXACGBoOc2tgfeNMWvwLSPY7yfg5qA117fiW6ICMB9oLyKN/fGjgT7Ap4dI5WxguTFmNuDE90HgcIwGHhGRrkHnJCJSzT8rvFZErg/q3x/4+DBjzwKuF5Gq/rjx+88rSBKQDEwzxmzBN4O9XyGlM7wH+hK4Q0QS/LFPA1rhG7/jLdR5HFXuxpg/8S3DeQFfAX6g1sAnxphl+GbPg9fBNxKRVv48quD7EeaMoz0xpdQ/kxbdSql/iq/8P577FbgCuMgYs66cfo8D00TkB4IKJ2PMNOAX4DcRmYmv4N6/TCIHuAF4TUTmAN8AE40xCw6R03dAooj8gu9HfH8czon4l7FcCgwUkT9FZDa+2dtu/i43Ar385zsb37KN8YcZeynwGPCdiPyEr1BOOqBPDr7lMr+LyAxgT1DbTmCR/weKFx2w3xxgIvC9iMzC923CjfuXmxxPoc7jaHP3GwOsMcb8VU7beOBp/3ldDmwOalsF9PG/b74ABhtjNh7zSSql/lGk7Dd9SimlAEQkEfjTGJNxsnNRf18ikoHvx53NT3IqSqm/OZ3pVkopApeEC14y8B/g85OVj1JKqX8W/SGlUkr5xAMf+n9IJ/guJVfemnCllFLqiOnyEqWUUkoppcJMl5copZRSSikVZrq85NSgX2copZRS6ng7nPsOKD+d6VZKKaWUUirMtOhWSimllFIqzLToVkoppZRSKsy06FZKKaWUUirMtOhWSimllFIqzLToVkoppZRSKsy06FZKKaWUUirMtOhWSimllFIqzLToPslE5DQR+UhEfhSROSLymogkiEgnEdksIj+JyEIRaefvf7OIrPb3/UlEmp7sc1BKKaWUUhXTovskEpEo4GPgKWNMF2NMR+Br4E1/l/eNMR2AG4BhQbs+6+/bF3j2ROaslFJKKaWOnBbdJ1cP4DNjTOb+DcaYL4BIoHpQvybA0gN3NsasBaLDnaRSSimllDo2WnSfXPWAFeVsXwfUBm4QkQXAK8CXB3YSkR7An+UFFpF+IrJIRBZNmjTpOKaslFJKKaWOlO1kJ3CKywIalbO9IfATvuUlw0QkEfhORDr72+8XkevwzX4PLS+wMWYSsL/aNsc3baWUUkopdSS06D65vgRmi8hXxpilACLSC9gDZAf1c/j/u/+biWeNMa+euDSVUkoppdSx0KL7JDLGOEXk/4BxIpKEb0Z6CXAncC6+5SXnAXbgRX//k5avUkoppZQ6OmKMrjw4BeiLrJRSSqnjTWcCj4D+kFIppZRSSqkw06JbKaWUUkqpMNOiWymllFJKqTDTolsppZRSSqkw06JbKaWUUkqpMNOiWymllFJKqTDTolsppZRSSqkw06JbKaWUUkqpMNM7Up4iip+8MixxIx/6LCxxlVJKKaX+SXSmWymllFJKqTDTolsppZRSSqkw06JbKaWUUkqpMNOiWymllFJKqTDTolsppZRSSqkw06JbKaWUUkqpMNNLBp6CrB1uwFL7DLBYcX/zCmZPFgBStS726x7FZG8DwP3dq5jsLVg73YSlZiOIiML903uY9X+czPSVUkoppSodLbqPkYhkAGONMdcf4X6nA48Dbxhjvg3RZyRwNbAPKAFuMMbsEpGpwBn+bbv92wsP67i1zkBiknC99wiSdhrWLjfj/ujxQLt35S+4v3+9zD7elfPwzH4bohOwXzcclxbdSimllFJHRJeXnAQiUgcYBjgOo/tQY0wH4L/AjUHbbzLGtAeWApcc7rEt9ZrjWf4TAGbPZiQqrky7KTo4JbNjne9BSQEUOQ/3UEoppZRSyk+L7uNERLqLyA8islBERvm3JYnIpyIyS0QmisgiAGPMJmNMH2DjERyiMbDsgGNagQxgVTn59BORRSKyaNKkSaXbYxKhIK+0o9cDSOCxpdF52G98Amu3W8ES9EWI1YbtX7fj/mXaEaSslFJKKaVAl5ccT78ZY7r6C+El/qUhQ4Bpxpj3RKQ2MPco4j4tIk8DTuDZoO1vA4nAaiDrwJ2MMZOA/dW2KX5yuv9BAQTPbhsDGN/DPZtxTb4XAGv767E0/xfe379BUmpiPf9aPAs+xezedBSnoJRSSil1atOZ7uOnh4iMB0YDMUAE0ByYDmCMyQJ2HUXcocaYpsCtwJSg7TcZYxoDLwLjDjeYyVqOpUlbACS1FiY/u7RRgt4Oxf5lJLYIrF1v8f3gUgtupZRSSqmjojPdx88AY0wrEYkD+vi3ZQEXAF+ISBOg5jHEzwGiy9m+B4g93CDetYuw1W+B/cYnMCWFuL+ZiLXTTXh+eh9Lw9ZYW18GxovJ3YXnm1eQqnWxVKuP/drhgRiuT8ZCOWu/lVJKKaVU+bToPn4W+tdsZwKb/dvGAO+JyAPAQspZBnIYnhaRYfjWgNwftP1tESkAioA7Dz+cwf3da2W2eGa/DYB31S94V/1Stvf2NZS81Pco0lZKKaWUUvuJMeZk5/CPJSJ2Y4zL/7gl8Igx5qqTkIopfvLKsASOfOizsMRVSiml1N+enOwEKhOd6Q6vziLyH3yz1MVA/1AdReR5fGvA93vHGDM5rNkppZRSSqkTQovuMDLGzABmHGbf+8KbjVJKKaWUOln06iVKKaWUUkqFmRbdSimllFJKhZkW3UoppZRSSoWZFt1KKaWUUkqFmV4y8NSgL7JSSimljje9ZOAR0KuXnCJKJvQMS9yIgdP4rWGTsMQGaL1mZdhiK6WUUkqdKLq8RCmllFJKqTDTolsppZRSSqkw06JbKaWUUkqpMNOiWymllFJKqTDTolsppZRSSqkw06JbKaWUUkqpMNNLBp6CXly4g8xtBXi8hhGd0mmQGlWmfU+Bi0veWcXPt55BpM3Cr1scvPzrTlweQ9f6idzaokrI2On3DSSudWvEamXjI8MpWrsWALHbyXhiNJHp6XicTtYPGozH4aDBKy9hT0vDW1KCc8kStjw9LqznrpRSSil1MuhM9zESkQwR+eAo9jtdRKaJyMUh2tuLyGwRWSwim/2Ph4hIJ//zn0RkoYi0O5LjZm5zkl3gZupV9RjeKZ3x87cf1Gfy77tJivJ9HjPG8NwvO3j50gzeuaY+8zbnk5VbXG7suFYtsaWmserfvdn06AhqPzgk0JbUrSsl27ax8oYb2Tvje9Ku7RVoW93vTlbdeJMW3EoppZT6x9Ki+yQQkTrAMMARqo8x5mdjTCfgPuB9Y0wnY8wz/ub3jTEdgBv8cQ7b/Kx8ujdMAqBhahR5xZ4y7ct3FyJArYQIAPYWeUiLsREXYcVqEdqfFs+yXYXlxk5sfz45X30NQOGaNdiSEgNt7py9WBMSALAlJ+POyfGfqBdPXt6RnIJSSimlVKWjRfdxIiLdReQH/+zzKP+2JBH5VERmichEEVkEYIzZZIzpA2w8xsM2AZYeyQ45BR6So0tXFVktgtf47hJf4PLy/C876H9utUB7UpSVHQ4Xu50uXB5D5jYnbm/5d5W3paaWFtOAcXtAfHeIdWRmEl2/PmdN/5LUyy9j7/czAfA4nDR+eyqNpk4m/tzWR3IqSimllFKVhq7pPn5+M8Z0FRErsERERgJDgGnGmPdEpDYw9zgd6wYR6QTUAK4vr4OI9AP6Abz22mvc7N8eH2kpM7stgMVfGD/z83b6nlOFuAhroN0iwsMda/Lg91nER1hJi7GR7p8FP5AnPx9rYkLpBuMFf0GfPngQOyZPIXfOT0Sf3oSM0aNYP2gwGx58CAB71ao0mvw6yy674kjHQimllFLqb09nuo+fHiIyHhgNxAARQHNgOoAxJgvYdZyO9b4x5jygKfCciEQf2MEYM8kY08oY06pfv36B7S1qxPL9ulwA1uUUUS3ODkB2gZvluwv5eHkOQ77bzPq9RTzywxYAmlePZcqV9RjVJZ09BW6aVY8pN6n8RZmkXHwRAFEN6lOyY2egLbJmTVy79wDgzs4honp1X4PVV+B7HA6M230MQ6KUUkop9felM93HzwBjTCsRiQP6+LdlARcAX4hIE6DmcT7m/jXhh/3hqUNGPHM35dPnk3XE2C2M6JTOs/O3c0+banx4bYNAv1s+Xc/orrUA3wz4X7sKsFmEwe1qBGbGD5Q7azZJHTvQ5P138TidbHp0BLWGDGbr8xPY+vwE6owcDhYLYrOR9ZRveXrDV1/BEh2NWCxsGf/cUQ6DUkoppdTfmxhT/vpcdXhEJAMYC2QDbYBMoBnQCagCvOfvuhBob4xpG7TvSGCBMebbCuJ3Ai42xgwLev42sB6wA68YY94Lsft+pmRCzyM5rcMWMXAavzVsEpbYAK3XrAxbbKWUUkodk/Jn4VS5dKb7GBljNhJ6XfUO/1VGEJGWQIPgdmPMyMOIPxuYfcDz044yXaWUUkopdRJo0R1enUXkP4ABioH+oTqKyPP41oDv944xZnJYs1NKKaWUUieEFt1hZIyZAcw4zL73hTcbpZRSSil1sujVS5RSSimllAozLbqVUkoppZQKMy26lVJKKaWUCjMtupVSSimllAozvU73qUFfZKWUUkodb3qd7iOgVy85RZS8dG1Y4kYM+Ii/zgrfzXHOXrqSL+IahyX25Y5VYYmrlFJKKXUgXV6ilFJKKaVUmGnRrZRSSimlVJhp0a2UUkoppVSYadGtlFJKKaVUmGnRrZRSSimlVJhp0a2UUkoppVSY6SUDT0EvLthO5lYnHmMY0bk2DVKjyrTvKXBxyVsr+Pn2s4i0WVi9p5DHZm0BoEu9RG5tWTVk7GoDBhLTsjVis7J15HCK160FQGx20h8fTUTNdLxOJ5uHDsbrcFB90GCimzbDEhPDzgnP45j3c8jYjR+9l9TzW2Gx2vhz4KPkr/DFtiXG0/zl0USkpeDOd/LH7UNx7cuj9X9fJrJqKt6SEvYt+ovljz5zrEOnlFJKKXVUdKb7KIhIhoh8cBT7nS4i00Tk4gr6jBSRJSIyR0TmiUgL//abRWS1iPwkIj+LSOOg/iHjHShzq4PsAjdTr2nA8M61GD9v20F9JmfuIimq9PPYc/O38+S/TuPdng34aWMeewvd5caOadESW2oaG27pzdbHRlBj8JBAW0LXrri2bWN9nxvJ/eF7Uq7pBUDujO/YcMtNbLzzdqoNvC9k3intWhJZNZX5F/fmz3uHc8booYG2hvf3Y+tHXzH/4t7s+Gom9QbcHGhb2OtO5l9ykxbcSimllDqptOg+QUSkDjAMcBxG96HGmI7AbcCjQdufNcZ0AEYAdx9NHvOz8uneKBmAhqnR5BV5yrQv31WAALUSIwLbUqJt5BZ5KPEYBIi0ln8Dqvh257Nv+tcAFK9dgzUxMdDmztmLNSEBAFtSMu69OQAULlsKgNfhwJuXFzLvKl3bs/V/vtj5y9dgTy6NnXBmI/b8tBCAHdN/JKnF2b4G48W1L3RMpZRSSqkTRYvuYyAi3UXkBxFZKCKj/NuSRORTEZklIhNFZBGAMWaTMaYPsPEIDlEf2FLO9ibA0qPJOafATXK0NfDcagGv8d0lvsDl4fn52+nfpnqZfW46pwoDvtrAFe+tomV6LDERVspjTUkNFNMAxuMB8RXozj8yiaxXn4affUlSj8vImzkz0E/sdmo89Ai7Xn8tZN6RVVIo2RMU210aO2/pKmpcfiEAVTq1xWLz5efKc9Du66m0/WIKqe1bH3pwlFJKKaXCRIvuY/ObMaYr0A64RkQswBBgmjGmM/AEkHYUcZ8WkfXA9cDQoO33+4v4AcDsigKISD8RWSQiiyZNmhTYHh9pLTO7LSJY/MXrM3O30bdlVeKCimqXx8vTc7fxZe8mfHNTE0rchp82lD977HXkB2azfRu84C/oq987iD1Tp7DmysvIemgo6SNHARBRJ4P0x8eQ88F7OH9dGPJ83LkO7ElBsU1p7NXjXiOlXUvafjGFmIzaFGzaCsDiOx9i/iU38Xu/YZw97tHywiqllFJKnRBadB+bHiIyHhgNxAARQHNgOoAxJgvYdRRxhwKtgAZAStD2Z40xrYBuwNSKAhhjJhljWhljWvXr1y+wvUXNWL5flwvAupwiqsXZAcgucLF8dyEfL8thyLebWJ9TzCMzsyjxGJwlHmLsFkSE1Bgb2/JLyj2mMzOTxAsvAiCyXn1cO3cG2uw1auLaswcAd04O9urVkchIagwdxtaRwylavbrCAcmev4iaV/qWrsc1qU/h1h2BNo/DyeI7H+KXy/tiT4gn64PPARCr78ODO9+B1+WqML5SSimlVDjp1UuOzQBjTCsRiQP6+LdlARcAX4hIE6Dm0QQ2xuSIyH+A8fhmvIPtw1fgH7EOGQnM3ZhPn2lriYmwMKJzLZ6dt417zqvOh9c1CvS75ZO1jO5Wm0ibhV5npdLn47XYLEKVGBuPdzut3Nj5P80mvkMH6r31Ll6nk62jRlB90GB2vjiBnS9NIP2R4WCxIDYbO8Y/Q1TDRkSffgYZE0tn4jffew+evNyDYu/8djbVLurI+TPew53v5M+Bwzl91AOsfPwFUtu1pMmj94II27/4npx5iwA496OJWGOiEKuVFSOfO5rhUkoppZQ6LsT4v6JXh09EMoCxQDbQBsgEmgGdgCrAe/6uC4H2xpi2QfuOBBYYY74NEbtMu4j8D3gVqA38B9gGWIFRxpjvDxXPz5S8dO1RnOmhRQz4iL/OahKW2ABnL13JF3GNwxL7cseqsMRVSimlThHlX1lBlUtnuo+CMWYjB88+AyAiO/xXGEFEWuJbIhK878hDxB55wPNeQU+nHqq/UkoppZT6+9Gi+/jr7F8WYoBioH+ojiLyPL414Pu9Y4yZHNbslFJKKaXUCadF93FmjJkBzDjMvveFNxullFJKKfV3oFcvUUoppZRSKsy06FZKKaWUUirMtOhWSimllFIqzLToVkoppZRSKsy06FZKKaWUUirM9OY4pwZ9kZVSSil1vOnNcY6AXjLwFOGaeF1Y4trv+pCsi1uEJTZA7W9/Z9e1bQ/d8ShU/egX9vbtGJbYyVPmhCWuUkoppSonXV6ilFJKKaVUmGnRrZRSSimlVJhp0a2UUkoppVSYadGtlFJKKaVUmGnRrZRSSimlVJhp0a2UUkoppVSY6SUDT0Evzt9O5lYHbi+M7FaLBqnRZdr3OF1c/OZy5t15NpE2C6v3FPLYzCwAutRP5NbW1ULGTrjpLiLPaoFYreRMGI1703oAku97FFvN2gBYYmJx79xO9uMPkNh3IBFNzsISFUPuW69QlDk/ZOzY6/phP705WKzkTxqLZ8uGQFtUpx5Ed7sS4/Xi/Oh1cJUQe/0dgXZbnQbsHdkfz+Z15caOuqovtkbNEIsV51vj8G7bGGiLaH8JkR0vA6+Xws+m4F7xO9G97sSa0RiJiqHwf6/iXvlHyLyVUkopVXmJSBXgPsBrjHk0aHsc8DqQDuQANxlj8kLF0aL7EEQkAxhrjLn+CPc7HXgceMMY820F/foB/8Z3AxsDPLW/v4jMxvdthB1YBvQzxnhFZDWwDYgCfjLGDD3cvDK3OsgucDO1V0PW7Clk/NxtTLyyfpk+kxftIim69K3x3M/bePLiOtROjODmaWu5+qxUkqMPfutEnHkO1qRUdg+9HXud+iTdeh97hg8EYO/zjwf6Jd01hIIfvgagYO735E6ZgCUxiSqPvxSy6LY3aYYlMZl9I/tjrV2PuBsHkDt2MADWWnWxn96cvY/2g6CbPe177G4ALClViOtzb8iC29awKZaEFBxP3YslvS4x196F4/kHffvWzMDWsCn5T9xdJnbhl29BUSGSXIXYWx7EoUW3Ukop9U81HlgLxBywfRDwpTHmfRG5G7gLeCpUEF1eEgYiUgcYBjgO0e924FzgX8aYTsCVwP0iEny3mQuNMW2BSKC5f1uOMaaTMeY8oKqIHPYdXuZvyqd74yQAGqZFk1vkKdO+fFcBAtRKiAhsS462kVvkpsRjECDSWv4NqKJankfBbN/nC9emdVjiEw/qY61WA2tSKiWrl/v6rVkBgLfAideZHzLviGZtKJr3PQCerPVY4hICbdFdLsOzeztJw18iYdBo5IDjxvbsS8EnU0PGtp3VipKFP/jy2LoBiY0PtEVe0ANv9g7ihjxH7F0jkTh/7KJC//nUwrOl/GJeKaWUUpWfMeYm4KdymroA//M//hio8G5+OtN9mESkOzAYiAO+M8YMF5Ek4E0gCVgJtDbGtDLGbAL6iMjIQ4S9BehqjCkBMMbkish/gH7AnUHHjgJSgU3lxPgV39caB+bbzx+H1157jVv823MK3GVmqa0WwWsMFhEKXB6e+3k7z/XIYMAX6wN9+rSoyu2friPGZqFHk2RiIqzlnow1KQVv7t7SDV43iJSZIY6/6t/kf/Z+2R3tdpLvGkreB1PKjQtgSUjGm7cv8Nx4PYHY1hq18SxewL7H7iayTWdie96K481nfeOQmIwlOQ33prWhY8cn480vjU1QbEu1WriXLsTx9H3YW3Yk6vKbKXz/BWxntCK61x1IZBSO54eFjK2UUkqp8HlfGptD9wrt36y+A3+95DfJGDPpMHePNMa4/I+zgeSKOutM9+H7zRjTFWgHXCMiFmAIMM0Y0xl4Akg7wphijCk8YNs6oHbQ8xn4CvqtQJmpYBGJBS4F5h0Y2Bgzyf8BoFW/fqXvpbhIK3nFpbPbFgGL+Gaun5mzjVtbVSUusrSodnm8PDVnK1/d1IRvbjmdYo+XORtyyz0Zr9OBBM1AG68pU3Bjj8BerzElK5YENtnSTyNl0AgcX35E8Z+/lRsXwFvgwBI0A43XWxrb46H4d9+ylOLf52OrVTfQLbpTD4pmfRUyLoApdGKJKY1dJm+vB9eSBb6xWPIL1pp1AHAvX0T+Y7fjGP8Asf0eqTC+Ukoppf6egusl/9/hFtwAXn89CL6Ce3dFnbXoPnw9RGQ8MBrfmp4IfMs9pgMYY7KAXUcY0yIikQdsa4iv8N7vQmNMBvAb8IB/W4p/vfcnwHP+mfXD0jI9lhlr9gGwLruIanF2ALILXCzbVcC0pdk8MH0j63OKeXjGZko8BqfLQ0yEFREhNcbO9jxXubGLl/5BzAVdAbCdVhfPnp1l2qNbn0/x4oWB5xIRSVK/wex9YTSuDWsqzNu18k8iz+sMgDU9A29O6fvatfovIlu0A3zryt2bS2e1I1t1oPiPXyqM7V69BHsr3wodS806mL2lsd1rl2Fvep7vnJqc41tKYrFChO9l8+bngkX/GSmllFKnoIXAFf7H1wAzK+qsy0sO3wBjTCv/L1X7+LdlARcAX4hIE6DmEcZ8F3hGRAYZYzwikoxvxvyecvruAer4H+f414AfsQ51E/hpQx43fbSG2AgLw7vW5tm527inXXU+uqFxoN/N/1vDmAtPI9JmodfZafT5aA02q5AWY2f0haeVG7vo17lEtz6fquMm4y1wsnfCGBL7DiT37VfA7SayaUsKf5kT6G/PaEBEgyakPT4hsC171AN4HQf/8Lfk93lEnNOWpMcmYgoLyH/9KWL/3R/nB5Mo/O4T4vs/QuR5XTAFDvImjgFAYhMwbhe4SiocE9eSX7A3PY+4YS9CUQHOt8YR3fMOCj+dTPGsz4jtOwx7q06YQicFU54Cm524e5/0L0GBwmmvH9FroJRSSqnj42TMe4nIU8CjwJPAOyJyL74fWt5d4X7GHNNSmH+8/VcvwbdWpw2QCTQDOgFVgPf8XRcC7f0/ety/70hgQairl4iIAAOBnoDb/zfaGDPH3z4b37cRXmAv0NcYs1dEFvh/RHm4jGvidUfQ/fDZ7/qQrItbHLrjUar97e/surbC3yUctaof/cLevof9G9QjkjxlzqE7KaWUUpVb+VdWOIE+sB7bmu7rPatO2DnoTPchGGM2AuVeLlBEdhhjOvgftwQaHLDvyEPENsAL/r/y2juF2H4kBbdSSiml1D9SZVrhqUX3sensv9qIAYqB/qE6isjzlF7yD+AdY8zksGanlFJKKaX+FrToPgbGmBn4ri5yOH3vC282SimllFLq70qLbqWUUkopVSlVpuUllShVpZRSSimlKied6VZKKaWUUpWSznQrpZRSSimlAvQ63acGfZGVUkopdbyd9Ot0fxJ9bNfpvrpQr9OtjrNw3hwns3GTsMQGaLlqJdOTGh+641Hovm9V2HJvuWolOTdfEJbYKVPnhiWuUkopVdlYTnrZf/i06FZKKaWUUpWSrulWSimllFJKBWjRrZRSSimlVJjp8hKllFJKKVUp6fISpZRSSimlVIDOdCullFJKqUqpMs10a9F9Cnpx/nYytzpwe2Fkt1o0SI0u077H6eLiN5cz786z2elwMfz7zYG2TfuKGd6lNp3rJ5Ybu+a9A4lr1RqxWdn06HCK1q4FQOx26owZTUR6Ol6nk/X3D8brcAT2qzVsGMZVwtbxz4bMu+HD95LSrhVitbH0vkdxrPTFtiXGc/aE0USkpeDJd7L4jqG4c/No/NgQEs85C1tcLKtGjiP7pwUhY4czb4Doq2/F1qg5WK0UvPk0nm0bA20R7bsT1flyjNdL4SeTca/IDLTFXD8A43FR+L/XKoyvlFJKqb+3SvT5oPIQkQwR+eAo9jtdRKaJyMUV9BkpIktEZI6IzBORFkdyjMytDrIL3Ezt1ZARXWsxfu62g/pMXrSLpGjf57HTkiKZ2qshU3s15JUr6tEwNZqO9RLKjR3XsiW21DRW9+7NpuEjqDV0SKAtqVtXSrZtY/W/b2TvjO9J69Ur0GavUYOEdu0qzDu5bUsiq6SysEdvlg4aTpNRQwNt9e/rx7ZpX7GwR292fD2TunffDMDaZ17h18v78PuNd1PvvttDxg5n3gC2Rk2RhBTyx95DwdRniL6uf6DNWjMDe6Om5I2+i/wx/csU3JaUqtjObHXI+EoppZT6+9Oi+29CROoAwwDHofoCQ40xHYHbgEeP5DjzN+XTvXESAA3Toskt8pRpX76rAAFqJUQctO+7i/fwf83SsEj5V6JPaH8+OV9/DUDRmjVYE0tnw105e7Em+Ip1W3Iy7pycQFv6/YPY8cbrFead1qU92z72xXasWIM9uTR2/BmNyP5pIQC7vvmRxHPOBsDjcAIQ26Au+ctWhYwdzrwB7Ge1pmTBTF9OWzdgiSv90BLZ4VI82TuIf/AFYvs/hsSVHju65x0UTX//kPGVUkqpU5XFcmx/JzTXE3u4U4uIdBeRH0RkoYiM8m9LEpFPRWSWiEwUkUUAxphNxpg+wMYjOER9YEuIY/cTkUUismjSpEmB7TkFbpKjS1cVWS2C1/juoFrg8vDcz9vpf171g+K5PF7mbcqjU4hZbgBbSmqZohSPB/wFuiMzk6j69Tnjqy9Jvewy9s30FaGpPa+hYOkySnbsrPBEI9NSKNlTGtu4S2PnL1tF9csv9MXr2BaLzQpAWqd2nD/nE84cP5LNU0J/8RDOvAEkPhmTv68096D4luq1MI5c8scOpOTXWURfeQsAER164N64Cu/eXYeMr5RSSqm/Py26w+s3Y0xXoB1wjYhYgCHANGNMZ+AJIO0o4j4tIuuB64Gh5XUwxkwyxrQyxrTq169fYHtcpJW84tLZbYsQmLl+Zs42bm1VlbhI60HxZq7NpUv9RCTELDeAx5GPLaG0KDdeL/gL+vT7B7Fz8hSWX3oZG4YOpc6oUURmZJDU7V/seuutQ56wK8+BPSmo4Delsdc++xopbVty7qdTiMmoTcHmrQDsmT2feR2v5ter+9L89XEnJW8AU+hEYuPLzR2PB9efvrXmrj/nY62ZgaVabSJadKB4xkeHFV8ppZQ6VelMt9qvh4iMB0YDMUAE0ByYDmCMyQKOZipzKNAKaACkHMmOLdNjmbFmHwDrsouoFmcHILvAxbJdBUxbms0D0zeyPqeYh2eU/oDym1V7ubBBUoWxHYsySbr4IgCi6tfHFTQLHFGzJq49ewBw5+QQUaM6KZdeiliEus+Op8bd/Uns0oWkbt3Kjb33l0VUv8K31D2ucX2Ktu4ItHkcTpb0f4hfr+qLLSGerR9+jlitWKKjAHBl70WsB3+QOBF5A7hX/0lEq04AWGpm4M3ZXdq2dhn2ZucBYG9yDp6sdUS27QYixN41kujLbyaieXvsLS4IGV8ppZRSf3969ZLwGmCMaSUicUAf/7Ys4ALgCxFpAtQ8msDGmBwR+Q8wHt+M92HpUDeBnzbkcdNHa4iNsDC8a22enbuNe9pV56MbGgf63fy/NYy58DQAvMawNa+EGuWs8w6WO3s2iR070Oi9d/E6nWwaPoL0Bwaz7YUJbHthAqeNGI5YLIjNxpann8G5eHFg37hzzyXxgvaB5RsH2vXdbKr8qyPnTX8Pt8PJ0kHDaTzyAVaPeYGUti1p9PC9IMKOL79n7/xFWGOiafnBq4hFwMCqx8aflLwBXH/+gr1pW+IfeglTVEDBW+OI7nUnhZ+8QdGPnxJ320NEtO6MKXDgnDwW48wL7Gtr0hz72W1w/T63wrFXSimlTkWV6ZKBYvZ/za2OGxHJAMYC2UAbIBNoBnQCqgDv+bsuBNobY9oG7TsSWGCM+TZE7DLtIvI/4FVjzA8VpGRcE687+hOqgP2uD8ls3CQssQFarlrJ9KTGh+54FLrvWxW23FuuWknOzeGZnU6ZqgW4Ukqpv4XQa05PkJlVGx9TIdtt16oTdg460x0GxpiNhJh9FpEdxpgO/sct8S0RCd535CFijzzgea8QXZVSSiml/tEq00y3Ft0nXmf/shADFAP9Q3UUkefxrQHf7x1jzOSwZqeUUkoppY47LbpPMGPMDGDGYfa9L7zZKKWUUkqpE0GLbqWUUkopVSlVdCnjv5tKtBJGKaWUUkqpyklnupVSSimlVKVUmX5IWYlSVUoppZRSqnLS63SfGvRFVkoppdTxdtIXVM9Jb3JMNU7HrSv1Ot3q+KrMN8eZFhmem+P0LF7FnPTw5N5x60p2X98uLLGrfDCfrxLCMyYAl+atCltspZRS6niqTMtLtOhWSimllFKVUmUquitRqkoppZRSSlVOWnQrpZRSSikVZrq8RCmllFJKVUq6vEQppZRSSikVoDPdSimllFKqUqpMM91adJ+CXpy/ncytDtxeGNmtFg1So8u073G6uPjN5cy782x2OlwM/35zoG3TvmKGd6lN5/qJ5cauee9A4lq1RmxWNj06nKK1awEQu506Y0YTkZ6O1+lk/f2D8Tocgf1qDRuGcZWwdfyzIfM+c8S9pLVvhdhs/N7/UfJW+GLbE+Np+epoItNScDuc/HrLUBLOaMhZI+8N7Jt4dmPm/OsmcpeWfzm8jCEDSWzjy3v10OEUrC7Nu/H40UTVSsftcLLi7sF48h0ktWtD3YcfAK+XrVPfY9fHX1Q05MRcezv2Js0Rq5X815/Cs2VDoC2yYw+iu10BXi/O/72OcbmIva5foN12WgP2jbobz+Z15cZu9Mi9pLbzjcuSgY/iWOnL3ZYYT7MXRxPhH5fF/Ybi2pcX2O+MJ4bhLXGxcuT4CnNXSiml1LGrRJ8PKgcRyRCRD45iv9NFZJqIXFxBn5EHtovIgiM5TuZWB9kFbqb2asiIrrUYP3fbQX0mL9pFUrTv89hpSZFM7dWQqb0a8soV9WiYGk3Hegnlxo5r2RJbahqre/dm0/AR1Bo6JNCW1K0rJdu2sfrfN7J3xvek9eoVaLPXqEFCu4qvaZ12fksiq6Uy51+9+f3u4Zw9dmigrfGQfmz+4Cvm/Ks3W7+YScOBN5M9P5M5F97EnAtv4tdbhrDzx19CFtyJ57bEnpbGnz17s/rBEdR7pDTvtIu7UrRlG4uvvpE933xPjRt8edf9z2CWXH8Li6/6N7Xv7Fth7vYmzbAkppA76m7yX3+a2H/fHWiz1qqLvUkz9g2/g30j7sS1NBP3qiXkjhpA7qgB5L/0GCV//Ray4E5p25LIKqn80r03f907nDNGl45Lg0H92Pq/r/ile292fDWTunffHGiLqlWDtM7huY64UkoppQ6mRfffgIjUAYYBjkP1PVbzN+XTvXESAA3Toskt8pRpX76rAAFqJUQctO+7i/fwf83SsEj5N29KaH8+OV9/DUDRmjVYE0tnw105e7Em+Ip1W3Iy7pycQFv6/YPY8cbrFeZdrVt7sj70xc5bvoaI5NLYiWc1YvechQBs/+pHUlqdXWbf0x++m5VjJ4aMndzxfHZ/7otdsGoN9qDYruy92BJ9edtTknFl+/J278vFFh+PNTYGj7OgwtztTc+leN73AHi2rMcSV/qhJarzZXj37CDx0ReJv/dxJL7sNwgx1/Sl4NO3QsZO69qebdN8ueevKJt7/JmNyJ7rG5ed038kqUXpuDQZcT/rnn+jwryVUkqpvzuL5dj+TmiuJ/Zwpw4R6S4iP4jIQhEZ5d+WJCKfisgsEZkoIosAjDGbjDF9gI3hziunwE1ydOmqIqtF8BrfHVQLXB6e+3k7/c+rftB+Lo+XeZvy6BRilhvAlpJappjG4wF/ge7IzCSqfn3O+OpLUi+7jH0zZwKQ2vMaCpYuo2THzgrzjqyaQvHu0tjGXRo7969VpF95IQBVO7dFbNag/VKJql6F3L9C32XRnpZKSXaI2L9mEtOwPq1+/JKqV13Gnm98eW+ZNJUW30yj1Q9fsuODjyvM3ZKQjDdvX7njYq1eC2/+PnJHDaB4wY/EXlM6ay6JyViSUvFsXht6XNJSKNlTfu75S1dR/TLfuKR1aotYfeNSu3dPchcvpWjrjgrzVkoppdTxo0V3+PxmjOkKtAOuERELMASYZozpDDwBpB1F3KdFZPb+PyClvE4i0k9EFonIokmTJgW2x0VaySsund22CIGZ62fmbOPWVlWJi7QeFG/m2ly61E9EQsxyA3gc+dgSSoty4/WCv6BPv38QOydPYfmll7Fh6FDqjBpFZEYGSd3+xa63Qs/k7ufKdRCRXH7slU+9Rtr5Lblg+hRi69bGuXFroF9G76vZ+NYnFcb25OVjTyw/dt1hg9jy6hQWdbmMlfcOpdHTo7CnppB+W28WtunCgjZdSDr/PGJPbxQyvilwYImLL31uTCA+Hg8lf/wCQMnv87DWqhvoF9WxB0Wzv64wd3eeA3tS+bmvGf8aKe1a0uazKcRk1KZw81ZiG2RQ/bJubHj50GOulFJK/d3pTLcC6CEi44HRQAwQATQHpgMYY7KAXUcRd6gxptP+PyCnvE7GmEnGmFbGmFb9+pX+KK9leiwz1uwDYF12EdXi7ABkF7hYtquAaUuzeWD6RtbnFPPwjNIfUH6zai8XNkiqMDHHokySLr4IgKj69XEFzV5H1KyJa88eANw5OUTUqE7KpZciFqHus+OpcXd/Ert0Ialbt3Jj75m3iPSrfcvZ45vUpzBoltbtcLLo9oeY270v9sR4Nr//eaCt5mVd2PHtnArzzv01k7QevrxjGtaneHtp3pG1alKyy5e3a08OkTWrY09Jxrg9eIuKwePBnZtHZI2Dvx3Yz7XyTyLadAbAmp6BN6f0ZXetWUrEOW19Y3RmC9xBs9qRrS6gZPEvFeaePX8RNa70jUtc4/oUbSsdF4/DyZ93PcTCK/tiT4hnywefk97rUsRi4Zw3n6Xhg3dTrXsXql9a/pgrpZRS6vjRq5eEzwBjTCsRiQP6+LdlARcAX4hIE6DmiU6qQ90EftqQx00frSE2wsLwrrV5du427mlXnY9uaBzod/P/1jDmwtMA8BrD1rwSapSzzjtY7uzZJHbsQKP33sXrdLJp+AjSHxjMthcmsO2FCZw2YjhisSA2G1uefgbn4sWBfePOPZfEC9oHlp0caPv02VS/uCOdfngPl8Pp+zHlmAdYOvIF0s5v6btSiQhbP/+ePT8vAsCenIi3xIW3uKTCvLNnzialSweaf/IuboeTNcNGUPc/g9n4zAQ2PjOBhk+U5r1+9DMUrFlH/pKlNP/8v2AMjmUryJk1N2T8kj/mE3FOW5JGvoK3sADHG08Te0N/nB9OonDGJyTc9TCR53XBFDjJf3UMABIbj3G7wFVx7ru+m03VCzvS9tv38DicLLl3OE0ee4BVo18gpW1LGj96LyLC9i++J2f+InLmLwrsm9r+XKp0u4AdX5U/5koppZQ6fsTs/5pbHRcikgGMBbKBNkAm0AzoBFQB3vN3XQi0N8a0Ddp3JLDAGPNtiNgHtYvIAmPMeYdIy7gmXncUZ3No9rs+JLNxk7DEBmi5aiXTIhsfuuNR6Fm8ijnp4cm949aV7L4+PFcHqfLBfL5KCM+YAFyaF3r9u1JKKRUk9JrTE+SP05scUyF7zoqVJ+wcdKb7ODPGbASuL69NRHYYYzr4H7cEGhyw78hDxD6o/TAKbqWUUkqpfyTLSS/7D58W3SdWZxH5D2CAYqB/qI4i8jy+NeD7vWOMmRzW7JRSSimlVFho0X0CGWNmADMOs+994c1GKaWUUkqdKFp0K6WUUkqpSulEX/bvWFSiVJVSSimllKqcdKZbKaWUUkpVSjrTrZRSSiml1D+AiDwuInNEZJ6InBm0PUJE3hGRuSIyXUQSK4yj1+k+JeiLrJRSSqnj7aRfsG9Z02O7TveZSyq+TreIXAD0Nsb0E5GzgKeNMd39bdcCTY0xj4jIbUCiMWZ8qFi6vOQU4X7rxrDEtfV5lx09w3ep8OrTFvDnGeG5gU2z5SuZWzs8sS/IWknRmCvCEjvq4c/DPua7rm176I5HoepHFd/WXimllDoSx7q8RET6Af2CNk0yxkwKen4h8F8AY8xSEUkJatsNJPsfpwHbKjqWFt1KKaWUUuqU5C+wJ1XQpSq+4no/t4hYjDFe4GfgURFZBniBCm9FrWu6lVJKKaVUpWSxyDH9HYZcSmezAbz+ghvgCWCcMeZMoDcVF+9adCullFJKKRXCXKAngIicAWwJaqsD7PA/3gXUriiQLi9RSimllFKVkljD/lvOr4HuIjIXyAfuEJGngEf9f6+IiAWwA0MqCqRFt1JKKaWUUuXwLyW564DND/r/uwroerixtOhWSimllFKVkhzeuuy/BS26TzET5mwhc7MDtzE8dkkGDapEl2nf43Bx0StLmH//OUTaSpf8v/vbThZvcTDuqvoVxo+7vh8RpzcHq428V5/EvWVDoC26cw+i/3UVeL04PpxEyV+LiDizBfG9B2CMoeCb/1H007chY1e/ZyCxrVojVitZI4dTvHYtAGK3U+vx0USkp+N1Otn0wGC8Dgc17h9MTNNmWGJi2DHhefJ//jlk7DoPDCSxTWuwWlk7bDgFq0tjN3xmNFG10/E4nKwcMBhPvoPEtm2o+/ADGK+X7VPfY9cnX1Q4LraON2CpfSZYrLimv4zZk+WLX60uEdcPx2RvBcD17WuYPVnYuvRBajRAIqJx//gW3k1/nZQxj72uH/bTm4PFSv6ksXiCYkd16kF0tysxXi/Oj14HVwmx199Res51GrB3ZH88m9dVODZKKaXUqUCL7qMkIhnAWGPM9Ue43+nA48Abxphyqx0RGQksCG4XkQXGmPP8x/0VWA7EANOMMU8fzrEzN+eT7XTzVu8mrNlVwLgfs3j1ukZl+rzxy3aSYsq+LZzFHr5bkUO1+IgK49tPb4YlMYWcEf2x1a5H/E33sPeJ+wGw1aqL/fTm5Dx8OwTdkCnuxrvJGXUPpriI1KemhiwAY1u2xJaaxro+vYlq0JCaDwxhw52+Ai+ha1dc27aRNexBUq7pSWrPXuye+ib7vvuO7c+Ox5qcTL3XXg9ZdCec2xJ7WhpLevUmpnFD6j48hGV9fLFTL+pK8dZtrL7vQapd35Pq/9eLrZPepO5/BvPX/92Ct7CI5l9Pq7DoltpnQGwSJe8+jFQ5DVvXm3F9+Hig3bNiPu4Zr5fZx/3zR1BSCPGp2C+9J2TRHc4xtzdphiUxmX0j+2OtXY+4GweQO3YwAFZ/7L2P9isTe99jdwNgSalCXJ97teBWSiml/PTqJSeQiNQBhgGOYwz1ozGmE9AGuEpEkg5np3kbcul+hu+a7g2rxpBb6C7TvnyHExGonRRZZvvLc7dyY+tqh4wf2awNRT/PAMCdtR6JSwi0RXe9HM/uHaSMfJnE+0cj8b47pRpHHhITh0TFYIoKQ8aOb3c+e6d/DUDR2jVYE0vvtOrO2Ys1wXcsW3Iy7pwcAAqXLQXA63Dgyc8LGTu5w/ns/twXu2DVGmxJpbFd2XuxJfpi21OScWX7Yrv25WKLj8caG4PHWVDhuFjrNce7bK7vfHdvRqLjy3Yoch68U4lvLCwpNTG7NoaMHc4xj2jWhqJ53wPgyVqPJTh2l8vw7N5O0vCXSBhUGnu/2J59KfhkasjYSiml1PEgFjmmvxNJi+5jJCLdReQHEVkoIqP825JE5FMRmSUiE0VkEYAxZpMxpg+w8TgdPhHfLVgrrvr8cpxuUoJmsa0WweufpSwo8fDcrC3cfUF6mX3mb8jFa+CsGrGHjG9JSMabt690g8cD4ntDW2vUxuTvI2dEf4rm/0Bcr9sAcH71X1KfepO0Z9+j8McvQ8a2pabi8RfTALhLYzt/zySyXn0af/ElSZdeRu7MmYFuYreT/vAj7Jr0WsjY9tRUXEGxTVDsvN8yiWlQnxYzv6TqVZeR/a0v9tbXp9L862m0mPklOz/8uOKBiUnEFOSWPvd6CNw51+vB0rgNEb2fwPav28Die30sdZsRceuz2C65C8/voZd/hHPMD4xtvAfGzmXfY3dTPP8HYnveGugniclYktNwb1pb8bgopZRSpxAtuo/db8aYrvjuQnSN/7IxQ/At++iM78LpaUcR92kRmb3/Dwi+7WgXEckEFgK3GmNKDtxZRPqJyCIRWTRpku9a7XFRVvKKPIE+FgGLv4h6emYWt55Xg7hIa6B9b4GL1+dv575OtQ4rYW+BE4kLmsU13tKlBx43xb/PB6D49/nYamdgSUgmpvt17L7rKnbfdRURZ7fCVqdBubE9+flYE0tnWk1Q7Br3DWL31CmsuvwyNg8bSq3HRgEQUSeD2qPHsOf993AsXBgyb3d+fmA2+8C8Mx4cxJbXpvB7t8tYde9QGjw1CntqCul9e/Nb2y78el4Xks4/j5gmjUJEB4oLICouKL4BfPHN7s2UvH4vJe/8B4ocWM+50DeWG/6kZPL9lLw/AvsVg0OGDueYewscWGKDYnuDY3vKxq5VN9AtulMPimZ9FXo8lFJKqeNErHJMfyeSFt3HroeIjAdG41tjHQE0B6YDGGOy8F0w/UgNNcZ02v8HBE3z8iPQCvgM6FTezsaYScaYVsaYVv369QOgZe14Zqz0hVm7uzCwRjvb6WL5DifTFu/mgU/XsW5PIQ9/uYGZq/ZhFeGRrzYwZsYmFm918NEfoU/FtWIxUed1AcBaKwNPdmlf1+qlRLbw3R014swWuDetRRISfbO+JcXg9eB15GFJqVJubGdmJokXXgRAZP36uHbsDLRF1KyJe/ceANzZOURUr45ERpL+4DCyRgynaPXqkDkD5P2aSVp3X+yYhvUp3l4aOzK9JiX+2K7sHCJrVMeekozxePAWFYPHgzs3j8ga1UPG92Ytx9rEd+6SVhuTt6e0UUr/CZoiJ2B822z+9fOFeWAJ/c80nGPuWvknked19sVOz8Cbszso9l9Bsc/Bvbl0VjuyVQeK//glZM5KKaXUqUh/SHnsBhhjWolIHNDHvy0LuAD4QkSaADWP90GNMUZEHgXmi8g0Y8zOQ+3TsUEic9fuo/fbK4iNtDLikjqM/zGLezqm81HfMwP9bn53JWMuq0ukzUKvc3wF2dZ9xTw3awvXnlM1ZPzi3+cR2aIdKY+/iiksIPe1scTdeDeOD16j4LuPSbz7EaLadsVb4CD35dEYRx6udStIGTMJDLg2rqZk8YJyY+fNmU18hw7Uf+ddvE4nW0aOoMb9g9nx4gR2TJhA+vDhiFgQm41t454hqlEjos84g3qvlt6RdeO99+DJzT0ods4Ps0np0oGmH7+Lx+FkzbARZDw0mE3jJrBp3AQajBkOFl/sDWOeoWDNOvKXLKXZp//FGINz+Qr2zp4bcly8axZhqd+SiN5PYEoKcU2fiK3zTbjnvI+lYWtsbS4HrxeTuwvX9JfBZsd+7SOICMaAe9bbJ2XMS36fR8Q5bUl6bCKmsID8158i9t/9cX4wicLvPiG+/yNEntcFU+Agb+IYACQ2AeN2geugL1+UUkqpU5qYoCsPqMO3/+olQDa+HzRmAs3wzTxXAd7zd10ItDfGtA3adyQHXJ3kgNgHtR9w9ZLAVVNEpAdwvTGmdwXpGvdbNx75SR4GW5932dHzvLDEBqg+bQF/ntEkLLGbLV/J3NrhiX1B1kqKxlwRlthRD38e9jHfdW3bQ3c8ClU/0hlwpZT6BznpF8le36HpMRWy9X5acsLOQWe6j5IxZiNQ7uUCRWSHMaaD/3FLoMyiWWPMyEPEPqjdGHNeecc1xnyN7xalSimllFKnlBO9LvtYaNEdHp1F5D/4fi1XDPQP1VFEnse3Bny/d4wxk8OanVJKKaWUOqG06A4DY8wMYMZh9r0vvNkopZRSSqmTTYtupZRSSilVKVlO8A1ujoVeMlAppZRSSqkw05lupZRSSilVKZ3oW7kfC53pVkoppZRSKsy06FZKKaWUUirM9OY4pwZ9kZVSSil1vJ30tR1ZF7c4phqn9re/681x1PEVzjtSrmt/dlhiA9T/+S9mpDUOS+wL96zit4bhuSNl6zUrcQzoGpbYcS/9wML64ckboM26lfxYPTxj3mXHKnZf3y4ssat8MD8scZVSSqnjQYtupZRSSilVKYml8qyU1qJbKaWUUkpVSpXpNvCV5+OBUkoppZRSlZQW3UoppZRSSoWZLi9RSimllFKVkt4cRymllFJKKRWgM92nmAlztpC52YHbGB67JIMGVaLLtO9xuLjolSXMv/8cIm2ln8ne/W0ni7c4GHdV/QrjJ982gOhmLcFqZfczj+HasA6AKg+OxF7rNAAsMbG4dmxj58ODsCalkDZ0OLbkVFw7t7Nr5NCQsesPu5fkdq0Qq43l9z+Kc9VaAGwJ8Zz5/GjsaSl4HE7+umso7tw8LJER1Oh5OVW7d+WPf99VYd7p9w0krnVrxGpl4yPDKVrriy12OxlPjCYyPR2P08n6QYPxOByB/Wo/NAzjKmHLuGcrjB/R42asDZqCxUrxf5/Fu2NToM123kXYz78UvF5Kvp6KZ/UfWJueT0SXXmCz4fpxGu7fZ4eMXWvQQOJbt0ZsVjY8PJzCNaW513tyNBG10vE6nay915d7w1dfwp6ahikpwbFkCVlPjQsZu+7Qe0lq6xvzVUPKjnmTZ0djT/WN+fIBvjFPu7grp93ZF4mwk/Xam+z6/JsKxyXm2tuxN2mOWK3kv/4Uni0bAm2RHXsQ3e0K8Hpx/u91jMtF7HX9SsfttAbsG3U3ns3rKjyGUkop9XegRfcxEpEMYKwx5voj3O904HHgDWPMtyH6XA/cCcQBHxtjnvRvzwN+B+KB140xrx7OMTM355PtdPNW7yas2VXAuB+zePW6RmX6vPHLdpJiyr4tnMUevluRQ7X4iArjRzVtgS0llW333EJE3Qak9h/MjiH9Adj91MhAv9R7h+H47ksAUu4axN7XX6Jkw9oKYyed15LIqqksurw3cU0a0mjkUP74P18BVvfefmz/+Ct2ff096Tf2pM5dN7Nu7ATq3H0rJbt2Y09NqTB2XKuW2FLTWPXv3kQ3bEjtB4ew5vY7fMft1pWSbdvYMORB0nr1JO3aXuyc8iYAETVqkHB+O3Jnz64wvqX+2UhCMoUv3I+lRgYRV91B0cT/+Nqq18Fa/2wKnx0I+29UFRFFRNdeFL44BCxWogc9j3vJPHC7Dood36ol9rQ0VtzQm+hGDTlt2BBW3erLPflfXSneto11DzxIlWt7UuW6XuyY7Mt99e134t63r8K8E9u0JKJKKn9c1ZvYJg2pP3woS/7tG/M69/Rj5ydfsXv699S4oSe177iZTS+9zml33cofvfogNhstP3+fPd/+gLe4pNz49ibNsCSmkDvqbqy16hH777vJe+oBAKy16mJv0ox9w+8oHRcgd9QA37ilVCG290AtuJVS6hSny0tUhUSkDjAMcByi61pjTCfgXOAKEani3748aHv/wz3uvA25dD/DV4A2rBpDbqG7TPvyHU5EoHZSZJntL8/dyo2tqx0yfvS57cj/fjoAJRvWYk1IOKiPrXpNbCmpFK9chiU+AWtiIkl9+lHz5anEXXRpyNipndqz/ZOvAXCsXIM9OTHQFndGI3J+XgjA7m9/JLG572Y9G56dyNZ3px0y78T255PzlS924Zo12JJKY7tz9gbOw5acjDsnJ9BWa/Agdkx6/ZDxbU1a4l40CwDv9o1ITHxpW7vueHN2Ej1wHJF9H4XYBKwZp+NZ9YevyC4pwrtpJZZqp5Wf+wXnk/2lP/fVa7Alls3dVl7uXi/uvLxD5p3SsT07P/PFdq5cgz1oXGJPb8Teeb4x3zPjRxKan01ii2bs/fkXTIkLb0Eheb8vIaZBvZDx7U3PpXje9wB4tqzHElf6fonqfBnePTtIfPRF4u99HIlPLLNvzDV9Kfj0rUOeg1JKKfV3oUX3cSIi3UXkBxFZKCKj/NuSRORTEZklIhNFZBGAMWaTMaYPsLGimMaY/f29QDZw4JRhDWBLiHz6icgiEVk0adIkAHKcblKCZrGtFsHrn0UsKPHw3Kwt3H1Bepk48zfk4jVwVo3YQ46BNTkF7769pfl7PCBlP4EmXtebfR+9C4CtZi3stTPY8+wYtg+6g4QrrsWamlZu7IgqKbj2lBa8xl0aO3/ZKqpdeiEAKR3aIjbrIXMNZktNLVNMB8d2ZGYSXb8+Z03/ktTLL2Pv9zMBSOt5Dc6lyyjZsfOQ8SU+GePYV7rBWxrfUiUdnHkUvjAY9+9ziOh+ExKfVKa/ceaVKdQPzN0VnHvQmOcvyiSqQX3O/uZL0q64jJwZvtw9DienvzOVJm9NJv7c1iHzjkhLwZUdYlyWr6JKd/+Yt2+LWK1EpKVSEtTftXdvmQ8wB7IkJOPNCxqXoNyt1Wvhzd9H7qgBFC/4kdhr+ga6SWIylqRUPJsr/nZEKaXUP59Y5Zj+TiQtuo+f34wxXYF2wDUiYgGGANOMMZ2BJ4DyK8pDEJH+wFxjTK5/0xki8hOQCXxe3j7GmEnGmFbGmFb9+vmWBMRFWckr8gT6WAQs/iLn6ZlZ3HpeDeIiSwvWvQUuXp+/nfs61TqsPL2OfCzxQbPbXlNmaYBERBDZoAnFy/70bfC4KV6+BG9eLqakmKK//sCeXv6MrjvPgS0pKLbxBmJveP41ks5rSctpU4iuU5vCrK2Hle9+nvx8rInlx04fPIgdk6ewtPtlrB8ylIzRo4jMyCD5wn+xc+rhzbSaQicEF80maFy8HtzLfDPGnmULsFSvc1B/iY4rW7QfkLst6BsF4y3NvdYDg9j+xhT+uuQy1g0eSt0xowBYP/QhVvz7JtYNeYiMEY+EzNud78AWPC5BsTe94Bvz5h9OIapObYqytuLOz8ceNNNuS0osU7QfNC4FDixxpedpgsfF46Hkj18AKPl9HtZadQP9ojr2oGj21yHjKqWUUn9HWnQfPz1EZDwwGogBIoDmwHQAY0wWsOtIAopIvIi8CuwyxowNalpujOkApAPni0i7w4nXsnY8M1b6iqC1uwsDa7SznS6W73AybfFuHvh0Hev2FPLwlxuYuWofVhEe+WoDY2ZsYvFWBx/9EfoUipb8TmznfwFgz6iHe3fZWeCY89pTuGhB4Llr8ybsdRsg0dFgsRDZ+AxcWZsoz74Fi6h22cUAxDaqT9G2HYE2j8PJsnseIrNnX2wJ8Wz/qNzPISHlL8ok5eKLAIhqUL/M7HVkzZq4du8BwJ2dQ0T16qRedimIUO+58dQc0J+krl1I+le3kPE96/7C1rwDAFK9Dt59u0vbNizHdmYbAKwNm+Pduh7PppXYTm8NFivYI7HUrIt35+byc/8tk5RLfLlHV5C7KzuHyBrVfQ1W3wcrj8OBcZddYhRs34JFVL3UN+YxjepTtD1ozJ1OVtz7EIuv8435jmmfk/fHX6R0vgCx2bBERxHXuCEFa9aHjO9a+ScRbTr7UkrPwJtT+t5yrVlKxDltAYg4swXuoFntyFYXULL4l5BxlVJKqb8j/SHl8TPAGNNKROKAPv5tWcAFwBci0gSoeYQxXwLGGGNWl9dojHGLyD7g0Gs/gI4NEpm7dh+9315BbKSVEZfUYfyPWdzTMZ2P+p4Z6HfzuysZc1ldIm0Wep3jW0a+dV8xz83awrXnVA0Zv2D+T8ScdwE1X56Kt6CA3c88Rspdg8h5/UVwu4k6pzUFc2eV5l9SzN63JlHzhTcwbg95X/wPz97scmPvnjGbtG4daf3le7gdTpYPHk7D4Q+w9skXSD6vJQ0euhdE2PX19+z9ZdHhDEdA7qzZJHXsQJP338XjdLLp0RHUGjKYrc9PYOvzE6gzcjhYLIjNRtZTz+BcvDiwb/y555LYoT37/MtOyuNZtgDbmecSfd/zmOICiv/7HBFX3E7JV2/i+ulzom4ciu2cDphCJ0XvjQNnHq6F3xF9/wvgKqbk67d8s8zl2DdrNkmdOnD6B+/idTrZ8MgIag8dzJbnJrDluQlkjBqO+HPfPPYZABpPegVLVDRYLWSNey5k3tkzZ5ParSMtPnsPt9PJqiHDqf/IA6x/6gWSzm1JvWG+Md89/Xv2LfCN+Y4PP6HFF+/jLSpi/bgXfctdQij5Yz4R57QlaeQreAsLcLzxNLE39Mf54SQKZ3xCwl0PE3leF0yBk/xXxwAgsfEYtwtc5f84Uyml1KnFUol+SCkm6Ot/deT2X70E35rrNviWfDQDOgFVgPf8XRcC7Y0xbYP2HQksqODqJdnAX0GbRhljfgy6eonVv/+QQ6Rp3G/deGQndphsfd5lXfuzwxIboP7PfzEjrXFYYl+4ZxW/NWwSltit16zEMaBrWGLHvfQDC+uHJ2+ANutW8mP18Ix5lx2r2H39YX0xc8SqfDA/LHGVUkqFdNIr3l3Xtj2mQrbqR7+csHPQme5jZIzZCJR7uUAR2eFfBoKItAQaHLDvyEPETg2x/eDLgiillFJKnWIq0yUDtegOr84i8h/AAMVUcHk/EXke3xrw/d4xxkwOa3ZKKaWUUuqE0KI7jIwxM4AZh9n3vvBmo5RSSin1z3KiL/t3LPTqJUoppZRSSoWZznQrpZRSSqlKqTKt6daZbqWUUkoppcJMi26llFJKKaXCTK/TfWrQF1kppZRSx9tJX9uRc/MFx1TjpEydq9fpVseX97NbwxLXcuVkCoZdEpbYADFjv2HbFeeGJXbNz39lb9+OYYmdPGUOc2uH5wY2F2StJLt3+7DEBkh952eyLm4Rlti1v/2dkpeuDUvsiAEfhX1clFJKqaOlRbdSSimllKqUxFJ5VkpXnkyVUkoppZSqpLToVkoppZRSKsx0eYlSSimllKqUKtN1urXoVkoppZRSlZJFbwOvlFJKKaWU2k9nuk9BL3y3iUUbcvF4DY9d3YCG1WMBWL3dydivNlDk8lArJYonejXCZhWm/7mb9+dvp8jlpXf7mlzRomrI2PZ/9cZS92ywWCj5ZAJm12YApEY9om55HO+eLQCUfPayry02kYirByJxSZh9uyn579iQseNvuIOIM89BrFb2vfwk7qz1ACQOeBhb9Vq+48TE4tm1nb1jHySqTUdir/g3Yrfh+Px9in6eGTJ21FV9sTVqhlisON8ah3fbxkBbRPtLiOx4GXi9FH42BfeK34nudSfWjMZIVAyF/3sV98o/KhzzOg8MJLFNa7BaWTtsOAWr1/rytdtp+Mxoomqn43E4WTlgMJ58B4lt21D34QcwXi/bp77Hrk++CBk7+prbsDdpBhYrzinP4Nm6IdAWeUF3IrtcAV4PBR9Pxr08k/j7nkASUsDtwr1+OQUfTAwZO+Gmu4g8qwVitZIzYTTuTb4xT77vUWw1awNgiYnFvXM72Y8/QGLfgUQ0OQtLVAy5b71CUeb8CsflxQXbydzqxGMMIzrXpkFqVJn2PQUuLnlrBT/ffhaRNgur9xTy2Czfe6hLvURubRn6vRjOcVFKKaWOlBbdR0BEMoCxxpjrj3C/04HHgTeMMd+GI7fDtWhDLtmOEt65symrdzh5ZvpGJvU9E4BaqVFMvu1MRIRHpq3hr6x86lWN4f1ftjPl9rPweA3/nriErmekEBd18FvHknEmEpdM8aShSLU6RHS/jeKpwwPt7qU/4/qibCETcUlfXDPexuzcVGHeEWc0x5KUQvbDd2I7rR4JN99DzuODAMh9aUygX8LtgymcNR2JjCL2yn+T/ejdiNVK2tjXKVr4E7hKDopta9gUS0IKjqfuxZJel5hr78Lx/IO+c6qZga1hU/KfuBuCbiRV+OVbUFSIJFch9pYHcVRQdCec2xJ7WhpLevUmpnFD6j48hGV97gAg9aKuFG/dxur7HqTa9T2p/n+92DrpTer+ZzB//d8teAuLaP71tJBFt61RUyyJKeSNuQdrrbrE/F9/8scNAcCaXhdb42bkjbqzTO4A+c8OxTjyKh7zM8/BmpTK7qG3Y69Tn6Rb72PP8IEA7H3+8UC/pLuGUPDD1wAUzP2e3CkTsCQmUeXxlyosujO3OsgucDP1mgasyS5k/LxtTLy8Xpk+kzN3kRT0Xntu/nae/Ndp1E6M4OZP1nH1GSkkRx/8XgznuCillPr7qExrunV5SZiJSB1gGOA42bkAzFu9jx7NqwDQqHosuQXuQFtMhBURodjlJbfATa3UKDZnF3JGzVgibBaiI6w0Oy2edbsKy41tbdgC95+zAXxFdEx82Q6FBwxBdBzEJGDv8n9E3vEM1nO6hMw7snkbCufOAMC9eT2W+ISDj1+1BtakFFxrV2BvfDYlS34DtwtTXETJ6mXYatUpN7btrFaULPwBAO/WDUhsad6RF/TAm72DuCHPEXvXSCQu0ddQ5BsDa7VaeLasC5k3QHKH89n9ub8oXbUGW1JioM2VvRdbou9c7CnJuLJzfNv35WKLj8caG4PHWRAytv3scyn+5XsAPFs2ILGl4xLZ0Zd7wkMTiBswKpC78RqM89Bvx6iW51Ew2/cZ0bVpHZb4xIP6WKvVwJqUSsnq5b5+a1YA4C1w4nXmVxh/flY+3RslA9AwNZq8Ik+Z9uW7ChCgVmJEYFtKtI3cIg8lHoMAkSHW8oVzXJRSSqmjoUX3URCR7iLyg4gsFJFR/m1JIvKpiMwSkYkisgjAGLPJGNMH2HgkMUUkWkR+DWq/T0T6iMjZIvKTiMwQkedF5IMjyT3H4SI51h54brMKXm/pbN8D/11Ft7G/0ah6DGlxdmqnRrF4Uz6OIjfOYg9LsvLxeEPccTUuCePMLX3u9YBI4LH1zLZE3vEM9svuAKsNSamOJS2dks9fpnjyw9jadIf45HJDWxKT8ebuDTw3nqDYfrGX/x+OL3zDYU1MxpO7rzSV/FwscQcX6gCW+GS8+aV9g/O2VKuFceTiePo+Sn6dRdTlN/vG7YxWxI94nZib7qd4duilHwD21FRcOTmlubtL4+f9lklMg/q0mPklVa+6jOxvfUtgtr4+leZfT6PFzC/Z+eHHIWNbEpIxwbkHjYu1em28+bnkPXEPJQt/JPqqW3zHL3KS8NALxD/4HLYmzUPGtiallBlzvO6Dxjz+qn+T/9n7B5ywneS7hpL3wZSQsQFyCtwkR1tLj2cBr3/mucDl4fn52+nfpnqZfW46pwoDvtrAFe+tomV6LDERVsoTznFRSin19yFWOaa/wzqGyOMiMkdE5onImQe03SIiC/xtXSuKo0X30fnNGNMVaAdcIyIWYAgwzRjTGXgCSDuWmEAxkCki+++BfjnwIfAccIsx5kJgXqhgItJPRBaJyKJJkyYFtsdFW8krdAf1A0vQVzPj/q8xcx4+F7fX8FnmLpJi7NzZtTZ3Tl3O8I/XUCs5ivTkyPIPWuREouNKnxtv4Ot7s3MTRc/3p/i1IVDowNb6YvB68GatgoJ8cJfg3bgcS2rNckObAmfZotmYsksD7BHY6zbCteovALwFDixxpTPWltj4sgVkcOxCJ5agWXnjDYrt9eBasgAA15JfsNb0zZa7ly8i/7HbcYx/gNh+j5Q/Hn7u/PzAbPaB45Lx4CC2vDaF37tdxqp7h9LgqVHYU1NI79ub39p24dfzupB0/nnENGkUIncHEvyNQlBsPB5cf/4CQMni+djSMwBwTnqCvCfuwfHaaGJ73xcyb6/TgQSNeZlxAd+Y12tMyYolgU229NNIGTQCx5cfUfznbxWOS3yktczstohg8RfGz8zdRt+WVYkLKqpdHi9Pz93Gl72b8M1NTShxG37aUP5SkHCOi1JKqVOHiFwAVDPGdATuAJ4JajsTuABoZ4w53xjzQ0WxtOg+Oj1EZDwwGogBIoDmwHQAY0wWsOs4xJwM9BaRFkCmMaYIiDXG7F/PkBkqmDFmkjGmlTGmVb9+/QLbW2UkMOOvPQCs3VlA9cTSAjrfX4xbLELVhAgKSnwFUZczUnn3zqYMviQDiwjVEssvur0bl2E9uz0AUvU0TO6e0sag27SaQidgMLu3ItVOg4goEAuWWg3x7tlabuzi5X8Q1c63/MRWuy6ePWWHN6plO4r/DHwxgGv1MqJatAWrFYmIxFanPu4t5a8bd69egr1VR1+aNetg9u4ubVu7DHvT83zHbXKObymJxQoRvjHw5ueWObfy5P2aSVr3iwCIaVif4u07A22R6TUp2e0bJ1d2DpE1qmNPScZ4PHiLisHjwZ2bR2SN6uXGdq1aQsS5nQGw1szAm1Oau2vtUuzN2gJgP70F7iz/28biK2RNYYFvBjiE4qV/EHOB70O77bS6ePbsLNMe3fp8ihcvDDyXiEiS+g1m7wujcW1YU+GYALSoGcv363zfjKzLKaJanO8bmOwCF8t3F/LxshyGfLuJ9TnFPDIzixKPwVniIcZuQURIjbGxLf/gNfrhHhellFKnlAuB/wIYY5YCKUFttwKbgB9F5CMRqXDCVX9IeXQGGGNaiUgc0Me/LQvfp50vRKQJUP6U7RHENMYsEpGxwM3AC/5+dhGpaYzZBoReBB1CxyYpzFm1lxsnLiEm0spjVzdg3PQNDLywDt8s2cNnmTuxWy3USolkxFUNAN+Sk+37iomNsPLolfVDxvas/BVL49ZE3vEMFBdS8ukE7Bf3xfX921hPb4Ot/VXg9WL27qTkkwngceH+8QMib3sSvB7cv34Djn3lxi5eNI+olueT+sQkTKGTfROfJP6mAeS//yq43USc1cL3Q0k/b34uBT98RdrY1zHFxeT/d5Jv2Ug5XEt+wd70POKGvQhFBTjfGkd0zzso/HQyxbM+I7bvMOytOmEKnRRMeQpsduLufdL3NYGBwmmvVzjmOT/MJqVLB5p+/C4eh5M1w0aQ8dBgNo2bwKZxE2gwZjhYLIjNxoYxz1CwZh35S5bS7NP/YozBuXwFe2fPLT/3xfOJaHYeCY+8jCkqwDnlGWKuu4uCaa9TNPNT4vr9h8hzO2MKHDjeeBKA+PvHIhFRYLFQ8L/XQuZd9OtcolufT9Vxk/EWONk7YQyJfQeS+/Yr4HYT2bQlhb/MCfS3ZzQgokET0h6fENiWPeoBvCF+mNghI4G5G/PpM20tMREWRnSuxbPztnHPedX58LrSmf1bPlnL6G61ibRZ6HVWKn0+XovNIlSJsfF4t9NO+LgopZT6+zjWH1KKSD+gX9CmScaYSUHPqwK7g567RcRijPECDYFvjTGdRKQnMAK4J+SxjAmxPlcdZP/VS4BsoA2+meZmQCegCvCev+tCoL0xpm3QviOBBaGuXiIiLx8Y0xhTJCID/Y+v9vfrCowD9gC/ATWNMTcfInXj/ezWIzzbw2O5cjIFwy4JS2yAmLHfsO2Kcw/d8SjU/PxX9vbtGJbYyVPmMLd2k7DEviBrJdm924clNkDqOz+TdXGLsMSu/e3vlLx0bVhiRwz4KOzjopRSqoyTfukQ58Bux1TIxk6YWeE5iMjTwJfGmLn+5z8ZYzr4H38K3G+M2SAi0cBX/qXC5dKZ7iNgjNkIlHu5QBHZEfQitAQaHLDvyEPEvjvE9gnAhKBNPxljzvEfZxBHvoxFKaWUUuqfIfx3pJwL9ATmisgZwJagtl+A7sDL+CZglxy0dxAtuo+fziLyH8Dg+xFk/1AdReR5fGvA93vHGDP5MI9zn4j0wPfpcgNw51Flq5RSSilVyZ2A63R/DXQXkblAPnCHiDwFPAq8ArwpIr2AXKBvRYG06D5OjDEzgBmH2fe+YzjOMwT9clYppZRSSoWHf+32XQdsftD/3xKg1+HG0quXKKWUUkopFWY6062UUkoppSona+WZP648mSqllFJKKVVJadGtlFJKKaVUmOl1uk8N+iIrpZRS6ng76dfpLhh2yTHVODFjvzlh56Bruk8R3pkhb5B0TCzdXiTvjs5hiQ2Q8Nostl/VJiyxa3y6MKyx3e/2Dkts243vUDD04rDEBoh5+tuwjkvhw93DEjt6zHRybr4gLLEBUqbOxT3lhrDEtvV9PyxxlVJK/X1o0a2UUkoppSolCf/NcY4bXdOtlFJKKaVUmGnRrZRSSimlVJjp8hKllFJKKVU5hf828MeNznQrpZRSSikVZjrTrZRSSimlKqdK9ENKLbpPQS98uZZFa/fi8Roe+78zaFgzDoDVW/MZ+8kqikq81EqN5oneZ2KzWhjw2h/syS8hwmbh7DqJDLmqUcjYkZffgrVhM7BYKXp3PN7tGwNt9nYXY7/gMvB6Kf7yTTwrfyfy6n5YM05HoqIp+nwynmW/hYwd9393EHFmc8RiJXfik7izNgTaortcSsyFV4HXQ/5/J1Hy1yKizu9GbPdeEBFJwVcfUjjnm5MSG2DCrC1kbs7H7TU81iODBlVjyrTvcbi46MU/mT+kBZG20i+g3v11B4uzHIy7pkHI2PYLb8JS7yywWCn5eAJm5yYApEY9om4djXf3FgBKPn0Js2szlvpNsXe/DYwX9/wv8fz+w0kbF1u33lgyfLm7PpuA2bU5kHtkn1GB3F1fvIzZnQWxiURceQ/EJmFyd+P68KmQsaOvvhVbo+ZgtVLw5tN4tm0MtEW0705U58sxXi+Fn0zGvSIz0BZz/QCMx0Xh/14LGXvCT1vJ3OLwvZ4X1aFBlegy7XucLi569S/m39ucSJuFJ2dmsSgrn/hIKzUSInjy0roVjotSSqnDI5VoeYkW3RUQkQxgrDHm+iPc73TgceANY8y3FfS7GhgIWPG9Fp8bY8aKyEjgaiAH34Xn/wQeM8Zki0gn4G1gAxAB/McYM+twc1u0di/Z+cW8M6g1q7fl88ynq5l0dwsAaqVFM3lAS0SER95bxl+b8jinXhIAE+88h+S4iApjWxucjSSkUDD+Piw1M4i85g4KX3oIAEuNDKwNmlLw9AAIuiGTK3M2xZ9MQuISiRn4FM4QRbf99OZYk1LIeeQubKfVI77PQPaOHgSArXZdIs5oTvZDtwViS2w8MZf0JHvE3WCxkvbEJIp+/QlT6DyhsQEyN+eT7XTxVp/TWbOrgHE/ZPHq/zUu0+eN+dtIiin7z9FZ7OG75TlUiw897paMM5H4JIpfHYpUq0NEj1spnjI80O7+ay6uzyeWPd9LbqX49WFQUkzUwBdDFt3hHhdLnTORuCRK3ngQqVoH+8W3UvL2iEC7Z+nPuL56tWxOF/XF9f07mF2bQo4JgK1RUyQhhfyx92BNr0v0df1xPDcUAGvNDOyNmpI3+q4y70UAS0pVbGe2wrXkl5CxM7PyyS5w89YNjVmzu5Bxs7fwaq+GZfq8sWAHSdFlX89Rl9ThzOqxFeatlFLqn0vXdB9nIlIHGAY4DtHvWuBa4FJjzAXGmLbAK0FdhhpjOhljOgK/AO8Gtb3v394DGHck+c1bkU2PVjUAaFQzntwCV6AtJtKGiFDs8pDrdFErNXp/riTE2A8Z23ZGK1y/+go477aNSGxCoM3evjvenB3EDHqW6NtHBNq8m1YDYIoKMAWhhyyyeRsK584AwL15PZa40tjR3S7Hs2s7KaNeJumBMUh8IrYatXBvWA1uN5QUU7J6KbZaGSc8NsC8dbl0PysVgIZVY8gtdJdpX77diQC1kyPLbH/5p63ceG71kHEBrI1a4l48G8A3wx0dX7ZDYTljWpiPRMVCZDSmpDBk7HCPi6VhCzx/zvHlvmsTckDu5sDco+KQmHhsna8n4vansTbvEjK2/azWlCyYCYBn64YyuUd2uBRP9g7iH3yB2P6PIXGJpefV8w6Kpld8o5p5G/LofnoKAA2rRJNb6CnTvnxHge/1TCr7eiZE6RyHUkqdyrToPgwi0l1EfhCRhSIyyr8tSUQ+FZFZIjJRRBYBGGM2GWP6ABsPEXYwcJsxJlBZGGPyyutojPkv4BaRmgdszwEKReSwv1vJyS8hOa60gLZZBK+3dLbvgTeX0O3RuTSqGUdagm+GNS7Kxi0TFtH3xUX8uiYnZGyJT8Y49pVu8HrAn5qlajrGkUfBs4NwZc4i8rI+pf1sdqKuu4fib94LGduSmIw3b2+5sW01auPNzyXn0f4UzfuB+Otuw71jK/bGZyHRsUhUNBGNzgKr9YTHBsgpcJESNItttQhe/wxrQYmH537M4u6OtcrsM399Ll5jOKvmIWZG45Iwjtyg3L2B3PF6sJ7Zjsi7xmG//E6w+nJw/fQJUQNfJOr+V3H/NiNk6HCPi8QmYpyluZug+Hg8WM9oR8TtT2PvcQdYbUhKdSQtHdcXr1Dy5iNYz+0O8cnlx45PxuTvK43tCXovVq+FceSSP3YgJb/OIvrKWwCI6NAD98ZVePfuCpkzQE6B+4DXk7Kv55wt3N2+zD9VYiIsPPTVBm5+fxUzVu1FKaXUcWK1HNvfCaRTL4fnN2NMVxGxAkv8yz+GANOMMe+JSG1g7hHGtOwvuEXkfuByYK8x5qoQ/TcCpwVvEJGWwG5jDviO3NfWD+gH8Nprr3FbPd/2uGgbeQXuoH5gCVoPNe6Wpni9hhe+XMtnC7ZxVdt0nrzpLAB27Svi9pd/5/OH25WboCl0IjFBs5XGW/r1vceD+68FALj/WkBExyt8g1C1FhGX3kTJdx/g3bo+xKmDKXCUmTk33rKxizPnAVCUOY+Yi6/GOPJw/O9Nkh8ejzdnN+6d2/Ds2n7CYwPERVrJKyqdDbWIYPEXgE9/v5lb29UgLrK0ON1b4OL1eduYeH1jsp2ug+KVUeREouMIvAGCxtzs3ETRc3cBYP/XjdjOvQT3kp+wt7+SwiduAq+biOsewJu1GrNjw0Ghwz0upqjggNxNae67NlH8Yn8AbF3+jbXVxXg3LcObtQoK8wHwblqGJaUm3vyDi1hT6ERiQ78XXX/63ouuP+cT1eVKLNVqE9GiA47nH8TWpHnInGH/61n6b6jM6/njFm5tU73M6wlwb4d0APKLPfT972rOqxOvM99KKXWK0Znuw9NDRMYDo4EYfGupmwPTAYwxWUDF02MH84iI3b//s8aYTkCNCvqfiW8dN8ANIjILuAe4o7zOxphJxphWxphW/fr1C2xv1SCJGX/sBGDtdgfVk6MCbfmFvgLPYhGqJkVSUOwrFN0eLwCxUTZsFfxK2LN2CbYWHX0xatTB7N1T2rZ+ObazzwPA1qg5ni3rwB5BZK/+FL0zvsKCG6Bk+WKi2/mWE9hq1cWbXTrcJav+IrLl+QBEntUC18a1ABT/NpecR+4k7+2XwHjx5uw+4bEBWp4Wz4wVvm8I1u4upFq875uGbKeL5dudTPt9Nw98vJZ1uwt5+PP1zFy5F6sIj3yxnjHfbmLxVgcf/V7+28u7YSnWphcAIFVPw+SWjjmW0n/evqUaxje77PWAuwS8Xl9hnZR2UsbFu2kp1rPa+3KvUhuTFyL3Il/uZs9WLNXqQEQUiAVLekO8e7aWG9u9+k8iWnXyhaqZUSYP99pl2Jv53ov2JufgyVpHZNtuIELsXSOJvvxmIpq3x97ignJjt6wdx4xV+wBYu+eA13NnAdP+3MMDn69nXXYRD3+90XdM/7dJ0XYLdmtpka6UUurUoVMth2eAMaaViMQB+9dFZAEXAF+ISBOgZsi9y/cO8KyI3G+Mcfln0Q8iIhbgPmC5MWan/0ea7xtjhh3NiXQ8swpzlu7hxmd/JSbSxmM3nMG4z1Yz8NIGfJO5k88WbsNuFWqlRjPi+jMA6P/qYopcHrxew6DLG4aM7f5rAbaz2hDzwAuYogKK3nuWyKv7Ufz5FErmfEZ0nwext+iIKXRS9PbTWNLrYT2tITH3jA3EKHh1OBTkHxS7OHMekS3bkTrmNbyFBeROfJL43neT/9/XKPj2YxLveZSodl0wBU72vfQ4AEmDRmGtUh1voZO8Sc+EzDucsQE6Nkxi7tpcek9dTmyklRHdMxg/M4t7Oqfz0W1nBfrd/PYKxlxRj0ibhV4tqgKwdV8xz/2QxbX+5wfyrPwVS5PWRN41DooLKPl4AvZL+uKa8TbW09tgu+BqMB5Mzk5KPp4AHhfeLWuI7P8sYPBuW4931aKTMi7eVb9hbdSaiNufhuJCXJ+/iO2iW3DPfAdLkzbY2l0JxovZuxPXZxPA48Y16wMi+z6J8Xrw/DodnPvKje368xfsTdsS/9BLmKICCt4aR3SvOyn85A2KfvyUuNseIqJ1Z0yBA+fksRhn6couW5Pm2M9ug+v38r+86lg/kbnrcun93ipiIyyMuKgO42dv4Z4LavJRn9NLX8/3VzGmRwYAI7/dRNa+Ytxew/XnVDloJlwppdTRqUxXL5FyViYov/1XLwGygTZAJtAM6ARUAfYvQl4ItPf/GHL/viOBBaGuXuJfh30XcAOwfw3BR8aYiUFXL9kDeIFpwCRjjNd/9ZKLj7DoNt6Z9xxB98Nn6fYieXd0DktsgITXZrH9qjZhiV3j04Vhje1+t3dYYttufIeCoReHJTZAzNPfhnVcCh/uHpbY0WOmk3Nz+bPTx0PK1Lm4p9wQlti2vhX/eFMppf6mTnrFW/zklcdUyEY+9NkJOwed6a6AMWYjUO7lAkVkhzGmg/9xS6DMhZSNMSMPEdvgu1rJK+W0jQTK3d8YMxuYXXHmSimllFKnAL05zimhs4j8BzBAMdA/VEcReR7fGvD93jHGTA5rdkoppZRS6m9Di+6jZIyZAYS+3lrZvveFNxullFJKKfV3pkW3UkoppZSqnHR5iVJKKaWUUuFVma5eotfpVkoppZRSKsx0plsppZRSSlVOlWh5ic50K6WUUkopFWZ6c5xTg77ISimllDreTvo0c8mEnsdU40QMnKY3x1HHl/en+8MS19LhWTZ1bR6W2AB1fljMn2c0CUvsZstXsr5D07DErvfTElxv/F9YYttv+y8rmodnTABOX7yShfXDE7/NupUUPtojLLGjH/+ade3PDktsgPo//0XJhJ5hiR0xcFrY7qaZMrX829krpdQ/gqXyLNqoPJkqpZRSSilVSWnRrZRSSimlVJjp8hKllFJKKVUpiV69RCmllFJKKbWfznQrpZRSSqnKqRLdkVKLbqWUUkopVTlVouUlWnSfgl74bBWL1uTg8Rge6302DdPjAVi9JY+xH62gqMRDrbRonrilGTarhXHTVrBkwz4Kij3ce2UjLjirasjYiTf3J6ppC7DayHn2cVyb1gGQMng49pqnASCxsXh2bGP3yMGB/ZLvGoxxudj3xoSQsavfM5DYVq0Rq5WskcMpXrvWF89up9bjo4lIT8frdLLpgcF4HQ5q3D+YmKbNsMTEsGPC8+T//HPI2Mm33k1Us5aI1cruZ0bh2ujLO23oSOzptQGwxMbh3rGVnY/cT7Uxz2NNTsW4SihesZScV5+rcMxf/HkbmVkO3F7DyItOo0FadJn2PU4XF09ayrx7mhFps1Do8jJqxmY27yvGbhGm/l+jkLGr9B9IdIvWiM3K9seHU7LONy7Y7NQcORp7zXS8BU62DvONS1znrqT2vgWx28l+Zyr5M74JGbvWoIHEt/bF3vDwcArXlI55vSdHE1HLN+Zr7x2Mx+Gg4asvYU9Nw5SU4FiyhKynxlU4LrauN2KpcxZYrLi+eBGza7MvfvV6RN70GN49WwBwffkKZncWETc8gsQmYTwuvFtW457xZsjYybcNILpZS7Ba2f3MY7g2+F7TKg+OxF7L9160xMTi2rGNnQ8PwpqUQtrQ4diSU3Ht3M6ukUNDxn5x4Q4ytxXg8RpGdEqnQWpUmfY9BS4ueWcVP996BpE2C79ucfDyrztxeQxd6ydya4sqIWNHX30rtkbNwWql4M2n8WzbGGiLaN+dqM6XY7xeCj+ZjHtFJnEDn8CSkIxxu3CvX0HhRxMrHHOllFInhxbdx5mIZABjjTHXH+F+pwOPA28YY76toN/VwEDAiu/1+9wYM/Zwj7NodQ7ZecW8M6Qtq7fm88y0FUy691wAalWJYfKgcxERHnlrCX9t2Mc5DVK4uFUNHuh5Ojn5xfR74beQRXfk2edgTU5l5/23Yc+oT/Idg9j1nwEA5IwfFeiXfPdQnDO/Djy3Vq1OVIvzKFwY+nrCsS1bYktNY12f3kQ1aEjNB4aw4c47AEjo2hXXtm1kDXuQlGt6ktqzF7unvsm+775j+7PjsSYnU++110MW3VFNW2BNTmX7wL7Y6zYgtf/97Bh6NwB7nh4Z6Jc68EEcM74KPN8xbADevNyKhhuAzC0Osp0upv5fI9bsLmT87K1M7NmgTJ/JC3eSFF36z/HVX7Zz+ZkptM1IqDB29Dktsaamsfm23kTWb0i1QUPIGuAbl/guXXFt38a2Rx4k6aqeJF3Vi73/+4DUm/qyud/NYLWRMfU9HLN/wJSUHBQ7vlVL7GlprLihN9GNGnLasCGsutUXO/lfXSneto11DzxIlWt7UuW6XuyY7CuAV99+J+59+w45LpY6ZyKxyZRMGYZUrYP9or6UvDMy0O5ZNg/X168etF/xu49BYX6FsaOatsCWksq2e24hom4DUvsPZseQ/gDsfqr0GKn3DsPx3ZcApNw1iL2vv0TJhrUVxs7c5iS7wM3Uq+qxJruI8fO3M/GyumX6TP59N0lRvtfTGMNzv+zg9SvqEm2zcPsXG7iwfgK1EyMPim1r1BRJSCF/7D1Y0+sSfV1/HM/5in9rzQzsjZqSN/ouOOCmZvnPPYhx5lWYt1JKqZNLi+6/ARGpAwwDHIfody1wNXCpMcbh31ZxVXaAect30+PcmgA0So8n1+kKtMVE+t4OxS4Puc4SalWJAeCsjCQA4qJsxMeEfstEtWyLc5Zv1tS1cR2W+INTs1ariTU5lZJVywLbkm69h7wP38Se0eCg/vvFtzufvdN9hXrR2jVYExMDbe6cvVgTfMeyJSfj2rULgMJlSwHwOhx48kMXJNGt2+L4wZ/3hrVY4hMP6mOrXhNrSirFK/15Gy9eR8WF337zN+bR/fQUABpWiSa3yF2mffnOAgSolVRahK3cWci+QjcT52+nc4Mkbjm3Wrmx49qeT943vnEpXrcGa0Jp7p6cvVj842JNSsa9exfRTZvh/HUBxuUCl4vCv5YQUbcexatWHhQ78YLzyf7SF7tw9RpsB4y5rZwxx+vFnXd4xZ+lwTl4/poDgNm1CYmOL9NuCsv552AMFDkPGTv63Hbkfz8dgJINawPvj2C26jWx+V9TS3wC1sREkvr0w1alKnlfTMPx3VcH7QMwPyuf7g2TAGiYGkVesadM+/Ldhb7XMyECgL1FHtJibMRFWAFof1o8y3YVllt0289qTcmCmQB4tm7AElead2SHS/Fk7yD+wRfw5u2l4O1nMY5c8HoxBRX+T4dSSv1jSSVa061XLwkTEekuIj+IyEIRGeXfliQin4rILBGZKCKLAIwxm4wxfYCNhwg7GLhtf8Ht37fcCkdE+onIIhFZNGnSpMD2nPwSkuNL/8/eZhW83tJZswde/4Nuw2bRKD2BtITSfiUuD2M+WM4dl4QujK3JKXj37Q08Nx4PSNl/DAk9byTvk/cCz+MuuZKS1Stw795V4YnbUlPx5OSUbnCXxnb+nklkvfo0/uJLki69jNyZM0vHwW4n/eFH2DXptQrz9gTljcd9UN6J1/Ym93/vBp57nU5qPPc61ce/RlSzlhXmnuN0kxw0i221CF7/TGVBiYfn5myl//k1Au37Ct2s2FXA7W2q8+b1jfh9q4NlOwrKzz0lFc/e0nEJHvOCxZlE1q1PvY+/JKH7ZeT/OBNbStlx9OTuw1rOhwzwjbkrp/zY+YsyiWpQn7O/+ZK0Ky4jZ4a/UHQ4Of2dqTR5azLx57aucFwkNgnjLP2mwHiD3i9eD9Yz2hJx61PYu/cDq3/WuKiAiFvGENFnNJaMs0LGPpz3YuJ1vdn3ke81tdWshb12BnueHcP2QXeQcMW1WFPTyo2dU+AJ/Xq6vDz/yw76B31ISoqyssPhYrfThctjyNzmxO0t/67FEp+Myd9Xbt6W6rUwjlzyxw6k5NdZRF95S2BM4h98nvgHnsXWuHnIMVFKKXVy6Ux3+PxmjOkqIlZgiYiMBIYA04wx74lIbeBI789sCZrhvh+4HNhrjLnqwI7GmEnA/mrb7L8NfFy0jbyg2W0RwRL0KXHc7efg9Rpe+GwVn83fwlXn12bDDgcTv1rDrRfXp3Gt0BPrXqej7Oy28Zb9GtweQUT9Rux9+WkAbLVOI7p9F3Y/PJDIZq0qPHFPfj7WxNLYJih2jfsGsXvqFPJ/+omoJk2o9dgoNg8ZTESdDKr378+uyW9QtHp16LwdDqzxCbgCsU2ZvCUigogGjSme8FRg2+4nHwXAmlqF6uMmsvWW0LcHj4u0lJkNtYhg8RdSz8zayq1tqhEXaQ20Wy1CvZSowMz3+RkJrMsu5MzqMeXknh+YzfZtKB2XqvcMIvvtKTh//onIxk2o/ugocr/+nIjap5UeKyGhTNEezJOfH5jNBjBBsWs9MIjtb0whd/ZPxJzehLpjRrHuvsGsH/oQAPaqVWny5uv81eOKkONiipxIdByBkQ4ad7NrE8Uv/T975x0fRdX9//fd3Wx6JYEAoRN6B+m9KMLPgl1RBBUERFRAHxvSLJSgYsUogoKIiopdUEF6SUB6CQECIZSQukk2Zcv9/TFLskl2FxCX55vH+369eLGZe+czZ8+cmT1z5s4dbYiPod996DvegG3HT1i+dYydD47Ad8RMit+d4FLbnp9XPhbtlfepb+NmZC5w7FObleKDe0uHCxXt+wuf2nWxZWZU0g6usD8FlO3PTWd5qH1UaVUbR9sLfWrxn99SCTbqiQwwUNtRBa/kk8ICRKBTxd/5GLLZsOzZBoBlzxb8+t8KQMFHr2p2hFUjePJ8TFNHutRWKBSK/0n0Vad+XHUsrXoMFULMB14GAgAj0A74GUBKmQp4Lu9WxiaE8HGs/7qUsi9Q0/Mq5ekUG8GaXWcBSD6TR3R42QNgeWYt7dTpBNXD/TAX2ygqsTHny0PMeKCNx4QboHjfLgJ6DwLAp15DbBWq1/6de1C0a3vp34H9hyCEjsgXZxP2wBj8u/fBv0c/l9oFO3cSev0NAPg2aoTl3PnSNmOtWlgvaMmRNTMLY3Q0wteX2v95ltRpL3lMuAGK9u4isK+T3enny7X7d+lJYeK28ivptaTKbs4Ha/nhIhXpGBPEmiNa1fVYRiE1gn0AyCywcOC8mZV7M5nywwmOZxbxwi8nCfbVU2KzcyFf2x87T+fTpMKDlxcx79pJyCDNL8aGjbA42e5Tsxa2DM0vtqwsfKKjKdq/l8AevcBgQPj54dsoluKU4y618xJ2EnGjpu3fuBElTj73rVULi8PnlswsfGtGl/OLLT8feQm/2E8eQN+yBwAiqg7S5JTg6spOTdJ5OMnF5cVmsJUf1uFM0d5dBPZz7NP6DbFeKL9PA7qW36eWUyfxadAY4e8POh2+TVtgST3pUrtDzUB+O6Yl58eyiqgR5NifZisHLxTy9cEsnl59iuPZRbz4h/YgaLvoQD6+tSEz+9cmw2ylrYsLKABr0h6MnfpqX7VWfexZF8rakg/g07ar9p2atceWeszhE83nstCs3aVRKBQKxf9JVKXbe0yQUnYSQgQBDzqWpQK9gO+FEM2AWleouRR4XQgxSUppcVTRr4g+rauzfl8698/ZQoCfgRkPtCZu5SEm3tqUXxLPsmrLaXwMgpjIAKYNb8Xh03kcPJXLo2/tKNV4a3xHwgIrV+oKt23Ev3NParz5MdJsJvONWYSNfoKcxe+C1Ypfu+so3LyutH/up2UPyfm27YT/dd3LtTtjWv8nwb1702jpMuwFBZyePo2akyZz7u23OPfWW9R+6SWE0CEMBs7EzcOvSRP8W7Sg4cKyoTUpTzyOLbfyg4/mrRsI6NqLmm8vQRYWcCFuJhFjnyTro3fAasW//XUUbCpvV/RrbyF8/UCnJyve/YwrAL0bhbLhuIkRy48QaNTz0vV1eX19Go/3rMmXI5qV9hu5IolXbqwHwNP9Ynjyu+PohbZ+sxquk7T8jX8S1LM39T5eht1cwNlZ04h6YjIX3n2LC+++RfTzL4FO80v6G/Ow5eSQ+/231F/8GfbiYi68/47b5DVn3Z+E9e1N8xWaz0+8OI06z0zm9BtvcfqNt6g/8yWEQ/vU7HkANI1/D52fP+h1pMZ5ntHFnpSAvkknjA/PgZJCLN+9g+H6UVj/WIquaWcM3W/VxivnnMfy3dsAGIe/BD6+IHRYfv/ErbZ5i7ZPa727BLvZzIV5M4gY9xRZH76txWL76zBvLNunsqSY7E/iqbXgI6TVhun7r7BlZ7rU7l0/mI0n83jwm2ME+OiY1rc2r285y+NdavDFXWXDr0Z9e5yXB8QAWgV8X7oZg04wuXvN0sp4RSx7tuLTphvBz72DLDJj/iQO/zvHUvjNRxSt/ZagR57DeF0/pDmfgkXa89NBT7ymxaLQUbgy3qWuQqFQKP77CCldjy1U/D0uzl4CZAJdgJ1AW6AvEAVcHNC8HegppezmtO50YJu72UuEEAIYB9wHpaMhvpRSXmqOsNLhJf80ut6vc3JAO69oA9T7Yzd7WjS7dMe/QduDhzneu41XtBtu2Ivlo3u9ou3zyOccaucdnwA0332Y7Y28o9/l2GEKpw71irb/rJ841rO1V7QBGm3aR8lb7ocRXQ3GiSvJGtnLK9oRS650FJtCoVBcNv/1pxityx64qkTWcP/Sa/YdVKX7H0ZKmQK4nC5QCHFOStnb8bkjUO6pRCnl9EtoS+A9xz+FQqFQKBQKRRVBJd3Xln5CiOcBCRQD4911FEK8iTYG/CJLpZSLvGqdQqFQKBQKhcIrqKT7GiKlXAOsucy+T3rXGoVCoVAoFIqqTVWap1sl3QqFQqFQKBSKqom+6iTdaspAhUKhUCgUCoXCy6hKt0KhUCgUCoWialKFhpeoSrdCoVAoFAqFQuFl1Dzd/w7UTlYoFAqFQvFP818vM9u+GnlVOY7+ziWX/A5CiFlAb7QRImOklAcqtNcATgARUsoidzpqeMm/BLn9Wa/oii6zOTusi1e0AWp+u52jXVp6RTt2+wGvvhzH/s0or2jrbltM6uAOXtEGqPPrLq+98KjeH7tJv6vbpTv+Dap/uZUzt3T2ijZAre92YP/+Ea9o627+iKKZN3lF2++lH7z20qBGm/Z5RVehUCguF+HlBymFEL2AGlLKPkKIVsA8YEiFbs8CGZfSUsNLFAqFQqFQKBQK11wPfA4gpdwPRDg3CiE6oI0oOH4pIZV0KxQKhUKhUCiqJjrdVf0TQowRQiQ6/RtTYQvVgQtOf1uFEDoAIUQgMBuYfjmmquElCoVCoVAoFIp/JVLKeCDeQ5dcINzpb7uU0u74/DowR0ppEuLSw1xUpVuhUCgUCoVCoXDNRuAOACFEC+C043N1oCMwWgixAmgBLPEkpCrdCoVCoVAoFIqqiffn6f4JGCKE2AjkAY8KIeYAU6WUnS52EkL8CYz0JKSSboVCoVAoFAqFwgWOoSTjKiz+j4t+fS+lpZLufyELVh4k4UgGNrtk5qj2xMaEAHAkNZc5y/dRWGIjJiqQ10Z3wKDX8fvOMyz+JRmL1c7IwY0Z0jXGrXbQvY9ibNkOodOT+/5rWFNPlLb59/9/BFw/DOw28j6Pp2RfIn49BhI45E4w+mL+8QsK1//iVjvi0cfxb9cRoTeQ/to0Sk4cA6D68zPwiakLgC4wCOvZNM4++yT+HTsTOWEy2O3krFxO3i8/uNUOf/gx/Np2ROj1XJg3E0uKph35zHR8atcp0z6XxvkXJ1HjlTfRh1dDWkooPrSfrIVvePb5mlMkppiw2SUzhjUitkZAufaMvBIGzdvFtqmd8fXR8ddJE/N/PYXFZmdIm0ge7FnLrXbIiHH4tuqA0OvJeutlrCe1B6jDn5yKoZbD9oBArOfPkjlrCqEPTcTYrBU6vwByP3mPop1b3GqHjhyPX5sOoDeQ9fosLCc1v0RMfgmfWprPRWAgtnNnuDB9cpk/x01GWizkfPSWR78E3j0Gn+btQKcnL342ttNl8eLXdyj+A29F2u0UfPkhWEoIvOfR0nZDvcZkTx+P7dQxl9rB9z2KsWV7hF5PzruvYU3V/BI64QUM0VoMi4BAbOlnyZ79H/y69CHwluEIHwP53y2naNPvbu1e8GsKiSdysdlgxh2NiY0OBCDpbAGzfzhOUYmdmAhfXr27KQa9YHtyDnE/nUAnBPf1qMktHWu41Tb0HY6uXivQ6bD8+C7ywinN1hoNMN43HZmZBoDl5/eRGakYBo5E1GyMMAZg/WMJ9pS9Hn0e/sgE/Nt2BL2eC/NmYHEcR1H/mV52HAUEYjl3hvMvPIU+LILIZ17CEF4Ny/mzpE9/xqO+QqFQKFyjku6/iRCiPjBbSnnPFa7XHJgFfCSl/NVNny7ATMAIhAE3SinPCSFaA68BgWjj8bcA06SUJZe7/cQjGWSYiln2Qm+STpuYt2I/8VO6A1CneiCLnumBEIIXF+1i7/FsmtUN5eOfj7Lk2Z5Y7ZLhszYwoENNfI36Sto+zduhD4sg68VxGOo2JPjBiWS//BQAhjoNMLZoR+Zzj4DjhUwiMJiAG+8gc9pjoNMT+Wo8RTs2IAsLKmn7teuAIaIaaeNGYmzYmMiJUzjzlHbhmf7qtNJ+UZOew+RIriMfm0TahIexFxVR95Mv3Sbdfm06oA+vxtmJD+HToDHVxk/i3DOPAZAxd3ppv2oT/0P+mh9L/z737ATsptxL+/yEicx8C0vHtCLpXAHzfk4hflSLcn0+XJ9GeIB2OEopifvlJO892JwgXz0j4vdzY5tIqocYK2kbW7ZHH1aNC8+MxqdeI8IefpKMlyYCkP3mrNJ+YeOexvzHTwCYN/5G7sdvoQsNI2rWO26Tbt/W7dGHV+P8pEfwqd+I8EefIv35CQBkzZ9Z2i/8sWco+P2n0r/11aPx69CVwu0bPfrFp1lbdKHh5Ewfj75OQ4Lun0DubC1x18c0wKd5O7KnjimNF4CcGdp+0UVEEfTgE24TbmOLdujCIsh8YSyGug0JGfk4WbO0WMx955XSfiGjJ1O47meErx+Btw4nc+pjCL2eyNkfUrR9A1gqH1qJx3O1/TmurbY/fzpB/MOtAIip5sei0a20Y+irJPal5tG+fgjzfz7Bx2Na42fUceeC3dzcoTquHroRdVtAYBglnzyHiKqLYeAoLJ/PKG23HdqM9dfyz/tYN3wBJYUQXA2fm5/wmHT7tdGOozOPj8LYoDHVxk/m3NPjAbgwZ3ppv2pPPEv+au14iRj3FNkfvkPJiWS3ugqFQvFfQ1d1Hk+sOpb+DyCEqIc2gXr+JbrGAfdKKfsBnYAMx4D9JcCTUsp+Uso+QBow50ps2LwvnaGOSnWTmBByC8qSigBfA0IIikts5OaXUCcqkD3JWXRtWR2jj54AXwNtGoVz/GyeS23fdl0o3LgGAOup4+iCQkrb/AfejC39LBEz3yVsyiuI4FAMNWOwnkgCqxVKiilJ2o8hpr5L7YAuPchb8zMAJceT0YWEVupjqFkLfUQ1ig/tB8BmykUXFIwuIAC72ezWJ/7XdSP/D63CbjmRjC7YhXa0Q/uw4yVU0o4937UfKrL5aA5D20YC0CQ6kNxCa7n2A2n5CCAmwg+A1Kxi6kT4EepvQK8T9G0Wzt5U19vy69gV85/atZvl5DGXtutr1EQfVo2SpINav6OHALCbC7AXuP8Ofh27UbDO4ZeUY+iCQyr10deohT68GiVHyl7OFfbw45i+WOxW9yLGtl0o2vwbALbUCvHS/yZsF84S9tI7hDz1MqLC9wq84yHM3yxxq10pFl3ZXr0m+rAILMmH8GnampK9CWC1IIuLKEk6gCGmnkvtzUnZDG0XBTj2p7lsfwYY9doxZLGTa7aW7tNQfx/yiqyYi22lfVyhb9ge+4ENAMgLpxD+QeU7FFW+IKWkEABdtdrI9BS3PgHw79ydvN8cx9GJZPQhlf1iiK6FwRHruuAQ9KGhhD04hlrvLiHohv/nUV+hUCiuOVc5ZeA1NfWabu1/ECHEECHEH0KI7UKImY5lYUKIb4UQ64QQ7wshEgGklCellA8CKZeQPQYMdKxjk1JagQeA16WUpeUmKeU7QM+L80VeDpl5xUSE+Jb+rdcJ7PaySuLk9xIYMHk1sXVCiQz1JdNUTERwWYU1LMhIboHFpbYuNBy7Kbtsgd0GjuTCULMO9rxcsqaOp2jzHwTf/QjWc2n4NG2F8A9E+PljbNIK9JUr6ACG8Ahs2VllC2xl2qW23TuCnBVLS//O+fwT6iz5gnrLV2H64Ru3PtGHR2DLcbLbZq2kHXrXA+R+tazsqxUUUPOND4me/wF+bTu61QbIKrAQHlh2U8ng5HNziY3Xfz3JhIF1Stsz8y1EBPmUbTvAB1OFRL3U9rAI7LnOPq9se/Cw4eStWl5+RR8fwsc9g2nFx27t1odHYHfyi3Th85A77sf0zWelfwfdeCslSYewXkh3q3sRXUg4dlNOmb5TvOhr1kHm5ZIz4zGKt/xB4B0Pl/YToeHowiOxnnRfedWFhpfziyvbA2++l/zvV2jbCw3Hlltmiz0vt9xFgDNZ+RbCnfaPocIxNOWzwwx8dQdNogOJDNb6jexdW6twz9/FbZ3dDy0hMAxZ4HT3xG6n9C3Ldhu6pl0xjpyN4YbRoNNiStewHcbRb2IYMg5bovvhWXB5+zT07gfI+VKLdUOtGHzq1Cfj9Vc4+9SjhNxyF/pqkR63oVAoFArXqKT76kmQUg4AugO3OxLgp4GVjkr1q8CV/ko9AtQVQvwghOjqWNYQOOSi7xmgWsWFzpO9x8eX3Y4O9vfB5FTd1ukEOqcnf+ePv44NC27EarPz7aZTBAf4YHJKsk0FlnJJuzPSnI8ILEtUpN1eNjTAZqN452YAinZuxlCnATLfRP5Xiwl/YT6h45/Hev4MtvSzLrVt+fnonKtyztqAMBrxjW1G0f49gJZchN19Pym3DuLErYPw79QFY+MmLrXt+fnonSqhUspK2sbGTSk+UHbb/sJrUzn7xMNcePVFqj35nEvdiwT56TEV2sr0RJnP5/yUwiN9ahPkV5aUB/vpy1XDTYVWwgPLkrxythfkI4KcfV7ednyM+DRsSsmhMtsNtesS8dQ08n/4kuI9CW7tthfkl68QS3slbWOjJpQc1LQNMXXx79mfvK+XcTnYzfnoAoOdFlSIl13asJfiXVswxDQo7ebfdyhF637EE9JcUD5pli780qAJliP7ymwJKrNFFxhc/mLGiSA/Ayan6rYQlDuG4oY3Y/3ULljtklWJ6WTml/DppjT+eOE6/ni+M9uTczhyxkXFGqC4AJyr29KO9qIzrfJd8sHjlCx5Fory0Xe4XrP9+G5KPnySks9ewue2yS5Ey7Dn55Xfp/bKse7buBnFB7TjCJuV4oN7sZtykSXFFO37C5/adT1uQ6FQKK4pOnF1/66lqdd0a/+bDBVCzAdeBgLQxmG3A34GkFKmApcu+zkhpbRKKeOA+4AXhRBtgVTAVdZYQ0p5oeJCKWW8lLKTlLLTmDFlL1fq2LQaqxPOAJCcZqJGuH9pW55ZS651OkGNcH/MRVbaNAxn477zWKx2CoutHE0z0bBmhVveDkoO7sa/e38ADDENsGeWfe2SI/vw7dgDAN9WHbCkaFXK4oSNZL04FtOn72hDNrIqfRUAinbvJKi/lmQYGzTCmn6+XHtAt14UJmwr/VsfFo602ZDFxWCzYc8zYajuusJYtHcXgX0HAeBTryG2Ctr+XXpSmLit/EqOirzdnK8Nj/FAp/ohrNmfCUDyeTPRodqdg8z8Eg6k5fNVwnkmfX6EY+lmnlt5lHqRfiSdLaCg2IbNLtmSnEOH+q6rrsX7/yKg1wAADHUbYMuoYPt1PSjevb30b2H0JWzMZLIXvIzlxFGPdhfv20VAbye/VKhe+3fuQdGuMu3A/kMQQkfki7MJe2AM/t374N+jn1t9y+E9+HbV2vW165fb95akffh20J41MLZsj/VUWVXbt1Nviv/a6tn2g3/hdzEW6zTAllHedr+O3Snes8Npewfw69AN9HqE0RdDvUZYT590qd2pYQhr9mUAkHy+gOjQsovQPMfFkk4nqB5ixFxiI7vAgkEn8PPRY9ALQvwNnMstdqltP3UAfXPtOBGRdZCmzLJGpxta8uIwE6EDg2P7ZlO5Pq4o2ruLwH6OfVq/IdYLFY6jruVj3XLqJD4NGiP8/UGnw7dpCyyprv2iUCgUCs+oBymvnglSyk5CiCDgQceyVKAX8L0QohngfuoJFwgh6jmGouQJIXagJdtLgW+FEJsdiTxCiMnAb1ei3bdtNBv2nGf4yxsI9DMwY1Q74r7Yz8TbW/Dz9tOs2nQKH4OOmMgApo9sh9FHz7CedRn+8gZ8jXomDGuOQe/6h71452Z8O3an2isfYC80k/v+awQ/8Bh5n3+A+devCX18Kn7d+yPNBeS8oz3kF/bUTPRR0dgLCzDFz3Nrd8Hm9QR070XMB59iNxeQ/toMqj02icwP3garBf+O11Gwfl1p/5ITxyg+dICYD5eBhOKjhzFv3eRS27x1AwFde1Hz7SXIwgIuxM0kYuyTZH30Dlit+Le/joJN68qtE/3aWwhfP9DpyYr3PENHn6bhrD+Szf0f7CPAqGfGsEbE/ZLCxEF1WTmhbWm/EfH7ee2OWHz0OsYPqMOojw7g66Pjns41CPV3fagW7diI/3U9qB63CLu5gOy3XiH0oYnkfvoeWK34tulI4db1pf196jfG2LgZkbPKbM6cOQV7vqmSduG2jfh37kmNNz9Gms1kvjGLsNFPkLP4XbBa8Wt3HYWby/yS++nC0s++bTvhf133cu0VKdm1GWP7boTNeB9ZaCbvwzkEDh9PwYp4Cld/Q/D4F/Ht2h9pzsf0vvbwowgMQVotLh9wdKY4cTN+HXtQ7dV4ZGEBOe+/RvCICeQtXwhWK8ZWHbQHJR3Y83Ix//EjkbM/RBYXk/d5vDY8ygV9mkWw/lAW97+3hwBfPTNujyXupxNMvKEev+y5wKrEdHwMgpgIP6bd1hijQUfLmGDufWc3AkGzWoH0ahruUtuelIiucSeMI2cjiwux/PQuhgEPYl33GbomnTF0vQWkHZlzHsuP74DBB597piKEDonEuvZTj34xb9Fivda7S7CbzVyYN4OIcU+R9eHb2j5tfx3mjWX7TJYUk/1JPLUWfIS02jB9/xW27EwPW1AoFAqFO4R0vuWquGwuzl4CZAJdgJ1AW6AvEAVcHOi6HegppezmtO50YJuH2UtWAnXQHrhMAcZJKUuEEB2BVwA/R9e1wKuOMd+ekHL7s1f2BS8T0WU2Z4d18Yo2QM1vt3O0S0uvaMduP8Dx3m28ot1ww17s34zyirbutsWkDu7gFW2AOr/u4uSAdl7RrvfHbtLv6nbpjn+D6l9u5cwtnb2iDVDrux3Yv3/EK9q6mz+iaOZNXtH2e+kHjvVs7RXtRpv2eUVXoVBUGa7t+AwX2Nc8dlWJrO76d6/Zd1CV7r+JlDIFcDldoBDinJSyt+NzR6BxhXWnX0L7DjfLdwKD/4a5CoVCoVAoFIr/Iirp9g79hBDPoz0BVQyMd9dRCPEm2hjwiyyVUi7yqnUKhUKhUCgUimuKSrq9gJRyDbDmMvs+6V1rFAqFQqFQKP5HUS/HUSgUCoVCoVAoFBdRlW6FQqFQKBQKRdXkGs+1fTWopFuhUCgUCoVCUTVRw0sUCoVCoVAoFArFRdQ83f8O1E5WKBQKhULxT/NfH9th//PJq5unu++bap5uxT+LTHjeK7riulexfOByuvJ/BJ9HV3j1pSHFr93qFW3f51Zh++LBS3f8G+jv/sRrdoNme8kbt3tF2/jU117Vtrx/t1e0AXzGfYF923+8oq3rOserL1Pyps+9HYsKhULhETW8RKFQKBQKhUKhUFxEVboVCoVCoVAoFFWTKjR7iap0KxQKhUKhUCgUXkYl3QqFQqFQKBQKhZdRw0sUCoVCoVAoFFUT9SClQqFQKBQKhUKhuIiqdP8LWfDVARKOZGCzSWY+3IHYmBAAjpzKZc7yvRSX2IgK82Pu+M4YDTq2HUwn7vP96HQwfFAjbulZz63225vPsPN0AVYpmT6wDo0j/cu1ZxRYGLzoAJvHt8HXoKPQYmfm76c4lVOCj06w5O5Yt9qGvsPR1WsFOh2WH99FXjgFgKjRAON905GZaQBYfn4fmZGKYeBIRM3GCGMA1j+WYE/Z61Zb3/s+dHVagE6P9Zf3kBmpmnb1BvjcPRWZeQYA6+qFyMzT6PuOQFerCRj9sG74DHn8L48+f+uPVBJTTNjskum3NCS2ekB5v+SXcP0bu9n6bCd8fXR8uuUsaw9nk19sY3jXGgxrX/2/Yru+2z2IGE3b9vtCZKZDO6o+hmEvIrM0n1vXfghZpxGNOqPveBPoDNh3/YA9aYtHv3hT/+0tZ9mZlo/VDtMHxtC4motYXHyQzWNbcz7fwku/nSptO5lTzEv969CvUahL7QVfHyTxSCY2m2TGqHalx1BSai6zP99PUbGNmKgAXh3dAYNex+87z7Dk12NYrHYeHNyIIV1i3Nq9YM2p0liZMawRsTUqxEpeCYPm7WLb1M74+uj466SJ+b+ewmKzM6RNJA/2rOXB4971ubePI4VCoajKqKT7Eggh6gOzpZRXNBm1EKI5MAv4SEr5q5s+04Ftzu1CiG1Syq6O7e4ADgGBwMtSylVCiL7Ap8AJwAg8L6Vcd7l2JR7OIMNUxLIX+5CUmsu8z/cS/3RPx8Zh4eTuGH30zF2+l7U7zzC4SwzzV+xn8XO98DPqueOltdzcoy5CVH5aeOfpfDLNVpbcHcvRjELmbzjD+7c1KtdnUcJ5wvzLwm7htnPc3CKCbvVCPNot6raAwDBKPnkOEVUXw8BRWD6fUdpuO7QZ66/x5daxbvgCSgohuBo+Nz/hNukWMS0QAWFYPnsREVkXff+RWL+cVdpuP7wV628fllvHfngztj8/Bf8QfO5+CYuHZCExxURmvoVPH27J0fNm4laf4oMHmpXr89HGM4QFlPmlQ71gRnSvSbHFzu3v7+XWdlEufe5N20Xt5hAYhvWrlxDV6qDvNQLrqlfKdJK2YvtzUdkKBl/0HW/G+vV0EHoMd7+M/VgC2CzXXH9nmiMW73TE4sYzvH9rhVhMTC+Nxbphviy5U7vgM5fYePLHFPo0dB2TiUcyyMwtZunzvUg6bWLeFweIn9wNgJjqgSx6ujtCCF5c9Bf7jmfTtG4oi39JZvF/emC1S+5/eSMD2tfE16ivrH1Ci5WlY1qRdK6AeT+nED+qRbk+H65PI9wRK1JK4n45yXsPNifIV8+I+P3c2CaS6iHGa+5zbx9HCoVC4RI1vOTfjRCiHvAskH+VUmullH2AvsBzTsuXO5YPBeKuRHDzvvMM7VYHgCZ1QsnNL/vxbFonFKOPlgiEBBrx99U+hwYayTNbMBdbCfA1uEz+ALacNDGkaTgAsZH+5BZZy7UfPG9GADGhvqXLDqeb+fVIDiO+SGJx4nm3dusbtsd+YAMA8sIphH9Q+Q5FBZVXKikEQFetNjI9xa22rmE7bAcd2hmnEH7ltWVR5d0ozx1zbMPsettObDmWy5DW1QCIrRFAbmEFv5wpQAB1wsv80qq2ZoOvj46wAB+3Pvem7bq6bbEf3qStk5kKFbQpLr+uqNkEmboPbFawFiPPHUVE1P6v6G85mceQpmHAxVi0lWs/mO6IRRfJ6bLdGdzbNhKdG59v3p/O0G5apbpJTAi5BSWlbRePj+ISG7kFJcREBbInOZuuLaIw+ugJ8DXQplE4x8/mudY+msPQtpGadnRgpVg5kJav2R3hB0BqVjF1IvwI9Teg1wn6Ngtnb6prbfCuz719HCkUCoUrhBBX9e9aopLuy0QIMUQI8YcQYrsQYqZjWZgQ4lshxDohxPtCiEQAKeVJKeWDQMo/tPmGwNGKC6WUWUChuIKoyTQVExFcltzp9QK7vfwbVHclZZCcZqJnm2gARg6J5Y6X1nLTs79xex/3Q0uyzNbSChyAXiewS03bbLHxxqYzjO9Ws7Q9p9DKofRCRnepweI7Y9mVVsCB82bX4oFhyILcsr/tdkrfPmu3oWvaFePI2RhuGA06zQZdw3YYR7+JYcg4bIm/uLVbBISC2eSkbSuv3aQrPve/in7gw6Xa2hc0YBg0GuvWlW61ATILLEQE+pT+bdCV+dxcYuP1307xWL/Kww3sdsmC31O56zr3Q0u8antAKBQ6+7y8tmjcGcNds9D3fQh0BkRAKNLZlsJ88K2Q1F0j/SyzlXB/T7F4lvFdoyutZ7HZ2XzSRF83VW6ALFMJ4U7HkPP+BJjyfiIDp6yhSUwIkaG+ZFU45sKCjJjMrqv/WQUWwgPL7K4UK7+eZMLAOqXtmfkWIoLKYis0wAdThUS9HF70ubePI4VCoajqqOEll0+ClHKAEEIP7HUMDXkaWCml/EwIUQfY+Dd05wohnnX6O8Lpc38hxCagEfBoxRWFEB2BC1JK6aJtDDAG4IMPPmB0e215cIAPpoKyH3ydEOgcE8tLKfnwhySsNjtzxl6HXifIzC1i6a/JrH3zRgx6wbMfJNK6YQRN61Ye6xrkq8fkVFHUCUqrhfP+TOPh62oQ5Ft2S12vEzSM8CutfPeoH8yxzCJaVhjDCmgVOOfqtrQD2teWF05R8sHjABj63Iu+w/XYEn/Gfnw3JcefhNAojHf8h5JFUyrrArLYXL7iJ2WZdsYpLIue0OzteQ+6doOw7/oFEVELfY+7sG37FnnhpEvdiwT76stVLIWg1Odzfj3Jwz1rEeRX/lC8kFfC67+dYlj7KDo3cD2u2Ou2l3jQzkzFunSSpt31LnStByJz0xFhTomsX2D5BO8a6gf56jEVu4nF9Wd4uFP1crF4kd+Tc+nfKNRj9SMowIDJqbotnI4hgLhxnbQLpq8PsWrTKSJCfDmZXlblzS2wlEvay2n76TEVltntrD3npxQe6VO7XKwE+5WPLVOhlUbVy49dL4cXfe7t40ihUChcooaX/E8yVAgxH3gZCEAbT90O+BlASpkKpP8N3WeklH0v/gOynNrWSil7Ag2AxxzDVgDuE0KsAx7HRTLusCdeStlJStlpzJgxpcs7Nq3G6h2nAUhOM1EjouwHesUfx4kK82P8sOboHT/02fkl6PUCP6Meg15HSKAP57JcV6M71g5izdEcAI5lFlIjSLt1n2m2cCDdzMp9GUz56QTHM4t4YfVJgn31lNjsXHAMcdl5Op8mkX4ute2nDqBv3gMAEVkHacosaxRlYSwv3qIWOjA4EhuzqVyfSr5KPYiumTYmV1SLQea51i699W4woh8wSntQ7DIShY71QlhzUNutyelmoh1DGjLzLRw8U8DKnelM/vIoxy4U8vy32u326d+fYMr19Twm3N623Z52CF2spk1EDDLfjc+LC0BK5Lmj6Oq3B50eDEZEtbqlD+Vda/2OtQOdYrGIGo5qcGks7s9kys8pHM8q5oU1ZQ9Q/nIkm+sbh3n0S6cm1ViToD0QmJxmItrpGMpzVLB1OkH1cD/MRTbaNAxn0950LFY7hcVWjp420bCm62pxp/ohrNmv+SH5vJno0IuxUsKBtHy+SjjPpM+PcCzdzHMrj1Iv0o+kswUUFNuw2SVbknPoUN99ld6bPvf2caRQKBRVHVXpvnwmSCk7CSGCgAcdy1KBXsD3QohmgOdpA/4mUsoiIUQRcLE8tlxK+aynddzRt11NNuw5x/CZfxLob2DGQx2IW7GPiXe0ZN1fZzGZLXyzIQWA/h1qMmpIE1o1COeeGesQCJrXC6VXm8q35QF6NwxhwwkTI75IItBHz0uD6vD6hjQe71GTL4eXPTg48sujvHKDdv3wdN/aPPnDCfQ66N0ghGbVXVS5AXtSIrrGnTCOnI0sLsTy07sYBjyIdd1n6Jp0xtD1FpB2ZM55LD++AwYffO6ZihA6JBLr2k/d+sSenIihUQd87n8VWVKI9Zf30fcdgW3DcnSx16G/7iZNOzcd2y/vIao3QFejET53vVSqYflmNrgYswrQp0kYG45mc/9HBwj01TP95gbMX3OSx/vX4auxrUv7PfjxAV4d1ojMfAs7T5mY9GVSadvU/9eAxi58403b5fGdUL8DhrtmQUkR1t8Xou95P7YtKxANO6Hv8P80bVM6tt8Xgs2K/cA6DHe9DNYSbFu/cNyRcI039Xs3cMTil0cJNOp4aUAdXt94hse7R/PlfU1L+4386iivXF9X86WUpJlKqOnmIcSL9Gkbzfo957n/lY0E+BmYMbItcV8cYOLtzfllexqrNp3Cx6AjJiqAaQ+2xeij59Zedbn/lY34GnU8flszDHrXF4F9moaz/kg293+wjwCjnhnDGhH3SwoTB9Vl5YS2pf1GxO/ntTti8dHrGD+gDqM+OoCvj457Otcg1N/9ad2bPvf2caRQKBRVHeFiZILCiYuzlwCZQBdgJ9AW7eHGKOAzR9ftQE8pZTendadTYXaSCtqV2l3MXnIQrar+tZRyvmP2ksFXmHRLmfD8FXS/fMR1r2L54IomdrkifB5dQdHMm7yi7ffSDxS/dqtXtH2fW4Xtiwcv3fFvoL/7E6/ZDZrtJW/c7hVt41Nfe1Xb8v7dXtEG8Bn3BfZt//GKtq7rHOzfjPKO9m2Lvepzb8eiQqH4P821fRLRBXLni1eVyIqOL1+z76Aq3ZdASpkCuMwqhRDnpJS9HZ87Ao0rrDv9EtqV2qWUXZ22W+kJOinln8Cfl7ZcoVAoFAqFQvF/BZV0Xx39hBDPoz0tVAyMd9dRCPEm2hjwiyyVUi5y3VuhUCgUCoVCcUl0//Vi+2Wjku6rQEq5BlhzmX2f9K41CoVCoVAoFIr/q6jZSxQKhUKhUCgUCi+jKt0KhUKhUCgUiqpJFZqnWyXdCoVCoVAoFIqqSRUa0111Lg8UCoVCoVAoFIoqipqn+9+B2skKhUKhUCj+af7rZWa5b/rVzdPderqap1vxzyJT3/SKrqjzJPZVD3tFG0B36yJsX430irb+ziXIfdO9oi1aT/eqduHUoV7RBvCf9ZNXX6ZC7ude0Sb0XuzfP+IdbUB380fI7X/rRbCXRHSZjUyP94529TFYPrrXK9o+j3yOfe1Er2gD6Pq/5dVzl0Kh+B+gCo3prjqWKhQKhUKhUCgUVRRV6VYoFAqFQqFQVE1UpVuhUCgUCoVCoVBcRCXdCoVCoVAoFAqFl1HDSxQKhUKhUCgUVRM1T7dCoVAoFAqFQqG4iKp0/wtZsHgHCfvOYLNJZj7Vh9j6EaVtx05ms2DJDu68sTm9OtcF4Od1yXz23T6KSmyMGNaaWwY1da+9+iSJJ3Kx2SUzbmtMbHRgufaMvBIGzUlk27Su+Pro+CvFxPxfU7BYJUPaRvJgr9putd/6/RSJKSZsdph+S0NiawSU184v4fr5f7H1+evw9dHx6ZazrD2URX6xjeFdoxnWobp7uz/fS8KhdM0nYzsTWycUgCMp2cz5dDfFJTaiwv2YO7EbRh89j83ZQEZuEUaDnjaxETz9QHv3Dv8b+pm5RUz7IIGMnCJqRQbw+qQebrUNA+5HV68V6PRYvn8bmX4KABHdEN8RM7BnnAbA8sN7yAupGO97EREYhrRZsJ9OwrpmsVttfbd7EDEtQKfH9vtCZGaqph1VH8OwF5FZaQBY134IWacRjTqj73gT6AzYd/2APWmLR7+8uXAtiX+dxGqzM+u5m4htpO2jAnMxU1/9gfPpJkJD/Jk7fRhBQX78/Nt+ln25g6JiCyPu6cqtQ9q69/mvKVos2mDGHWWxmHS2gNk/HKeoxE5MhC+v3t0Ug17w8+4LLN9yhiKLnQd61uKWjjXca688SMKRDGx2ycxR7YmNCQHgyKlc5qzYr+3PMD/mju2E0aDj522n+ez349oxdEMjbulR1732R5tJ2H0am83OzGcGEdsgsrTtWEomCz7azJ03taZXlwYAPPbcKjKyzRh99LRpHs3T4/t49Pnbm86wMzUfq10y/Ya6NI70L9eeUWBhcPx+Nj/eFl+DjkKLnZlrTnEqpxgfnWDJvU3c2/79URKTs7HZJDOGtyS2VpDm87Q8Zq88QlGJjZhIf14d0QqDvqzmM3vlYXz0OiYP86B9heetbbvTiIvfik4nGH5LK4/nLYVCUYWpQg9SqqT7KhFC1AdmSynvucL1mgOzgI+klL966Hc3MBHtBTcG4AlgH/AOUA8IBhZJKT+4nO0m7jtDRraZZa/fStKJTObFbyX+VW3O57TzecSv2EWAv09p/9y8YpZ/v5/F827GZrMz/MlVDOjegKBAY2XtE7lk5pewdGwbks4VMO/nFOIfalmuz4d/niY8QNOXUhL3SwrvPdiCID89Iz7Yx41tI6ke4ltZO8VEZr6FTx9pxdHzZuJWn+SDEc3L9flowxnCAspCukO9YEZ0r0mxxc7t7+3l1vZRCFH5NlTiwXQycotYNnMgSadymPfpX8S/0FdrFIKFz/XG6KNn7qd/sTYhjcHdtR/1hc/1ITy4sq3/hH7cst1MvKc1TeqGedTW1WuJCAyn5ONnEdXr4XPDQ5QsnV7abjuwGctPCyutV7xsBhTmedQWtZtDYBjWr15CVKuDvtcIrKteKW23J23F9ueishUMvug73oz16+kg9Bjufhn7sQSwWVz75a+TZGbls+yDUSQdO8/ct9fw4Zv3A7Dk823069mEmwa34bOvdrD860TuHtaRz77awZL3RmCz2blv9McM7N2UoCC/ytrHc8nMt7B0XFstFn86QfzDrQCIqebHotGtEELw4ldJ7EvNo2F1f5ZvOcPHY1pjs0uGv7eHAS2rEeRX+RSZeCSDDFMxy17oTdJpE/NW7Cd+SneH02DhU121/fn5PtbuOku3llEs/+M4i5/tqR1DL29gQIeaBDkdZ6Xae06TkVXAsnfuJul4BvPe20D8vNsASDtnIv6zHQT4Vz72Fs4ZRniof6XlFdl5Op/MAgtL7m3C0QuFzP8zjffvaFyuz6Lt5wnzL/veC7ee5eaWEXSrH+JRO/FoNpl5JSyd1JmktDzmfXOE+AkdAYiJ9GfRxI6az5fuZ19KLu0bhQNwJquQLYcy6dMqyr32FZ63AOZ/uI3Fc2/Cz8/AHeO/5uaBTVwe/wqFQnGtqDqXB/9DCCHqAc8C+ZfodzcwDLheStlTStkV+AsYBSRIKQdIKTsDSy5325sTTzO0fywATRpUI9dUVNpWu0Ywc/4zgNo1gkuXnUrLpXnjSIw+evz9fGjbvAbHTmW71k7KYWg77YezSXQguWZrufYDafkIIKaalqimZhVRJ8KP0AADep2gb7Nw9qa6dsmW5ByGtNEqfrE1AippHzyjadcJL0vAWtXWqmy+PjrCAgxuf3A37znH0J71NLvrhpGbX1La1rReGEYfPQAhgUb8HUmYTghCAionTf+Efm5+CTl5JSxceYDhL/7Od+tPuNXWNW6Pbd96AGT6SYR/cLl2WejCn1JCUcEl7dbVbYv98CZtlcxU8Asq36G4vIao2QSZug9sVrAWI88dRUS4v3Oxafsxhl7fGoAmjWqQayosbduWeILBA7ULtuv7NWf3vlROns6iedOaGH0M+PsZadsqhmMpGS61Nydlu43FAKMeIQTFFju5ZisxEX6cyiyiRe0gjAYd/kY9beuGcCzd7Fp7XzpDu8Zo2jEh5BY47c86oeX3p6+eU+cLaF4vTNP2NdC2UQTHzri+4NmccJKhA5tp2g0jyx+f0SHMeeFGatcsn/zqdIKQoEtf/AFsSTExpLlWIY6N8ie3qMJxdN6sHaNhZXqHzxfy65FsRiw/wuId591qbz6UwdBO0ZrttYPJLSi72ArwNTh8biPXbCEmsuwu1ZvfHeWR6xt4tPtKz1sAocG+5BWUYC60EuDvoxJuhULxX0cl3f8QQoghQog/hBDbhRAzHcvChBDfCiHWCSHeF0IkAkgpT0opHwRSLiE7CRgtpSzNbqSUJcARoJcQIsixrPhy7czMKSQitCwx1et12O3u36Bap1YIuw+eJ7+ghIJCC3sOn8dms7vsm5VvITywLBE16EWptrnExuu/pDBhUNlt9cx8CxFO/UMDfDBVSKbd9TXoKmivPsVj/WMqrWe3Sxb8doq7rnM/VCDTVESEU3Vd72T3RXYdvkByai4922pJRWCADyNnrOOhmWvZcSDdrfbf0U89n0/KGRNTR3di0dS+rFiTTHp2YUVZAG2YSEFu6d/SboOLyYXdhr5FN4wPz8FnyBjQaxcMssiMcdQrGB98GV39Vu4NDwiFwjJt7DZK3/hrtyEad8Zw1yz0fR8CnQEREIo0m8r6F+aDb4VE3Yms7AIiwsuSLy0WtdiylFjxMWjJa1hYAKa8IurWDmf3vlTy84soMBez90AaVk+xGOQ6XgCmfHaYga/uoEl0IJHBPtSp5sfukybyi6wUFNvYeyoPm831cZGZV1x+f+pc7M+kTJLTTPRsXYM61QPZnZxFfqGFgiIre45nu9fONhMR5uyTytoVCQzwZeSTX/HQU1+x469Uj32zCqyEO1Wx9TqBXZYdR2+sT2N8j5ql7TmFVg6lmxndJZrF9zRhV1o+B865vhjJyishPKisCm+oYPuURXsY+OIGmtQKJjJE67dy82la1A0hOrzy3QpnrvS8BTDyjrbc8dhKbnrkC24f3MxjX4VCUYXR6a7u3zVEDS/550iQUg4QQuiBvUKI6cDTwEop5WdCiDrAxivU1EkpK5XEpJS/CyGKgRVCiN+Bt6SU5bIPIcQYYAzABx98wOgbteXBgUZM+WU5uk4n0Hl48jcsxI9xwzsw9sWfqR4ZSEx0CLWjg132DfLXYyosS5qFoFR7zg8neKRvTLnb9cF+BnKd+psKrTSqME7bXd9y2j+n8HDv2pWGAlzIK+H11acY1iGKzg1D3X7H4AAfTE7VZ50o84mUkg9XHcJqtTPn8a7oHeNQZ0/oCsD5LDOjX/6T718f8o/pG/SCNrHVSoeudGwWxamzeVQPrzx8QBYVIPyDKE0/pNT+oVW+i995DABDv/vQd7wB246fsHz7hsOwCHxHzKT43QmuDS8xl69uSwmOLcnMVKxLJwGg73oXutYDkbnpiLDosv5+geWT9goEBfpicqpYan7R/Ct0Arvdjk6nw2QqJCI8gLDQAMY91JtHJy2nRvUQYmqFEVMzzLW2n6HcBZxzvADEDW+mXZCtPsmqxHSGXVeDsQPqMvbjA9QI9SUmwpfaEa4TwWB/H0xO1W3nY0hKyYc/JmG1SeY82gm9ThAWZGTczU0Z+/pWqof7ExMVQO1IN3EeaMSUV+RS2x2zXxgMwPmMfEZP/prvP3nQbd8gXx2mYluZvhDoHBdp89al8XCXGgT56kvb9TpBwwi/0sp3j/ohHMsspGV0ZfuD/Cv6vLztcQ+31Xz+/VFWbTtDu4Zh/L47nffHtyfhqOu7Zxe50vNWZraZpd/sZe1nD2Aw6Hh2zlpaN61O04bVPG5HoVBUQdTsJf9Khgoh5gMvAwGAEWgH/AwgpUwFPJdEKyOFEJUHcGp6G6WU/w8wA6+5aI+XUnaSUnYaM2ZM6fKOrWuyesNxAJJPZlEjMrDiqpXo370By964lSmPdEUnBDUiXVcvO9UPYc0+7XZ/8nkz0aHaD3VmfgkH0vL5avs5Jn12mGPnC3nuyyTqRfqRdK6AgmIrNrtky9EcOtRzPW60Y/1g1hzI1LTTzUSHGh3aFg6eKWBl4nkmf5HEsQtmnv8mGYDp3x1nyuB6HhNugI7Nq7N6m1YhTE7NpUa1soRixZpkosL9GH9nq9KEGyitsAb5+2AweD6MrlS/fs1gklNNFBRasNns7D+WRf1ari907CcPoG+pPWQpouogTU7DLZyu4KXzcJKLy4vNYCtLwCpppx1CF9tN+yMiBpmfWdYonLSLC0BK5Lmj6Oq3B50eDEZEtbqlD1q6olP7evy69qDml+PpRFcv2/dtW8bwx/ojAKxee4hu1zUEYEDvZnwW/xBTJgxECEGN6q7jpVND51gsKI1FgDzHxZtOJ6geYsRcovmgf8tqLBvflslD6mtxHup6yEbHptVYnXBG004zUcPpYmjF2hNEhfkx/tZm6J1+CPp3qMmyF3oz5a6WmnaE6/HXHdvGsPrPJE37RCY1olzvd2esVkcsBhgvHYsxQaw5oiW4xzIKqRGs3Q3ILLBw4LyZlXszmfLDCY5nFvHCLycJ9tVTYrNzIV8bKrLzdD5NIl3b3qlxOGv+OqfZfjaf6DBnn2vr63SC6mF+mIut/JRwFruUTF60l/d+Osa6ven8ttv18JUrPW9lm4rQ63X4+Row6HWEBPty7oLH0XwKhULhdVSl+59jgpSyk2PIx8VSUyrQC/heCNEMqHWFml8A84UQT0kprUIblOgHVAPOOKrbvwLvX65g3y712LD9JMOf/JbAACMznuxD3IdbmTiyc+lY1IpMfuU3zqbnExjgw0uP93ar3adZBOuPZHP/+3sJ8NUz47bGxP18gonX12PlxHal/UZ8sJfX7mqCj17H+IF1GRW/H18fHfd0rUlogOuQ7NMknA1JOdz/4X4CffVMv7kh81ef5PEBdfhqfJvSfg9+dIBXb2tMZr6FnSdNTFqRVNo29eYGNK5euULXt0MtNuw6w/AXfyfQ38CMR68jbqn2IOO6xDRMBRa+WauNq+5/XW1G3dSM8bM3UFhsw26XPHWf+xk0/q7+uDtaMmrGOvR6wd2DGhMZ5jrRsScloG/SCePDc6CkEMt372C4fhTWP5aia9oZQ/dbwW5H5pzH8t3bABiHvwQ+viB0WH7/xK3d8vhOqN8Bw12zoKQI6+8L0fe8H9uWFYiGndB3+H8g7UhTOrbfF4LNiv3AOgx3vQzWEmxbvwDpevgHQN8esazffJT7Rn9MYKCRmc/dxLy3f+OJsf0YM7Inz0z7lk+/2EbdmAimPaM9NDf5xZWcOZ9LYIAv055xf3ehT7MI1h/K4v739mixeHsscT+dYOIN9fhlzwVWJabjYxDERPgx7TbtQcIpnx3mbE4xgb56pg5r5N7uttFs2HOe4S9vINDPwIxR7Yj7Yj8Tb2/Bur/OYTJb+GajNoNM//bRjLoxlsnvJXA200ygvw8vjXAfL327NWTD1hMMf2yFdnxOGUjc+xuY+EgPt8fn+OdWUVhk0WJxTC+32gC9G4Wy4biJEcuPEGjU89L1dXl9fRqP96zJlyPKhmCMXJHEKzdqzyE83S+GJ787jl5o6zdzczeqT6so1u/P4P647QT4GZhxXwvivj3CxJti+SXxHKu2ndF8Xi2Aafe2wOhTdoGwIymLjQcyGNTO9TCwKz1vNa4XQaumUdwz8RuEEDRvVI1e17mfMUahUCg8IYSYBfRGy5vHSCkPOJa3AeIAf+AscL9jGLBrHSk9j4tTeObi7CVAJtAF2Am0BfoCUcBnjq7bgZ5Sym5O604HtrmbvUQIoQOeAm4DLIAVbZx3G2AykONY9oyU8i8PZkqZ+ubf+HaXRtR5Evuqh72iDaC7dRG2r0Z6RVt/5xLkvule0Ratp3tVu3DqUK9oA/jP+omSN273irbxqa8h93OvaBN6L/bvH/GONqC7+SPk9me9oi26zEamx3tHu/oYLB/d6xVtn0c+x752ole0AXT938Kb5y6FQnHV/NfHdsiTcVeVyIp6Uzx+ByFEL+ABKeUYIUQrYK6UcoijrTWQJKUsFkLMA3ZIKb9yp6Uq3VeJlDIFcDldoBDinJSyt+NzR6Dc3FxSyumX0LYD8x3/nNkLLPt7FisUCoVCoVAooPwzcA7ipZTOVZDrgc8BpJT7hRClLwmQUu5z6pcNeJwaTCXd3qWfEOJ5tKfPioHx7joKId5EGwN+kaVSykWueysUCoVCoVAonJ8x+js4EmxPtxqrAxec/rYKIXTOE1gIIXoALYE5nralkm4vIqVcA6y5zL5PetcahUKhUCgUCsUVkguEO/1tv5hwO561+w/gA4yQUrqfnQA1e4lCoVAoFAqFQuGOjcAdAEKIFsBpp7axwFkp5axLJdygKt0KhUKhUCgUiqrKVQ4vuQx+AoYIITYCecCjQog5wFTgJiBMCDHK0fd7KeXr7oRU0q1QKBQKhUKhULjAMZRkXIXF/3H8737uWheopFuhUCgUCoVCUTW5xq9yvxqqjqUKhUKhUCgUCkUVRb0c59+B2skKhUKhUCj+af77L8c5887VvRyn1oRr9h3U8JJ/CfLse17RFTXHY//9ca9oA+gGvo3957He0R6yEHlirle0RYNnkEde8Y520xcofOGKhpFdEf6v/OzVNxhS+J1XtPG/xftvR/xrqle0RftZYP7WK9oEDPPaW2N1ty7y2ls6wfGmzrS3vKNdeyLJ3Vp5Rbvx1v1e0VUoFFUblXQrFAqFQqFQKKom3p+95B+j6liqUCgUCoVCoVBUUVTSrVAoFAqFQqFQeBk1vEShUCgUCoVCUTVRw0sUCoVCoVAoFArFRVSlW6FQKBQKhUJRNalCL8dRSfe/kAWLtpKwNw2bzc7MyQOIbVCttO3YySwWLNrKnUNb0qtLfQAys81Mm7+WjGwztaoH8/q0G91r/5BMYnI2Nrtkxr0tiK0VBEBSWh6zvzlCUYmdmGr+vPpASwx6HRM++IuMvBKMBh2t64Xy9LAm7rV/Pk7i8RxsNsmMu5oRWzNQ0z6Tz+zvkikqsWna9zZjz0kTC34+Ubpu0tl8PnmsPU0d9lTS/mQnCfvPaT6Z2JPY+uEAHDmexZyPtlNcbCMqIoC5z/TB6KOnuMTKD2uP8fvWkyyccf2lfb7sLxIOpGv6E7oRWzdM0z+RzZzFiRSX2IgK92fupJ4YffTMW7yT/cmZFBRamPJgB7q2relW2zDwAXT1W4FOj2XVW8j0UwCImg3xfXAm9gunAbB8/y7yQirG4VMRQWFIqwX76SSsqz92q/32pjPsTM3HapdMv6EujSP9y7VnFFgYHL+fzY+3xdego9BiZ+aaU5zKKcZHJ1hyr/v9CfDmu6tJ3HUcq9XOrKm3E9s4GoACczFTZ67kfLqJ0JAA5r58N0FBfmRm5fPSrK/JzMynZs0w3pgz3L3Pvz+qxaJNMmN4y/KxuPKIFi+R/rw6ohUGfdlJe/bKw/jodUz2FItf7CPhcIa2P0d3IrZOKABHTuYwZ9kex/70Y+6ELuxLzuLNL8qmkEs6lcunL/Wlab0wNz5ZQ+KuE1htdmZNvY3YRjWcfPIN59NzCQ0NYO6suzh89BwL3l1duu6Ro+f49MMxNGviPl4WrD5J4olc7Ri9rTGx0Y7j6GwBs388QZHFRkyEH6/e2QSDXvDzngss33KWIoudB3rW4pYO1d1rrzxIwpEMbHbJzFHtiY0J0ew6lcucFfs1v4T5MXdsJ4wGHT9vO81nvx+nqMTGiBsacUuPuu61P95Owt4zms8n9a183lq8gzuHNKdX53oAbPvrNHHxW9EJGH5rG265vqlbbYCIMRPwb9cR9AYuzJ5OyYljAEQ9NwNjjGaXCAzEevYMOZ9/QrVHy6anNDZuQtr4UZQcS/K4DYVC8e9GJd1XiRCiPjBbSnnPFa7XHJgFfCSl/NVNny7ATMAIhAE3An7ADuAQEAi8LKVcdbnbTdybRka2mWUL7iDpeAbzFm4kfs6tAKSdMxG/PJEAf59y68R9sImJD3WlScNIz9rJ2WTmFbP0qetIOpPHvG+TiH+sAwAxkf4smtARIQQvfnaAfSdNtG8YBsD7Y9sTHmT0rH0sh8y8EpZO6EDS2Xzm/ZBM/Ji2mnY1fxaNbatprzjMvlN5dGwYxqcT2gNwLqeIOauS3SbcifvPkZFTyLJ5Q0lKyWLeoh3Ez7pBaxSwcPr1GI165n64g7VbTzG4dwM+XrmPyPAAsnOLPNoNkHjgPBk5RSx77QaSTmYzb/FO4qcNKNOf2h+jj565ixNZuz2VwT3rM+7uNgQF+HAuo4Dn39riNunW1WuJCAqj5KP/IKrXw2fww5R8Oq203bZ/E5YfF1Zar/jT6VCY59HunafzySywsOTeJhy9UMj8P9N4/47G5fos2n6eMP+y08jCrWe5uWUE3eqHXNovu06QmZnHskXjSEo+x9w3fuLDd7X5pJcs20i/3i24aUh7PluxheVfbWXMqH7EvfkzTzx2A00cyblb7aPZWrxM6kxSWh7zvjlC/ISOgCMWJzpicel+9qXk0r6RdpF1JquQLYcy6dMqyr32oQtk5BazbFo/klJzmffZHuKf7a01Clj4jHbhNHfZHtYmnmFw1zosndYPgHOZZmYv3e024U7cdYLMrHyWLXrU4ZOf+fCdUQ6fbKJfn+bcdGM7PvtiK8u/2saYUX1Z+tGjmvb5XF6b/6PHhDvxRC6Z+SUsHduGpHMFzPs5hfiHWmp+qebHokdaan5ZeZR9qXk0rB7A8q1n+Xh0K2x2yfD39zKgRQRBfpV/OhKPZJBhKmbZC71JOm1i3or9xE/pXuaXp7pqfvl8H2t3naVbyyiW/3Gcxc/2xGazM/zlDQzoUJOgCucfgMS9Z7Tz1pvDSDqRybwPthA/+ybAcd76fFel89b8+K0snnczfn4G7hj7FTcPaoIQrt+B4de2A/rwaqSNH4WxYWOqTZjM2cnjAbjwWtnxFPnUc+T9+gPFh/aT9pi2X/RRNYh84mmVcCsUiktSdWry/0MIIeoBzwL5l+gaB9wrpewHdAIyHMvXSin7AH2B565k25sTTjF0gFbBa9IwklxTcWlb7egQ5jx3PbWjyxKm3LwickxFLFyawPDHv+K7NYfcax/KZGgn7Qe/Sa1gcs2W0rYAXwNCCIotNnILLMRU0yqmQghCAir/yFbSPpLF0A5axa9JzSByzVYnbX2ZttlCTDW/cuu+tzqFRwfVd6+9M42hfRtq2vUjyM0r80nTBhEYjXoAQoKN+DuSjXH3tefOGz1Xzkr1/zrD0N4NNP164eX164dj9HHoB/qW6gc5fJKSZqKpo+ruCl1sB2x71gMg008i/IPLtctCFyEm7VBUcEm7t6SYGNI8AoDYKH9yi6zl2g+eNyOAmDDf0mWHzxfy65FsRiw/wuId5z3qb9qaxNAb2wHQpHE0uabC0rZtO5IZPKgNANcPbM3uPafINZnJzi3g/Q//4L5R77Hqx51utTcfymBoJy0xb1I7mNwCN7FothATGVDa9uZ3R3nk+gYe7d689xxDHRXZJnVCyc0vKW1rWjfMaX/64O9bPjl99+uDjB3WwoNPjjJ0cFsnn5jLfJJwjMEDW2s+GdCK3XtPldeO/4NxD/fzbHtSDkPbaRcUTaIDyx9HxovHkZ1cs5WYan6cyiykRa1AjAYd/kY9besGcyy90LX2vnSGdo3RtGNCyC1w8kudUCe/GPH31XPqfAHN64Vp2r4G2jaK4NgZ1xeCmxNTGdo/VtNuUK3cMVQ7OoQ5zw6kdo3ysR8a4kdeQQnmQgsB/j5uE26AgC7dyf/tZwBKjiejDwmt1McQXQt9RDWKD5V/8U3EQ2PJXvKhW22FQuFlhO7q/l1DVNL9DyGEGCKE+EMIsV0IMdOxLEwI8a0QYp0Q4n0hRCKAlPKklPJBIOUSsseAgY51bFJKa4X2hsBRN/aMEUIkCiES4+PjS5dn5piJCC0bIqDXC+x2929QTT2TS0pqDlOf7MuiuGGs+H4f6ZmuE7asvBLCg8oSaIOuvPaUxXsZOHUjTWoFERmiVbaD/AyMeiuRh95OZMfRLLd2ZOVbPGsvPcDAWdtoUjOIyOCyqnlGXgkXTCU0q+26yg2QmVNIRGhZoq7X6Sr5ZNeB8ySfzKFnx9puddzq5xYREVqWmLry+a6D6SSn5tCzfS1AS9Rve/JHpi/czj2D3Q9zEIGhyILc0r+l3QYXkwubDX2L7hhHz8Vn6KOg1xJAWWzG+NCrGEe9og1LcUNWgZVwpyq2XiewS81uc4mNN9anMb5HWVU1p9DKoXQzo7tEs/ieJuxKy+fAOXMl3VL9rHwiwsv2i16vw263A2ApseHjSNLCQgMw5ZlJPZ1FyskMXnruVj5+fzQrvtpG+gWTa+28knJ3TwwVfD5l0R4GvriBJrWCS2Nx5ebTtKgbQnS4XyU9ZzJNxUSEOO9PF/FyJIPk0yZ6tq1Ruiwjp4gLOYU0c1PlBsjKziciPNCNT6zlfeJ0kZKRmceFDBPNmtbyaHtWvoXwQKfjqKJfPj/CwNkJNIkOIDLIhzrV/Nh9Mo/8IisFxTb2puZhc3O+yMyr4BedizhPyiQ5zUTP1jWoUz2Q3clZ5BdaKCiysue4NhTIpXaOmYgw5/NWZZ9XZOQdbblj3Ffc9NAKbr+xuce++vAIbDnZpX9Lm9Nx5CDsnhHkfrG0wnrVMERGUZJ8xKO+QqHwIlUo6VbDS/45EqSUA4QQemCvEGI68DSwUkr5mRCiDrDxCjUfAZ4UQvwAvCKl3OZY3l8IsQloBDzqakUpZTwQX/qn4zXwwYG+mPLLqkQ6nUCnc18BMuh1tGkRTbgjUe/Yuhan0nKoXi2wUt8gfwMmp8qZEJTTjhvVBrtdsuCHZFZtO8OwbrV5bYSW9KXnFDH63V1890J3l3YE+ek9az/QUtP+5TirEs4xrLOWDH674yzDuri/3a75xIjJqVqp05VpSyn58Mu9WK125kzpjV5/5QdocEAFfSHK63+9H6tVMufJHqX6PdrXokf7WqSl5/PU3A18Gef6te+yyIzwD6I0/ZBS+4dW+S5+W7tFbug/HH2nwdi2/4jl6zcchkXgO3IWxW8/5lI7yFeHqdhW3m5HIjJvXRoPd6lBkK++tF2vEzSM8CutfPeoH8KxzEJaRgfgiqAgv3KJoxaL2vcXOoHdbken02HKKyQiPAiDXkfbVnUJD9Nir2P7BpxKzaR6VOWhLJVjsXycxz3cVouX74+yatsZ2jUM4/fd6bw/vj0JR7Mr6TkTHOBTYX9WiJfvD2vx8lhn9E4P+Hy7/gS39fVcRa/kE+HJJ2XH4Dff7+S2mzt51AYI8tdjKvRwHN3bVPPLmpOs2pnOsE41GDugDmOXHKRGiJGYcD9qh/u6kibY3wdTgfNxVCHOf0zCapPMebQTep0gLMjIuJubMvb1rVQP9ycmKoDaka5jJTjQF5NTdVtXwe6KZGabWfrNXtZ+PgKDQcezs3+nddPqNG3keoicPT8fXbBTHNntpccRgDAa8W3SlIw3Z5e3a+gtmH5c5dYOhUKhcEZVuv85hgoh5gMvAwFo47DbAT8DSClTgfQrEZRSWqWUccB9wItCiLaOprVSyp5AA+Axx3CVy6Jjm1qsXp8MQHJKJjWi3FeAAerXCSf5RCYF5hJsNjv7j5ynfkyYy76dGoex5i9tSEHy2fxyFcO8Qu32vk4nqB7mi9mRzFltWhUv0M+AQe/+R7RTwzDW7LmgaZ8rINppSEOeI4nQ6QTVQ8u0Adbuz6CPY4iEOzq2imb1Ru2hy+ST2dSILEtmVvx0mKiIAMYPb/+3Em6Aji2rs3rLSU3/VA41nBKLFb8kERUewPh72pTqW212Cou17xQe4uu2sghgP7kffaueAIioOkhTRlmjU8Ini/LhYmp+cXmxGWwVb5442R0TxJojWgJ6LKOQGsFahTSzwMKB82ZW7s1kyg8nOJ5ZxAu/nCTYV0+Jzc6FfG1f7zydT5MKD14606lDA379ba/ml2Pnia5edku/bes6/PHnQQBW/76Pbl0aU79eFEePn6PAXKzF4sHT1K/nOonq1DicNX+d07TP5leIF+dY9MNcbOWnhLPYpWTyor2899Mx1u1N57fdrofHdGwWxert2sOpyadzqRHhtD9/O0ZUmD/jb29ZLuEG+CPxDH3aeb4A7NS+Pr/+vq/MJzWcfNLK2Sf76dalbHz92j8P0qfnpYc7daofwpp9WowknzcTHermOAoxYi7RjqP+LaqxbGwbJt9YH50Q1Ah1nXR3bFqN1QlnNO00EzXCy/b9irUniArzY/ytzdA7Jcv9O9Rk2Qu9mXJXS007wnW8dGxdk9UbtAcbk1OyLnneys4tQq8X+PkaMOh1hAT5ce6C+9F8hXt2EtRPeyDap35DrBfK7/uAbr0wJ2yrtF5g7/6Yt27waItCoVBcRFW6/zkmSCk7CSGCgAcdy1KBXsD3QohmgOd7vxUQQtRzDEXJE0LsAJoACRfbpZRFQogiwPWvoAv6dm3Ahm0pDH/8KwIDfJgxeYDjQclupWMunfHzNTDugc6MmvwNer2Ou29qTWRE5So3QJ+WUazfn8H9r+8gwNfAjPtaELcqiYn/rzG/7DzPqu1n8NELYqr5M+0ebVzr+IW7KbLYsNslT90c69buPi2qsf5QJve/tYsAPz0z7mxK3A/HmHhjA375K51VCWfxMeiIifBj2p1a8pFTYMFHr8PXxfcq55POddiQkMrwyT9qPpnYg7hFO5g4oiPrtp/ClF/CN2u0h6T6d63LqNtbX5avS/U7xbAhMY3hz/5KoL8PM8Z3JW7JTiYOb8e6hNOYCkr45g/tQqh/5zrcPTiWcbPWYZcSIWDSA+3datuPJKBvch3G0XOhuBDLd29juGEU1t+XomvWBUP3W0Hakdnnsax6CwDj/dPAxxd0OixrPnGr3btRKBuOmxix/AiBRj0vXV+X19en8XjPmnw5ollpv5ErknjlRu267+l+MTz53XH0Qlu/WQ3XlUuAvr2asX7TYe4b9R6BAb7MnHo78978mSceu54xD/XnmRdX8Olnm6hbtxrTnhuG0Whg/CMDGDkmHr1exz13dCWyWrBL7T6tHLEYt50AP0csfnuEiTfF8kviOVZtO4OPQRBTLYBp97bA6FOWIO9IymLjgQwGtavhUrtv+5ps+Ossw6etJdDfwIxHOhH32R4m3t2KdbvOYCqw8M2f2kVc/061GDW0KTn5xfgYdPgaLxGLvZqxftMR7ntooeaTF4cxb8EvPDF+EGMe6sczL37Bp8s3U7dONaY9dysAOblmfHz0+Ppe+tmIPs0iWH8km/vf30uAr54ZtzUm7ucTTLy+Hr/szWDVzvP46HXERPgybZiW1E/5/Ahnc4oJNOqZemsj97a3jWbDnvMMf3kDgX4GZoxqR9wX+5l4ewvW/XUOk9nCNxu1cej920cz6sZYJr+XwNlMM4H+Prw0oq177a712bD9JMOf+EY7hib1JS5+CxNHdXF53mpcP4JWTatzz4SvEQKaN44sndXEFebNGwjs1pva73+C3VzAhTkzqTb+KTLj3warFf/211GwcW25dXQhIWCxIEtK3KgqFIprQhV6OY6Q0vO4OIVnLs5eAmQCXYCdQFu0hxyjgM8cXbcDPaWU3ZzWnQ5s8zB7yUqgDtoDlynAOLTEfQdwEK2a/rWUcv4lzCwdXvJPI2qOx/77417RBtANfBv7z2O9oz1kIfLEXK9oiwbPII+84h3tpi9Q+ILr4Sb/BP6v/Izlo3u9ou3zyOdQ+J1XtPG/BfvaiZfu9zfR9X8L+ddUr2iL9rPA/K1XtAkYhn3Vw16R1t26CLn9Wa9oA4gus5Fpb3lHu/ZEkru5f6bhami8df+lOykU/xu4v0V9jZCZS64qkRXVRl6z76Aq3VeJlDIFcDldoBDinJSyt+NzR6DcfGtSyumX0L7DxeIUwP1EuQqFQqFQKBT/FqpQpVsl3d6lnxDiebTBtMXAeHcdhRBvoo0Bv8hSKeUir1qnUCgUCoVCobgmqKTbi0gp1wBrLrPvk961RqFQKBQKhULx30Il3QqFQqFQKBSKqomu6gwvqTqWKhQKhUKhUCgUVRRV6VYoFAqFQqFQVEm0dxJWDVSlW6FQKBQKhUKh8DJqnu5/B2onKxQKhUKh+Kf5r8/TTe7nV5fjhN6r5ulW/LN48+U48txCr2gDiOixyJNx3tGuN8W7L8fJ+Ng72pEPec0n4PCLN31+5h3vaNea4LUXqYD2MhWv2u7NeEmP94529THIAzO9og0gWr7ktfOLiB4Ltt+8oo1+EFhXe0cbwHCD97QViqqGmqdboVAoFAqFQqHwMlUo6a46lioUCoVCoVAoFFUUlXQrFAqFQqFQKBReRg0vUSgUCoVCoVBUTdTwEoVCoVAoFAqFQnERVelWKBQKhUKhUFRNqtBr4FXS/S9kwaKtJOxNw2azM3PyAGIbVCttO3YyiwWLtnLn0Jb06lIfgMxsM9PmryUj20yt6sG8Pu1GD9pbSNhzWtOeMpDYBpFl2imZLPh4C3cObV2q/dgL35ORZcZo1NOmWQ2eHtfbvfaSRBL2ncVmk8x8siex9SMAOHI8kznx2ykusRIVEcDc//TD6KPn980pLP56LxaLnZG3t2ZI30butT/ZScL+c5rdE3sSWz/coZ3FnI+2U1xs07Sf6YPRR09xiZUf1h7j960nWTjj+kv7PH5DmV+euYHYhlFOfslgwYcbufOmtvTq2hCAee+uY//hcxSYS5gyvi9dO9b77/jFi9oACz7eRsKeNE1/cr/KsfjxNi0WO9dj574zvLloW2l70vEMPn3jNpo2inQlzYKPt5Ow94zm80l9K2sv3sGdQ5rTq7Pm221/nSYufis6AcNvbcMt1zf979jtxVgBWPDRZhJ2X9QfVPkY/Wgzd97Uml5dGpRb77W3/8Too2PyWA/H6PI9JBxM17THdSG2bhgAR1KymfPJLopLbESF+zP3ie4YfcreIvfa4p0YDTomP9DevbYXzy0Ab771I4mJyVhtdmZNv5fY2JoAFBQUM3Xacs6fzyE0NJC5sx8gKMifefNXsXdvCgXmYp6ceBO9e7XwoP0TiTuTsVrtzJpxD7GNnbU/53x6LqGhAcx97X6CgvyZG/cd+w+coqCgmCmTbqZb1yYebVcoFFWDf2XSLYSoD8yWUt5zhes1B2YBH0kpf/0H7YmTUk7x0D4S8JNSLqywPBRoIKXcfbnbStybRka2mWUL7iDpeAbzFm4kfs6tAKSdMxG/PJEAf59y68R9sImJD3WlSUPXSUKp9p7TZGQVsOytuzTt9zcSP3eYk3YCAf7GSustnH0L4aH+nrX3nSUju5Bl828i6UQW8z7cQfwrg7VGIVg48waMRj1z47ezdutJel9Xh49X7mXJnKFYbXaGT/qBAd3r4WusHPKJ+8+RkVPIsnlDSUrJYt6iHcTPcsyDK2Dh9Os17Q93sHbrKQb3bsDHK/cRGR5Adm6RR7sBEnenaj5/9z6Sjl9g3rt/Ej//Todfcolfur2SX8aN7E5QoC/n0k08/+ovbhMpr/rFi9rgiMUsM8sW3E7SiUzmfbCZ+Nk3O/xiIn75znKx2LF1LZa+eRsA5y7kM/vdjW4T18S9ZzSfvznMob2F+Nk3lWl/vqtSnM+P38rieTfj52fgjrFfcfOgJghR+Z0JXrXbi7ECTsfoO3drx+h7G4ifd1uZ7Z/tcHmMnjlvYkviSfp2a1CprVT7YDoZuUUse3kQSSdzmPfpX8S/2E9rFLDw+b4YffTM/WQXaxNOM7i7ZueZCwVs2XOWvh1rX9puL5xbABITk8nMNLHs0ydJOnqGuXHf8uEH4wFY8ula+vVtxU3/7zo+W76e5Ss2MeaRQQy+oT1PT76VrKw8Hnn0PbdJd+LOY2Rm5rHskycc2t/x4cKxDu11Du1OfLZ8Q6n2+HE3EBTox7lz2Tw/dblKuhWK/xGqTk3+v4wQoh7wLJD/T2t7SrgvQXvgii4cNiecYugA7QTepGEkuabi0rba0SHMee56akeHlC7LzSsix1TEwqUJDH/8K75bc8i9duIphg5oVqadV5aQ1o4OYc7zg8tpA+iEICTI99J270xjaD+tatqkQQS5eWV2N20QgdGoVc1Cgo34+xnYczidru1rYzTqCfD3oU2zKI6n5rrX7qtVDZvUv7Q2wLj72nPnje4roeX0d5xg6MDmmn7DKHJNhaVttaNDmTN1KLVrhpZbJyhQ80lKajZNG0fhDq/7xUvaAJsTU8tisUE1ck0V4uW5QZXi5SLvfrKDsfd38qzdP7ZMO69CnD87kNo1gsutExriR15BCeZCCwH+Pi4Tbq/b7cVYAdiccJKhA52O0Yq2v3AjtWtWtv2NDzYx+r7rPGvvPsvQnloi3aReWPl4qRdeWtkOCTTi71t2IfbGZ7sZPaylZ20vnlsANm05zNAh2n5pEluL3Fxzadu27UkMvqEDANcPas/u3ScAaN1K+65BQX6EBAe41958mKFDOjhpF1TQbu/QbsfuPSmaZqAfACdSLtC0ifuLEYVCgfYg5dX8u4b8q5NuIcQQIcQfQojtQoiZjmVhQohvhRDrhBDvCyESAaSUJ6WUDwIpHvS6CiHecXzuJYTY6PjcSgixUAihd2iudWy3gaN9m6dtO2gjhPhBCHFICHGfEKI28CZwnxDi08v9zpk5ZiKcKj96vcBud/8G1dQzuaSk5jD1yb4sihvGiu/3kZ5Z4LJvZraZiDBnbZ1HbYDAQCMjJ33NQ5O+Zsfu0x7sLiQi1M+j3bsOnCM5JZueHWMq9Q8L8SuXBHjU1lW2e9eB8ySfzKGnh2qce9vNRISX/SjrDZf2y+YdJ7ht1BKmz1vDPbe6v+V+Tf3yD2rD34sXgIwsMxeyCmjmIcHMzLly7ZF3tOWOcV9x00MruP3G5v89u70UK2W2O+lf4vgHWPnjPlo2rUGN6sEe+2XmFhER4hwvLo6jQ+kkp+bSs502vGLl78m0bBRBjWruk9Yyu71zbgHIyswjIiKoTN+gw263A2ApseLjuGAICwvEZCpLyEtKLLz8ykoeHeN+iFlWVgVtvb5M2+Jae/OWwwy7Yy7TZ33JPXf18Gi7QqGoOvwrh5c4kSClHCCE0AN7hRDTgaeBlVLKz4QQdYCNV6C3Hbj4XvFbgFwhRDgwGFgFjAKOSCnHCSFaAC8CDzut72nb1aSUNwkhqgM/SSmXCyGeBAZLKZ+taIgQYgwwBuCDDz5gtHZnneBAX0z5ZYmQTifQ6VxX9AAMeh1tWkSX3qLt2LoWp9JyqF4tsFLf4EAjJqcKlE541gaY/Zw2jON8Rj6jn/6W7xc/4LJfcKCxvN1O2lJKPvxiD1arnTnP9EWv1xEcaORUmqm0vymvuFxCWFm7pExbR3ntL/dq2lN6o9df+XVqcKAvJtOV+aVH5wb06NyAtHO5PDX1O778cIQH273pF+9oa/q+5ePlErF4kW9XH+K2we6T4jJtZ9vxqJ2ZbWbpN3tZ+/kIDAYdz87+ndZNq7scBuJ1u70UK5q+8YpsP3Eqi982JLNwzq2XTFyDA30wFXg4jr49qMXLxG7o9TpOnDHx2/ZUFj7flx0H0i+h7b1zC0BQsD8mp+q2pq8d60InsNvt6HQ6TCZzaQJ9IuU87773K488PJBmTd1fjAcF+WNyumOh+dyhLXTltcM17R7dm9GjezPSzmTx5KTFfLVissfvqlD8q1FTBlYZhgoh5gMvAwGAEWgH/AwgpUwFPP8aOCGllMBBIUQsEAUsBW4AugNrgQ7AcCHEn8B7QMX7uJ62vd6xPB2wX4Yt8VLKTlLKTmPGjCld3rFNLVavTwYgOSWTGlFB7iQAqF8nnOQTmRSYS7DZ7Ow/cp76MWEu+3ZsU5vV649etjaA1ap9laAAIwaD+3Ds2Cqa1Ru127rJJ7OpEVWW9K/48RBREQGMv79DaVLcpml1NiaexmK1U1hk5WhKNg3rurG7onakk/ZPhzXt4e3/VsIN0LFtHVb/eUTTP5FxyYqh1WqnsMgCQHioPzab+4reNfXLP6gNF2PxmKafkkWNyEvHC8Afm4/Tp2t9j306tq7J6g1O2peIxezcIvR6gZ+vAYNeR0iQH+cuuB5J5lW7vRgrmn4Mq/9McuhnUiPKs/6Pvx9GSsnk6T/x3pKtrN10jN82HHWt3bw6q7ee0rRTc8tVr1esPkpUuD/j72pdGi8/bkhBSpj8+mbe+3IfaxNO89u2VNfaXjy3AHTq2Ihf1+zW9JPPEh0dVtrWtnV9/li7D4DVv+2mW9emFBWVMHvON8yaca/HhFvTblheu4aTdpt65bW7NcVqtVFYqF28hIcFYrNf8nSvUCiqCP/2SvcEKWUnIUQQ8KBjWSrQC/heCNEMqHWFmquA54FdwK/A+0C+lLJECJEEbJVSLgUQQlS8p+pp285n3ou/rDbg8gYtOujbtQEbtqUw/PGvCAzwYcbkAY4HJbuVm03gIn6+BsY90JlRk79Br9dx902tiYyoXOUG6NutoaY94QsCA4zMmDKQuIUbmfhwd5faAOOf/47CYit2m52nRru/jdq3S102JKQyfNL3BPobmfFET+I+2s7EBzuxbtspTAXFfLNGSyb6d63LqDvaMOz6Jgx/6nt8fQ1MGNERg5ukuW/nOpr25B81n0zsQdyiHUwc0ZF1209hyi8pr317a48+rqTfvREbth5j+LjPNL88cwNx7/3JxNG9XPqlxGJl3DNfY5cSgWCSh9kivOoXL2oD9O1anw3bUxg+caXml0n9iPtgMxMf6uo2XnJMRfgY9G4fziyvfZLhT3xDoL8PMyb1JS5+CxNHdXGp3bh+BK2aVueeCV8jBDRvHFk6q8k1tduLsQKOY3TrCYY/tqLsGH1/AxMf6eFS//GHupd+3v5XKpu2n2BQ71jX2h1rs2HXGYa/sEbz+djOxH36FxPvbcO6xDRMBSV8s1a7WOl/XQyP39OmTHv/eTb9dYZBXeu4t9tL5xaAvn1asn7DAe67/w0CA32ZOf1e5s1fxROP/z/GjLmeZ/7zKZ8uXUfdulFMm3oXhw+nceBgKmPGvleq8faC0YSFVT439u3TkvUbD3LfA28SGOjHzGl3M2/+dzzx+FDGjB7EM88u5dNl66lbN5JpL95JSYmVsY/Fo9VwYPKTN3m0XaH411OFKt3i4oH9b+Li7CVAJtAF2Am0BfqiVag/c3TdDvSUUnZzWnc6sM3d7CVCCCNwBmgvpUwVQqwGPnUMGQkAFgPRQAEwT0q5TgixTUrZ1TGkpNK2K85e4tQ/DNgAJEopH/LwlaU8+56H5r+PqDkeeW7hpTv+Xf3osciTcd7RrjcFeWLupTv+He0GzyAzPvaOduRDXvMJOPziTZ+fecc72rUmINPe8oo2gKg90bu2ezNe0uO9o119DPLATK9oA4iWL3nt/CKix4LtN69oox8E1tXe0QYw3OA9bYXiyrj02DpvU/zT1SWyvkOv2Xf4V1a6pZQpuJn1QwhxTkrZ2/G5I9C4wrrTL6FdAkQ6/X2D02czcLeLdbo6PrrctpRyiav+UsocoA0KhUKhUCgU/0bUy3GqNP2EEM+jDeEoBsa76yiEeBNtHPZFlkopF12LbSsUCoVCoVAoqg4q6a6AlHINsOYy+z7539q2QqFQKBQKhaLqoJJuhUKhUCgUCkXVpAo9SFl1LFUoFAqFQqFQKKooqtKtUCgUCoVCoaiaqEq3QqFQKBQKhUKhuMi/cp7ufyFqJysUCoVCofin+e/P02377epyHP0gNU+34p9FvRzHhba3XwKjXo7jWtubsViVX46TucQ72tVGevflOIde9oo2gGj+ondfjuOtF9gYbgDLL97RBvC5keWiqVek75NHvKKrUHiNKjS8RCXdCoVCoVAoFIqqSRVKuquOpQqFQqFQKBQKxTVGCDFLCLFeCLFZCNHSaXmQEOJzIcQGIcQqIUSIJx2VdCsUCoVCoVAoFC4QQvQCakgp+wCPAvOcmp8CfpBS9gZ+A8Z50lJJt0KhUCgUCoWiSiLF1f27DK4HPgeQUu4HIpza+gNfOT5/DXTzJKSSboVCoVAoFArFvxIhxBghRKLTvzEVulQHLjj9bRWidCC5r5TS4vicCYR72pZ6kFKhUCgUCoVCUSWR0n6V68t4wNMUT7mUT6btsmyjdiGEzvF3OOWT80qopPtfyIJFW0nYm4bNZmfm5AHENqhW2nbsZBYLFm3lzqEt6dWlPgCZ2WamzV9LRraZWtWDeX3ajR60t5Cw57SmPWUgsQ0iy7RTMlnw8RbuHNq6VPuxF74nI8uM0ainTbMaPD2ut3vtJYkk7DuLzSaZ+WRPYutrd3iOHM9kTvx2ikusREUEMPc//TD66Pl9cwqLv96LxWJn5O2tGdK30X9FG2BB/IYyvzxzA7ENo5z8ksGCDzdy501t6dW1IQDz3l3H/sPnKDCXMGV8X7p2rPe/6RdvxuLH20nYe0bTntS3svbiHdw5pDm9Omu+3fbXaeLit6ITMPzWNtxyvfsp2RZ8vI2EPWmaXyb3q6z98TbN7s712LnvDG8u2lbannQ8g0/fuI2mjSJdSbMgfj0Ju1M1u/9zY+VYid/AnTe3pVdXzbfz3l3L/kPnKDAXM2V8P7p2qu/WboAFH20mYffFWBxU+Rj9aDN33tSaXl0alFvvtbf/xOijY/JYD8foZ7tJOHhe88v4rsTWDQPgSEo2cxbvpLjERlS4P3Of6oHRR1+m/XEiRoOOySM6uNf24rkF4M23fiJxZzJWq51ZM+4htnFNAAoKipk67XPOp+cSGhrA3NfuJyjIn7lx37H/wCkKCoqZMulmunVt4l777Z9J3HlM055+V5m2uZip01aUab96P0FBfmV+mfstPj4Gpjx1k1tt38hwmj75INgle19aULrcEBhA5w9nEVC7BsVZuWwd8QzWvAJibhlAs8kPoTP6cPj1xZz60otTGyoU/xtsBO4ANgohWgCnndq2A7cA3wK3A797Erpk0i2EqA/MllLecyUWCiGaA7OAj6SUv17JupfQjZNSTvHQPhLwk1IurLA8FGggpdz9T9niwYbpwLbL+d5CiHZAKynlMg99/gQGSymLKixvC5yUUuZcrm2Je9PIyDazbMEdJB3PYN7CjcTPuRWAtHMm4pcnEuDvU26duA82MfGhrjRp6DpJKNXec5qMrAKWvXWXpv3+RuLnDnPSTiDA31hpvYWzbyE81N+z9r6zZGQXsmz+TSSdyGLehzuIf2Ww1igEC2fegNGoZ278dtZuPUnv6+rw8cq9LJkzFKvNzvBJPzCgez18jZVD3pvaAIm7UzWfv3sfSccvMO/dP4mff6fDL7nEL91eyS/jRnYnKNCXc+kmnn/1F7dJd5X2izdjce8ZTfvNYSSdyGTeB1uIn31Tmfbnuyppz4/fyuJ5N+PnZ+COsV9x86AmCFF5wF/i3jQysswsW3C7Q3sz8bNvdrJ7Zzntjq1rsfTN2wA4dyGf2e9udJtwJ+5O1bTfu5+kYxeY9+5a4uffrWmfzSV+6VYCAirGSo+yWHnlJ49Jd+kx+s7dms/f20D8vNvKbP9sh8tj9Mx5E1sST9K3W4NKbaXaB86TkVPIslduIOlkNvOW7CT+pQGl7Qtf1C7M5i7ZydodpxncQ4vpMxcK2LL7LH071b603V44twAk7jxGZmYeyz55gqSjZ5gb9x0fLhwLwJJP19Gvbytu+n+d+Gz5Bpav2MSYRwYxftwNBAX6ce5cNs9PXe426S7VXvI4SUfPMnf+93z4/qMO7T817aEd+ezzjSz/YhNjHh6o+eVsNlu2JtGndwuPtneY/yx5yafQB/iVW97sqZGk/bCOk5//SOz4+4gddx9J7yyj2ZSHWTvgQYTBwKBNyzn93R/Yi0su6SOF4l/MT8AQIcRGIA94VAgxB5gKvAYsFUI8ASQDj3kS8sqYbiFEPeBZIP+f1vaUcF+C9sAVXThcC6SUuz0l3JfgKSD6SlbYnHCKoQO0H4cmDSPJNRWXttWODmHOc9dTO7psxpvcvCJyTEUsXJrA8Me/4rs1h9xrJ55i6IBmZdp5ZdcItaNDmPP84HLaADohCAnyvbTdO9MY2k+r7DVpEEFuXpndTRtEYDRqVbOQYCP+fgb2HE6na/vaGI16Avx9aNMsiuOpuddcG2DzjhMMHdjc4Zcock2FTn4JZc7UodSuGVpunaBAzScpqdk0bRyFO6q0X7wai6kM7R/rsL1aOdtrR4cw59mB1K4RXG6d0BA/8gpKMBdaCPD3cZlwl2pftLtBNXJNFeL8uUGV4vwi736yg7H3d3Jv947jDB2kJVlNGkWV164ZypypN1E72k2snMqiaePqbrUBNiecZOhAp2O0ou0v3EjtmpVtf+ODTYy+7zrP2rvPMrS3lpQ3qRdObn5ZIte0fnhpZTsk0Ii/b9mF2BvL/mL0bS3xhDfPLQCbNh9m6BCtyt4ktha5uQWlbdu2JzH4hvYAXD+oHbv3pAAQFKgluSdSLtC0ifsLhk1bjjhp1yQ31+ykfZTB17dzaLct1QZ4/c0feeShAVyKrQ/+h/QNCZWW1+jflVNfaXWf1K/XENmtHZFd23L+j63YSyzYzIVkbt9LSLOGl9yGQvF/Gbu0X9W/SyGltEspx0kpe0kph0gpU6WU/5FSlkgpM6SUN0op+0opH5FSFnvSuuykWwgxRAjxhxBiuxBipmNZmBDiWyHEOiHE+0KIRIeBJ6WUDwIpHvS6CiHecXzu5biCQAjRSgixUAihd2iudWy3gaN9m6dtO2gjhPhBCHFICHGfEKI28CZwnxDiUzf2/CmE+I9jezuEEB0dy7s52jYIIV50LBsphPjIse0ebr7iACHELw4b+jnWayqEWONY7z3Hsr5CiNlOn7cKIX4VQnxwcbmDiY71EoQQNYUQDwODgU+FEPe583NFMnPMRDhVfvR6gd3u/g2qqWdySUnNYeqTfVkUN4wV3+8jPbPAZd/MbDMRYc7aOo/aAIGBRkZO+pqHJn3Njt2n3fbLzCkkIrSskuPK7l0HzpGckk3PjjGV+oeF+JVLvK6VtqZvJiI8oEzfcGm/bN5xgttGLWH6vDXcc2t7D9pV3C/eisWcK4/FkXe05Y5xX3HTQyu4/cbm7u3+G3EOkJFl5kJWAc08XERp2k6xchnam3ec4LaRHzM9bjX3DHMfK671PfscYOWP+2jZtAY1qgd77JeZW0RESFmS6zJeDqWTnJpDz/ba8IqVvx2lZaMIalQLwBPePLcAZGXlERER5KSvx27XfowtFis+jguGsLBATCYtad685TDD7pjL9Flfcs9d7n4GHNrhztq6Mu0SJ+3QQEyOC/Kvvt5Gq5Z1iK4RWlnwMtH5+iCtVgCKM3MwhofgV70axReySvsUZ2ZjDP/721AoFFfGlYzpTpBSDhBC6IG9jiEUTwMrpZSfCSHqoI17uVy2A3Mdn28BcoUQ4WiJ5CpgFHBESjnOMYbmReBhp/U9bbualPImIUR14Ccp5XIhxJNoQzSe9WDTISnlHCFEY+B9IcT1QBxwo5TSJIRY4ajiAwRIKft50JJSyhuFEB3QbkGsAxYAD0kpTwsh5jrmfnQmDrhBSpkphHgaqObUtl9KOVcIMQm4S0q5wLH+bCnl4Yobdzx9Owbggw8+YLRjSGBwoC+m/LJESKcT6HTu58wx6HW0aRFdeou2Y+tanErLoXq1wEp9gwONmJwqUDrhWRtg9nM3AHA+I5/RT3/L94sfcNkvONBY3m4nbSklH36xB6vVzpxn+qLX6wgONHIqzVTa35RXXC4hvFbamr4vJtOV+aVH5wb06NyAtHO5PDX1O778cMQ1t/2a+MVrseiLKc/ZdjxqZ2abWfrNXtZ+PgKDQcezs3+nddPqLoeBaNpO+/MSdl/k29WHuG2w+2QeIDjI94qPodJYOZvLU1O/5cuPRrrXr3iMXsL2E6ey+G1DMgvn3HrJxDU4wAeTU3W7Urx8c0CLlyd6oNfrOJFm4rftqSx8oR879p/3rO3FcwtAUJB/acILF/2i1aSE0JJknU6HyWQuTaB7dG9Gj+7NSDuTxZOTFvPVisketM2utXWikvaJlHR+/2MvC98dzY6EZI/f0RPSLkEIkBJjeAjFF7Kw5OYR3LhsqJoxPLRcEq5QVEUkV/cg5bXkSoaXDBVCzAdeBgIAI9AO+BlASpkKpF+umJRSAgeFELFAFLAUuAHoDqwFOgDDHeOZ3wMq3vP0tO31juXpcEV74zfHeslAkMOuJsD3DjuaATGOvlsuofWn4/9DlD312h5Y5tDqD9S62FkIEQWkSSkzHYt2XoaeW6SU8VLKTlLKTmPGlM1+07FNLVav107kySmZ1IgKcicBQP064SSfyKTAXILNZmf/kfPUjwlz2bdjm9qsXn/0srUBrFZt9wQFGDEY3Idjx1bRrN54QtM+mU2NqLJEa8WPh4iKCGD8/R3Q6zWNNk2rszHxNBarncIiK0dTsmlY143dXtQG6Ni2Dqv/PKLpn8i4ZMXQarVTWKTNQBQe6o/N5r6iV6X94s1YbF2T1RuOObSzLqmdnVuEXi/w8zVg0OsICfLj3AXXo+M0u520Iy8d5wB/bD5On671Pfbp2LYOq9dp19BXHCth/tguUf3t2DaG1X8mOfQzqRHlWf/H3w8jpWTy9J94b8lW1m46xm8bjrrWblGd1VtPadqpOeWq1yt+TSIq3J/xd7cpjZcfN5xA2iWT52/kvS/3snbHaX7bdsq1thfPLQCdOjbk1zW7Nf3ks0TXCCtta9umHn+s3QfA6t92061bU6xWG4WF2gVGeFggNrv7nxlNe4+mfeycC+39Du09dOvahB9/2oldSiY9/SnvLlzD2nX7+e33vZf8vhXJ3L6HmFu04Sl1br+Bc79vJXPHPmoO7oUwGND7+xHWKhbT4eNXrK1QKP4eV1LpniCl7CSECAIedCxLBXqhJaXNcEoiL5NVwPPALuBX4H0gX0pZIoRIArZKKZcCCCEq3n/0tG3nM+DFXyEbcKkBfp2B9UKI64A0IAM4DFzvsClASml2XChYL6F10QbnX8F9wB1SyhwhhK9D42K1OxtoLIQIklLmoyXll9K7nO9Ujr5dG7BhWwrDH/+KwAAfZkwe4Hg4rVu52QQu4udrYNwDnRk1+Rv0eh1339SayIjKlUWAvt0aatoTviAwwMiMKQOJW7iRiQ93d6kNMP757ygstmK32XlqtPtbtH271GVDQirDJ31PoL+RGU/0JO6j7Ux8sBPrtp3CVFDMN2u0ZKJ/17qMuqMNw65vwvCnvsfX18CEER0x6F3/8HpTG6Bv90Zs2HqM4eM+0/zyzA3EvfcnE0f3cumXEouVcc98jV1KBIJJHmaLqNJ+8WYsdq3Phu0nGf7ENwT6+zBjUl/i4rcwcVQXl9qN60fQqml17pnwNUJA88aRpbOauNZOYfjEldr+nNSPuA82M/Ghrm7jPMdUhI9B7/ah0lLt7o0dsbLUESs3EvfuOiaO6e0+Vp5eqcWKgElj+3rW79aQDVtPMPyxFWXH6PsbmPhID5f6jz/UvfTz9r9S2bT9BIN6x7rW7hTDhl1nGP7cagL9DcwY15W4T3Yx8b62rEs4janAwjd/aBcr/TvH8Pi9bcu0951j019nGNS1rnu7vXRuAejbpyXrNx7kvgfeJDDQj5nT7mbe/O944vGhjBk9iGeeXcqny9ZTt24k0168k5ISK2Mfi0erHcHkJ93PLtK3dwvWbzjIfSPeIjDQl5kv3cW817/niceHMOaRgTzz3DKHdhTTXrwDo1OMbN9xlI2bDzNoYBuP9jvTbvYU9k5dwMHX4um2dC5NnxhBXvIpEh+bgb3EwvEl3zBo03JshUXsnfY20ma7bG2F4v8ilzMu+/8K4uJJw20Hx+wlaJN+d0GrwLYF+qJVgj9zdN0O9JRSdnNadzoeZvEQQhiBM0B7KWWqEGI18KljyEgAsBjtQcECYJ6Ucp0QYpuUsqtjSEmlbVecvcSpfxiwAUiUUj7kwpY/0arX1wECGC2lPCGEuAl4Ae2J1RNSyjHuZkhx9b2FEH7Ar1LKvkKIrmhDSIrR5nIc5fDpYCnls0KIe9EeQD2HVtHOkVJOd569RAgxGOjqWH4H2gwxU6WUK13Z4kDKs+95aP77iJrjkedcuuGf0Y8eizwZ5x3telO8q53xsXe0Ix/ymt1wDfzizVhMe8sr2gCi9kTkmXe8o11rAjJziXe0q41EpnuagvYqtKuPQR562SvaAKL5i147v4josWBd7RVtDDeAxYtT8fncyHLhfkrLq+E+ecQruor/WS7vnY5epNj2y6UfqvGAr/7Ga/YdLlnpllKm4GbWDyHEOcf75nE8eNi4wrrTL6FdAkQ6/X2D02czcLeLdbo6PrrctpRyiav+jmn1LlUumFlxWj4p5Q/ADxWWlduGCxunO30uQrtAQUq5DehZofuflA0dWSml/BxACLEA2O1Yr6+T3q9odwVwJNqekm2FQqFQKBSK/1mq0pjuq305Tj8hxPNoQx6KgfHuOgoh3kQbh32RpVLKRddi2y5sWUH5qfbm/V0jhBDPoj38eZHfpJSv/E25OUKI9oAPWvX+u79rl0KhUCgUCoXi/w5XlXRLKdcAay6z75NXs62r2baLdV1V7n/6m1qz0YbfXDVSykn/hI5CoVAoFAqF4v8W6jXwCoVCoVAoFIoqSVV6kNIrb6RUKBQKhUKhUCgUZahKt0KhUCgUCoWiSiJVpVuhUCgUCoVCoVBcRCXdCoVCoVAoFAqFl7nky3EU/xOonaxQKBQKheKf5r/+cpw8y7dXleME+wz7v/NyHMX/Bt58O6J923+8og2g6zoH+/ePeEf75o+QB2Z6RVu0fAl59DXvaMc+R8kbt3tFG8D41NdYlz3gFW3D/Uuh0EvTz/vfgn3tRO9oA7r+byETnveKtrjuVcj7yivaBN/p1WPIvmmyV7QBdD3ne/VtmkUz3b++/Wrwe+kHCl8Y4hVtAP9Xfob8r70jHnS7d7UVin8xKulWKBQKhUKhUFRJ1IOUCoVCoVAoFAqFohRV6VYoFAqFQqFQVEnUy3EUCoVCoVAoFApFKarSrVAoFAqFQqGokkhUpVuhUCgUCoVCoVA4UJXufyEL4jeQsOc0Npudmc/cQGzDqNK2YykZLPhwI3fe1JZeXRuWW++1t/7A6KNn8ri+7rW/PkjikUxsNsmMUe2IjQkBICk1l9mf76eo2EZMVACvju6AQa/j951nWPLrMSxWOw8ObsSQLjHutX9NIfFELjYbzLijMbHRgZr22QJm/3CcohI7MRG+vHp3Uwx6wfbkHOJ+OoFOCO7rUZNbOtZwr718DwkH0zWfjOtCbN0wAI6kZDPnk10Ul9iICvdn7hPdMfroeWz2ejJyijD66GgTW42nR3Tw7POlu0g4cB6bTTJzQjdi64Vr+ieymPNxIsXFVqIiApg7uRdGHz1xixPZc+QC5iIrTz7Qnl4d3ftF3+0eREwL0Omx/b4QmZlavkNAKD4PvY/l/QfBZkHEtELf7W7QG7Anb8eeuMqt9lvrTrPzVB5Wu2TG0Po0rh5Qrj0j38INb+9hy9Md8DWUXcMv23GO3an5xN3e2KNf3nx3NYm7jmO12pk19XZiG0cDUGAuZurMlZxPNxEaEsDcl+8mKMiPzKx8Xpr1NZmZ+dSsGcYbc4a71V7w/VESk7O1WBzekthaQQAkpeUxe+URikpsxET68+qIVhj0ZbbPXnkYH72OycOauNf+6gAJRzK0/flwh9I4P3IqlznL92rxEubH3PGdMRp0/Lwtlc/WHKPIYmPEDY25pWc99z55/3cS/0rRfPLCLcQ2qlHmk5dXcf6CwyczbicoyI+f1+xj2ZfbKCq2MOKebtw6tL1Hn1/pcfTz7gss33KGIoudB3rW8nwcfXuExKRMbHbJjBFtiK0drGmfNjH7i4MOnwfw6kNtMeh1xH11iL0nsjEX2XhiWFN6ta7uXvujzSTsvnjeGkRsg8jStmMpmSz4aDN33tSaXl0alFvvtbf/xOijY/LY3h79Yug7HF29VqDTYfnxXeSFUwCIGg0w3jcdmZkGgOXn95EZZceY4fqHwWb9/+ydd3gUVduH77Ob3hNKKKGX0IsgvUonooKiKIgUiYCKKIgVKfoqTQWUFopIEwV7o0jvJCi9JrTQAimk193z/TGb7G6yu5Rk9X0/z31dXMzOnPnNk+ecOfPMM2fOkLflS/vaXZ9FV7UB6PTk/jAXedOkXb467s9NxXjriqb90zzkrVjw9sftsZfBOwCZfIvcr6fb1Z49fzNRf10gz2Dk/Xf6Fmov35vOIU9mTO3P6XM3mLNgc8G+Z87dYEXE89SpVb5E9H18PNgfGcPMuRvQCcHAp+7cHhWKfxMq011MhBBVhRBr72O/ukKI9UKIng7KDBRC/CGE+FMI8arF+hQhxHYhxCEhxMh7OW7U4VjikzJYNe8Zpkzowcx52wu2Xb2RTMTKA3h5uhXZ79qNFPZGXnSsfSaehORsVr7dnslDmzDz6xMF20LKerP09TasmdgBN1c9x84nkZGdxxe/R7NsQhu+eLMtS345R3aOwbb2+WQS0nJZOaoxk5+oycxfL5i1S3mwdEQD1rzUGDdXHcdiUwH4+LcLLAtvyKoXG/HFjqvY+xBU1MmbxCdnseqDbkwZ2ZKZK/4ybxSw8O1OrP5PdyqU8WZr5JWCTQvf6cTK97vdMeCOOh5H/O0sVk3rxZQXWzNzWZSFvmDhe11YPaM3Fcp6s/WAdjHv0a4qK6f1YvGUbsxe+ZcdZRAV64J3AHnr3sPwx0L07QcXKaN/sC9kpph/tx9E3o8fkvf1O+iqNgV/20HUocupJKTn8uVzdZkcVpVZW2KLlFmy9xoBXtb37unZBjaeTHToE4CoPy+QkJDKqqWjmDrxcWZ8+mvBtuWrdtG5Qz1WLxtF21a1WLNuHwCzZv/GKy/2YO2KFx0G3FHnkkhIzWHlay2Y/Ew9Zn53pmBbSGlPlo5pxprXW+LmouPYxeSCbdcSM9l7KsGx3afjiU/JYtW7HZkyrCkzvzpq3ihg4bg2rH6vExVKe7H10DWS03NYs/k8X7zdgVXvduTL36NJy8i1rf3XRRIS01gV8TxT336UGXM2mn2yZi+dO9Rh9eIRtG1ZgzXrD5KcksnqdftZvmAoqxc/z5dr9pKWlmXf9ns8j5Izclmz9xrLwhuyclQjvtx1lbSsPNvaZxNISMlm5RttmPxsQ2auO2nWLuPF0tdasuattpr2hdsA9HywPCsmtCHi1RbM+f6MTV2AqCNXiE9MZ9XnTzHl9W7MnL+zYNvVGylErD5ou9+KS2Fv1CW7uvmIyvXAO4CcL98i95d5uHQdarXdcGoPOSveJmfF21YBN35l0FVr4lBbV6U+wieAnCVvkPvDZ7j2HG6tfXw3OUvfJGfpm1rADbj2GEbu5pXkRIx3GHBH/XVBay+Lw5n69mPMmPN7wbblq/fQuX0dVi8Jp22rmqxZf4DmTauyMmIEKyNGMPP9J2ndoobDgPte9QFmfbaR5fOHs2bpCyxbuctuv6tQlBRGaSzWv78TFXT/AwghqgBvAml3KPqTlLIr0BwYJoTI/2rSSSllJ6AFMPpejr3n4AXCutYFoHb1MiSnZBZsq1jOn+kTw6hY3r/Ifp8u2sGIQa0cax+/SVhrLSNbO8SP5PScgm1e7i4IIcjOMZCcnkNIGW+ORCfRql4Z3Fz1eLm70KhGIOevp9rWPptEWBMtI1+7nDfJGeYLv5ebXtPONZKckUdIkAcA/p6upGblkZFtKChjU/vwdcJMmcfaVQJITs0u2BZaJRA3Vz0Aft5ueLprAaZOCPy8XB36o0D/r6uEddSyb7WrBpKcZqFf1ULfx71Av2EtLYvn4+WKn3fRYCIfXeXGGE/vBtAy3B4+VttF2WogQSbHaSs8/SA9CXIyQRoxXvwTXXAN23bHJNO7QSkAapX1IjnTOtg6eT0dAVQKdLdaP2/nVQa1KGfX5nx27ztLWK8mANSuWc6qLe4/GE3Pbo0A6N61IYePXCY5JYOk5HQWLN7CM0Pn88Mvh+xq7zkVT1hzzYbaFX1JTjcHuQVtMddAckYuIaXN2fvZP57j+e7ViuhZaR+LI6x1JU27kj/JaWbt0Er+hdqLnss30qhbxR83Fx2e7i40rhlEzDXb7Xz3/mjCejQy+SSY5JQMs08iz9OzawPNJw/V5/CxWC7FJlA3tAJuri54erjRuGElYi7esm/7PZ5HlxOyqFfRR7PdTU/jyn7E3MywrX0inrCWFTTtED/7Pk/PJaSM5vMGVQMA8PFwwdfB+bQn8hJhXeto2tVLk5xivrGoWM6P6e/0omJ5vyL7fbpoNyOeedCubj766k0xntACeXnrMsLT+jwiK93mfq4PPUveXscfktHVegDDkR2a9s1LCE9fq+0ys9BlwMMH4eWLS+cBuI2Ygb7JQ3a1d++zbC/lSE62OIciY+jZtSEA3R9qwOGjl632nbd4K6OGd3Zo+/3o+/t5kpqWRUZmDl5ebnb7XYXi34gaXlJCCCF6A+MAH2CjlPI9IUQA8AUQAJwGHpRSNpdSXgKeE0JMdqQppcy/MgcDl2XRlEF54Ao2EEKEA+EAixYtYkQ/raoTbmcQFGgOMvQuOoxGiU5nv2Nc//MR6oeWI7iML+fO27+gJ6bkEOhrDsBcdMJKe/yCKA6cusWTnapS2t+dg6fiCbIoH+DjRoqdDGBiWi6BPuaLchHt1ac5EH2bJ1uVp7SvVm5Ih4r0n3MYF73g5R72H+cnJGcR5Odh9om+qE/+PHWT6NhkRvStB4C3lytDJm/BVa9jZP8GtKhv/5H7XemfjCP60m1GPN6gYF1OroEPFh3ghScb2dXGyx8yzZlajAa0r/JKcHFH324Qeb/MwuWRN7XtmangWxq8AyAzFV3FehjTdtuUTszIJcgii63XCYxSohOCjBwDn26N5dMnavHS12cLyuw9n4xRShpU8GbzKcfZ7sTENIICzcGN5hcjOp2O3BwDrqbgNcDfi5TUDGKvJHLxUjxfLR+Np4cbQ16IoE3LWpQtUzTYSkzNIdDHfLPioi/UXpYe4cDZRJ5sV4nSflq59XuuUK+yH+UCPTh3zf79cEJKtlW71RfSBvjzbDzRV1MY0SeU1IxcDkcnkpaRi9AJjsQk0qdtJfs+CfC27ZPcPFxdTD4J8CIlNZPKIUEcPnqZtLQshE5w9PgV+vRsbN/n93geuboIDl9KIS0rDyEERy+n0qdpGdvaqdnWPi+sHfEnB04l8GTHypT2M/svJ9fAf746wQth9ociJSRlEBRg0W/Z8Hlh1v9yjPqhwQSX9eXchXi75QBtGEe65XlkpOA8MhrQhbbCrWpDjNdjyNv8BRjz0DfphvF6DKTEQ1n7/Yvw9rfSlkYDCAFSgsGAvl4bdNUbIa/FkLthKSKoHKJ0RXIWjYfcbNyGfYgh5i9ITSqinZiURlCgvfZS+BwyB8zxCancik+lTm37We771R86sB2PPzsPFxc9Y0Z2daivUJQEpTye/p+5s1NBd8kRKaXsIoTQA0dNAfXrwHopsNQTPAAAjdBJREFU5WohRCVg170ICiHKAD8C1YAXLDbVE0LsBEKB92ztK6WMACIKfpo+A+/r7U6KRZZIJ4TDC9eFy4ls3nmOhTMe5+BfRYcXWOLj5UKKRXZbFNKeNao5RqNkzren+GH3ZYL83Ll00xzcJKfnWgXtVtoeLqRYZOWEwFp7YB1Ne+Mlfoi6SYe6gazYfZUt7zyIi07HW1+foWGIL6EVvIto+3q7Wtmt05m1pZQs/v4keXlGpo9pjd409nfay60BiEvMYMT72/jp0zC7fvH1ciMlzULfwi9SShavP0ZenmT6a+0K9C9cTWb+V0d4/vEGhFYLsqtNToZ1dltKQLs303ccgiHyBy2rbS6AYetiXHq9CtnpyPTbyJSbNqV93PWkZJmH++iEQGfKWs3YfJnhbcrj464v2J6UkcviPddYMCCUhHTbN09W+j4epFhkt3U6gU6n/f1CJwou7impmQQF+uCi19G4QWUCTUFps6bVuBybYDPo9vEs3F4KtcXhjbX28tM5fth/jSbVA/jj8E0WjG5K5LmiwY0lvl6upFj8fUXq8+ez5BmMTB/5IHqdIMDHjVGP1mHkx3spG+hBSBlvKpYu2g4LfJJqxyfCwicpmQQFeBPg78Wo4Z144dWVBJfxI6RCICEVAu3afq/nUd8HgxnZpTIjl50g2N+dkCB3KgZ52JI2+dzslyI+D39A0/7+DD/suULfdpW4cCONBT+fY3jPGoRWKlqP+fh6u5GSatFv6e6m34pm4fTHOHjYZl7Cmux0sMxuSyP555G8dZmcRS8D4NLxafQPdMd4/jC6Oq3JXTtVGwfuAJmVgfD0oSBjIqXpPNUy39mfaQ8rXR4aiL55T4yXTmCMPaPdIAPGSyfQBVXAaCPovuv2kpppFTx/9/Of9HvE8bC4+9FPSExjxVd72fbLBFxcdLwxaT0N61d0OIRFofg3oYaXlBxhQoiPgQ8AL8ANaAL8BiCljAVsRzd2kFLeklK2AWoCLwoh8lNBJ6WUHYCKQFshRJu71WzWuBIbt2tjJ6MvxBNc1tdh+V82n0QaJeMm/cT8L/awdXc0m3ectVm2ee1SbIq8pmlfTaFckGfBtlTTxVinE5QN9CAjy0Cj6oHsPnqT3Dwjmdl5nLuSQvXyPra1q/ux6ZiWrYqOS6ecvzk4TzUNe9DpBGX93MjIMZCUnouLTuDhqsdFL/DzdOFGcrZN7WZ1y7Jxn/ZoNDo2meBS5oza2o3nKBPoyegnGxYExAB5Bm0cmI+nq9VLeDb16wezcc9FTf/ybYIthjOs/f0MZYK8GP104wL9rOw8pi2JZOpLbRwH3IDx6il0tbQbAIJCkGmm8ciefojg6ugadkXf+1VEqUroe7wEgLx+lrz1k8jbNB/hHYC8Zrs+m1X2ZZMpWx19K5Ng0xOEhPRcTl5PZ/2ftxj/bTQxtzJ558fz/HE6Cb0QvPvTef6z4RKHr6bxzZ/2m3zzB6qxYbM2Hjo6Jo5yZc3Dmho3rMSW7dqY4I1/HKN1y5pUrVKGc+dvkJ6RjcFg5PjJK1StUtq2ds1ANv11Q9O+nka5AMv2YtEWAzzIyM7j18jrGKVk3NKjzP81hm1Hb7L5cJxtv4SWYuNBLZCLvppCsEU7X7vlPGUCPBjdty56i6DwoWYVWDWxI+MHNEQnsNrHyu6mVdmwRXsXIvr8TWufNKjElh2nNZ9sPUHrFtqwoC4d67J68QjGj+mB0AmCy9oPXu/1PAJ4qH4pVo1uzLjeVdEJQbC/7Rvj5rVKsSnquqZ9LZVyFsF5kfM/O4+sHAPTvz7JlMGNHAbcAM0ah7Bxu9ZOoy8kEFzmDv3WH6eRUjJu8q/MX76Prbtj2LzznN3yxssn0NdtC4AoXQmZYjGuX5jPb2kaZqJv2BGEwLXf6+g7DEBXuwW6UNvD74yXjqNv0E6TKlMJmWKRdddZaqcBEhl/FV1wFXDzAKFDV7EWxvirNrWbN63Khj+OAxB9Po5yFnXfuEEltmw/BcDGLcdp3cL8JGHrjlN0bBtq1x/3q590Ox29iw4PD1dcXPT4+3kSF5diU1uh+DeiMt0lx0tSyuZCCB/gOdO6WKA98JMQog5Q4V4EhRD+UspkKWW6ECIFsEoxSSnzhBC3AdtpMxt0alODnftiGDhqNd5ebkyZ0INZ87czZkT7grGolrw8vF3B8oE/L7P7wHm6dbQ9q0PHxuXYcSSOQf/ZhZeHC1OGNGbW1ycY83hdfj9wlR92X8bVRUdIGS8mPdcYN1c9j7WvzKD/7MLdTcfL/erYDWA71glix6lEBs0/gpe7nimP12LWrxcY06MKvx+5xQ9RN3F1EYQEeTCpX03cXHTUD/Hl6c8PIxDUqeBN+1DbGcBOzSqy889rDHxnE96erkwZ2YJZK/5izNON2BZ1lZT0HL7bGgPAQw+GMPSRuoz+aAeZ2XkYjZJXB9p/nA/Q6cEQdkZdYeCE3zT9l9ow64soxgxqyrYDsZr+Zi0geKhlZZrVK8vJmATCJ5tnGfjsnYcIsPEUQJ4/BFUfwOXJ9yEni7w/FqJvNwjD3rXkrXmjoJx4YgqGjZ8DoO/wHKJcLTAaMOz8ErD9olPHWgHsik7m2eUn8XbXM6l3VT7+I5aXO1fkm+fN2b0hK07xn0er4+6io/8D2uwTV29n8+mWWJ58wP5sFJ3a12HH7tM8M3Q+3l7uTJ34ODNn/8YrL3YnfNhDTHh3LStW76Zy5VJMeqsvbm4ujH6+C0PCI9DrdQx4ohWlS9kOvjo2KMOO4/EMmnVAa4vP1GPW92cY06cWv0fd4If917T2UsqLSU/Xw83V3O4Onk1k14l4ujWxPWSoU5Py7Dxyg4FTt+Pt6cKUYQ8wa+0xxjxRn21/XSclI5fvdl4E4KEHyjO0d23GzTvI9YQMvD1ceG9IE/s+aVebHXvO8szzizWfvP0IM+du5JVRXQgf2oEJ761nxVd7qVypFJPe6APAuHe+4dqN23h7uzNpQh+72nDv5xFoQ06u387G213PxL62x/8DdGxUlh3HbjJo2l68PPRMGdyIWetOMaZvKL9HXuOHvVdw1esIKe3FpGcbcDo2hZOXknlhzoECjbmjmxPgU/Qdhk6tq7Nz3wUGvrhW67fGd2XWgp2Meb6t7X5rmDkPceCvWHYfuEC3DrXs2m48G4WuZnPchkxDZmeS++s8XLo8R9621ehqt8Cl1aMgjcjbceT+8jkYzE8LdFUaoKvZDOOZ/ba1z0Sir/0gbiNmQHYmuT9+hkuPoeT9sRJdnZa4tHlM006KI/eHuWDII3fbWtyHfYQ0GjAc/A3Sb9vU7tQulB27z/DM8EV4e7sz9e3HmDl3A6+M6kr40I5MeG8dK9bupXJIKSa9+QgAt5MzcHXV4+5+53dS7lXfzc2FBnUrMmDoQhBQt3Z52rex73eF4t+GUG8WFw8hRFVgGpAAtAQOAY2BTkAZYLWp6AGgnZSytcW+k4H9UsoNdrQXAXVNP3+QUn5iWp8C/AnoTfu/fgczC4aXlDSi9DCM+9+4c8H7RNdqOsafnneO9iNLkCemOkVb1H8Pee4j52jXeoucTx93ijaA26vfkrfqWadouwxaCZk/OkUbz0cxbh3jHG1A99BcZOTbTtEWD34Iqeucoo1vf6eeQ8bd45yiDaBr9zHyZsSdC94Homw4WVMd36TcLx7v/UzmO72dog3g+Z/fIM3xC5z3jc/jztVW/H/jf2Y89X8DKtNdTKSUF4EBtrYJIW6YhoEghGiGNkzEct/Jd9B+wc56x89iFQqFQqFQKBT/Vaig27l0FkK8jfb8PhsH0/sJIWajjQHPZ6WUcqlTrVMoFAqFQqFQ/C2ooNuJSCk3AZvusuxY51qjUCgUCoVCofinULOXKBQKhUKhUCgUTkYF3QqFQqFQKBQKhZNRQbdCoVAoFAqFQuFkVNCtUCgUCoVCoVA4GTVP978DVckKhUKhUChKGjVP9z2gZi/5l+DMj+PIxBVO0QYQQYOR1z53jnaFl5z64Q2Sv3KKNv5PIy9/4hxtQFR+DRk72znalcZCytdO0cbvKeSNhc7RBkS5kcjr852jXX60Uz+OI28tcYq0KPM88tIsp2gDiCrjkQnLnaNdaghkfO8Ubbz6Oq8+AXz7843rnT/jfj88mXvGqdpOrU+F4r8cNbxEoVAoFAqFQqFwMiroVigUCoVCoVAonIwKuhUKhUKhUCgUCiejgm6FQqFQKBQKhcLJqKBboVAoFAqFQqFwMiroVigUCoVCoVAonIyaMvBfyJyInUQeuYLBYGTqhB7Uql6mYFvMxXjmLN5F/z6Nad+qOgAz523j+OkbpGfkMH50J1o1q2Jfe9F2Ig/Hatpv9i6qHbGD/n2a0L51DQCys/P4eeNx/th5hoWznnJs97L9RB65isEgmTquM7WqlTJrX0pkzrL99A+rT/sWVTh07Bqzl+4v2H72fDwrPu1HaI3StrWX7CHycL5PulGrmrlczMUE5izZQ/8+DWnfshoAL771A/FJGbi56mlUtxyvj+7o0PbZC7cS9dcl8gxG3n+rD7VqlDXrX7jFnEVbeeLRB+jQuhYAf2w/xbLV+8jNMzD0mdb07tbAvl+WRxJ59Lpm+6sdqFU1yMIvScz5MpL+verQ/sHKAPy2PZrVP54gKzuPwX0b8mi32va1vzhI5LFrms9f7VhUe/lB+veqS/sWmvb+w1eZFbEPnU4w8NEGPNrN8dRjsxdsIeqvi5pf3n60wC/pGdlM/M9PxN1Kwd/PkxmT++Hj48Fvm46xat0BzfYBrXisdxP7ti/da27n47sWrdNle+kf1pD2LasC8OI7PxGfmIGbm55GdYJ5fVQHB9r7iDx6VdMe16VoW1y6T2uLJu2EpAwmfbyV+KQMKpT15ZNJvRz45A/NJ3lG3n/nUWrVCDb75IMfTD7xYsaUx/Hx8WB/1Hlmzt2ITggGPtmSx8KaOvT5nMW7iTxiOkdf70Gt6oXb+m76P9yI9q2qWe330WdbcXPRM26U/bY+Z3kUkceua+1lbLuC9nLmfALTIw6QnZNHmSAvZrzRGTdXPX/sucgX3x4lN9fIkMcb0rtTDfvaETvMfcsbvWz0LTvp/0hj2rfSNGbN28aRk9fIyMxhbHiHgvX2mD1vE1F/XtDa4sR+1n6f+h1xN5Px9/dixvtPcvrcDebM21iw75lzN1ixOJw6tcvb1r7HOv1t0zFWfbOfrOxcBg9o7bBOG0x+hdLtm6NzcSFq1ERSTkYD4OrvS/NFH+BeJoi81HQODJlA7u0UynRsSeNpryONRqLnr+bS6h8d+sWZ+vdapzPnbeX4qRukZ2QzfnRnWjWv6tB2heK/jX9t0C2EqApMk1IOuMf96gLvA0uklBvslFlu0j59F3o9AKOUcrODMvullK1srG8H7JNSGu7W/qjDscQnZbBq3jOcPX+LmfO2E/FxfwCu3kgmYuUBvDzdrPYZNaQNPt7u3LiZwtsf/m436I46fJn4pHRWLXiWszE3mfn5FiI+0dx79XoyESv2FtFetmY/pUt5k3Q7w7HdR68Sn5jBqjmPc/ZCAjMX7SFi2iMmu1OIWHMIL0/XgvLNGlZg5ex+ANy4lca0ebvsBtxRR64Qn5jOqs+f4uz5eGbO30nEzH5m7dUHi9gNsHB6XwL9PR3aDRD11yUSEtNYtWgoZ2PimPHZJhbPHmTyy20ivtxtpZ+RmcPS1Xv5ct5z5BmMPDNiGV06hOLu7lpU+9h1rT4/eYSzFxKZGbGfiA97a9pxqUR8fRgvD/N+yanZrPnpBF/MeBiDwcjAV3+iS5uq+HgX/fuijl0zaT+m+TxiHxEfhpm11/5p5XOAjxfv54sZffDwcOGJ0d/ySNfaCGH72wlRf13U/BIxnLPRccyYu5HFc54FYPmafXRuH0qfno1Y/c0B1nwbyVN9m7N6/UGWzx+CwWDkmeeX0rVDHXx8PIpq59fp3Ce1Ol2wi4gZfTXbb6QQsSbSdp1Oe/SOdRp19KrmlzlPaNoLdxEx/TEL7agifpm1aDdjhrWidnXbbbCoT57XfDJnI4vnDjb5ZC+dO9ShT8/GrP5mP2vWHyR8SAdmzd3I8vlD8fBw5fFnF/Bo7yb2fV7Q1p/Wzv/524mY9YTJ9mQiVh0oYjvAtRsp7I28RKfW1e3bfuw68UmZrPq4j9YWFx8k4j89tY1CsHBqD9zc9MyIOMDWfZfo8GAllq0/yvLpYeQZjAx87We6tKmCu1vRy1LU4Vjt/J8/iLMxt5g5bysRH2s36VevJxOxch9eXtb12eOhOox/sTOJSRmMGPe1w6A76s8Lmt+XvsDZ6BvM+PQ3Fn8+VPP7qt107liXPr2asPrrfaxZt5/woZ1YueQFAG7EJfPRx7/YDbjvtU6f6vcgq9ftZ/mCoVo7H76Yrh3r2mznpds2wz24FNu7PItf/Vo0njaBXY+EA1BnQjiX1/7C1R82U23YE9R+ZQgnpsyl0Ufj2dFjCHkZWXQ78K3DoNiZ+vdTp6OGtDVfi/7zqwq6Ff9zqOEl94AQogrwJpBWUppSyo2OAu478AFQ9ArpgD0HLxDWtS4AtauXITkls2BbxXL+TJ8YRsXy/lb7+Hi7A3AxNonQmmWwx54D5wnrVl/TrlHWWru8P9Pfe6SI9qih7ej/iOPMHMCeqFjCumgZ2drVSpGckmVhtx/T3+pGxXJ+Nved9+VBRg5qbl878hJhXeto2tVLF9V+pxcVy1tr63QCPx/3O9oNsPtADGHdG2r6NYIL+SWA6ZP7UrF8QMG6I8eu0PrB6ri5ueDl6Uaj+hU5fynetu2HrhDWuaamXS2I5NRss3awL9MndKZiOd+CdZevJVO3RmncXPV4erjSuG5ZYi4n2daOukLYQ7VM2oV8HuzL9De6UDHY12off193UtNzyMjMw8vT1W7wB7B7fwxhPUx+qWntl/1R5+nZVWtL3R+qx+FjsVyKTaRu7fK4ubrg6eFG4wYhxFy8Zcf2y4R1sajT1EJ1+nbPIu1FJ+6uTvdEXja3xeqlSU6x8Hk5P6a/1d1KOzk1i9spWSxcGcnAl9fx46ZTDnwSTViPRhY+Md+M7o88T8+uDUw+qc/hY7EA+Pt7kZqWRUZGDl6ebg59vufgRcK6WZ7/ln7xZ/q7valYzr/Ifp9G7GTEwBb2nQLsOXSVsM5aYFu4LYZWC8LNTQ+An68bnh4uHDl9k1ZNK+LmpsfL05VGdcpwPjbZjt3nCetWT9OuUcju8v5Mn9iniN0N62pBsI+3G342AlZLdu87R1jPxpp+zXKF/B5Dz65aO+3epQGHj1622ndexBZGDe9sX/se6/RSbAJ1QyuY23nDSnbbeblu7bi89lcAUk6cwy3I7AP/BrW5uf0AANd+3kpQc+1vyElMxtXfFxcfL/LSHCc7nKl/P3VacC26nEhozbIoFP9r/OuDbiFEbyHEFiHEASHEVNO6ACHE90KIbUKIBUKIKAAp5SUp5XPAxbuQfloIsVkIcVQI0cCk21oIsV0IsVMI8a5p3RAhxEjT8lNCiINCiN+FEF/mrzdt+0AIsUsIsUMI4SmEeAdoAmwSQjx0t39vwu0MggK9Cn7rXXQYjY6/Er/n4AX6DV3O5JmbGPCY/QA5ISmDoAALbf2dte8WTducgbxb7fjEDG4lplPHwc1CUbvFHbW9vdwZMnYdw15dx8G/Yh2WTUxKt/a5XofRaHRgT7qVPYH+XlYXJKuytzMJ8r97v1Qq78fhU3GkpeeQnpnLkdM3MRhsl9e0zcHK3fh8yBONeeLF9fR5/mse71nHYdnEpHSCArwL6Wt+yc0x4OqiBWkBAV6kpGRSOSSQw8diSUvLIj0jm6MnrpBnsO3H+2kv3t5uDHntW4a99i0HD1+xWy7hdkYhnztuL7HXkrkYe5uJYzuxdFZf1v50jJsJ6TbLJiam2fdJbp61T1K1m5ShA9vw+LMLePipuTz+yAMO/0atbd2bX9b/cpT6oeUILuPrsFzR9lLUL3+euEH0xSTaNQspUj7Az8MqULe2+/76lpycPD74dDMvDG7tsFxiUhpBgfbaYh6uria/+2ttMZ/4hFRuxadQJ7SCfe17rNPKIUEcPnrZ3M6PXyEvz3Y7dy8bRHZ8YsFvY54BTDddycfOENK3OwBlH2qNMB3n7Owv6Lr/W3oc/oULy7916Bdn6t9Pne45eIF+Q5YxedZGBvS9c7JGofhv4187vMSCSCllFyGEHjgqhJgMvA6sl1KuFkJUAnbdh26clLKbEKIfMFwI8RowC+glpUwRQqw1Zc4BLdAHxgIdpZSZQoh5Flplga+klO8KIeYC3aWU/xFCdAN6SimLRGRCiHAgHGDRokWM6KdVta+3OykWAZxOCHQ6+5kxgLYtqtG2RTWu3kjm1Yk/8s3iwTbL+fq4k2KRUdTp7qx9t/h635/29xtP0a9n3Ttou92z9rR3tMfmcfFpjBj3LT99+Zzdsj42fW7/ftfXx51LV8wXuuTUTKugvYjtaeZARafDoe0Bfh6MeuYBRk78nbKlvAkp52uVCXes7dgvCUkZrPzuKFtXP4uLi443p2+lYWhZQquXslnex8e9IHA062t+ETqB0WhEp9ORkpJJUKA3Af5ejBrWkRdeW01wGT9CKgQSUj7Qvu2p99bOp73VAzDV6evf89MXz9rRdr8nv7jodTSqV65g2EqzhhW4fPU2ZUt5Fynr4+Nh3yeikE8CvElITGPFV/vY9vN4XFx0vDH5WxrWD6FOrXK2bfdxJyX17m2/cDmRzTvPsXB6vzveXBZpLxY+l1Ky+Osj5OUZmT6hE3q9Dl9vNy5fTSkon5KabRWEF7X73urzwuUE5i/bw/ODWt0xK+rj42EVTFueo1ZtMTXTKjj/7qdD9HvE/lO0Au17qNMAfy9GDe/EC6+uNLfzCrbbeW5yGm4BFk9sjEaQWuB6atoims55l0pP9ubWjoNkXLqKe5kgar08mF9rdMaYm0eLL6aTGHWM5GNn/nb9+6nTgmvR9WRenfg93ywZ4rC8QvHfxr8+0w2ECSE+Rhuq4QW4oWWQfwOQUsYCN+9Dd7vp/1NAIFAGqA38JITYDtQBQizK1wIOSinze+dDFtvipZQnCuk5REoZIaVsLqVsHh4eXrC+WeNKbNyudYDRF+IJLus4e5WXZyQzKxeAQH9Pu1nRAu1tp03atwguY3u4x/3QrFEFNu6I0bQvJhJc2ueu9tuy5zwdW1V1rN04hI3bz2raFxLumNEDCjJPPl5uuLg4Po2aN63Chq0nNf3zNylX1rFfGtavyK590eTmGcjMyuFczE2qV7E9FrhZg3Js3Hle076UdFd+eahNVVZ98ijjR7REJwTBpYsGfwDNGpa30E60Wy6fpJQs9HodHu4uuOh1+Pm6c+OW/ZFYzZtUYcMW235pXD+ELTu0trRx60lat9CGLXTpWIfVEcMZ/3I3hE4QbMeXzRpVZOOOc5r2xQSCy9zZL3dbp1pbjL5r7aqVAom+kEB6Rg4Gg5HjZ+KoGhJgs2zzplXZsEU71TWfmB+vN25QycInJ2jdogZJtzM0n3u44uKix9/Xk7g420M0NNtD2LjN4vy/Q1v/ZfMppFEybvIvzF++j617Yti846xt7Qbl2LjrgqZ9KYngMub2svaXU5QJ8mL0oAfQ6zXfNgoty66oK+TmGcnMyuPcxSSqV7btF+u+5c79VlZ2LtPmbmHqm73uahhC86ZV2fDHMU0/Jo5ywYX8vl1rpxv/OE7rljULtm3dfpKO7Ry/LHyvdQrQpWNdVi8ewfgxPRy281u7owh5XEsA+NWtQcaVGwXb8tLSiRz+Fjt7DcPV35eLq37EvXQgMs+AISsbaTCQk5SMZ8Vgu7Y7U/9e69TqWhTgiaGEnqIqFH8nKtMNL0kpmwshfID8dGUs0B4tQK4D2H92aJ/854H5PUM8cBotS50jhPCSUmYIIWqZtl8FHhRCuEopc4HOwJ5CWpZ6AAbAHbA99sAGndrUYOe+GAaOWo23lxtTJvRg1vztjBnRHjfTI1RLcnLzGDXhW4xSIhC8NtL+jA6d2tbStEeu0LTf6M2seVsZE97Rpva90KlVVXYeuMjAMes17dc6M2vRHsYMa2VX+3ZKFq4uepsvZllpt67Ozn0XGPjiWk17fFdmLdjJmOfb2tUe/dYPZGblYjRKXg1v71i/bS127DnHMyOW4e3txtS3+jDzs828MrIzbq5FbQsK8Kbfw014ZsQyPNxdeDm8My4utu3o1LIKOw/GMvDVH/H2dGXK2A7MWryfMUMetGv7uA+3cP1mGt5errz3cjv7dresws4Dlxg49nvNL2M7MmvxPsYMaWFTu2aVIBqElmHAmO8QQlC3RqmCGVNs6rerzY6953hmxBK8vdyZ+tYjzPxsE6+MfIjwoe2Z8N63rFi7n8qVgpg04WHN9nfXce1GMt5ebgXrbGq3rs7O/RcZ+NLX5jpduIsxw9vYr9O3fyQzOw+jwcirI9ra125VTdN+eR3eXq5MGdfF9KJka5vaHu4ujHq2BUPHfYder+OpPg0pHWT7BqZTu9rs2HOWZ55frPnk7UeYOXcjr4zqQvjQDkx4bz0rvtpL5UqlmPRGH9zcXGhQryIDhi0CBHVDy9O+TS2b2mA6//efZ+DoNZpfXu/OrPk7GDOinU3bXx5u9sOBPy+z+8AFunW0PdtNp5aV2RkZy8DXfsLb040pr7Rj1pIDjHmuOdv2XyYlPZvvNmkB+0OtKjP0iUb07V6bga/+hLu7Cy8NboaL3vbNTqc2NU391kpTv9WLWfO2MSa8g027z8bc4uTZOMLHfVOw7rOP+hHgZ/sl2U7t67Bj9xmeGbZQ8/u7fZk553deGd2N8GGdmfDu16xYs0fz+1uPAXA7OQNXV73NF5yttO+xTgHGvfMN127cxtvbnUkT+tjVvv7bdsr36kjnbavJS00navR7NPpwPMcnzaF022Y0mPoKCMHV7zcTvzsKgKRDx3lo51cg4faRU9zYaP9BrjP177VOc3LzGPX6eu1aJOC1kZ0c+l2h+G9ESPnvvFvMn70ESABaomWWGwOd0LLSq01FDwDtpJStLfadDOy/m9lLTEH7m1LKIUKIPsA7QCpwQUoZLoQYAnhIKRcKIcYBg4DrwBVgr5RyueXsJaZx3lmm9WOBocDLUsqdDv5cKeOX3ZN/7hZRehgycYVTtAFE0GDktc+do13hJeTNCOdolw2H5K+coo3/08jLnzhHGxCVX0PGznaOdqWxkPK1U7Txewp5Y6FztAFRbiTy+nznaJcfDanrnKKNb3/krSVOkRZlnkdemuUUbQBRZTwyYblztEsNgYzvnaKNV1/n1SeAb3++cXWcYb9fnsw941Rtp9an4p+gZMaQ/kv412a6pZQXAZvTBQohbkgpO5iWmwE1LbdLKSffQXuIxfJpYIhp+Wfg50Jll1v8nCul/FgIoQPWA4dNZVpZlF9osTwbmO3IFoVCoVAoFArFP8+/Nui+A52FEG+jDeXIBkbbKyiEmI02BjyflVLKpfd53C+FEOXRhox8J6U8fJ86CoVCoVAoFIr/IlTQbQMp5SZg012WHVuCx32mpLQUCoVCoVAoFP89qNlLFAqFQqFQKBQKJ6OCboVCoVAoFAqFwsmooFuhUCgUCoVCoXAyKuhWKBQKhUKhUCiczL92nu5/GaqSFQqFQqFQlDRqnu57QM1e8i/BWR+wEUGDnfaxA9A+eOCsD56IciOdqu3Uj+M4+yMwzvyYihM/MOOsjx2B8z945MyP4zi1LcZMd442IGq84bQPQYnKr4Fhs1O00XeD3N+dow3g2ouMcd2dIu318SanapO30SnauPQgY0JP52gDXjNsfgtPobgn1PAShUKhUCgUCoXCyaigW6FQKBQKhUKhcDIq6FYoFAqFQqFQKJyMCroVCoVCoVAoFAono4JuhUKhUCgUCoXCyaigW6FQKBQKhUKhcDJqysB/IXMWbSfycCwGg5Gpb/amVvUyBdtiLsYzJ2IH/fs0oX3rGgBkZ+fx88bj/LHzDAtnPeVYO2KHWfuNXja0d9L/kca0b6Vpz5q3jSMnr5GRmcPY8A4F621qL91L5JErmvb4rtSqVtpCO4E5y/bSP6wh7VtWBSAhKYNJs/4gPimDCsG+fDIp7B/RBpi9cCtRf10iz2Dk/bf6UKtGWbP+hVvMWbSVJx59gA6tawHwx/ZTLFu9j9w8A0OfaU3vbg3+Gb8s3k3kEVN9vt6DWtULaS/ZTf+HG9G+VTWr/T76bCtuLnrGjero0C9zlu4j8uhVTX9cF2pVK2XWv5TInKX76B9W39r2j7dqtpf15ZNJvexrL9lD5GGTXyZ0K+qXJXvo36ch7VsWtn07bq46xo3sYFfbmfU5e8EfRP11kbw8I++/8yi1agQDkJ6RzcQPfiDuVgr+fl7MmPI4Pj4e7I86z8y5G9EJwcAnW/JYWFO72o5sT8/IZuKHPxN3MwV/P09mTO6Lj48Hv20+zqpvDpKVncvgAa14rHdju9pzVhwi8nic5vMxbalVJRCAMxcSmb7kINk5BsoEejLj9Y64ueqZtSySI2dukZGZy9jBzWjfPMS+9vJIIo9e17Rf7UCtqkFmn19KYs6XkfTvVYf2D1YG4Lft0az+8QRZ2XkM7tuQR7vVduyXub8QFRWt+WXy09SqVV7zS3o2EyetIS7uNv7+3syY9iw+Pp7M/PgHjh69SHpGNmPH9KFD+3r2tT/7jahDMVqdTn6SWjXLm30+aS1xN5Px9/dixoeD8PHxYMbHP3H8RCzp6VmMf60PrVvat92153PoqjcEnZ6cdbORcZcAEBWq4zHiPxhvXgEg57vPkHGX0TfpiEvbR8DVnbxd32M4tMWhX+5VX1ejMa4PPw9SkrfnR4f6s+f+StShaM0vUwaY/ZKezcRJX5n98tEgfHw8mTHrR46fuEx6ejbjX3uE1q0c+KX7YHTVG2h2fzvXbHf56ngM/wDjLZPd33+OvHkZXY1GuPZ+HqSRvL0/Y/jTsV8Uivvhbwu6hRBVgWlSygH3uF9d4H1giZTyrifKFEJ0klJuv4fy/kA1KeVhIYQn8LaUcuK92FochBDbgZ5SyixnHifq8GXik9JZteBZzsbcZObnW4j4RKuSq9eTiVixFy9PN6t9lq3ZT+lS3iTdzriDdizxiRmsmj+IszG3mDlvKxEfP2XWXrkPLy9r7R4P1WH8i51JTMpgxLiv7QbdUUeuEJ+Yzqq5T3L2fDwzF+wiYkZfTftGChFrIovYPWvhLsYMb0Nti0Dx79YGiPrrEgmJaaxaNJSzMXHM+GwTi2cPMvnlNhFf7rbSz8jMYenqvXw57znyDEaeGbGMLh1CcXd3/Wf88vnTnD1/i5nztxMx6wmTdjIRqw7g5VnUpms3UtgbeYlOras71j96lfikDFbNeUKzfeEuIqY/ZmF7VBH9WYt2M2ZYq3uw/SlNe/5OImb2M2uvPljELwDX4lLYG3WJTq2rFdlWoO3M+vzroqYd8Txno+OYMWcji+cOBmD5mr107lCHPj0bs/qb/axZf5DwIR2YNXcjy+cPxcPDlcefXcCjvZsghO3vVTiyfflX++ncrjZ9ejZi9bqDrPk2iqf6NmP1uoMsnz8Yg8n2rh1C8fHxKKp9/AbxtzNZNaM3Zy8mMXNpJBFTzfM9L5zcDTdXPTOWHmTr/sv0bF+NHu2qMX7YgyQmZzJi4ia7QXfUsetaW/nkEc5eSGRmxH4iPuyt+TwulYivD+PlYfZncmo2a346wRczHsZgMDLw1Z/o0qYqPt5F6xwgKiqahIQUVq0Yy9lz15gx63sWLxqt+WXFVjp3akCfhx9k9ZodrFm7m/Dnu9GzR1NeH/cYiYmpPP/CfLtBd9ShGBISUlm1/GXOnrvOjI9/YvGCF0za2zXtsGas/moXa77eTfjwrowe2R0fbw9u3LjN2xO/sht066o1QPgEkj1/PKJcVdz6jCB7ybsF2/OO7iL3e4t58T19cGnzCNkL3wCdHo+XPsFwfB9k2+7b71kfcH14ONmL3oCcbDxe/dxu0F3gly9fMfn8RxYvHGnyyzaTz5uzes3OAp+PHtXD5Jck3p64xm7QrataH+EbQPbCCYjgKriFDSd72Xtmu4/tIvfHBdZ29xpO9uI3NbvHfKaCboVT+K8eXiKEqAK8CaTdx+7T7rF8U2AAgJQy8+8MuO8FYe9qepfsOXCesG71AahdoyzJKZkF2yqW92f6e49Qsby/1T6jhraj/yOOs2cAew6eJ6xbPZN2GZJTzPcPFcv7M31iHyqWs9ZuWFfLbPh4u+Fn40JeoB11mbAudTTt6qVJTrXQLufH9Ld7UrGcX8G65NQsbqdksXDlAQa+9DU/bjz5j2gD7D4QQ1j3hpp+jeBCPg9g+uS+VCwfULDuyLErtH6wOm5uLnh5utGofkXOX4r/+/1y8CJh3eqatAvVZzl/pr/bu0h9AnwasZMRA1s4commH3mZsC61zbanZFvb/lZ3O7ZHMvDldfy46ZQD7UuEdbXwS0ohv7zTi4rl/Yrs9+mi3Yx45kGHdjuzPnfvjyasRyNNu2YwySnmYGh/5Hl6dtUy5N0fqs/hY7EA+Pt7kZqWRUZGDl6ebnYD7jvZvj/qAj27an1D9851OXwslktXEqkbWh43Vxc8Pdxo3CCEmIt22uKfVwnrqN00164aSHKquT5DqwXh5qoHwM/HHU8PLd/TsLZ28+Tj5Yafj+2AGGDPoSuEda6paVcLstKuGOzL9AmdqVjOt2Dd5WvJ1K1RGjdXPZ4erjSuW5aYy0n2/bL3NGG9m2v6tSqQnGzh9wNn6dnjAc0v3Zpy+PAFzfYGVTTbfTzw8/VyoH2GsN4PmLTLF9I+R8/uTUzajTl85KKm6a31hRcu3SS0dgW72vrQZuT9tQ0AeeMiePlaF8iwvnTqSlfAeDUaDHmQm43h0ml0wZVLTF9bl4rw8AZ3T2S2/RzS7j2nLfxSgeTk9IJtms+1a073bk2K+uXiLUJrV7Rvd+1m5B3ertkddwk8C9mdacPuTAu7czKLblcoSoC/fXiJEKI3MA7wATZKKd8TQgQAXwABwGngQSllcynlJeA5IcTkO2hOAroDeuBJ4GOgnil73A94FBhk0l8kpYwwaZYCmpi2zQaChBAVpJSDhRD7pZStTOW8gQZAZeAFKeVuIURDYB6QBZwEytnK4gshHkG7cTACH0spvxdCzAEaAX7AKCnlQYvy/sAKwB/tpuhRKWWSECISOANcNpVZL6XcJoTwA76XUnZx7HmNhKQMggLMFwi9XofRKNHpiv8l1/vVzsnJ44NPN/PC4NZ30Pa8a+3Ya8lcvJLEms+fwtPDlaGvrad188qULeXzt2oDJCalExRY2C9GdDrb97wJSelWfgz097IKGv8u2zU77l4bYP0vR6kfWo7gMr6cO287OCvQv51BkL+lvriz7bG3WfN5f832cd/RulllypbytmF74bboWFuz/Rj1Q4MJLuvLuQv2bXdmfSYmphEUYP57LLVzc/NwddEC14AAL1JStcBg6MA2PP7sAlxcdIx5wXE34Mj23JzC+llUrhjI4WOxpKVlIXSCoyeu0qdnI9t/Z3IWQf4eFtpFff7niTiiLyUx4omGBetycg18sHA/Lzxpf9hKwu3MQm3FcVusVN6Pw6fiSEvPQegER07fpM9Dtez7JSGVoCDzOaB3KeQX13y/eJNicSOUk5PLB/9Zzwvh9r/gmJiYSlCghXZhn+dr+3uTYroJ2rP3DLM+/ZmMzGwi5ofb1cYnAJmebP5tNIAQICUYjegbtkVXszHGK9Hk/rIYY/x1XKvWBXcvkEb0les4zujeoz6GPHJ3fIfH2HlIYx65G+x/CTkxsZDP9Xrrtm7D53v2nmbWJz+RkZlDxPwXHNudZmm30cJuA/r6bdDVaIzxajS5vy7R7N75HR5jPkMa8sjdtNK+tkJRDP6JMd2RUsouQgg9cNQU1L6OFkSuFkJUAnbdo2Y/oImUUgohhJSyvylo7gQghPhFSvmFEMIb2A3kfys6VUrZ3lRmLNrwjjdt6OdJKXsJIR4A3jFpfAoMlVLGCCH6A4/bsW0o8KypXP5V+QMp5S0hREdgBHDQonw2MEhKmWq6megNrAZqA71N+9UF3gK2AYOBZYUPKoQIB8IBFi1axIgntIuhr487KRbZUJ1OlEjAbVNb3Fn7wuUE5i/bw/ODWhFas6zdcr7ebvek7aLX0ahuOQJNF+pmDSty+cptm8GlM7UBfLzdSUkprG//IZOvjzuXriQW/E5OzbQKlP4u27X6NGcU79RWLlxOZPPOcyyc3o+Df8XaLWe23Z2UtLvXd9HraFTP0vYKXL5622bQXcQvd2V7NAunP8bBw1cc2u3M+vTx8SgIps12a9pCiIKgJCUlk6AAbxIS01jx1T62/TweFxcdb0z+lob1Q6hTq9w92y50hfQDvQjw92LUsA688Noagsv6EVIhgBCLLL7V3+nlZl2fFm1RSsnidUfJy5NMH9cBvV475oUrycz/6jDPP9GQ0GpBNnXBVJ9WbQWH9Rng58GoZx5g5MTfKVvKm5ByvlaZ8CJ+8fUkxSIDbd8vGQWB4oWLccybv4Hnh3elTqj9rKuPj6dVoG5Vp4W1TcF52zahtG0TytVriYwdt5x1X71mWzwrHeHpg8z/bZRaYImWmc6apQWmrt2fxaVVL/L2/EzeH2twH/4+MiUeY+INZGKcXdvvWf/ILlzbP0bmB4PAmIfb0xMwxp5BXr9gxy/22rrOjl/q0LZNHc0vr33BurXj7s5uaTTbHXeJrE9HaXZ3G4RLi17kHd2Ja7vHyPxwsGb3U+Mxxp5F3ihqt0JRHP6J4SVhQoiPgQ8AL8ANLdv8G4CUMha4eY+aLwFzhRAvArZ64ueEEDPQAmbLMQx771J/p+n/U0D+lcFbShljWj7kYN+xwEghxFTAL3+8uBBiGvAEUPhKUAmYZtre1GL7OSnlLQAp5SmTVgBaFv+bwgeVUkaYnhY0Dw83Z0qaNa7Exm2nAYi+cIvgMkUfsd8v1trxBJe1f5EDyMrOZdrcLUx9s5fDgBugWaOKbNxxTtO+mEBwGdsBbj5VKwUSfTGB9IwcDAYjx8/EUbVS4N+uDdC8aRU2bNWGcUSfv0m5so593rB+RXbtiyY3z0BmVg7nYm5SvYrtMczO9UsIG7ed0bQvxBNcxnF9/rL5FNIoGTf5F+Yv38fWPTFs3nHWbvlmjSqwcUf0vdl+oZDtIQG2tRuHsHH7WZPtCXe2/Y/TSCkZN/lXzfbdMWzeec5mWWfWZ/OmVdmw5YSFtnn4TuMGldiyQzu/Nm49QesWNUi6nYFer8PDwxUXFz3+vp7ExSXb1L6T7Y3rh7BlxxmT/ilaP6iNye/SoQ6rI4Yx/qWuCCEItvP3NmsQzMbdFzXty0kElzbfDK397TRlgrwY/UyTgoA7KzuPaYsPMvXltg4Dbk27HBt3nte0LyURXNpxWwF4qE1VVn3yKONHtEQnhJU9hWnerAYbNh3W9KOvU65cQMG2xg2rsmXrMQA2bj5M61ahZGXlMG36d7w/5WmHAbemXZ0Nm45o2jE3KBdsod2oClu2HjdpH6F1q9rk5RnIzMwBIDDAG4NBFtHMx3j+OPpG7QEQwZWRybfMGy1uBGVmGvkRqOHEfrLnjyP3lyUgjciUhBLTF95+SKMB8nLAaERmpCL87bT1ZtWtfV7ELxY+bx1a1C9Go327L1jYXbYyMtniyVVhu5EIb/9CdqchAu78vo5Cca/8E5nul6SUzYUQPsBzpnWxQHvgJyFEHcD+IDbbREkpd5kC2zDgZ8AVQAhRCugmpewhhKgAPGOxX57FsgFwt6MvLf7PD+pdTUNRrgEPObDtppTydSHEQ8BEtED/ppTyIyHE40D/QuXHAKuklPuEEJ/ZsRVgCTAX2COlzHVwfCs6ta3Fzn0xDBy5Am8vN6a80ZtZ87YyJrxjwZjL+6VTm5qa9qiVmvaEXsyat40x4R1sap+NucXJs3GEjzPfM3z2UT8C/DyLlO3Uujo7919k4Etfa9rjuxa8EGhL28PdhVHPtmToa9+i1wue6tOI0kG2L7rO1AbN5zv2nOOZEcvw9nZj6lt9mPnZZl4Z2Rk316KnYFCAN/0ebsIzI5bh4e7Cy+GdcXGxXTdO9UubGuzcf56Bo9do2q93Z9b8HYwZ0c6m9svD2xYsH/jzMrsPXKBbR/uzC3RqVU2z/eV1eHu5MmVcF9OLkq0d2N6CoeO+Q6/X8VSfho7rdN8FBr641uyXBTsZ83xb27YPa2O2/a9YzfYOtocjOLU+29Vmx56zPPP8Yry93Jn69iPMnLuRV0Z1IXxoBya8t54VX+2lcqVSTHqjD25uLjSoV5EBwxYBgrqh5Wnfxv4wCke2hw9px4RJ37Pi6/1UDgli0gRtVptx767nWlwy3l7uTJrQ2772g5XYGXmFga//irenK1NebsOsZZGMefYBth2IJSU9h+82azcyD7WsTLP6wZyMiSd80qYCjc/e7UKAb9FuuFPLKuw8GMvAV3/UtMd2YNbi/YwZ8qDdfmvch1u4fjMNby9X3nu5nV27ATp1rM+OnSd4ZtCneHu7M3Xy08z8+AdeeflhwsO7M+GNFaxYuY3KlcswaeKTnD59lRMnYwkfaX6J8LM5IwgIKNoeO3Wox46dJ3lm8FxN+70nmfnJT7zycm/Cn+/KhLdWsWLVDk373SfIyclj5EtLkKYhEePGPmzXbsOpA+jqPoj7ix9DdiY56+fgGjac3A1foq/XCpeO/bQgMjGOnHWzAXAb+CYisCxkZZLz3Wd2te9L35CLMfYc7i9/ChKM12Iwnomy7/NdJ3nm2dl4e3swddJTzPz4R155OYzwEd2Y8OZKk19KM+nd/ppfXoxAmjLW48b2sW/36YPo6jyI+6hZkJ1Bzrdzce01jNxNK9DXbYlL+34gDZrd387V7L5yDvfRnwAS47Xzdu1WKIqDyG/ATj+QafYSIAFoiZYdbgx0AsqgDaEAOAC0k1K2tth3MrDf1uwlpiEbu9GGZWQAQ0xDMNYB5YBH0IZflAX2AJ2klC0Ka5qyxjvRAvhhhcZ075dSbhBCeAAbpJSdhBBdgFlAPBAJVJBSDrFh3wKgPlpQ/w5wCfjJtN8BoLaUckD+7CVoNx9zgHPAVeColHJhvj2F/u6LQAsp5Q2HzgcpE+2PrSsOImgwMmG5U7QBRKkhyBsLnaNdbqRTtUn+yina+D/tNLvB5JdbS5yjXeZ55PX5dy54P9rlRyNvRty54P3qlw13ap2Sus452r79ndsWY6Y7RxsQNd5AXv7EOdqVXwPDZqdoo+8Gub87RxvAtRcZ4+yPIy8OXh9vcqo2eRudoo1LDzIm9HSONuA1464nT/u3UTLjU/8l/G2ZbinlRUyzgxRGCHFDStnBtNwMqFlo38kOdI1AGxvrLTPIfW1sn1zo9220lxvzf7cqXM40nV8n08+dUsqmJptfxc6QGCnlKBurm9kol6+7GSgy95RlwG2iBbDtLgJuhUKhUCgUCsU/zH/Lx3E6CyHeRhu+kQ2MtldQCDEbbQx4PiullEudap1txgohwtDu8i6gjdseAgyxKHNMSvlySR9YCPEW0As7NzEKhUKhUCgUiv8u/iuCbinlJmDTHQtqZcc615q7Q0o5E5hZaPVy0z9nH/sj4CNnH0ehUCgUCoVCUTL8V38cR6FQKBQKhUKh+P+ACroVCoVCoVAoFAono4JuhUKhUCgUCoXCyaigW6FQKBQKhUKhcDJ/2zzdin8UVckKhUKhUChKGjVP9z3wXzF7ieJvIOVr5+j6PeW8D0yAcz8y4doLMr53jrZXX6d9NEiUGgKZPzpFGwDPRyHrZ+doe/RBss0p0oLOkP2rU7QBcA9Dxi9zirQoPcypHw1x6kdgnPXhHdA+GuREvyRkOcf2Uh5PO007X9/43VCnaOv6feFUbWfWZ96qZ52jDbgMWum0j2+JsuFO0VX896GGlygUCoVCoVAoFE5GBd0KhUKhUCgUCoWTUUG3QqFQKBQKhULhZFTQrVAoFAqFQqFQOBkVdCsUCoVCoVAoFE5GBd0KhUKhUCgUCoWTUVMG/guZvWALUX9dJM9g5P23H6VWjbIApGdkM/E/PxF3KwV/P09mTO6Hj48Hv206xqp1B8jKzmPwgFY81ruJfe25vxAVFa1pT36aWrXKa9rp2UyctIa4uNv4+3szY9qz+Ph4MvPjHzh69CLpGdmMHdOHDu3r2df+7DeiDsWQl2fk/clPUqtmebPdk9YSdzMZf38vZnw4CB8fj4L9PprxPa6uLox/tY997XmbiPrzgmb3xH7UqhFs1p76nVn7/Sc5fe4Gc+aZp706c+4GKxaHU6d2ebv6cyJ2EHk4FoPByNQ3elGrepmCbTEX45kTsZP+jzSmfasaAMyct5Xjp26QnpHN+NGdadW8qgPbNxL153nNLxMfp1bNcha2ryfuZgr+fl7M+OApfHw8SEhM4733vyUhIY3y5QP4dPpA+9qfb9C0DUben/iEtfaUdWa/fPA0Pj4ejB77BQkJabi56WnYoDITXn3YrnY+X63Zwa+/RpKTk8f41/vRokXtgm15eQY+eP9romOu4+qiZ9r0IQQHB/DnnzF88vH35OYa6N27Oc8N6WLD9t+19mIw8v57T1rbPvkbs+3/eUaz/ZVlJCSk4ubmotn+mv32MidiJ5FHrmj1OaFH0fpcvIv+fRrTvlV1AGbO28bx0zdIz8hh/OhOtGpWxb7P5/5K1KForT6nDDC38/RsJk76ymz3R4Pw8fFkxqwfOX7iMunp2Yx/7RFat6ptV1vTd+I5unArUX9d0rTf6mPdt3z4s6ktejJjcl+tb9l8nFXfHCQrO9fUtzQuMb/M/PhHjh67pNn9cphDu/P57ptINv9+jNwcAy++2o2mhc67G9dvs2LJLmrXKc9j/ZsDcOzwZebP+YO8XANdezbgqUGt/1btOZsuE3UxBYNRMqVvDWoFe1ltj0/NodvMP9k/sQXurjr+upTCxxsuk2sw0rtRaZ5rV8GuP+5V22CUbDmZyLKdV1k7upFd3XycWadzt13h0OVU8oySKWFVqVm2kO1pufT47Ah7X38Adxcdy/ddZ2d0MilZeQxtXZ6wBqXs+2XJHiIP55//3ahVrXTBtpiLCcxZsof+fRrSvmU1q/0++mw7bq46xo3scEffKP5/ojLd/zKi/rpIQmIaqyKGM/WtR5gx1xw8Ll+zj87tQ1kdMZy2LWqw5ttIklMyWb3+IMvnD2F1xDC+XLOPtLQs29pR0SQkpLBqxVimTh7AjFnmObCXr9hK504NWL3yVdq2CWXN2t0A9OzRlJVfjmXJotHMnmt/buioQzEkJKSyavnLTJ30JDM+/slCe7um/eUY2rYOZc3Xuwu2XbuexN59Zx375M8Lmk+WvsDUd/sy49PfzNqrdtO5Y11WLxtJ21a1WLNuP82bVmXlkhdYueQFZv5nAK1b1nQYcEcdjiU+MYNV8wcxZUIvZs7bWrDt6vVkIlbuw8vLzWqfUUPa8uXnz/D5tMeJWLnPse0JqaxaOoqpEx9nxqfmeaqXr9pF5w71WL1slMl2TWfW7N945cUerF3xosOAO+rP8yQkprJq2Wimvvs4Mz79xay9ciedO9Zj9Rcv0rZVbdZ8s7dg28LPhrFy6ei7CrivXk1g27ajrFw1jvkLRjNzxrdW23/9JZJy5QNZtWoczw3pwoL5vyGlZNbM75g3fxRrvnqdjRv/JC7utrXth85rfvniJaZO7M+MTyzay8odmu3LX6Jt69qs+WaP2fbPn2flshcdBtxRh2OJT8pg1bxnmDKhBzPnbTf/PTeSiVh5AC/PwvXZhi8/e5rPP+pLxMr99rXz2/mXrzB18lPMmGWej335im1aO1/xitbOTefQ6FE9WPHFy8ybO5zFSx3Px+3Uc/SvS9p5tGgoU996mBmfbTJrf7Wfzu1qszpiGG1b1mDNt1Fa37LuIMvnD2Z1xFC+/MpB33IffunZoykrl49hycKRzP7szvO3X792mz07zjB/2VBmzH2azz/ZZLU9NzePzz7ehLuHK/kflZNSMu/TzUyf8zQLvxzOts0nuXUz5W/TjrqQQkJaLivDGzD5serM/O1ikWMv3nGVQC+XAs1Zv19i3uA6rBnZkE3HE7iZkmPTH/eqDbA+Mo7YxCzyjHf+Hpsz6/TQ5VQS0nP58rm6TA6ryqwtsUXKLNl7jQAL2/s/UJZlz9Zh5ZC6fLn/un27j1whPjGdVZ8/xZTXuzFz/s6CbVdvpBCx+mCR8x/gWlwKe6MuOXaK4v89Kuj+l7F7fwxhPRoCULtmMMkpmQXb9kedp2fX+gB0f6geh4/Fcik2kbq1y+Pm6oKnhxuNG4QQc/GWbe29pwnrrWVoateqQHJyhln7wFl69nhA0+7WlMOHLwDQsIGW8fPx8cDP1wt77N57hrDeD5i0yxfSPkfP7k1M2o05fORiwbZPZv/C88OKZkGttPedI6xnY5NPypGcYqEdGUPPrpq/undpwOGjl632nRexhVHDOzvU33PwPGHdtIxM7RplSE4xBxYVy/szfWIfKpbzt9rHx9sdgIuXEwmtWdaB7WcJ69XEwnaL+jwYTc9uWrape9eGHD5ymeSUDJKS01mweAvPDJ3PD78csq+99yxhPZtq2oV9fjCant0am7WPahcTnRD4+Xo69Icl+/aepkfPZgghKF3aD39/b1Is/L9nzykeDnsQgA4d6nP6zBViY+OpVLkM/v7e6PU6OnVuyLFjFwv55QxhvezZbtFeujbi8BGT7bq7s33PwQuEda2raVcvY+XziuX8mT4xjIrl7dRnbBKhNctgj917Tlu08wokJ6eb7T5wlp49tL+pe7cmBe3cx1t7qnPh4i1Ca1d0aLtTz9EDMYR1N/UtNQr3LRfMfUvnulrfciWRuqGF+5b4EvNLwwaVLey+c71G7T9P5271EUIQVMoHP39PUi3+BldXF/4z60lq1g4uWHf1ShIVKwXh5+eJXq+jTYfanDx+9W/T3nPuNmGNtSxr7XLeJGfmWW0/cTUNAYQEaW0kNjGbSkEe+Hu6oNcJOtUJ5Ghsqk1/3Ks2wFMtyzG8Q0X0ujt/pNCZdbonJpnepkx1rbJeRWw/eT0dAVQKdC9Y5+2uB+B6cg5VLP6mItqRlwjrWkezu3pp6/68nB/T3+lFxfJ+Rfb7dNFuRjzzoF1dxb8DFXT/gwghfhFCVDct1xJCfCWEWCCE2CqE2CKEqGba9pZp3Z9CiD6mdcuFENOFEAeEEPq7PWZiUjpBAd4Fv/V6HUajEYDcHAOuLppUQIAXKSmZVA4J5PCxWNLSskjPyOboiSvkGYy2tRNSCQryMWu7WGrn4eqar20dWOXk5PLBf9bzQnh3+3YnphIUaKGtt6Pt702K6WK27tv9NKhfiXLB/kUFrXySRlCgPZ9YansVaAPEJ6RyKz6FOqH2H88CJCRlEBRgDlY0fceZoD0HL9BvyDImz9rIgL5N7duemObALwZr21MziL2SyMVL8bz31mMsWzCCtev2c/NW0cycWduOX3Jt+9zHx4Mh4QsZ+sIiDkbFOPwbARISrdtMQIA3KRaBYEJiKoGm7Tqd1l0lJBTdxzJ41Gwv1F5c9Hb8Ym6LPt4eDBmxgKHhCzkYFW3f5tsZBAVa1KfLXdbn0OVMnrmJAY85qs9C55Beb9vnFufQnr2n6fvEDCa//w0Dnmzr0A6nnqNJ6dZ+KXweWfYtqVlUrli4b7lqv2+5D78U2P3ht7wwwr7d+SQlpRNoYb9/gBepKbYz7wX7JKYTcBf7OEs7MT2XQG9zttZFJwraYkaOgU82XOKlrpUKtiek5RLk42rW9HIlpVBAer/a94oz6zQxI5cgiyy2XicwSrPtn26N5cWOIVb7nI3L4KmlJxix+gzPtixnV7tofy7ueP6v/+UY9UODCS7r67Cc4v8/akz3P8vnwFBgIvACcBpIllKOEkLUA94FhgNLpJQfCSGqAEuA/Ge8MVLKN2wJCyHCgXCARYsWET5ACzx9fNxJSTUHjjqdKAhmhE5gNBrR6XSkpGQSFOhNgL8Xo4Z15IXXVhNcxo+QCoGElA+0+cf4+HpaBUw6YU87o6CzvXAxjnnzN/D88K7UCbWfpfPx8bTqeO3bnUFQoA8XLt7kjy1HWThvBAcj7QdQmraHVTBt1+7UTKsg9LufDtHvkeYOtQF8fdxJSTVfLDV9x5mgti2q0bZFNa5eT+bVid/zzZIhd2e7Pb+kZhIU6IOLXkfjBpUJNN14NWtajcuxCZQtUzQz4+PrYb+tiMI+1/SmvT8AgLibyTw/egk/rx9XRPfo0QvMnPkdAC1bhlq1mZSUjIIgG8DXx4OUlAy8vT2QUuLiosfX18N6n+QMatS0Ht6jtZe7qFNTewGY9sHTZttHRfDzt6/bcjm+3u6kpNxnfd5I5tWJP/LN4sE2yxWx28rnOpt2t21Th7Zt6nD1WiJjX/uCdWuL+rxA35nnqE2/2OtbvEx9SwdeeG0NwWX9CKkQQEj5gBLzy4WLN5m3YAPPD+ti1+6Tx64wb7Y2JOeBB6tZ2Z+akklAkP3MvmaXu1UgnJqSSTXT+H5naheU8dCTkmko+C0s2uL0Xy/yfMeK+HiYL/O+HnqrrG9KZh41ytrOGN+r9r3irDoF8HHXk5Jltl0nBDqh2T5j82WGtymPj7t1rqp2sBdfD6/P7YxcRq09y5KBdQqy35b4ertZ9+c6x+f/hcuJbN4ZzcLpj3Hw8BVHLlH8C1CZ7n+WjUBrIYQX0BAIBgYKIbYD8wE/IYQOGCuEmA6MACxvlfdiByllhJSyuZSyeXh4eMH65k2qsGHLSQCiz9+kXFlzsNW4fghbdpzWDNt6ktYttJf6unSsw+qI4Yx/uRtCJwguWzRAA2jerAYbNh3WtKOvU65cgFm7YVW2bD2maW8+TOtWoWRl5TBt+ne8P+Vphx2opl2dDZuOaNoxNygXbKHdqApbth43aR+hdava/PLrIYxS8trrK5i3cBNbtx1n8x9HbWs3rcqGP46ZtOOsMuONG1Riy3bNXxv/OE7rljULtm3dfpKO7UId2g3QrHElNm7T/Bp9If6O2Y68PCOZWbkABAZ4YnCQRWn+QDU2bD5qtr2she0NLW0/RuuWNalapQznzmsvaBoMRo6fvELVKqVtaze11C7k84aV2bLthKa95RitW9Yy2a5d6Hx8PHB1sd29NGpUjZUrx7Fy5Ti6dWvKpk1/AZCQkEKewYi3t/nRbrPmtdi48U8Adu08QdMm1alSJZgzZ66SlpaFwWBk795TPPBAjUJ+qc6GzZbtxdIvldmyzdRe/jha8OKhte32Hx41a1yJjdvPaNr3Wp/+nhgMDuqzWXXrc6hIO7c4h1qHkpdnIDNTG5MbGOCNwWg7U2zWd+I52rQKG7Y66ls0n23ceorWD2ovmHbpUIfVEcMY/1JXhHDUt9ybX7Kycpg243venzzAod31GoYwb+lQ5i0dSqcuddlu6hsTE9LIyzPi5eVud1+ASpVLEX0ujvR07XyK3H+ehk0rO127wC9V/dh0PEHzS1wG5fy1scQJaTmcuJrGusg4XvvqDDE3M3hr/TmqlPbg7PV00rMNGIySvdG3eaCqHZ/fo/a94qw6BWhW2ZdNpxI17VuZBPtq2f2E9FxOXk9n/Z+3GP9tNDG3Mnnnx/MApGZpNyO+Hi5WmfEi2o1D2Lhde08o+kICwWUcn/+//HEaKSXjJv/K/OX72Lo7hs07791fiv8fCGmnYSn+HoQQLwEtgK1AAJAgpVxp2uYF1AXCpZQvCCGaAfOklK2EEMuBaVLK03dxGEnK1wAYjUamzPiVczFxeHu5M/WtR1i17gCvjHyItPRsJrz3LdnZeVSuFMSkCQ/j5ubCuHfXce1GMt5ebkya8DCVQoLMyn5PgWGzWfv9bzh37jre3u5Mnfw0q9bs4JWXHyYtPYsJb6wgOzuHypXLMGnik5w+fZXRL0dQrap5zPJnc0YQYDH8BX03yP1d0/5gPeeib2ja7z3Jqq928crLvUlLy2LCW6vIzsrVtN99Ajc3cwbmwMFz7NpzuujsJa69ION7TfujH80+ebcvq77exyuju5GWls2Ed78mOzuXypVKMemtx3Bzc+F2cgYvj1vJyiUv2Pa4V19kwnKTXyRTP97IufO38PZyY8qEXqxef4gx4R1wMz1C/WzJLpo0qED7VjXIyMxh1OvrMUqJEPDC4Da0bWF+C16UGgKZP5p9/tEPml+83Jk68XFWrd3LKy92N9m+1uSXUkx6qy9ubi78sfU4i5ZtQ6/XMeCJVjzWp5m17Z6PQtbPmvaH35t9PvEJVn21m1de6qlpv7PG5JfSTHq7H25uLox4cQlZWTkYDJJRI7rSvm2hmxKPPki2Wa36/PNf2L37JB7urrz19pOEhlYkImIDffu2xtfXk7fe/JJb8SmUCvLl/Q8G4efnxbZtR5k/71fcPdwYMKADDz/8IILOkP2r2S//+Y5z0aa2+F5/k+29tPbytoXt7zyu2T46gqysXAwGI6PCu9G+bR1r293DkPHLTPW5iXPn40312YPV3/7JmBHtzfW5dDdN6legfavqWn1O+FarTwQvDG5lVZ8AovQwyNtoaufrTOeQB1MnPcWqNTt55eUw7Rx6c6Vmd+XSTHq3P3l5Rka+GFHw8t3I8O60bVPIbpcezjtH9d0g+Suz9ozfOBdzE29vN6a+1YdV3xzklZGdtb5l0vea7SFBTJoQZupb1nMtLhlvL3cmTehNpYpB1rb7P31ffjl9+hqjxyy2tnv2cOu+xaUHCVlfWR1u6cLtHNgbjbu7K2Mn9KRGrWBWLN1F2KNNKFVaC65+/fEvcrLz6PukNj53z44zLFu0A3cPVx7r35zuvRpSyuNpp2kDlPJ4GuN3Q7W2+NN5ouMy8HLTM6VvDVbvu86YbpVxs7jpHRxxnMVD6+HuqmPbqUQWbL2Cu6uOAS2CCWtinT3X9fvivrXzeWr+Ub62MXuJrt8XkLfR3F5Ksk5depC36llNW0o++P0S525m4O2uZ1LvqqyJvMnLnSvipjfbOWTFKRY9E4q7i46Xvj5LapYBCTz5QBkebmidjHAZtBJ5M0LzyydbOHfBdP6P78rq7w4z5vm25vN/2V6a1C9fZPaSA3/FsvvAhSKzl4iy4fwPc+cB/IoCVND9DyOE8EMbVlIN0ANfAOWAdGAmcBD4DTACG4C+xQm6SxyLoNspmIJup2AKup2CRdBd0lgG3U7BFHQ7BRtBd0lhGXQ7BVPQ7Qzyg26nYBF0lzgWQbdTMAXdTsFG0F1S2Aq6S1rf+N1Qp2jnB93O0nZmfeYH3U6RNwXdzkAF3f8e1Jjuf55ewGIpZbbp91M2ynS0WJ4OIKUc4mS7FAqFQqFQKBQlhAq6/0GEEHOBWsCT/7QtCoVCoVAoFArnoYLufxAp5Zh/2gaFQqFQKBQKhfNRs5coFAqFQqFQKBRORgXdCoVCoVAoFAqFk1FBt0KhUCgUCoVC4WRU0K1QKBQKhUKhUDgZFXQrFAqFQqFQKBRORn0c59+BqmSFQqFQKBQljfo4zj2gpgz8t5D2rXN0fR5HHpnkHG1ANJ6CcdOLTtHWdZ+Hce/rztFuMxOZuMIp2iJoMMbtY52iDaDrNBvjhlHO0e65AHnmP07RFqHvOK2tgNZe5PX5TtEW5Uc7rU51nWZjWDPYKdr6Z1Zg/ONlp2gD6Lp+hjzwplO0RctpyEuznKNdZTzy2udO0QYQFV5y6td0nXq9cJJfRIWXnP51VGd+ZdiZX0dV/PeghpcoFAqFQqFQKBRORgXdCoVCoVAoFAqFk1FBt0KhUCgUCoVC4WRU0K1QKBQKhUKhUDgZFXQrFAqFQqFQKBRORgXdCoVCoVAoFAqFk1FTBv4LmT1/M1F/XSDPYOT9d/pSq0YwAOkZ2Uz84Hvibqbg7+fJjKn98fHxYH9kDDPnbkAnBAOfas1jYU3tas9Ze5TIU7cwGCVTwx+kViV/AM5cus30lX+RnWOgTIAnM8a0ws1FT0JyFpMiIolPzqJCaW8+GdvGvvYvMUTFJGEwSKY8XZda5X0AOHstjWnfnSUrx0BIKU8+HFQPF72OlyKOEJ+ag5uLoGEVf15/rJZ97e9OE3U2AYPByJQhjalV0U/Tjk1h2trjmnZpLz58vikueh3ZuQZ+3neFLX/eYMHYlnf0+ZxF24k8HIvBYGTqm72pVb1MwbaYi/HMidhB/z5NaN+6BgCz5m3lyImrZGTmMDa8U8F6m9o/niXqXCIGo2TKoAbUquCr2X41lWnrTpn84sWHQxriotcx89vTnLiUTHqWgXH9QmlVp5R97V/PExVzW9N+KtTa59+fIyvXSEiQBx8OrIuLXkdCag6Tvj5NQmoO5QM9+GRIA8d+WfUXkSduan55qTW1KgcAcOZCEtO/iNLaS6AnM15rh5urnplfHOJ4dALpmbmMf+4BWjUub1/bme1l6T4ij17V7B7XhVrVzD6MuZTInKX76B9Wn/YtqwKQkJTBpI+3Ep+UQYWyvnwyqZd9bSfWJ8DcrbFEXU7FYJRMfrgatcp6WW2PT8ul+5zD7HujGe4uOr7Ye52d0bdJycxjWJvyhDUsbd/2n6OJik7SbH+6HrUq+Jht/+4MWTlGzefP1sdFb875TPv2DK56wbjHatvXXn+SyDPxWt8ytCm1QrRz9MzlZKavPW7qWzyYMbI5bi46ftt/hdV/nCcrx8DgHjV4tG1lh36ZszyKyGPXMRgkU8e2o1bVIE3/fALTIw6QnZNHmSAvZrzRGTdXPX/sucgX3x4lN9fIkMcb0ruTg3N02X4ij1zVtMd1Ltpelu3X2kuLKhw6do3ZS/cXbD97Pp4Vn/YjtIZtv8+et4moP039+cR+1v351O+Iu5mMv78XM95/ktPnbjBn3saCfc+cu8GKxeHUqW3/PLqX68XpczeYs2CztX7E89SpZVvfqX5ZuJWovy5pdr/Vh1o1yprt/vBns92T++Lj48Fvm4+z6puDZGXnMnhAKx7r3diuT+ZE7DD352/0stGf76T/I41p3yq/P9/GkZPXTP15h4L1jvjum0g2/36M3BwDL77ajabNqxZsy8sz8Om037lw/hYuLjomftCXMmX9OHTwAksWbCM3x0DHLnV5dli7Ox5H8feigm4nIYSoCkyTUg64x/3qAu8DS6SUG+yUmQz0AxJNq/pLKW/djX7UXxdISExj1eJwzkbfYMac31k8dwgAy1fvoXP7OvTp1YTV3+xjzfoDhA/pyKzPNrJ8/nA8PFx5/Nl5PNq7CUIUnQ8/6tRN4pOzWDWlC2cv32bmqsNEvNXRZDQsfKMDbq56Zqw8zNbIq/RsXZlZq48w5qmG1DYFW3btjk4iITWHla805+y1NGb+cI6IUVrwH1LKk6UvNkUIwbtrTnLsUgpNq2t6C0Y2JtDbzbH22QQSUrJZ+WZbzl5JYebXJ4l4rZWmXdaLpeNba9rLDnPs/G2a1gpi2e8xlPZ3JzE1584+P3yZ+KR0Vi14lrMxN5n5+RYiPtGaxdXryUSs2IuXp7WNPR6qw/gXHyIxKZ0Rr621G3RHnUskISWHleNbcfZqKjO/PUPEy80120t7svSVBzXbVxzj2MVkmtYIZHRYTbw9XLiRlMk7Xx6zG6RFxdzWfD7mAc3nP8YQMbKx2eejtXbw7lenOHY5labV/Pn4p2jG9K5ObVOw5dAvJ+KIv53Fqo96cPZSEjO/OETEpC7aRgELJz6ktZcvoth6IJae7aoy6qlG+Hi5ciM+nbfn7rUbdDu1vRy9SnxSBqvmPMHZ8/HMXLiLiOmPAXD1RgoRa6Lw8nS12mfWot2MGdaK2tXtB6zg3PoEiLqUQkJ6LiuG1OPczQxmbb7MooF1rMos2X2NAC/zpeHJZmUZ2qY8mbkGBn9xym7Qrfk8m5WvPsjZa6nM/P4sES8+YLb9pWaa7atPWPn8WmIme08n0LG+fd9EnYknPiWbVe900M7RtceJGG+6QRew8NVWWlv56hhb/7xO6/plWLPlPF+82Q6DwcjAD3bS5YHy+BSqlwL9Y9eJT8pk1cd9OHshkZmLDxLxn54mfcHCqT1wc9MzI+IAW/ddosODlVi2/ijLp4eRZzAy8LWf6dKmCu5uRS+pUUevEp+Ywao5j3P2QgIzF+0hYtojQH57OWTVXpo1rMDK2f0AuHErjWnzdtkNLKP+NPXnS1/Q+vNPf2Px50MBWL5qN5071tX686/3sWbdfsKHdmLlkhc07bhkPvr4F4cB9/1cL1ZGjDDrf/Kr3YDbqX7565Jm96KhnI2JY8Znm1g8e5Bm91f76dyuNn16NmL1uoOs+TaKp/o2Y/W6gyyfPxiDwcgzI5bRtUMoPj4eRbUPx2p2zx/E2ZhbzJy3lYiPn9Lsvp5MxMp9eHnZ6s87k5iUwYhxX98x6L5+7TZ7dpxh/rKhJCWm8/rLa1i6Jrxg++bfj1O2nB+vv/swe3aeZXnETsa/E8b82ZuZGzEYD083XglfQedu9ShlP3eg+AdQw0v+ixBCVAHeBNLuovgEKWUn07+7CrgBdu+LJqxHIwBq1yxHcnJmwbb9kTH07NoQgO4PNeDw0csA+Pt5kpqWRUZmDl5ebjYDboA9R24Q1raKpl05gOQ0c0AaWjkAN1c9AH7erni6u5CclsPt1GwWfneSge/9wY87L9i1e8/pRMKaaRmW2hV8SM7ILdjm5a5HCEF2roHk9FxCSnsCIAT42bnIWmkfv0VYy4qadogfyemW2i4W2jmEmLKCox6pTf+OVe6oDbDnwHnCutXX9GuUJTnF7POK5f2Z/t4jVCzvb7VPw7oVAPDxdsfPRsdfoH0ynrAW2kWtdkVfktPNPre2PZeQ0prt3h5aYHAxLoNQU7bQpvbd+jwjj5BSHiRn5HI7I4+Fmy4yaM4hfoy87tgvf10jrEM1Tb9KIMmp2QXbQqsGWrQXdzxNNvt4afV58WoKoVUDi2/7/bSXyMuEddEysrWrlyY5xWx3xXJ+TH+rOxXLmf2anJrF7ZQsFq6MZODL6/hx0yn72k6sT4C9Mcn0bqAF5bXKepGcmWe1/eT1dISASoHuBeu83bV6uJ6cQ9VSDtriqQTCmptsr+BbyOeFbC/lWbBt9k/RPN+tqkO79xy7SVirEE07xM/KL6GV/C3aihue7noux6VTt0oAbi46PN1daFwjiJhrqfb1D10lrLMWCNWuFmTdFqsF4eZm0vd1w9PDhSOnb9KqaUXc3PR4ebrSqE4Zzscm29aOijW3l2qlSE7JKtimtZduVu3FknlfHmTkoOZ27d697xxhPbUb4do1y5GcklGwzao/72Luzwu0I7Ywanhnu9qa/r1fLwr0F291qO9UvxyIIay7ZlvtGsFWfe7+qAv07Kr1x9071+XwsVguXUmkbmh53Fxd8PRwo3GDEGIuxtu2++B5wrrVM2mXsba7vD/TJ/ahYrnC/bl2Xvh4uznsz/OJ2n+ezt3qI4QgqJQPfv6epFr8DQf3xdCtp/b3tW5Xk3Nnb3A7KYNSZXzx9vFAr9fRql1NTp+4dsdjKf5eVNDtZIQQvYUQW4QQB4QQU03rAoQQ3wshtgkhFgghogCklJeklM8BF0vguOFCiCghRFRERETB+sSkNIICvQt+6/U6jEYjALm5BlxNF68Afy9SUrWTfOjAdjz+7DwefnIOjz9iv6NLSMkmyM98sdbrBEaj9Rfo/zx9i+grKbRrUo7Ym2lcvJ7KxOHNWPpuJ9ZujuFmUmZhWc3utBwCfczZA5dC2uOXH6PrpD3UruBDaV+tnI+HC0M/O8Swz//k4Lkku3YnpmQT6GuhrS+kvfAQXcf/Qe0QP0pb/H13S0JSBkEB5kf4ms+lgz00cnLy+OCTTbzwXFv7tqcW9ou19vglh+n69nZqV/SltJ9Wbs/JePp9sIcpa07wVIdK9rXTcgj0NgehRXz+5Qm6TtlH7fLelPZ140pCJhdvZjCxfyhLRjXh6z3XuJmcbUsagITkLIL8LdqL3kZ7OXmT6NjbtGuq3YTs+esa/cb+wuSFBxjQ0/5QBGe2l4TbGQT5m4NGW3ZbEnstmYuxt5k4thNLZ/Vl7U/HuJmQbttuJ9YnQEJ6HkGF61Rq+hk5Bj754zIvdqpotc/ZuAyeWnyc51eeZlDLcna1NdsdtJcvjtJ14i7N5ybb1++9Qr3KfpQLcByIJKTeRd9yNoHoqym0axhMpbLeHI5OJC0zl/SsPI6c14YZ2dW/nUmQv9kGm23xxA2iLybRrllIkfIBfh5WgbqVdlIGQQGW7eXuzv/4xAxuJaZTp2YZu2Uc9uc5edb9uUXQFp+Qyq34FOqEVnBow/1cL8z6qQ6z6M71SzpBgYX7XAu/uJjsDvAiJTWLyhUDOXwslrS0LNIzsjl64ip5BqMDu++zP/90My8Mbn3HsklJ6QRa2O8f4EWqRXCflJhOQJC2XafTmcp4Enc9mfhbqeTlGjh86BIGO3+D4p9DDS9xPpFSyi5CCD1w1DQ05HVgvZRytRCiErDrPnRnCCHeBBKllP0Kb5RSRgD50bbM/6yvj4+HVeeo04mCk1YIgdFoRKfTkZKaSVCgNwmJaaz4ai/bfpmAi4uONyatp2H9ijYfGfp6uZJikYHStEW+PSz+8RR5eUamv9QSvU6Hi07QqGYpAn21i2mz0NJcvpFK2UDPIto+Hi6kWGTOhDBrA8wa0hCjUTLnlxh+OHCdvq0q8NGzWjbjZnI2I+b/xY9vtbLpSB+vwtpYa49spml/d5of9sTSt53jsaFF/OLjTkqqucO09Is9LlxOYP6y3Tw/qBWhNYPtlvPxvIPtzzfRbP/xLD/su0rfNiG0rVeatvVKczUhk9ci/uLrt2yPo/fxcCHFIhMqdIW0n6uvaf96nh8O3qBuiA+NqvgVBOoPVPfncnwmZf1t36j4ermRYvE0RCcKtZdvj5OXJ5k+ti160/jftk0r0LZpBa7eTOPVGTv5ZlZv+7Y7qb34eruTkmYOsO5Uny56HY3qlSPQFKg3a1iBy1dvU7aUd5GyzqxPAF8PvVV2WwiBzvTkavrGywxvWwEfd+vLQu1gL74e0YDbGbmMXHOGpc/WLch+F7XdUruQ7UMbabb/HM0P+6/RpHoAfxy5yYKRTYl0cJMD4Ot5h77ll7PkGSTTX2iOXicI8HFj1COhjPxkH2UDPQkp40XF0l725PH1drOu08Jt8esjWt81oRN6vQ5fbzcuX00pKJ+Smm0VhFtr3/v5D/D9xlP061nXYRkfHw+rYFqz29Sf64r25/l899Mh+jlIoFjp38P1okD/5z/p98gDDrWd6hdvd1IsglS7fknJJCjQiwB/L0YN68ALr60huKwfIRUCCCkfYNvuwv25uNv+fI+pPy9rs8zJY1eYN1sbD//Ag9Ws7E9NySwIsgF8fN1JTcnCy8sdKSUuLnp0Oh3j3wlj8pvf4uPrQanSPpSvYPtvUPxzqEy38wkTQnwMfAB4AW5AE+A3ACllLHDzPnTzh5cUCbgd0bxpVTb8cRyA6PNxlCtrfnzXuEEltmzXHn1v3HKc1i1qknQ7Hb2LDg8PV1xc9Pj7eRIXl2JTu1mdMmzcf0XTvpJMcJA5eF67OZoyAZ6MfqIBelPnV7WCL9FXkknPysVgNHL8fCJVy9t+nNi8RgCbDmtuir6eRrkAcyCXagoidDpB2QB3MrINAAWZCm8PPS56+51i89ql2BSpPYaLvppKOYugP9UUAOl0grKBHmRkGezq2KNZ40ps3HZa079wi+AyjocAZGXlMm3OH0x9s7fDgBugec1ANv15Q9O+lkq5QPOFPzXTwvYADzKyDeQZjGTmaH9DoI8rBgcZGiuf30innL+ldlGfVy3jRfSNdNKz8zAYJScup1K1jP1Ap1n9smzce0nTv3ybYIugaO3vZykT6MXoAY0KAu48g5HMbO24gX7ud297CbeXZo0qsHFHtKZ9MYHgMo7Hr1etFEj0hQTSM3IwGIwcPxNH1ZAA23Y7sT4BmlX2ZdNJ7VWQ6FsZlDNlnBPSczl5PZ31f95k3PpzxNzK5O0fYrTjZmn+8vVwscqMF7U9gE1/xWna19Mc2K75/Neo6xiNMO6LY8z/PYZtx26x+XCcbbtDS7Gx4BxNIdjiHF279QJlAjwY/Vgd9BbBz0MPlGfVOx0Y/2R9dEJY9UdF9BuUY+MubXhb9KUkgsuYA8i1v5yiTJAXowc9UNAWG4WWZVfUFXLzjGRm5XHuYhLV7byXorUXzZfRFxMJLn3n9x0Atuw5T8dWVR2W0frzY5p2TBzlgs3DGrT+/CQAG/84TuuWNQu2bd1+ko7tQu9ow71eLwr0d5yiY1vH+s71SxU2bD1psvumtd31Q9iy44xm99ZTtH6wOgBdOtRhdcQwxr/UFSEEwWVt99PW/Xk8wWV9HdqSlZ3LtLlbmPpmL7sBN0C9hiHMWzqUeUuH0qlLXbZv0exPTEgjL8+Il5e5D2vctArbNmvb9++JpkEjbehVw8aV+HzpEN6e8ggJ8Wk0aBzi0DbF34/KdDufl6SUzYUQPsBzpnWxQHvgJyFEHcDxM74SpFO7UHbsPsMzwxfh7e3O1LcfY+bcDbwyqivhQzsy4b11rFi7l8ohpZj05iO4ubnQoG5FBgxdCALq1i5P+za238zo9EAFdv51nYHv/YG3pytTRjRn1qrDjBnQkG2HrpGSnsN3288D8FDzigx9uA6j+tVn6NRt6PU6nupag9J2HjN3rF+aHSfjGfRpFF4eeqYMqMusH88xJqwGv/95gx8OXMfVRUdIKQ8mPallQUZHHCErx4DRCK/2qWlTF6Bjo2B2HI1j0Ie78fJwYcpzjZn1zUnG9KvD7wev8sOeWE27tBeTBje6d5+3rcXOfTEMHLkCby83przRm1nztjImvGPBWFRLzsbc5OTZG4S/trZg3WcfPUGAf9GgoWPDsuw4fotBM/drtg+sz6xvTzPm0dr8HnmdH/ZfxVWvI6S0J5OeqU9OnpHR8w5hlCCAV/vavzB2rFeKHScTGDTnEF7uLkx5KpRZphclf/8rjh8O3sBVLwgp5cmkJ0Nxc9ExsntVhs07jF4neLJNhYJhBDb90jyEnVFXGfjmBq29jG7FrOWHGDOwCdsir2jtZYsW3D7UohJP9azFqPe3YZQSIeC1Z+3PouPM9tKpVTV27r/IwJfX4e3lypRxXUwvSra2WZ8e7i6MerYFQ8d9p7XzPg0pHVQ0yw3OrU+AjrUD2HnuNoO+OIm3m47JD1fj482XefmhENaFm2eaeW75ST58TBvj/OYPMaRmGZASnmoejK+H7ctGx/pl2HE8nkGfHNTayzP1mPXDWcY8XJPfD8Xxw4Fr5vYyoB5uruacz8Gziew6GU+3JrZvMjs1LsfOI3EM/GAn3h4uTBnahFlfH2fM4/XY9tcNUjJy+W6XNqb4oablGNqrFuPmR3I9IQNvT1feG2x/JgqATi0rszMyloGv/YS3pxtTXmnHrCUHGPNcc7btv0xKejbfbTqr6beqzNAnGtG3e20GvvoT7u4uvDS4mdVsLFbaraqy88BFBo5Zr53/r3Vm1qI9jBnWymZ7AbidkoWri97mi5lW2u3raP35sIV4e7kz9d2+zJzzO6+M7kb4sM5MePdrVqzZQ+VKpZj01mOadnIGrq563N3v/P7CvV4v7kXfqX5pW4sde87xzIhleHu7MfWtPsz8bDOvjOxM+JB2TJj0PSu+3k/lkCAmTQgDYNy767kWl4y3lzuTJth+ggbQqU1NrT8ftVKze0IvZs3bxpjwDnb681ucPBtH+LhvCtZ99lE/Avzs3wTWqBVM7TrlCR+8BHd3V8ZO0F7qXbF0F2GPNuGRfg/wwcQfGD3sCwKDvHnzvT4AzJ21kZPHruDiouelcd0LsvuK/x6EtJO1UBSP/NlLgASgJXAIaAx0AsoAq01FDwDtpJStLfadDOy/h9lLJkgpDzowp2B4SYnj8zjyyCTnaAOi8RSMm150irau+zyMe193jnabmcjEFU7RFkGDMW4f6xRtAF2n2Rg3jHKOds8FyDP/cYq2CH3HaW0FtPYir893irYoP9ppdarrNBvDmsFO0dY/swLjHy87RRtA1/Uz5IE3naItWk5DXprlHO0q45HXPneKNoCo8BJkfO8cca++OPV64SS/iAovQfJXTtEGwP9pZMJyp0iLUkNIyHKO7aU8nnaKrgV3HhOkKEBlup2ElPIiYHO6QCHEDSllB9NyM8AqrSalnHwH7cmAwzIKhUKhUCgUiv8eVND9z9BZCPE2IIFsYLS9gkKI2WhjwPNZKaVc6lTrFAqFQqFQKBQligq6/wGklJuATXdZdqxzrVEoFAqFQqFQOBs1yl6hUCgUCoVCoXAyKuhWKBQKhUKhUCicjAq6FQqFQqFQKBQKJ6OCboVCoVAoFAqFwtlIKdU/9c/qHxCutP8+7f9l25Vf/n9p/y/brvyi/PJv0P5ft/3f/k9luhW2CFfaf6u2s/X/V7Wdra+0/379/1VtZ+v/r2o7W19p//36zrb9X40KuhUKhUKhUCgUCiejgm6FQqFQKBQKhcLJqKBbYYsIpf23ajtb/39V29n6Svvv1/9f1Xa2/v+qtrP1lfbfr+9s2//VCNPAeYVCoVAoFAqFQuEkVKZboVAoFAqFQqFwMiroVigUCoVCoVAonIwKuhUKhUKhUCgUCiejgm6FQqFQKBSK/1KEEOKftkFRMqig+1+OEKKBEGKzEGKXEOJzIYRXCWq7CyEeE0LUFUL4CCEWCSFWCiEql9QxbBzPs4S0utv7V0L67YUQA4QQlUpC7y6O1/nvOE5xEUL4CSFcLH6XEUJ86YTjtBJCdHGC7ldCiDUW/5YJIcYIIdyKodlJCBElhNgphPhWCFG6BO2dIITwMS1/K4TYJ4TYK4R4oaSOYdIuVZJ6Jk1n+mWEEMLVtCyEENOEED8LIRqX1DEsjlVJCFHTCbrLC/1eUoLaAwr97ldS2haaJX6OCiE6FfrdroT1/xBCPC2E0JekLrC3hPUA++elEKK5M46nULOX/OsRQmwHhkspY4QQvYEeUspXSkj7W+AEUBXwBz4HEoAPpJS9S0C/FfAWcAz4GZgNSOAzKeVXxdSeZGeTlFJOLab2NKAsEAk8DHwipdxSHE0L7SbAe0AsMAEIAj4BdFLKp0pAfx+ajwUQCCSalqWUsk0xtccD+Rfv4UBnYAgwSUr5ezG1XwBGo/nlR6AdcBvIklK+URztQsf5FNgDHAIeAqoDt4BGUsph96m5B3hYSpkkhGgGvHi/Wra0pZRtTcvbpJSdTQHDJillsQIeU9A6HWgLXEdr85uBKVJKYzFNd7Zf9kspW5mWxwCZwAZgiZSyRzG1H0Xrt84C3wAvmfR3Sik/LZbhmn5jYADwNLDGtNoD6CKlLNZNgxDCDygPfAkMttD+SkpZv5jaTjtHTZliN2Aj0A2tz/IAdkgpmxZHu9BxfNH88iiwG1gopbxZArrTgGi04DsPQEp5tgR0t0opHzItr5dSPlF4vaJkcblzEcX/c6SUMsa08JsQYlwJapeVUj5uuoifkFJuBiipbDTwKTAQqAusBRoBGcB2oFhBt5RySnGNc0CH/ABVCLECWA+USNANfAaMAGoAi4GawDtSym0lIS6lbJ2/nB+klYSuiSeklK2EEAHAPuAHoK2UMrcEtJ8HmgIV0G52KkopjUKIHSWgbUldKeWrpuWlQoiNUsoeppvb+yVHSpkEIKU8JISoUmwrzeRZLP9kOoahhJ5mTwZipJSv5a8QQrwGvA18UAL6zvRLGoAQwhvoJqXsY/pdEtfMd9BuKGsAvwPVpJQ5QojdaH1acbmAdoPQEy3IBDAAJdGnVQVeBaoAb6IFrwa0G/3i4sxztA1am2uM5hOB1vaXl4B2AVLKVGCeEGIVMBeIFEJsBd6SUt4ohnSw6V/b/EMBJXGDaXmiB5WAnuIOqKBbUUEIEW5aFkBI/m8pZXEnyXcTQtRCG8aUbLFcUkF3tpTyPHBeCPGuqcNDCFHsIM1k64vAcbQg/kvAFXhTSrm1mPJZ+QtSynQhhHsx9SwxSClPA6eFEHOA5lLK2yWob0lJPybLAJBS3hZCpEkp3ypB7VRTdvWKEOKMRabVUILHAPAUQlSVUl4UQpQHypjWF8dX1YUQH5qWBVAz/7eU8u1i6AIYhRBeUsqM/CyrKbC87+EwFrQpfFMmpfzEFISURNDtTL9cMmVe26Nl6/OzpYHF1AVIl1KmA0eFEDFSyhzT+hxHO90tUsoUYIcQIkxKea0kNC20jwJDhRDDpJTLSlIbJ56jUso9QGchxNtSyg/vuMN9Yhq+MhTwBZagPalriZYU6nS/ulLKocU2zjZBQhsyKYBSFssqAHcSKuhWFO6ASrJDOomW1Sq8fKqE9KuZLrIC7eYhf7l6CWgvRcvU1UF71NkNSAZ+A4obdFcUQuSP0RNoHd8+SmCIBhBo0XGmAy3ys5ZSyk3F1HY29YUQa9Bsr2yxLKWUzxRTu5nJ5wKoZ7Fct5i6hXkRWGzKkLoA40xB7K/F0Bxc6PeGYmgVZi6wRAgxXEqZaXoq9THmYQnFodhDSO6AM/3yElrw9IWUcrdpXQU03xSXehZtO9RiuV4JaFvSwfRkIT9oLYn+JZ9fhRAvY3ETUtxhd/w95+jHQog+WNu9ogT1Hwc+MiU+8tkvhChW2xRChAGvAD7560qoLr8DWttY/r4EtBU2UEH3vxwppdVLaqasq05KmVkC2s66O8/H8qK7wc7y/WI0ZbS3CiGG5meMhBAlkXUJLbZ19rHXiUqg2EG3ML9IapkZ0Q5Q/KC+RTH3t4uU0t9Z2oVoCoRZZC/zmXW/glLKHQBCiHJAZeCClPLW/Ztopf29aez1NlMm1wCslFIuKAH5DCFENSnlhfwVQogQILsEtAv8YqFdCXCXUkaXgHwDYHGhoU0JwJES0HZaOy/ERKBTSbWVQvyENoTvICX0xOtvOkc3oNXhaUr+SR1ASqGAGwAp5bRi6k5Be99lBFpA3LWYesCdh1Garn1flMSxFBoq6P6XY+9lRCHEXCnl2mJqlwYGob1MeQT4Au3llVdNjymLS3MpZUlknmxR3jTMRgB+FssVSkLc9MLjJSAVGA94A7OklMnF0f0bOtHWFsslGtRLKS8VZ/87IbQ39XPyhyGZ1nWSUm4vwcMEAb8JIQ6hvUR14U473AkhRBCwCshFazP1hRAnpJRjiqsNIKX8Bu2FPlvHLk57eRtYJ4T4GO3pVijaeOBR96lX2LZHTMeweiFRCFESLyTOKZxJlFJmCSE+AYo7g1EmEJ8/fEII0RCojfZErSSJcVLADdoQmdlO0gZACFEd8JBSnixBWb2UcmwJ6hWmkhAiSEqZWMK6yVLKy0IIFynln0KImcCMEj6GLZ5Fu24rSgg1e8m/HNOwhvyXET/H4mVEKWX7YmpvQhvLFor2JvrzQBKwWhZzZgSTvtPesBZCPGdvW+GnA/ehHYF281EKuAJEAfHAICnl48XRvotjO/Wt9OIEacK5M6O8iTajQDywS0o5w7TeKf4QQjQFngNCpGlGgGJozQb2W94ECyFeRQt8ivvexZ2OXSz/CCHKoF24qwOXgVUlNc5YCHEQOy8kSimLNRWcEGKXrf5PlMDLw6YbsuZSSimEaAm8i5YxriylHFEcbZN+/js6jdFuAndgGupT3PYizFNfvoKWqNluoV2sMelCiLFoLwdeAhah3UQlA/tKKsAXQkwF1tjKRpeQfiTay+vn0J4alciQHlP/tQQYC5QG6kgpOxVX9y6OW+z2rrBGZboVTnsZEe1R7zKT3hEp5SnTcklN9F/D4kUqK4r7IpW9wFqUzHzXDaSUbYQQHsBJKeULJu0SyVzeAWd/ZOG+MyPSuTOj9JNStjBpjxJC9JNSfocT/CG0OW4Ho93I/lQCko1tZOdmo83C4NSgm2L4RwhRFi2j+4npdyOgtRDiRyllnuO97wpnvpAohBAeUsosixV6tJepi0uyNGe73gYGSO2F6s0loA3m4TsHS0jPko2Yb4x7A/lT+Um0KTKLwyApZSOhvYAcBdQ0vWewHa293zeFbugHCiFumX6X5Dh3pJQPlpRWId1pAEKIiWhD2Jxy06BwPiroVjjzZcQAi5f6ECX/ZnQi2hg9ZwROTbAz3zVQ3On3ckzjaCUQa1rW4fyA+O+gpP6Gkn4El14gLOUCIcQCIcTRkj6OEOIAWsCwTEp5qIRki9hoypL+t3/c7HegOYAQogXaGOODaFPZFTuji3NfSJwLLBNCPC+lzDC9DPsx2pCq4pIjtGkxu6LNzZ3fNn3s73L3FPdJ3B20nZn1zJ/+8boQ4qLFe0XF7lMsb+idiRDCH+1mxNfi2MW+MRbadJgT0drIELQZUUp6ulNbHP4bjvGvQgXdisFoF/XyaC8KxWAOZouLs9+Mvi2l3FlCWoVx5nzXEvNcsUbMY6GdPdsD/Hs70YVCiAeklH+afr+ONpyqYQkfp6Np7K9b/qP44j52p9ALqyYE2mNmZ3O4GPtaZnTfoeQzus588fYb0xO5rab/JfA1xcy4mngP7QlINNqQO4T2ld4rJaBdgGmoQyngJtq7KLHADWCclPJiMbULP2HMAg5LKYvzZOcLIYS36SbkUdNx/Ci52a4sh97kk293SbxjBNq4/K1o2ehYSu6r30uAMcA8U//yOn9D0C3N3xxQlBBqTPe/HKF9QesLtHl5zwO10L6gN9Ly0aqTjl2sl/qEEG2lNv9qiesLIbbnj5kTQkTj3Pmu/98ghPj0fjtqYT0zygy0wBhw/nSHJfWWvhBiMvAE2lz0HsClEhiPbu/rqM7+iFOxENo0aQPQMrpV8l96FkLs+7syj87CmbM6lGBbnA98KKW8IoSogzZeei0l8EVgIcRCtJuG/C+veqMFmLlSytcd7VuMYxbbL0KI5WgfPjqE9j5ABtpc+nvyh0EVU3+rlPIhIcSHUsq3hRDfSyn7loDuFillFwv9gutTMXXtvhTs7D7334rKdCtmAF9KKX/OXyGEeAL4CG2mAWdSrDejHQXcJaAfKJw437Vp+Eo4UAnt6cJ8WTKf9f1HO9FiZkacNjPKXVBSb+n3QHsZ+QPgP5TAvM7ODKyd3F6cmtF15ou3d4EzZ3UoKe1QKeUVACnlaSFECynlBNO7JMWlspRypGl5mxDidyllLyHErhLQtkdJ+KWMlHKIafkLIcQvQB9gF9rwweKSIrQ5+v1ML8nWLgFNgDOmd358hBAD0Z5YlAQj0GbQKjxz1N/R5/4rUUG3oo6U0moKLynleiFEiUzrdQecPYa5OPpOm+9aCNEDyP8cdgza04V5QoipUsriXrSc2ok6M0i7U3DpzOwiJdcW06X26WpX01CKB4orKISYgHZTliaE+BZtKBjA8hIYL+q09iKlPAh0KLTuMtAfil+fTn7x9k44s+8qKe1kIcTTaB/06mChWxL6AUKIAKl9PdYLKGdaXxIv4NujJOwuLcT/tXf/sZZV5RnHvw8wCIV2DARTiVVrrIitihgpYgVG2lGLaKqNcaCitFKtjYSKEKRCi4HxFxYtMlpRCwFBRPxRjT8gMAMJDDARRjqImkBhoGqwRqdkVBTm6R9rX+bM9N6Zc+fstfc+d55PcnLuPffetVf2Wdn33eus9b7a3SXLzW7Ak5v9Ea1UA6Us13yUsgzpJEqWlzY8EVgMzCwZaqsGxpmUKsuD/cRsoUnQHXMVe1kIm/p2WOUA8DTgL1zKNQOskfR6yke/L9/BNmfUvoj2OTMyDTljP6ySD3xds6b2lhbafI2bFIfAPk3mm10p53vSoLvPf7ptvp9ZJ/n/nUBZonUcJV3jcU2g2UbV4TOAayX9N2XfyzlN23e00HZN/wKsajY8HwJc1vT7R5M0qs2pFGeWZK6n1F9oy1nAWynn+lZKYD+x5hOQs9poK8aToDt+Kukg22tnXpD0HEp+1NrWbvc3htv+JAGDRgJuAGz/rLn4T6SDi2ifQVrNG8G1bTRi+xvNl5c0D2Dim7TRf7D/0RznMbWQebPnf7rTfGO/duhtuxTaes8sP5p4I6tLQakXqRRA+5ntmcmbUyZtexvWTtqA7SubvQZ/AHzQ9kywfdyETY+mUtzikEyeShGXKqunStoT+ASwXNJFlIJqG7f919tte/2k/YvxZSPlTk6ldPLVlIwiM1XjXgssc8nfHbOY5ONslbyzf+qRXMVN+rdVtg+f8w8HQtJT+7hQ97CEoDWaoMiMpJWU0vK/GHltN2ClJyxg1adJ388+N94OmaQPNmu3Z9a8Q0tr3SUda/tySe9jq08XPGFthJokHWX7ulmyl7SS0q82SU+nbIQ9FPgycCnwSuBNto9uof1qmW5iS5np3snZfkDSS4GjKWnx7gOWjP6D31G1N/X1vWlwAp8FVkh6h+1HVPJ0fwj4QlsHqHkR7XFmZO2O/uEAxsoks7r/CnxK0t+4FAvZlbJB8/J2utbbP921E/59tY23NcdL7bFo+7TmuUaGmLua5zZSym6h8nnZtXl+ZJu/NSGVwlgnsmWe7mNbaPoC4ALbo59KfV7SS1poG8pa8dky3ayg5B2PliToDmw/QjtFH7ZWe/1vn+uL1+7oH9q+SJIpOYChpNq6zPaFLfUNKl9E+wjSJsyMMrW79G1/qbkxW6kyYB4DLrX98RYP0/k/3Qnfz9r7LmqOl07GomYpqGJ7otzOtr/TPN/QBHz7UyYLdt/mH46n5qbea5rnS5pPd59ie/Ukbc7h45QlNn8JrKJkMpqY7WPmeL2tjZo1M93EKNt55FHlATybkmFhKtvv8byd0EIb1231/arm+fqW+riC8o9r5n34IHAw8PUJ2lw612Paxwpw/s42Xmq+n2Mef5K+VxsvXY1FytrtA2fOA/C1Ftv+GPABSoXRRcDl03BeKBtArwBup+TR/0TL7c+c6+XN8zdqv88t9fuLwDJKhpRjgBua11f23beF9shMd1Tjypu0arbf83KENrI61EwXBnVmRmrOdPW6S991K7sNdbz0/enCDve95njpcCzK9t0jG25bKTPfONClWMtK27+R9KRJG+zovCy1fWTT719JekbL7d/ZZC/aQ9LplMI706BmppsYkaA7qnLl9b8V2+8zYGgjMK59Ea0RpFXNjFJzLPZ8kzbU8TLVOYBrjpfa18XGD5qCKnu1XFAF4FFJ+wNWKdX+hDYa7eC8WNLezfNujKy9bqVx+2QASWdQlmW9us32a3GT6WYk9SEuG/0nznQTW0r2kqiu9vrfGu0361pP9+bqZZ1pM0vHVhfRtgpAIGkxJUg7iBKkLaec8yW2d/hCXTszSq2xKOkq5rhJs/3eHW13zGMPdrz0lemmOfb5k37CUPPa1cF1cRfKzdTBwPeBi2z/ctJ2m7afBXwUeAFwJ3Cm7VtbarvmOT8UOI9SKfJu4EO2vzZRh7ds/zW2v9JcH88EvmC7jVz9VUk6G3gdsCflBmq961d13Tn1vb4lj4X/oML63y7ap5Q67uN8nd9CG2cD6ygVLx8Ebq7U191nHn2cqwGNld7WjE/TeJm2R81rV0fXxaXAbn2fxyGdl6bd/WgmHVvu+43N8z8DS9hqr8RQH8Bqyob+5cBetLzWPY/Nj13GiswjJrPF+l/gENszG1kG2757mqFzO+t/l1J2zl9Jyb1+ZwttPk7S2ZLWUWaL7qXs1G+r7TWS7pV0i6T1km6SdHWTq3ZStcbK9yhV4zo39PFS6/2UtHSuR0tdh7rXrtrXxQuB5wKfk3RxsxysFZKOaN7D62cebbVNxfMi6TmSPkzZBPppSZ+ZtM2t7Crp94Hfsr2S6VnCu9H2JmCRS7GdF/bdoYVqWgZETLfam/qqtV9p6UoX63832t4kaZHtjZLavojOBGnnAOdS8ka3pWb6umpjpdZN2gIYL7Xezy72XdS8dlW9Ltq+S6VM+4OUtcXHUzJ3tGEF8FeUm+6216jWPC+XUz7VqdFvgPdTlq+c3Gwqv2s7vz8U5zUbQNdJug0Y/JKYaZWgO7pQe1NfzfZrBAxdBAu1L6I1g7SaOWOrjsVK61GnfbzUej+72KhZc7zUHos3Aj+nVC98m+2H22i3cb/tO1psb1TN8/KQ7S+10M6sbH8V+OrIS28HkPRRt5dTuzWSrmDzzcfxlBubeyjXsKggGymjM7U29dVsX9J1to8a+X6VS8qpScp6V9ukudVFFDbPDtntVEabOc4rKDckrwL+HrjV9jtaavuLwFVsnul6l+0jhrxhcKTdFcx+k3aO7R26SZv28VLz/exqo2bNa1fFsfhSygz3fsC3gatt/3DCNmc+dflTYBNlWdkmaD9LT5vnpdn4CXAs5SZ4FZv7/YNJ2h7z+Dv8/6ImlQJKs7K99U1+tCBBd1RXe2d0zfZrBQy1goXaF9GOgrQqmVGatmuPxdZv0pp2pnK8NMeo9n7WVvna0knGCEnPpBSFeZXtifJpS/qnOX5kt5Slp8Z5kTRXHnvb/utJ2h7z+IMMuqN7WV4SXai5/rd2+1U+6qw1O9fB7MTpldvHdXPG1h6LVdajTvF4qf1+1k69V3O8VB2Lki6gbKT8LmWD7FsnbXN7S3kkvdv2+yY8TOvnxfYJ2/q5pBNsT1pgapuHqNh2TJEE3dGF2pv6qrVfM2CoHCxU0UWQNttMF9DWDGDtsVhtPeo0jheo/n5C3Y23NcdL7bF4mWfJnV05wPwzYNKgu/Z5mU0bVV235eKKbccUScrA6ELtTX3V2lfF1HiUYOFw24dSZnduoszsrGjxGNOoZrrDqmPR9gbb7wFeC5xM2bj1aEvLKKZ1vFRNX0nd1Hs1x0vtsThXsZo3tnmcCvrIpNHKTLSkKyRdPvL4jEpV0LayxsSUy0x3VFN7Z3RHO69rfgRcM0vHNGt9pqurXfqVZ3WndbzUnrlsfUlPzfEygIwRNZc6DPKcd+jHlJvhbwMvA55Bmdz8BOUTmNjJJeiOmmqv/62+vpi6AUOV9b8LQI2Zri7GCtS9SZvW8VJ75rLGkp6a46WrsViNpBfbXj3Lj745QbN9npe1LbVzoDcXq/q0pG/ZfrmkVS21H1MuQXdUU3v9b0cpjWoGDLXzl0+VmjNdHaa/qnmTNlXjpauZyxr7LmqOlwGkYlvbQhvnAEdt/aLtD+xog32eF7dT1RVgT0lPt32fpCdT0jVCnUI8MYWSMjBiFl2kxhs5VtX85dNiIeSMVcX85SPHmIrx0tX72VXqvdhM0kWU830z8CiA7U/22qltUDdVXZH0R8D5wF6USc3TgRuBk22f19ZxYnol6I6YRUf5ixMsLBAd5S/PeJmFpNXASxhZ0mP7bf32qj9dBJiS3jRL25e00XYNkq5ijqqubeUXjxhHlpdEzKKjmdXaOaOjO12sR814mV0fKeaG7ETmCDCBVoJu25dI+j3gKXOs7R6aMylVXbeZZ3xSkg4D/gHYh+bGO0VxYlSC7oj+JFhYIDq6Sct4mV0fKeaGrHqAKekMSuGdA5pA8yND/nShyfZzVgeH+jfK/oW7yTrumEWC7oj+JFiI+ch4GbFAUsy1rqMAc6ntIyWttP0rSc+ofLyJ1arqupUHbN/RwXFiSiXojuhYgoWYj4yXOU196r1aOggwLWnv5nk34LcrH68VHVR1XSfpXMrmSUO7GzVj+iXojuhegoWYj4yXWUxLRpu+VA4w303Jyf0s4DrKHoNpsAZYbvtBSc+mFKz5HKWq65+30P7G5vnQ5rm1dfSxMCR7SURExAIjaQWzB5jn2G4jwETSfsD/eEoCCUnX2T5q5PtVzTKZ67PhMbqwS98diIiIiNYdYPtBKOu8gUNs3w7sMWnDkl4g6Rrgy8CV20qxOjAbJC2TtFjSMbRU1bVJ54mk1ZJubh6rJd08aYdjYcnykoiIiIVng6RlwNeBw2kpwGx8HDjO9j2SXgRcRElpOXS1qrq+D8D2iydsJxa4LC+JiIhYYCQtpgSYB1ECzOWUNd1LbF87YdtbL9O4xvY0BN1Avaquki62/eaR7z9l+y1ttR/TL0F3RETEAlUjwJR0GvBd4FrgEODlwHvbPEYNtaq6Sno+8AZgGXB58/IewFG2nz9p+7FwJOiOiIhYYGoFmE3bK+f4kYe8IVHSauAljFR1baOoj6TfAV4AfAQ4uXn5MeA/bW+YtP1YOLKmOyIiYuFZCjyPkQCzrYZtL5ntdUmtZEWpqEpVV9v/C9wg6TUdFeGJKZXsJREREQvPRtubgEW2NwKtBJjb8a4OjjGJ2lVdL225vVhgMtMdERGx8NQOMGfTRmaU1nVY1fU7ks4BbgYehVSkjC0l6I6IiFggOgwwZzPUTWJdVXX9afP8ouY5FSljC9lIGRERsUBsq1CN7fsrH/sK28tqHiNimiXojoiIiLElH/XsJL0FeDslW8yewEO2D+23VzEkWV4SERER2zWSj/pISTNVHPdg83KKnd1bgT8B/hH4GJvTB0YACbojIiJiPP8FfBN4BfCt5rXHgLN769GwbLD9C0m72v6RpFbyosfCkaA7IiIitmskH/XRtn/Yd38G6LImY8xPJH0T+EnfHYphyZruiIiIGJukNwDvpMxyQ6lEudPP6kp6ou2fN1/vAzyWipQxKkF3REREjE3SXcCRtjOTO0LS9bZfNvL9DbaP6LNPMSxZXhIRERHzcU8C7s0kHQG8H3iOpJspudEXAff22rEYnMx0R0RExHZJ+tvmy+cD+wA3AJsAbH+yr34NhaTP23593/2I4cpMd0RERIzjkeb5tl57MVzvnPlC0tHALbZ/uo3fj51MZrojIiIiJiTpZtuHSfo74HeBg20f03e/Yjgy0x0RERFjk7QG2Bd4CNgfeAD4MXCK7ft67FrfNjXPB9o+SdL1vfYmBmeXvjsQERERU2UNcHhT4nwpcBNwLrCi117171pJdwBXStqDUg4+4nFZXhIRERFjk3Sd7aNGvl9l+8itU+bt7CTJtiWdYPvf++5P9C8z3RERETEfGyQtk7RY0jGUFHmMPAelYlDz5Rt77UgMRoLuiIiImI8TgD8EPgu8EjhO0m7A8l57NVy5GQkgy0siIiIiqpG00vaSvvsR/Uv2koiIiNguSR+0fZqk1cDMjJ0oKykO67FrQ7e27w7EMGSmOyIiIiKissx0R0RExNgkPQ04E9gbeDPwx7Zv6LVTPZK0dK6f2b6my77EsCXojoiIiPn4FHAScKHtX0k6Fdhpg27gROBh4P6tXjeQoDsel6A7IiIi5kO275YeT8qxd5+dGYAzgdNtn913R2LYkjIwIiIi5uMHkk4C9pJ0HKUE/E7L9veAs/ruRwxfNlJGRETE2CTtQsnVfTDwfeAi27/st1cRw5egOyIiIsYmaQXwZeB624/23J3BkLQG2Bd4CNgfeIDyKcAptu/rsWsxEFleEhEREfNxIfBc4HOSLpa0rO8ODcQa4HDbhwJLgZuAc4EVvfYqBiNBd0RERIzN9l3Ap4GrgEXA8f32aDAOsP0gPL7O+xDbtwN79NutGIpkL4mIiIixSboR+DlwKfA22w/326PB2NDM+n8dOJxSrZOR59jJZU13REREjE3SS4FXA/sB3wautv3DfnvVP0mLgVOBg4D1wHLKmu4ltq/tsWsxEAm6IyIiYt4kPRM4A3iV7Sf13Z+hkLT7zNe2f91nX2JYEnRHRETE2CRdQNlI+V3gK5QsJr/pt1f9k3Q28DpgT+AJwHrbh/XbqxiSbKSMiIiI+bjM9pG23277WzMBt6QT+u5Yz5YCzwOuBA4A7uy3OzE0CbojIiJibLZvneNHb+y0I8Oz0fYmYJHtjcAL++5QDEuC7oiIiGjDzp6l4zxJ+wLrJN0G3NJ3h2JYkjIwIiIiYgdJugKY2SB3POXm4x5KdcqIxyXojoiIiDas7bsDPTm97w7EdEj2koiIiIiIyjLTHREREdslaelcP7N9TZd9iZhGCbojIiJiHCcCDwP3b/W6gQTdEduR5SURERGxXZKeDZxu+8199yViGiXojoiIiLFIeqrt9X33I2IaJeiOiIiIiKgsa7ojIiJibJLWUHJQPwTsDzwA/Bg4xfZ9PXYtYtBSkTIiIiLmYw1wuO1DgaXATcC5wIpeexUxcAm6IyIiYj4OsP0ggO3vAYfYvh3Yo99uRQxbgu6IiIiYjw2SlklaLOkYStlzRp4jYhbZSBkRERFjk7QYOBU4CFgPLKes6V5i+9oeuxYxaAm6IyIiYt4k7T7zte1f99mXiGmQ5SURERExNklnS1oH3A3cC6zqt0cR0yFBd0RERMzHUuB5wJXAAcCd/XYnYjok6I6IiIj52Gh7E7DI9kbghX13KGIaJOiOiIiI+ThP0r7AOkm3Abf03aGIaZCNlBEREbFdkq4ARoOGmRSBtn1sD12KmCoJuiMiImK7JD1trp/Zvr/LvkRMowTdERERERGVZU13RERERERlCbojIiIiIipL0B0RERERUVmC7oiIiIiIyv4PusJDILv+JP0AAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 864x864 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 상관관계 도출\n",
    "corr_matrix = regular_season_temp.corr()\n",
    "corr_matrix = corr_matrix.sort_values(by = 'OBP', axis = 0, ascending=False)\n",
    "corr_matrix = corr_matrix[corr_matrix.index]\n",
    "\n",
    "# 상관관계의 시각적 표현\n",
    "f, ax = plt.subplots(figsize=(12, 12))\n",
    "corr = regular_season_temp.select_dtypes(exclude=[\"object\",\"bool\"]).corr()\n",
    "\n",
    "# 대각 행렬을 기준으로 한 쪽만 나타나게 설정해줍니다.\n",
    "mask = np.zeros_like(corr_matrix, dtype=np.bool)\n",
    "mask[np.triu_indices_from(mask)] = True\n",
    "\n",
    "g = sns.heatmap(corr_matrix, cmap='RdYlGn_r', vmax= 1, mask=mask, \n",
    "center=0, annot=True, fmt='.2f', square=True, linewidths=.5, cbar_kws={\"shrink\": .5})\n",
    "plt.title(\"Diagonal Correlation HeatMap\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_name</th>\n",
       "      <th>year</th>\n",
       "      <th>SF_1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>가르시아</td>\n",
       "      <td>2018</td>\n",
       "      <td>0.032787</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2011</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2014</td>\n",
       "      <td>-0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2015</td>\n",
       "      <td>0.009646</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2016</td>\n",
       "      <td>0.009901</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2442</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2014</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2443</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2015</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2444</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2016</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2445</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2017</td>\n",
       "      <td>0.008547</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2446</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2018</td>\n",
       "      <td>-0.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2447 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     batter_name  year      SF_1\n",
       "0           가르시아  2018  0.032787\n",
       "1            강경학  2011  0.000000\n",
       "2            강경학  2014 -0.000000\n",
       "3            강경학  2015  0.009646\n",
       "4            강경학  2016  0.009901\n",
       "...          ...   ...       ...\n",
       "2442         황진수  2014  0.000000\n",
       "2443         황진수  2015  0.000000\n",
       "2444         황진수  2016  0.000000\n",
       "2445         황진수  2017  0.008547\n",
       "2446         황진수  2018 -0.000000\n",
       "\n",
       "[2447 rows x 3 columns]"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#희생 플라이 구하기\n",
    "#OBP(출루율) 계산 공식 이용하여 SF(희생 플라이)계산 >> (H+BB+HBP)/OBP-(AB+BB+HBP)\n",
    "regular_season_df['SF'] = \\\n",
    "    regular_season_df[['H','BB','HBP']].sum(axis=1) / regular_season_df['OBP'] - \\\n",
    "    regular_season_df[['AB','BB','HBP']].sum(axis=1)\n",
    "regular_season_df['SF'].fillna(0, inplace = True)\n",
    "regular_season_df['SF'] = regular_season_df['SF'].apply(lambda x : round(x,0))\n",
    "\n",
    "#한 타수당 평균 희생 플라이 계산 후 필요한 것만 추출\n",
    "regular_season_df['SF_1'] = regular_season_df['SF'] / regular_season_df['AB']\n",
    "regular_season_df_SF = regular_season_df[['batter_name','year','SF_1']]\n",
    "regular_season_df_SF"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\HOME\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\ipykernel_launcher.py:2: FutureWarning: Indexing with multiple keys (implicitly converted to a tuple of keys) will be deprecated, use a list instead.\n",
      "  \n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_name</th>\n",
       "      <th>year</th>\n",
       "      <th>AB</th>\n",
       "      <th>OBP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>가르시아</td>\n",
       "      <td>2018</td>\n",
       "      <td>85</td>\n",
       "      <td>0.418367</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2011</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2014</td>\n",
       "      <td>0</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2015</td>\n",
       "      <td>156</td>\n",
       "      <td>0.342541</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2016</td>\n",
       "      <td>81</td>\n",
       "      <td>0.222222</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1381</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2012</td>\n",
       "      <td>4</td>\n",
       "      <td>0.400000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1382</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2013</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1383</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2016</td>\n",
       "      <td>9</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1384</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2017</td>\n",
       "      <td>71</td>\n",
       "      <td>0.316456</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1385</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2018</td>\n",
       "      <td>24</td>\n",
       "      <td>0.230769</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1386 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     batter_name  year   AB       OBP\n",
       "0           가르시아  2018   85  0.418367\n",
       "1            강경학  2011    1  0.000000\n",
       "2            강경학  2014    0  1.000000\n",
       "3            강경학  2015  156  0.342541\n",
       "4            강경학  2016   81  0.222222\n",
       "...          ...   ...  ...       ...\n",
       "1381         황진수  2012    4  0.400000\n",
       "1382         황진수  2013    0  0.000000\n",
       "1383         황진수  2016    9  0.000000\n",
       "1384         황진수  2017   71  0.316456\n",
       "1385         황진수  2018   24  0.230769\n",
       "\n",
       "[1386 rows x 4 columns]"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#day_by_day에서 연도별 선수의 시즌 전반기 출루율과 관련된 성적 합 구하기\n",
    "sum_hf_yr_OBP = day_by_day_df.loc[day_by_day_df['date'] <= 7.18].groupby(['batter_name','year'])['AB','H','BB','HBP'].sum().reset_index()\n",
    "\n",
    "#day_by_day와 regular season에서 구한 희생 플라이 관련 데이터를 합치기\n",
    "sum_hf_yr_OBP = sum_hf_yr_OBP.merge(regular_season_df_SF, how = 'left', on=['batter_name', 'year'])\n",
    "\n",
    "#선수별 전반기 희생 플라이 수 계산\n",
    "sum_hf_yr_OBP['SF'] = (sum_hf_yr_OBP['SF_1']*sum_hf_yr_OBP['AB']).apply(lambda x: round(x, 0))\n",
    "sum_hf_yr_OBP.drop('SF_1', axis = 1, inplace = True)\n",
    "\n",
    "#선수별 전반기 OBP(출루율) 계산\n",
    "sum_hf_yr_OBP['OBP'] = sum_hf_yr_OBP[['H', 'BB', 'HBP']].sum(axis = 1) / \\\n",
    "                       sum_hf_yr_OBP[['AB', 'BB', 'HBP','SF']].sum(axis = 1)\n",
    "# OBP 결측치를 0으로 처리 \n",
    "sum_hf_yr_OBP['OBP'].fillna(0, inplace = True)\n",
    "\n",
    "# 분석에 필요하지 않은 열 제거\n",
    "sum_hf_yr_OBP = sum_hf_yr_OBP[['batter_name','year','AB','OBP']]\n",
    "sum_hf_yr_OBP"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1.3.4. 추가 변수 생성"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id='m5'>나이별 평균 성적</a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 나이 변수 생성\n",
    "regular_season_df['age'] = regular_season_df['year'] - \\\n",
    "                           regular_season_df['year_born'].apply(lambda x: int(x[:4]))\n",
    "\n",
    "# 나이, 평균 출루율, 출루율 중위값으로 구성된 데이터프레임 구축\n",
    "temp_df = regular_season_df.loc[regular_season_df['AB'] >= 30].groupby('age').agg(\n",
    "    {'OBP':['mean','median']}).reset_index()\n",
    "temp_df.columns = temp_df.columns.droplevel()\n",
    "temp_df.columns = ['age', 'mean_OBP', 'median_OBP']\n",
    "\n",
    "# 나이에 따른 출루율 추이 시각화\n",
    "plt.figure(figsize=(12,8))\n",
    "plt.plot('age', 'mean_OBP', data=temp_df, marker='o', markerfacecolor='blue',\n",
    "         markersize=12, color='skyblue', linewidth=4)\n",
    "plt.xticks(temp_df['age']) # 나이 표시\n",
    "plt.grid(linestyle='-', alpha=0.4)\n",
    "plt.ylabel('평균OBP')\n",
    "plt.xlabel('나이')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_name</th>\n",
       "      <th>year</th>\n",
       "      <th>AB</th>\n",
       "      <th>OBP</th>\n",
       "      <th>age</th>\n",
       "      <th>lag1_OBP</th>\n",
       "      <th>lag2_OBP</th>\n",
       "      <th>lag3_OBP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>가르시아</td>\n",
       "      <td>2018</td>\n",
       "      <td>85</td>\n",
       "      <td>0.418367</td>\n",
       "      <td>33</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2011</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>19</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2014</td>\n",
       "      <td>0</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>22</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2015</td>\n",
       "      <td>156</td>\n",
       "      <td>0.342541</td>\n",
       "      <td>23</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2016</td>\n",
       "      <td>81</td>\n",
       "      <td>0.222222</td>\n",
       "      <td>24</td>\n",
       "      <td>0.342541</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1381</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2012</td>\n",
       "      <td>4</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>23</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1382</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2013</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>24</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1383</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2016</td>\n",
       "      <td>9</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>27</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1384</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2017</td>\n",
       "      <td>71</td>\n",
       "      <td>0.316456</td>\n",
       "      <td>28</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1385</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2018</td>\n",
       "      <td>24</td>\n",
       "      <td>0.230769</td>\n",
       "      <td>29</td>\n",
       "      <td>0.316456</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1386 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     batter_name  year   AB       OBP  age  lag1_OBP  lag2_OBP  lag3_OBP\n",
       "0           가르시아  2018   85  0.418367   33       NaN       NaN       NaN\n",
       "1            강경학  2011    1  0.000000   19       NaN       NaN       NaN\n",
       "2            강경학  2014    0  1.000000   22       NaN       NaN       NaN\n",
       "3            강경학  2015  156  0.342541   23       NaN       NaN       NaN\n",
       "4            강경학  2016   81  0.222222   24  0.342541       NaN       NaN\n",
       "...          ...   ...  ...       ...  ...       ...       ...       ...\n",
       "1381         황진수  2012    4  0.400000   23       NaN       NaN       NaN\n",
       "1382         황진수  2013    0  0.000000   24       NaN       NaN       NaN\n",
       "1383         황진수  2016    9  0.000000   27       NaN       NaN       NaN\n",
       "1384         황진수  2017   71  0.316456   28       NaN       NaN       NaN\n",
       "1385         황진수  2018   24  0.230769   29  0.316456       NaN       NaN\n",
       "\n",
       "[1386 rows x 8 columns]"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 나이를 포함한 변수 선택\n",
    "sum_hf_yr_OBP = sum_hf_yr_OBP.merge(regular_season_df[['batter_name','year','age']],\n",
    "                                    how = 'left', on=['batter_name','year'])\n",
    "\n",
    "# 총 3년 전 성적까지 변수를 생성\n",
    "sum_hf_yr_OBP = lag_function(sum_hf_yr_OBP, \"OBP\", 1)\n",
    "sum_hf_yr_OBP = lag_function(sum_hf_yr_OBP, \"OBP\", 2)\n",
    "sum_hf_yr_OBP = lag_function(sum_hf_yr_OBP, \"OBP\", 3)\n",
    "sum_hf_yr_OBP"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1.3.5. 데이터 사후 처리"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "lag1_OBP    0.41\n",
       "lag2_OBP    0.54\n",
       "lag3_OBP    0.61\n",
       "dtype: float64"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "round(sum_hf_yr_OBP[['lag1_OBP','lag2_OBP','lag3_OBP']].isna().sum() / \\\n",
    "      sum_hf_yr_OBP.shape[0], 2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\HOME\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\ipykernel_launcher.py:4: FutureWarning: Indexing with multiple keys (implicitly converted to a tuple of keys) will be deprecated, use a list instead.\n",
      "  after removing the cwd from sys.path.\n",
      "C:\\Users\\HOME\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\ipykernel_launcher.py:8: FutureWarning: Indexing with multiple keys (implicitly converted to a tuple of keys) will be deprecated, use a list instead.\n",
      "  \n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_name</th>\n",
       "      <th>year</th>\n",
       "      <th>AB</th>\n",
       "      <th>OBP</th>\n",
       "      <th>age</th>\n",
       "      <th>lag1_OBP</th>\n",
       "      <th>lag2_OBP</th>\n",
       "      <th>lag3_OBP</th>\n",
       "      <th>mean_OBP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>가르시아</td>\n",
       "      <td>2018</td>\n",
       "      <td>85</td>\n",
       "      <td>0.418367</td>\n",
       "      <td>33</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.383495</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2011</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>19</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.337880</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2014</td>\n",
       "      <td>0</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>22</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.337880</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2015</td>\n",
       "      <td>156</td>\n",
       "      <td>0.342541</td>\n",
       "      <td>23</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.337880</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2016</td>\n",
       "      <td>81</td>\n",
       "      <td>0.222222</td>\n",
       "      <td>24</td>\n",
       "      <td>0.342541</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.337880</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1347</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2012</td>\n",
       "      <td>4</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>23</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.358779</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1348</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2013</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>24</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.358779</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1349</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2016</td>\n",
       "      <td>9</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>27</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.358779</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1350</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2017</td>\n",
       "      <td>71</td>\n",
       "      <td>0.316456</td>\n",
       "      <td>28</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.358779</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1351</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2018</td>\n",
       "      <td>24</td>\n",
       "      <td>0.230769</td>\n",
       "      <td>29</td>\n",
       "      <td>0.316456</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.358779</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1352 rows × 9 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     batter_name  year   AB       OBP  age  lag1_OBP  lag2_OBP  lag3_OBP  \\\n",
       "0           가르시아  2018   85  0.418367   33       NaN       NaN       NaN   \n",
       "1            강경학  2011    1  0.000000   19       NaN       NaN       NaN   \n",
       "2            강경학  2014    0  1.000000   22       NaN       NaN       NaN   \n",
       "3            강경학  2015  156  0.342541   23       NaN       NaN       NaN   \n",
       "4            강경학  2016   81  0.222222   24  0.342541       NaN       NaN   \n",
       "...          ...   ...  ...       ...  ...       ...       ...       ...   \n",
       "1347         황진수  2012    4  0.400000   23       NaN       NaN       NaN   \n",
       "1348         황진수  2013    0  0.000000   24       NaN       NaN       NaN   \n",
       "1349         황진수  2016    9  0.000000   27       NaN       NaN       NaN   \n",
       "1350         황진수  2017   71  0.316456   28       NaN       NaN       NaN   \n",
       "1351         황진수  2018   24  0.230769   29  0.316456       NaN       NaN   \n",
       "\n",
       "      mean_OBP  \n",
       "0     0.383495  \n",
       "1     0.337880  \n",
       "2     0.337880  \n",
       "3     0.337880  \n",
       "4     0.337880  \n",
       "...        ...  \n",
       "1347  0.358779  \n",
       "1348  0.358779  \n",
       "1349  0.358779  \n",
       "1350  0.358779  \n",
       "1351  0.358779  \n",
       "\n",
       "[1352 rows x 9 columns]"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#1. 선수별 OBP 평균\n",
    "# SF = (H+BB+HBP) / OBP-(AB+BB+HBP)\n",
    "# OBP = (H+BB+HBP) / (AB+BB+HBP+SF)\n",
    "player_OBP_mean = regular_season_df.loc[regular_season_df['AB'] >= 30].groupby('batter_name')['AB','H','BB','HBP','SF'].sum().reset_index()\n",
    "player_OBP_mean['mean_OBP'] = player_OBP_mean[['H', 'BB', 'HBP']].sum(axis=1) / player_OBP_mean[['AB','BB','HBP','SF']].sum(axis=1)\n",
    "\n",
    "#2. 시즌별 OBP 평균\n",
    "season_OBP_mean = regular_season_df.loc[regular_season_df['AB'] >= 30].groupby('year')['AB','H','BB','HBP','SF'].sum().reset_index()\n",
    "season_OBP_mean['mean_OBP'] = season_OBP_mean[['H', 'BB', 'HBP']].sum(axis=1) / season_OBP_mean[['AB','BB','HBP','SF']].sum(axis=1)\n",
    "season_OBP_mean = season_OBP_mean[['year', 'mean_OBP']]\n",
    "\n",
    "#### player_OBP_mean(선수평균) 열 추가\n",
    "sum_hf_yr_OBP = sum_hf_yr_OBP.merge(player_OBP_mean[['batter_name', 'mean_OBP']], how ='left', on=\"batter_name\")\n",
    "sum_hf_yr_OBP = sum_hf_yr_OBP.loc[~sum_hf_yr_OBP['mean_OBP'].isna()].reset_index(drop=True)\n",
    "sum_hf_yr_OBP"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 결측치 처리하는 함수 정의\n",
    "def lag_na_fill(data_set, var_name, past, season_var_mean_data):\n",
    "    # data_Set: 이용할 데이터셋\n",
    "    # var_name: 시간 변수를 만들 변수 이름\n",
    "    # past: 몇 년 전 변수를 만들지 결정\n",
    "    # season_var_name_mean_data season별로 var_name의 평균을 구한 데이터\n",
    "  \n",
    "    for i in range(0, len(data_set)):\n",
    "        if np.isnan(data_set[\"lag\" + str(past) + \"_\" + var_name][i]):\n",
    "            data_set.loc[i, [\"lag\" + str(past) + \"_\" + var_name]] = (data_set[\"mean\" + \"_\" + var_name][i] + \n",
    "                                                                     season_var_mean_data.loc[season_var_mean_data['year'] == (data_set['year'][i] - past), \n",
    "                                                                                              \"mean_\" + var_name].iloc[0]) / 2\n",
    "    return data_set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_name</th>\n",
       "      <th>year</th>\n",
       "      <th>AB</th>\n",
       "      <th>OBP</th>\n",
       "      <th>age</th>\n",
       "      <th>lag1_OBP</th>\n",
       "      <th>lag2_OBP</th>\n",
       "      <th>lag3_OBP</th>\n",
       "      <th>mean_OBP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>가르시아</td>\n",
       "      <td>2018</td>\n",
       "      <td>85</td>\n",
       "      <td>0.418367</td>\n",
       "      <td>33</td>\n",
       "      <td>0.369982</td>\n",
       "      <td>0.375910</td>\n",
       "      <td>0.373119</td>\n",
       "      <td>0.383495</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2011</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>19</td>\n",
       "      <td>0.347434</td>\n",
       "      <td>0.348603</td>\n",
       "      <td>0.344259</td>\n",
       "      <td>0.337880</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2014</td>\n",
       "      <td>0</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>22</td>\n",
       "      <td>0.346682</td>\n",
       "      <td>0.337511</td>\n",
       "      <td>0.343131</td>\n",
       "      <td>0.337880</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2015</td>\n",
       "      <td>156</td>\n",
       "      <td>0.342541</td>\n",
       "      <td>23</td>\n",
       "      <td>0.353425</td>\n",
       "      <td>0.346682</td>\n",
       "      <td>0.337511</td>\n",
       "      <td>0.337880</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2016</td>\n",
       "      <td>81</td>\n",
       "      <td>0.222222</td>\n",
       "      <td>24</td>\n",
       "      <td>0.342541</td>\n",
       "      <td>0.353425</td>\n",
       "      <td>0.346682</td>\n",
       "      <td>0.337880</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1347</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2012</td>\n",
       "      <td>4</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>23</td>\n",
       "      <td>0.353580</td>\n",
       "      <td>0.357883</td>\n",
       "      <td>0.359052</td>\n",
       "      <td>0.358779</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1348</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2013</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>24</td>\n",
       "      <td>0.347960</td>\n",
       "      <td>0.353580</td>\n",
       "      <td>0.357883</td>\n",
       "      <td>0.358779</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1349</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2016</td>\n",
       "      <td>9</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>27</td>\n",
       "      <td>0.360760</td>\n",
       "      <td>0.363874</td>\n",
       "      <td>0.357131</td>\n",
       "      <td>0.358779</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1350</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2017</td>\n",
       "      <td>71</td>\n",
       "      <td>0.316456</td>\n",
       "      <td>28</td>\n",
       "      <td>0.363552</td>\n",
       "      <td>0.360760</td>\n",
       "      <td>0.363874</td>\n",
       "      <td>0.358779</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1351</th>\n",
       "      <td>황진수</td>\n",
       "      <td>2018</td>\n",
       "      <td>24</td>\n",
       "      <td>0.230769</td>\n",
       "      <td>29</td>\n",
       "      <td>0.316456</td>\n",
       "      <td>0.363552</td>\n",
       "      <td>0.360760</td>\n",
       "      <td>0.358779</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1352 rows × 9 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     batter_name  year   AB       OBP  age  lag1_OBP  lag2_OBP  lag3_OBP  \\\n",
       "0           가르시아  2018   85  0.418367   33  0.369982  0.375910  0.373119   \n",
       "1            강경학  2011    1  0.000000   19  0.347434  0.348603  0.344259   \n",
       "2            강경학  2014    0  1.000000   22  0.346682  0.337511  0.343131   \n",
       "3            강경학  2015  156  0.342541   23  0.353425  0.346682  0.337511   \n",
       "4            강경학  2016   81  0.222222   24  0.342541  0.353425  0.346682   \n",
       "...          ...   ...  ...       ...  ...       ...       ...       ...   \n",
       "1347         황진수  2012    4  0.400000   23  0.353580  0.357883  0.359052   \n",
       "1348         황진수  2013    0  0.000000   24  0.347960  0.353580  0.357883   \n",
       "1349         황진수  2016    9  0.000000   27  0.360760  0.363874  0.357131   \n",
       "1350         황진수  2017   71  0.316456   28  0.363552  0.360760  0.363874   \n",
       "1351         황진수  2018   24  0.230769   29  0.316456  0.363552  0.360760   \n",
       "\n",
       "      mean_OBP  \n",
       "0     0.383495  \n",
       "1     0.337880  \n",
       "2     0.337880  \n",
       "3     0.337880  \n",
       "4     0.337880  \n",
       "...        ...  \n",
       "1347  0.358779  \n",
       "1348  0.358779  \n",
       "1349  0.358779  \n",
       "1350  0.358779  \n",
       "1351  0.358779  \n",
       "\n",
       "[1352 rows x 9 columns]"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 생성한 함수를 이용해 결측치 처리 진행\n",
    "sum_hf_yr_OBP = lag_na_fill(sum_hf_yr_OBP, \"OBP\", 1, season_OBP_mean) # 1년 전 성적 대체\n",
    "sum_hf_yr_OBP = lag_na_fill(sum_hf_yr_OBP, \"OBP\", 2, season_OBP_mean) # 2년 전 성적 대체\n",
    "sum_hf_yr_OBP = lag_na_fill(sum_hf_yr_OBP, \"OBP\", 3, season_OBP_mean) # 3년 전 성적 대체\n",
    "sum_hf_yr_OBP"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1.3.6. SLG 데이터 전처리"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Diagonal Correlation HeatMap')"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x864 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 상관관계를 탐색할 변수 선택\n",
    "numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64']\n",
    "numeric_cols = list(regular_season_df.select_dtypes(include=numerics).drop(['batter_id','year','OPS','OBP'], axis =1).columns)\n",
    "regular_season_temp = regular_season_df[numeric_cols + ['year', 'batter_name']].copy()\n",
    "regular_season_temp = regular_season_temp.loc[regular_season_temp['AB']>=30]\n",
    "\n",
    "# 시간변수 생성 함수를 통한 지표별 1년 전 성적 추출\n",
    "for col in numeric_cols:\n",
    "    regular_season_temp = lag_function(regular_season_temp, col, 1)\n",
    "\n",
    "numeric_cols.remove('SLG')\n",
    "regular_season_temp.drop(numeric_cols, axis = 1, inplace=True)\n",
    "\n",
    "# 상관관계 도출\n",
    "corr_matrix = regular_season_temp.corr()\n",
    "corr_matrix = corr_matrix.sort_values(by = 'SLG', axis = 0, ascending=False)\n",
    "corr_matrix = corr_matrix[corr_matrix.index]\n",
    "\n",
    "# 상관관계의 시각적 표현\n",
    "f, ax = plt.subplots(figsize=(12, 12))\n",
    "corr = regular_season_temp.select_dtypes(exclude=[\"object\",\"bool\"]).corr()\n",
    "\n",
    "# 대각 행렬을 기준으로 한쪽만 나타나게 설정해줍니다.\n",
    "mask = np.zeros_like(corr_matrix, dtype=np.bool)\n",
    "mask[np.triu_indices_from(mask)] = True\n",
    "\n",
    "cmap = sns.diverging_palette(220, 10, as_cmap=True)\n",
    "g = sns.heatmap(corr_matrix, cmap='RdYlGn_r', vmax=1, mask=mask, center=0, annot=True,\n",
    "                fmt='.2f', square=True, linewidths=.5, cbar_kws={\"shrink\": .5})\n",
    "plt.title(\"Diagonal Correlation HeatMap\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\HOME\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\ipykernel_launcher.py:2: FutureWarning: Indexing with multiple keys (implicitly converted to a tuple of keys) will be deprecated, use a list instead.\n",
      "  \n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_name</th>\n",
       "      <th>year</th>\n",
       "      <th>AB</th>\n",
       "      <th>SLG</th>\n",
       "      <th>age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>가르시아</td>\n",
       "      <td>2018</td>\n",
       "      <td>85</td>\n",
       "      <td>0.552941</td>\n",
       "      <td>33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2011</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2014</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>22</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2015</td>\n",
       "      <td>156</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2016</td>\n",
       "      <td>81</td>\n",
       "      <td>0.222222</td>\n",
       "      <td>24</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  batter_name  year   AB       SLG  age\n",
       "0        가르시아  2018   85  0.552941   33\n",
       "1         강경학  2011    1  0.000000   19\n",
       "2         강경학  2014    0  0.000000   22\n",
       "3         강경학  2015  156  0.333333   23\n",
       "4         강경학  2016   81  0.222222   24"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# day_by_day에서 연도별 선수의 시즌 전반기 장타율(SLG)과 관련된 성적 합 구하기\n",
    "sum_hf_yr_SLG = day_by_day_df.loc[day_by_day_df['date'] <= 7.18].groupby(['batter_name','year'])['AB','H','2B','3B', 'HR'].sum().reset_index()\n",
    "\n",
    "# 전반기 장타율 계산\n",
    "sum_hf_yr_SLG['SLG'] = \\\n",
    "    (sum_hf_yr_SLG['H'] - sum_hf_yr_SLG[['2B', '3B', 'HR']].sum(axis=1) +\n",
    "     sum_hf_yr_SLG['2B']*2 + sum_hf_yr_SLG['3B']*3 + sum_hf_yr_SLG['HR']*4\n",
    "     ) / sum_hf_yr_SLG['AB']\n",
    "\n",
    "# SLG 결측치를 0으로 처리 \n",
    "sum_hf_yr_SLG['SLG'].fillna(0, inplace=True)\n",
    "\n",
    "# 필요한 칼럼만 불러오고 나이 계산\n",
    "sum_hf_yr_SLG = sum_hf_yr_SLG[['batter_name','year','AB','SLG']]\n",
    "sum_hf_yr_SLG = sum_hf_yr_SLG.merge(regular_season_df[['batter_name','year','age']],\n",
    "                                    how='left', on=['batter_name','year'])\n",
    "sum_hf_yr_SLG.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_name</th>\n",
       "      <th>year</th>\n",
       "      <th>AB</th>\n",
       "      <th>SLG</th>\n",
       "      <th>age</th>\n",
       "      <th>lag1_SLG</th>\n",
       "      <th>lag2_SLG</th>\n",
       "      <th>lag3_SLG</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>가르시아</td>\n",
       "      <td>2018</td>\n",
       "      <td>85</td>\n",
       "      <td>0.552941</td>\n",
       "      <td>33</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2011</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>19</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2014</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>22</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2015</td>\n",
       "      <td>156</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>23</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2016</td>\n",
       "      <td>81</td>\n",
       "      <td>0.222222</td>\n",
       "      <td>24</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  batter_name  year   AB       SLG  age  lag1_SLG  lag2_SLG  lag3_SLG\n",
       "0        가르시아  2018   85  0.552941   33       NaN       NaN       NaN\n",
       "1         강경학  2011    1  0.000000   19       NaN       NaN       NaN\n",
       "2         강경학  2014    0  0.000000   22       NaN       NaN       NaN\n",
       "3         강경학  2015  156  0.333333   23       NaN       NaN       NaN\n",
       "4         강경학  2016   81  0.222222   24  0.333333       NaN       NaN"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "lag1_SLG    0.41\n",
       "lag2_SLG    0.54\n",
       "lag3_SLG    0.61\n",
       "dtype: float64"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 총 3년 전 성적까지 변수를 생성\n",
    "sum_hf_yr_SLG = lag_function(sum_hf_yr_SLG, \"SLG\", 1)\n",
    "sum_hf_yr_SLG = lag_function(sum_hf_yr_SLG, \"SLG\", 2)\n",
    "sum_hf_yr_SLG = lag_function(sum_hf_yr_SLG, \"SLG\", 3)\n",
    "display(sum_hf_yr_SLG.head())\n",
    "\n",
    "round(sum_hf_yr_SLG[['lag1_SLG', 'lag2_SLG', 'lag3_SLG']].isna().sum()/\\\n",
    "      sum_hf_yr_SLG.shape[0], 2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\HOME\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\ipykernel_launcher.py:2: FutureWarning: Indexing with multiple keys (implicitly converted to a tuple of keys) will be deprecated, use a list instead.\n",
      "  \n",
      "C:\\Users\\HOME\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\ipykernel_launcher.py:9: FutureWarning: Indexing with multiple keys (implicitly converted to a tuple of keys) will be deprecated, use a list instead.\n",
      "  if __name__ == '__main__':\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_name</th>\n",
       "      <th>year</th>\n",
       "      <th>AB</th>\n",
       "      <th>SLG</th>\n",
       "      <th>age</th>\n",
       "      <th>lag1_SLG</th>\n",
       "      <th>lag2_SLG</th>\n",
       "      <th>lag3_SLG</th>\n",
       "      <th>mean_SLG</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>가르시아</td>\n",
       "      <td>2018</td>\n",
       "      <td>85</td>\n",
       "      <td>0.552941</td>\n",
       "      <td>33</td>\n",
       "      <td>0.481855</td>\n",
       "      <td>0.481498</td>\n",
       "      <td>0.476627</td>\n",
       "      <td>0.519126</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2011</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>19</td>\n",
       "      <td>0.372902</td>\n",
       "      <td>0.380882</td>\n",
       "      <td>0.361716</td>\n",
       "      <td>0.332527</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2014</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>22</td>\n",
       "      <td>0.362931</td>\n",
       "      <td>0.349344</td>\n",
       "      <td>0.359616</td>\n",
       "      <td>0.332527</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2015</td>\n",
       "      <td>156</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>23</td>\n",
       "      <td>0.389415</td>\n",
       "      <td>0.362931</td>\n",
       "      <td>0.349344</td>\n",
       "      <td>0.332527</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>강경학</td>\n",
       "      <td>2016</td>\n",
       "      <td>81</td>\n",
       "      <td>0.222222</td>\n",
       "      <td>24</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>0.389415</td>\n",
       "      <td>0.362931</td>\n",
       "      <td>0.332527</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  batter_name  year   AB       SLG  age  lag1_SLG  lag2_SLG  lag3_SLG  \\\n",
       "0        가르시아  2018   85  0.552941   33  0.481855  0.481498  0.476627   \n",
       "1         강경학  2011    1  0.000000   19  0.372902  0.380882  0.361716   \n",
       "2         강경학  2014    0  0.000000   22  0.362931  0.349344  0.359616   \n",
       "3         강경학  2015  156  0.333333   23  0.389415  0.362931  0.349344   \n",
       "4         강경학  2016   81  0.222222   24  0.333333  0.389415  0.362931   \n",
       "\n",
       "   mean_SLG  \n",
       "0  0.519126  \n",
       "1  0.332527  \n",
       "2  0.332527  \n",
       "3  0.332527  \n",
       "4  0.332527  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "lag1_SLG    0.0\n",
       "lag2_SLG    0.0\n",
       "lag3_SLG    0.0\n",
       "dtype: float64"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 선수별 SLG 평균 데이터(player_SLG_mean)를 만듭니다\n",
    "player_SLG_mean = regular_season_df.loc[regular_season_df['AB'] >= 30].groupby('batter_name')['AB','H','2B','3B','HR'].sum().reset_index()\n",
    "player_SLG_mean['mean_SLG'] = \\\n",
    "    (player_SLG_mean['H'] - player_SLG_mean[['2B','3B','HR']].sum(axis = 1) +\n",
    "     player_SLG_mean['2B']*2 + player_SLG_mean['3B']*3 + player_SLG_mean['HR']*4\n",
    "    ) / player_SLG_mean['AB']\n",
    "\n",
    "# 시즌별 SLG 평균 데이터(season_SLG_mean)를 만듭니다\n",
    "season_SLG_mean = regular_season_df.loc[regular_season_df['AB'] >= 30].groupby('year')['AB','H','2B','3B','HR'].sum().reset_index()\n",
    "season_SLG_mean['mean_SLG'] = \\\n",
    "    (season_SLG_mean['H'] - season_SLG_mean[['2B','3B','HR']].sum(axis = 1) + \n",
    "     season_SLG_mean['2B']*2 + season_SLG_mean['3B']*3 + season_SLG_mean['HR']*4\n",
    "    ) / season_SLG_mean['AB']\n",
    "\n",
    "# 선수 평균의 SLG(player_OBP_mean)를 새로운 변수로 더합니다.\n",
    "sum_hf_yr_SLG = sum_hf_yr_SLG.merge(player_SLG_mean[['batter_name', 'mean_SLG']], how='left', on=\"batter_name\")\n",
    "\n",
    "# 선수 평균의 성적이 결측치이면 데이터에서 제거합니다.\n",
    "sum_hf_yr_SLG = \\\n",
    "    sum_hf_yr_SLG.loc[~sum_hf_yr_SLG['mean_SLG'].isna()].reset_index(drop=True)\n",
    "\n",
    "# 결측치 처리\n",
    "sum_hf_yr_SLG = lag_na_fill(sum_hf_yr_SLG, \"SLG\", 1, season_SLG_mean) #1년전 성적 대체\n",
    "sum_hf_yr_SLG = lag_na_fill(sum_hf_yr_SLG, \"SLG\", 2, season_SLG_mean) #2년전 성적 대체\n",
    "sum_hf_yr_SLG = lag_na_fill(sum_hf_yr_SLG, \"SLG\", 3, season_SLG_mean) #3년전 성적 대체\n",
    "\n",
    "display(sum_hf_yr_SLG.head())\n",
    "round(sum_hf_yr_SLG[['lag1_SLG', 'lag2_SLG', 'lag3_SLG']].isna().sum()/\\\n",
    "      sum_hf_yr_SLG.shape[0], 2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1.4. 모델링\n",
    "### 1.4.1. 데이터 분할"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(872, 9) (150, 9) (872, 9) (150, 9)\n"
     ]
    }
   ],
   "source": [
    "# 30타수 이상의 데이터만 학습\n",
    "sum_hf_yr_OBP= sum_hf_yr_OBP.loc[sum_hf_yr_OBP['AB']>=30]\n",
    "sum_hf_yr_SLG = sum_hf_yr_SLG.loc[sum_hf_yr_SLG['AB']>=30] \n",
    "\n",
    "# 2018년 데이터를 test 데이터 2018년 이전은 train 데이터로 나눈다.\n",
    "OBP_train = sum_hf_yr_OBP.loc[sum_hf_yr_OBP['year'] != 2018]\n",
    "OBP_test = sum_hf_yr_OBP.loc[sum_hf_yr_OBP['year'] == 2018]\n",
    "\n",
    "SLG_train = sum_hf_yr_SLG.loc[sum_hf_yr_SLG['year'] != 2018]\n",
    "SLG_test = sum_hf_yr_SLG.loc[sum_hf_yr_SLG['year'] == 2018]\n",
    "print(OBP_train.shape, OBP_test.shape, SLG_train.shape, SLG_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "def wrmse(v,w,p):\n",
    "    # v: 실제값\n",
    "    # w: 타수\n",
    "    # p: 예측값\n",
    "    return sum(np.sqrt(((v-p)**2 * w) / sum(w)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1.4.2. 모델 선택"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>lag1_SLG</th>\n",
       "      <th>lag2_SLG</th>\n",
       "      <th>lag3_SLG</th>\n",
       "      <th>mean_SLG</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>23</td>\n",
       "      <td>0.389415</td>\n",
       "      <td>0.362931</td>\n",
       "      <td>0.349344</td>\n",
       "      <td>0.332527</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>24</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>0.389415</td>\n",
       "      <td>0.362931</td>\n",
       "      <td>0.332527</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>25</td>\n",
       "      <td>0.222222</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>0.389415</td>\n",
       "      <td>0.332527</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>20</td>\n",
       "      <td>0.437048</td>\n",
       "      <td>0.446916</td>\n",
       "      <td>0.445639</td>\n",
       "      <td>0.466540</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>21</td>\n",
       "      <td>0.285714</td>\n",
       "      <td>0.437048</td>\n",
       "      <td>0.446916</td>\n",
       "      <td>0.466540</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age  lag1_SLG  lag2_SLG  lag3_SLG  mean_SLG\n",
       "3   23  0.389415  0.362931  0.349344  0.332527\n",
       "4   24  0.333333  0.389415  0.362931  0.332527\n",
       "5   25  0.222222  0.333333  0.389415  0.332527\n",
       "7   20  0.437048  0.446916  0.445639  0.466540\n",
       "8   21  0.285714  0.437048  0.446916  0.466540"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "SLG_train.iloc[:,-5:].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import Ridge, Lasso\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "# log 단위(1e+01)로 1.e-04 ~ 1.e+01 사이의 구간에 대해 parameter를 탐색한다. \n",
    "lasso_params = {'alpha' : np.logspace(-4, 1, 6)} \n",
    "ridge_params = {'alpha' : np.logspace(-4, 1, 6)} \n",
    "\n",
    "# GridSearchCV를 이용하여 dict에 Lasso, Ridege OBP 모델을 저장한다.\n",
    "OBP_linear_models = {\n",
    "    'Lasso': GridSearchCV(Lasso(), param_grid=lasso_params).fit(OBP_train.iloc[:,-5:], OBP_train['OBP']).best_estimator_,\n",
    "    'Ridge': GridSearchCV(Ridge(), param_grid=ridge_params).fit(OBP_train.iloc[:,-5:], OBP_train['OBP']).best_estimator_,}\n",
    "\n",
    "# GridSearchCV를 이용하여 dict에 Lasso, Ridge SLG 모델을 저장한다\n",
    "SLG_linear_models = {\n",
    "    'Lasso': GridSearchCV(Lasso(), param_grid=lasso_params).fit(SLG_train.iloc[:,-5:], SLG_train['SLG']).best_estimator_,\n",
    "    'Ridge': GridSearchCV(Ridge(), param_grid=ridge_params).fit(SLG_train.iloc[:,-5:], SLG_train['SLG']).best_estimator_,}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[1;32m~\\AppData\\Local\\Temp\\ipykernel_2780\\1190445439.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m     17\u001b[0m \u001b[1;31m# GridSearchCV를 이용하여 dict에 OBP Randomforest 모델을 저장한다.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     18\u001b[0m SLG_RF_models = {'RF': GridSearchCV(RandomForestRegressor(random_state=42), param_grid=RF_params, n_jobs=-1\n\u001b[1;32m---> 19\u001b[1;33m         ).fit(SLG_train.iloc[:,-5:], SLG_train['SLG']).best_estimator_}\n\u001b[0m\u001b[0;32m     20\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     21\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34mf\"걸린시간 : {np.round(time.time() - start,3)}초\"\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;31m# 현재시간 – 시작시간(단위 초)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\sklearn\\model_selection\\_search.py\u001b[0m in \u001b[0;36mfit\u001b[1;34m(self, X, y, groups, **fit_params)\u001b[0m\n\u001b[0;32m    889\u001b[0m                 \u001b[1;32mreturn\u001b[0m \u001b[0mresults\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    890\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 891\u001b[1;33m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_run_search\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mevaluate_candidates\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    892\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    893\u001b[0m             \u001b[1;31m# multimetric is determined here because in the case of a callable\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\sklearn\\model_selection\\_search.py\u001b[0m in \u001b[0;36m_run_search\u001b[1;34m(self, evaluate_candidates)\u001b[0m\n\u001b[0;32m   1390\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m_run_search\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mevaluate_candidates\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1391\u001b[0m         \u001b[1;34m\"\"\"Search all candidates in param_grid\"\"\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1392\u001b[1;33m         \u001b[0mevaluate_candidates\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mParameterGrid\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mparam_grid\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1393\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1394\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\sklearn\\model_selection\\_search.py\u001b[0m in \u001b[0;36mevaluate_candidates\u001b[1;34m(candidate_params, cv, more_results)\u001b[0m\n\u001b[0;32m    849\u001b[0m                     )\n\u001b[0;32m    850\u001b[0m                     for (cand_idx, parameters), (split_idx, (train, test)) in product(\n\u001b[1;32m--> 851\u001b[1;33m                         \u001b[0menumerate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mcandidate_params\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0menumerate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mcv\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mgroups\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    852\u001b[0m                     )\n\u001b[0;32m    853\u001b[0m                 )\n",
      "\u001b[1;32m~\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\joblib\\parallel.py\u001b[0m in \u001b[0;36m__call__\u001b[1;34m(self, iterable)\u001b[0m\n\u001b[0;32m   1054\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1055\u001b[0m             \u001b[1;32mwith\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_backend\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mretrieval_context\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1056\u001b[1;33m                 \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mretrieve\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1057\u001b[0m             \u001b[1;31m# Make sure that we get a last message telling us we are done\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1058\u001b[0m             \u001b[0melapsed_time\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtime\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtime\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m-\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_start_time\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\joblib\\parallel.py\u001b[0m in \u001b[0;36mretrieve\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    933\u001b[0m             \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    934\u001b[0m                 \u001b[1;32mif\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_backend\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'supports_timeout'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;32mFalse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 935\u001b[1;33m                     \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_output\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mextend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mjob\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    936\u001b[0m                 \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    937\u001b[0m                     \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_output\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mextend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mjob\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\envs\\store_amount_prediction\\lib\\site-packages\\joblib\\_parallel_backends.py\u001b[0m in \u001b[0;36mwrap_future_result\u001b[1;34m(future, timeout)\u001b[0m\n\u001b[0;32m    540\u001b[0m         AsyncResults.get from multiprocessing.\"\"\"\n\u001b[0;32m    541\u001b[0m         \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 542\u001b[1;33m             \u001b[1;32mreturn\u001b[0m \u001b[0mfuture\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresult\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    543\u001b[0m         \u001b[1;32mexcept\u001b[0m \u001b[0mCfTimeoutError\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    544\u001b[0m             \u001b[1;32mraise\u001b[0m \u001b[0mTimeoutError\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0me\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\envs\\store_amount_prediction\\lib\\concurrent\\futures\\_base.py\u001b[0m in \u001b[0;36mresult\u001b[1;34m(self, timeout)\u001b[0m\n\u001b[0;32m    428\u001b[0m                 \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__get_result\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    429\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 430\u001b[1;33m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_condition\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mwait\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    431\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    432\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_state\u001b[0m \u001b[1;32min\u001b[0m \u001b[1;33m[\u001b[0m\u001b[0mCANCELLED\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mCANCELLED_AND_NOTIFIED\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\envs\\store_amount_prediction\\lib\\threading.py\u001b[0m in \u001b[0;36mwait\u001b[1;34m(self, timeout)\u001b[0m\n\u001b[0;32m    294\u001b[0m         \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m    \u001b[1;31m# restore state no matter what (e.g., KeyboardInterrupt)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    295\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mtimeout\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 296\u001b[1;33m                 \u001b[0mwaiter\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0macquire\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    297\u001b[0m                 \u001b[0mgotit\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    298\u001b[0m             \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "import time\n",
    "from sklearn.ensemble import RandomForestRegressor \n",
    "start = time.time() # 시작 시간 저장\n",
    "\n",
    "# 랜덤 포레스트의 parameter 범위를 정의한다.\n",
    "RF_params = {\n",
    "    'n_estimators': [50,100,150,200,300,500,1000],\n",
    "    'max_features': ['auto', 'sqrt'],\n",
    "    'max_depth' : [1,2,3,5,6,10],\n",
    "    'min_samples_leaf': [1, 2, 4],\n",
    "    'min_samples_split': [2, 3, 5, 10]}\n",
    "\n",
    "# GridSearchCV를 이용하여 dict에 OBP Randomforest 모델을 저장한다.\n",
    "OBP_RF_models = {'RF': GridSearchCV(RandomForestRegressor(random_state=42), param_grid=RF_params, n_jobs=-1\n",
    "        ).fit(OBP_train.iloc[:,-5:], OBP_train['OBP']).best_estimator_}\n",
    "\n",
    "# GridSearchCV를 이용하여 dict에 OBP Randomforest 모델을 저장한다.\n",
    "SLG_RF_models = {'RF': GridSearchCV(RandomForestRegressor(random_state=42), param_grid=RF_params, n_jobs=-1\n",
    "        ).fit(SLG_train.iloc[:,-5:], SLG_train['SLG']).best_estimator_}\n",
    "\n",
    "print(f\"걸린시간 : {np.round(time.time() - start, 3)}초\") # 현재시간 – 시작시간(단위 초)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "걸린시간 : 1115.496초\n"
     ]
    }
   ],
   "source": [
    "import xgboost as xgb \n",
    "start = time.time() # 시작 시간 저장\n",
    "\n",
    "# xgboost parmeter space를 정의한다.\n",
    "XGB_params = {\n",
    "    'min_child_weight': [1,3, 5,10],\n",
    "    'gamma': [0.3,0.5, 1, 1.5, 2, 5],\n",
    "    'subsample': [0.6, 0.8, 1.0],\n",
    "    'colsample_bytree': [0.6, 0.8, 1.0],\n",
    "    'max_depth': [3, 4, 5,7,10]}\n",
    "# GridSearchCV를 통해 parameter를 탐색하게 정의한다.\n",
    "XGB_OBP_gridsearch = GridSearchCV(xgb.XGBRegressor(random_state=42), param_grid=XGB_params, n_jobs=-1) \n",
    "XGB_SLG_gridsearch = GridSearchCV(xgb.XGBRegressor(random_state=42), param_grid=XGB_params, n_jobs=-1)\n",
    "\n",
    "# 모델 학습\n",
    "XGB_OBP_gridsearch.fit(OBP_train.iloc[:,-5:], OBP_train['OBP'])\n",
    "XGB_SLG_gridsearch.fit(SLG_train.iloc[:,-5:], SLG_train['SLG'])\n",
    "\n",
    "print(f\"걸린시간 : {np.round(time.time() - start,3)}초\") # 현재시간 – 시작시간(단위 초)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 테스트 데이터셋(2018년)의 선수들의 OBP를 예측\n",
    "Lasso_OBP = OBP_linear_models['Lasso'].predict(OBP_test.iloc[:,-5:])\n",
    "Ridge_OBP = OBP_linear_models['Ridge'].predict(OBP_test.iloc[:,-5:])\n",
    "RF_OBP = OBP_RF_models['RF'].predict(OBP_test.iloc[:,-5:])\n",
    "XGB_OBP = XGB_OBP_gridsearch.predict(OBP_test.iloc[:,-5:])\n",
    "\n",
    "# test 데이터의 WRMSE 계산\n",
    "wrmse_score = [wrmse(OBP_test['OBP'], OBP_test['AB'], Lasso_OBP),\n",
    "               wrmse(OBP_test['OBP'], OBP_test['AB'], Ridge_OBP),\n",
    "               wrmse(OBP_test['OBP'], OBP_test['AB'], RF_OBP),\n",
    "               wrmse(OBP_test['OBP'], OBP_test['AB'], XGB_OBP)]\n",
    "\n",
    "x_lab = ['Lasso', 'Ridge', 'RF', 'XGB']\n",
    "\n",
    "plt.bar(x_lab, wrmse_score)\n",
    "plt.title('WRMSE of OBP', fontsize=20)\n",
    "plt.xlabel('model', fontsize=18)\n",
    "plt.ylabel('', fontsize=18)\n",
    "plt.ylim(0,0.5)\n",
    "\n",
    "# 막대그래프 위에 값을 표시해준다.\n",
    "for i, v in enumerate(wrmse_score):\n",
    "    plt.text(i-0.1, v+0.01, str(np.round(v, 3))) # x 좌표, y 좌표, 텍스트를 표현한다.\n",
    "    \n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXEAAAEjCAYAAADEwTFYAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+17YcXAAAgAElEQVR4nO3de5xVdb3/8dd7HEclDcEGMm90KkvA+5gXHJmEvOHJLphaWZoIeUnNo43n/OB4Ics5muXpouIlf93IME9lgJGXgQktHfMSUilHQSmTQRBFRUQ+54+1BjabvWcWMDObxbyfj8d67L2+3+9a+7uX+J61v+umiMDMzPKpqtIdMDOzjecQNzPLMYe4mVmOOcTNzHLMIW5mlmMOcTOzHHOIm/UASVtJ+n+SnpW0QtInK90n2zI4xHspSddICkl7l6kfmtZ/r0z9DpLekvSbgrIomt6U9FdJ4yXVlFjH/LTdmRn7fFXa/rYSdXtJulXSAkkr06B8VtLXito1l+hn+3RZln5spK8CXwN+C1wC/D3LQpJOlnSvpKWS3pb0iqRHJNUXtBmU9v+irJ2R9H5J35b0ZLrO19P/HjMknbWhX84qp7rSHbCKuRv4N+CjwJ9L1B+dvn60zPJHkPz7+V1R+b3Aj9P37wKOAiYChwKjyqzry8BNHXVWUh+gZNhL+hgwBVgA3Aa8AAwEDgQ+UmKRvwPjS5Q/1lEfNtEYoDkivpSlsSQBPwFOBu4i+QPwJrAHcDwwBGjZmI5IugS4Ange+B/gfwGl6x4O/Ddw/cas2yogIjz1wgnYBlgOTC9TPwNYAgSwe4n6a9K6vQrKAvhuibbXp3UjisrnkwRvAMM76e+XgJVp+9sKyrcFXgJ+D9SUWG6novlmYE4FtvfbwPUb0P7EdLucU6JOQP+C+UFp24syrPfradvLgK3LtNmv0v8+PWWfPJzSS0XEm8D9wBGStimsk7QdUA9MTYtGlljFkcDCiPhLho+7NX2tK1E3mySEv1xu4XSv9Ly0P9sUVe8N9Ad+HhEri5eNiJcy9K8nVJEEeVYN6euPiisisWRDOyBpBPDvwNci4rKIeKtUu4jozl8k1sUc4r3b3UAf4LCi8gaSPdxbgFcoCnFJ/YB9WX8opZyt0tdlJepWkgylnCBp1zLLHw3sBXwX2K6o7pX09UMZ+9IlJG0j6WJJj6Xjya9ImiXphKJ2zZLab1B0Tjp2PT/DR3TH97qMZAjlii5cp1WYQ7x3m56+Fo97Hw28SjJEcT8wIt0bbtdA8m9nRsbPOQlYDcwqU99+8LTcAbULSIZA7mXtH4R2TwOPA2MlnVvUz24haVvgHuAbJMcTLiQZ998e+KWkCwuaXwWcnr6/N32f5QDkL0iGPX4sab8u6PMAYBjw03J74JZTlR7P8VTZiSQEHy4q+yvwq/T92SRhsm9B/XdIQrm2aLkgGTp5dzrtB1xNMoxwRYnPnk86vg3cDiwCtilq86H0s8am88spGBNPy/YCnkk//0/AMR183+b0+727xKSM26x9XHl0UXk1yR+2t4D3ldg26x0v6ORzzknXtQq4mRLHJtJ2g+hkTJzkD3MAJ5ao277Etljv+IKnzXPynrhNBw6Q1B9A0h7AB1m7l90+ZFI4pHIk8GhEtJVY3+kkZ4e8ADxKcrbDqIj4z076cR1QS7LXXuh8YClrz3hZTyTj8vuSnFUxFJgu6R5J7y+zyAcL+lg49e2kj0iqIjnIen9E3FHUj1VAI0mYf7azdXUmIr4HHAw8BJwB/E3SFaVO18xgp/R1aYm6i1h/WxQPsdlmyiFud5P8OxiRzrefWjgDICKeBp4lDfH0Z/lgyo+H3wUcC5xKEj4fAFZ01omIeAB4mIIDnOnY++eBmyPi9U6WfzUizk/79rP0+zwi6YgSzRekfSyelnfWT2BPoB9lhpIi4lHgNZI/KpssIv4UEYcBnyLp9wTgXknbb+Cq3khf31Gi7ses3QZXbmxfrTIc4nY/Sci2j4sfA8xPw7vd70jOYqkh2QuH8uPhz0XE3RHxY5JztJ8DJkt6Z4a+XAfUSToknR9LcjZKyQuOSomIeRFxCkkgbU0yplx8MHR52sfiaVWGj2jfo13YQZt/Ajtk7XMWEXEnyZk4NwKHkxyk3BDz09fBJdY9r30b0L3nyls3cIj3chHxBslFIx+VVE0S0sUBPYPkLJZDSYL5dZJTAztb9+skQTyQbKHzc5Kf8udK2opkTPiXEfFcpi+z7mffTXI63W4koddV2vfWd+6gzUBKD1tskkgOSJ5FMkx1ygYu/jjJqZwf7+p+WWU5xA2ScfFBJMHQl9JXYb5NMqTyEWBWJOeZdyoi/kgSzudK+kAnbd8iuTBodNqX3UjGuTfWM+nrjpuwjmJ/JRmaGFGqUtI+JAcK/9iFn7lGRATJ8NYGfaeIWE3yi+bDkkZ3R9+sMhziBsm4OCSXhr9NEtprRMTLJOPVR5GMcWc9tbDdf5CcGfHNDG1vSF+/BzwWEeVOSwRA0p6SSl1EBMk48mqSsfkukf7x+v/A0ZI+UdSXKpJTCl8FfrgpnyNplKT1DrRKqiX5ZfHgRqz2KuAJ4LbivhfYmIOmVkG+d4oREX+RtIAkHB6OiFJDATNIDqpB9ot82tf/jKQbgPMkjYyIezpo2yZpMnAa2fbC3wPcL+n3wH0k90XpRzK23wBMjIgFRcvsKOm0EutaEhG/zvCZl5BsqymSfgI8QDIG/mmS0ypPiojFGdbTkROBn0m6i+QP6Bskv5Y+R3Ih1sUllqkr873ujoh/RsQbko4GfgXcKelBkj/g/yS56nU/oD3cOz0YbZuJSp/j6GnzmEj2gIMS53On9cPS+n90sI6y50KT3AxrGcnFMVulZfMpOuc7Ld+P5JzxbUvUrXOeOElgf51k+OJlknOqXyS5RP9jJZZvTvtZanpsA7bXO9PPnUdy1elikptJ1W3otinT/lCSs0aeJgnUFcBTwPeBQUVtB3XwnQJoKGq/Fckfyd+l2/mtdNs9THJe/96V/vfoKfuk9D+qmZnlkMfEzcxyzCFuZpZjmUJc0kRJMyXNljSkoHxHSXekdb9Jr7AzM7Me0mmIp4+BGhgRw4FxJAc+2l1Ccle04cAvga90Sy/NzKykLKcYHgVMBoiIOe03SkrtDTSl7+8ieTTWeiSNJblyj3e84x0HfuhDPXrrZzOzXHvkkUcWR0RtqbosIT4AKLxb3SpJVZFcAfYE8EmShweMKLe+iJgETAKoq6uL1tbWDei+mVnvll7HUVKWMfFlJOfitludBjgk58nWS/od8F7W3mTHzMx6QJYQbyG5lwWSBlNw97ZIbv95WkR8lOTih/WeB2hmZt0nS4hPBWoktZA84bxRUpOkGklHSnogvXx3cXRynwszM+tanY6Jp0Mnxc8+bExf78NPADEzqxhf7GNmlmMOcTOzHHOIm5nlmEPczCzHHOJmZjnmEDczyzGHuJlZjjnEzcxyzCFuZpZjDnEzsxxziJuZ5ViW+4mbmeXChAkTmDVrFqtWrWLSpEkMGZI8TXLMmDHMmzcPgFdeeYVBgwZx5513cvvtt/Pd736XFStWcN5553HqqaeWbbvZiogenQ488MAwM+tqs2bNijPPPDMiIv785z/HscceW7Ldl7/85XjooYdiyZIlUV9fH2+++Wa89tprsf/++8eyZctKtq00oDXKZKqHU8xsizBjxgxOOeUUAIYOHcqSJUvWa7NgwQIWLVrEQQcdxLx589h///2pqamhT58+HHzwwfzlL38p2XZz5hA3sy3CokWLqK1d+xjK6upqVq9evU6ba6+9lvPPPx+A973vfTz44IO88sorvPbaazz00EOsWrWqZNvNmUPczLYIffv2ZenSpWvmq6qqqKpaG3ErVqzgscce49BDDwWgf//+jB8/nuOPP54xY8bw3ve+l0GDBpVsuznLFOKSJkqaKWm2pCEF5TWSfiDpPknTJPXtvq6amZVXX1/PHXfcAcDcuXPZdddd16mfPn06I0eOXKfsYx/7GLNmzaKpqYmqqip22WWXsm03V52GuKR6YGBEDAfGAVcXVB8D/D0ijgTuBMZ0Sy/NzDoxatQoVq5cSX19PRdddBFNTU00NjaycuVKAJqbmxk2bNg6y3zmM5/h8MMPZ9y4cVx11VVryku13VwpOfDZQQNpInBfRNyfzv8hIg5J338EGB0R50i6BPhHRPywo/XV1dVFa2tr1/TezKwXkPRIRNSVqstynvgAoK1gfpWkqkievfl7YIKkucDblHnepqSxwFiA3XfffUP6bmZbiEGXTK10Fypq/lWjumW9WcbElwH9CuZXpwEO8HXgmogYDJwKTCq1goiYFBF1EVFXePTYzMw2TZYQbwFGA0gaDCwsqNsD+Gf6fhGwW5f2zszMOpRlOGUqcJykFuBVYJykJmBCOn1fUhWwNXBxt/XUzMzW02mIp0MnZxUVN6avfwNGdHWnzMwsG1/sY2aWYw5xM7Mcc4ibmeWYQ9zMLMcc4mZmOeYQNzPLMYe4mVmOOcTNzHLMIW5mlmMOcTOzHHOIm5nlmEPczCzHHOJmZjnmEDczyzGHuNlmZMKECQwfPpxhw4bx5JNPrlP3gx/8gEMOOYRhw4Zx7733AnD//fdzxBFHcPDBB/OjH/0IgOeff573vOc9NDQ00NDQwNy5c3v8e1jPyfJQCDPrAS0tLbz44ovMnDmTOXPmcPHFFzNt2jQAnnzySVpaWnjggQeoqlq773XppZdy11130adPH+rq6vjc5z7Hyy+/zEknncS3vvWtSn0V60GZ9sQlTZQ0U9JsSUMKym+W1JxOf5J0Z/d11WzLNmPGDE455RQAhg4dypIlS9bU3XLLLeyxxx4ceeSRfPrTn2bx4sUA9OnTh2XLlrF8+XK23357JPHyyy/Tr1+/kp9hW55OQ1xSPTAwIoYD44Cr2+siYkxENEREA8mT77/RXR0129ItWrSIwgeJV1dXs3p18kzyp59+mne96100Nzdz4okncvnllwNw4YUXUldXx9ChQ/niF78IwOuvv84vfvELhg0bxgUXXMBbb73V81/GekyWPfGjgMkAETEH6F/cQNIewICIeLhru9fzNnRMctGiRXziE5/gsMMO4+STT+6wbW/QFdtvzJgxa8ZzDzjgAD75yU/2+PeohL59+7J06dI181VVVWuGTqqrqznuuOMAOP7445k7dy6LFi3iuuuuY8GCBSxYsID77ruPJ554gqOPPprHH3+clpYWdthhB2666aaKfB/rGVnGxAcAbQXzqyRVpc/ebHchcF25FUgaC4wF2H333Temnz1iY8YkGxsbueKKK9h7773XlJVru6Xrqu138803r3l/3nnnceqpp/bcl6ig+vp67rjjDurr65k7dy677rrrmrpDDz2UadOmcc4559Dc3Mw+++zD4sWLqa6uZrvttgOgX79+LFy4kMGDB1NdXU1VVRU77bRTpb6O9ZAsCbMMKBxgW10Y4JK2BfaLiAfLrSAiJkVEXUTUFf5c3Nxs6Jjk0qVLeemll7jyyiupr69fc3ZAufHLLV1Xbb92CxYsYNGiRRx00EE9+j0qZdSoUaxcuZL6+nouuugimpqaaGxsZOXKlZx99tk0NzfT0NDADTfcwPjx4xk8eDAHHXQQhx12GMOGDSMiOOaYY5gyZQqHH344w4cP59FHH+WMM86o9FezbpRlT7wFGA20SBoMLCyqPxa4p6s7VgnlxiSrqqp4+umnOeaYY2hubmbKlClcfvnlnHbaaTz11FPMnj2bPn36MHLkSEaOHFmy7Xe+850KfrOe0VXbb+eddwbg2muv5fzzz6/U1+lxVVVVXH/99euUNTU1AVBTU8OUKVPWW2b8+PGMHz9+nbJTTjllzR9T2/JlCfGpwHGSWoBXgXGSmoAJEbESaAB+1X1d7DkbMiZ5ww03UF1dzcEHH7zmJ+vhhx/OvHnzSrbtDbpq++28886sWLGCxx57jOuuKztK1+MGXTK10l2oqPlXjap0F6yETodTImJ1RJwVEfURcVxEPB8RjWmAExHnR8R93d/V7tc+JgmUHZME1oxJ7rnnnjz55JMsX76ct99+m9bWVvbcc8+SbXuDrtp+ANOnT2fkyJE9/yXMcsYX+xQYNWoU06ZNo76+nh122IEbb7yRxsZGJk6cyNlnn83pp5/OlClT6Nu3L7feeivbbbcd48ePZ8SIEVRXVzNu3DgGDhxYsm1v0FXbD5KgP+GEEyr8jcw2f4qIHv3Aurq6aG1t7dHPNOsKHk7ZtOEUb7+N336SHomIulJ1vef8NzOzLVCuhlP8l9x7QpvCB+ZsS+Q9cTOzHHOIm5nlmEPczCzHHOJmZjnmEDczyzGHuJlZjjnEzcxyzCFuZpZjDnEzsxxziJuZ5ZhD3MwsxxziZmY5linEJU2UNFPSbElDiupOl/SHtG5E93TTzMxK6fQuhpLqgYERMVzSUOBq4Li0bghQDxxW+PBkMzPrGVn2xI8CJgNExBygf0HdGcAC4D5JP5f0rq7vopmZlZMlxAcAbQXzqyS1L/cBYHFENABTgEtLrUDSWEmtklrb2tpKNTEzs42QJcSXAf0K5lcXDJ2sAqal738DDC61goiYFBF1EVFXW1u70Z01M7N1ZQnxFmA0gKTBwMKCugdJx8eBBuCJruycmZl1LEuITwVqJLUA1wCNkpok1QDfBxokNQNfAr7WbT01M7P1dHp2Sjp0clZRcWP6uhI4sas7ZWZm2fhiHzOzHHOIm5nlmEPczCzHHOJmZjnmEDczyzGHuJlZjjnEzcxyzCFuZpZjDnEzsxxziJuZ5ZhD3MwsxxziZmY55hA3M8sxh7iZWY45xM3McswhbmaWY5lCXNJESTMlzZY0pKB8N0n/kNScTiWfsWlmZt2j0yf7SKoHBkbEcElDgatZ+1zNHYHbI+Ir3dhHMzMrI8ue+FHAZICImAP0L6jbEVjaDf0yM7MMsoT4AKCtYH6VpPbl+gCfSodZvi1p61IrkDRWUquk1ra2tlJNzMxsI2QJ8WVAv4L51enDk4mI30bEvkA98CpwZqkVRMSkiKiLiLra2tpN7bOZmaWyhHgLMBogPXC5sL1CUjVAGuovdUcHzcysvCwhPhWokdQCXAM0SmqSVAOcKOn3kmYC+wO3dGNfzcysSKdnp6R72WcVFTemr5PTyczMKsAX+5iZ5ZhD3MwsxxziZmY55hA3M8sxh7iZWY45xM3McswhbmaWYw5xM7Mcc4ibmeWYQ9zMLMcc4mZmOeYQNzPLMYe4mVmOOcTNzHLMIW5mlmMOcTOzHMsU4pImSpqZPhB5SIn6gZJel7Rt13fRzMzK6TTEJdUDAyNiODAOuLpEs0uAxV3cNzMz60SWPfGjSB/BFhFzgP6FlZIOAAJ4pst7Z2ZmHcoS4gOAtoL5VZKqACT1Aa4CLu9oBZLGSmqV1NrW1tZRUzMz2wBZQnwZ0K9gfnX68GSAbwFNEbGsoxVExKSIqIuIutra2o3sqpmZFcsS4i3AaABJg4GF6fsBwIHAmZJ+BgwGbuuebpqZWSnVGdpMBY6T1AK8CoyT1ARMiIi69kaSmoHTuqOTZmZWWqchng6dnFVU3FiiXUMX9cnMzDLyxT5mZjnmEDczyzGHuJlZjjnEzcxyzCFuZpZjDnEzsxxziJuZ5ZhD3MwsxxziZmY55hA3M8sxh7iZWY45xM3McswhbmaWYw5xM7Mcc4ibmeWYQ9zMLMcc4mZmOZYpxCVNlDRT0mxJQwrK95b0u7T8x5KyPO7NzMy6SKchLqkeGBgRw4FxwNUF1c8CR0XEMGAF8OFu6aWZmZWUZU/8KGAyQETMAfq3V0TE8ogISdum5c+UWoGksZJaJbW2tbV1QbfNzAyyhfgAoDB5V0las5yknwLzgT8DL5ZaQURMioi6iKirra3dhO6amVmhLCG+DOhXML86Ila3z0TEZ4D3AFsDX+ja7pmZWUeyhHgLMBpA0mBgYXuFpL4Aaaj/A9i+G/poZmZlZAnxqUCNpBbgGqBRUpOkGuCk9MyU+4EDgJu6sa9mZlak01MC073ss4qKG9PXSelkZmYV4It9zMxyzCFuZpZjDnEzsxxziJuZ5ZhD3MwsxxziZmY55hA3M8sxh7iZWY45xM3McswhbmaWYw5xM7Mcc4ibmeWYQ9zMLMcc4mZmOeYQNzPLMYe4mVmOZQpxSRMlzUyf4jOkoHwfSTMktUj6efq0HzMz6yGdhrikemBgRAwHxgFXF1QH8K8RUQ8sAE7oll6amVlJWfbEjwImA0TEHKB/e0VE/Dki3kxnlwKvlVqBpLGSWiW1trW1bWKXzcysXZYQHwAUJu8qSessJ2kYMAT4bakVRMSkiKiLiLra2tqN7qyZma2r0wclA8uAfgXzq9OHJyNJJA9N3hr4fES83fVdNDOzcrLsibcAowEkDQYWFtR9CXghIiY6wM3Mel6WEJ8K1EhqAa4BGiU1pWei/CswTlJzOl3YnZ01M7N1dTqckg6dnFVU3Ji+HtflPTIzs8x8sY+ZWY45xM3McswhbmaWYw5xM7Mcc4ibmeWYQ9zMLMcc4mZmOeYQNzPLMYe4mVmOOcTNzHLMIW5mlmMOcTOzHHOIm5nlmEPczCzHHOJmZjnmEDczy7FMIS5poqSZkmZLGlJUt5ekOyQd0z1dNDOzcjoNcUn1wMCIGA6MA64uqNsDuARY3m09NDOzsrLsiR8FTAaIiDlA//aKiFgQEV8A5ndL78zMrENZQnwA0FYwv0rSBo2lSxorqVVSa1tbW+cLmJlZJlnCeBnQr2B+dfrw5MwiYlJE1EVEXW1t7QZ10MzMyssS4i3AaABJg4GF3dojMzPLLEuITwVqJLUA1wCNkpok1XRv18zMrDPVnTVIh07OKipuLGpzWRf2yczMMvLFPmZmOeYQNzPLMYe4mVmOOcTNzHLMIW5mlmMOcTOzHHOIm5nlmEPczCzHHOJmZjnmEDczyzGHuJlZjjnEzcxyzCFuZpZjDnEzsxxziJuZ5ZhD3MwsxzKFuKSJkmZKmi1pSEH59pImS5ol6ZeS3tl9XTUzs2KdhrikemBgRAwHxgFXF1R/BbgrIo4Afsf6TwAyM7NulGVP/ChgMkBEzAH6F9QdCUxJ3/8COLRLe2dmZh3q9BmbwACgrWB+laSq9Nmb20TEW2n5S0C/UiuQNBYYm84ul/S3je1whb0LWFypD1dTpT65y3j7bRpvv02T5+23R7mKLCG+jHXDeXUa4ACrCwK9H+uG/RoRMQmYlLGzmy1JrRFRV+l+5JW336bx9ts0W+r2yzKc0gKMBpA0GFhYUPdH4IT0/aeAe7q0d2Zm1qEsIT4VqJHUAlwDNEpqklQDfAMYK6kZOBD4Qbf11MzM1tPpcEo6VFJ81klj+roYOLarO7UZy/2QUIV5+20ab79Ns0VuP0VEpftgZmYbyVdsmpnlmEPczCzHenWIS/pDpfuQZ5JekdQs6Q+Svp2WbSdpYpn23t4Zldq2aflTaXmzpG9Wso+bE0mflXRDwfxZki6V1F/SzZIekNSSTjunbdq38SOSvlS53m+aLOeJm5UzNyIaACTdLmnfiHgcmFDZbm0Rym3bJe3ltlZE/ETSZyQdRHIa9GdIrii/HxgfEc0AkrYpWGxuRDRI2gr4E3ADOeQQLyCpL/BDoC/Jr5QTgK3Ssh2Av0XEGEmXAkenbT4N/B24DhgKbAvcGRH/1fPfoDIkbUtyNdyidP4PEXGIpF2Am4Ea4JGC9rsBt5Bsv4eAI9P27wZuJNnWbcCpEbGyR7/MZqZ421qHziE5zfkF4ELg48A97QEOEBFvllhuZ5L/h3OpVw+nlPAm8Ll0T+de4DhgGPBIRNSz9tYBnwSGRcQhwPPAF4FF6XKHAYdL2qeH+14JgyX9EZgHXBYRLxTVNwFfi4gRrL3HDsBVwOURMRL4n4Lyq9P1HAnMBE7qvq5v9spt2/4FwyljO1i+14mI+cCzQP+IeBh4H/AEQDqs0izpMUnD00UGS5pFsoPxq0r0uSs4xNe1G3CVpKuA/Un2CH8DvCTpOuDDabtzgf+WdA4gYL+0Xft59fcDH+zhvlfC3Ig4mOSir4+VqH9fRMxO37cWlP9LQfkjBeX7AN9KLx77PMl9e3qrctt2SUQ0pNMWed7zxpK0N8mv6JclHQ7MB94PEBHtw1C/BLZLF5mb3oF1F2CYpMN6vNNdwCG+rvOAH0fEJSR72AA1EfFtkp9nN6ZlrRHxZWBXYBTwJHAMgKQqoJ50D6A3iIjvAQek/xMVWlrwi+QjQPtFCS9L2jd9f2RB+6eB0wp+0Xy3m7qcGx1sWysgaWvg+yS3x74Q+CYwHfhU0a/irYqXjYhVwMvAO3qgq12ut4+JD073+gB+D/wauEXS06wdI2uQdBnwGvDLNKTvlfQm8DpwLXA38P301gSrgR9GRF7v1LixvkJyXKAwlP8duEnS68AM4O20/JK0/DWSYasVafl/ALdKguTGa2eTjG/2dqW2ra3rUmBKRDwHIOlHwFeBk4FrJNWSDJe+AtyULtP+//9WJPeByuW9n3zFpvU4SVu338JY0ieA4RFxQYW7ZZZLvX1P3CrjZElnpO+XsPaAsZltIO+Jm5nlmA9smpnlmEPczCzHHOJmZjnmEDfLSNJlkjb4QbuSTpMUkrbvjn5Z7+YQNzPLMYe4mVmOOcTNzHLMIW650T4mLWkXSb+WtFzSM5JOTuuPTe9S91p6o/8jipYfJOk2SS9IWpkue2V6u9fiz/p4uo43JD0v6asd9OtkSY9LelPSc5ImpveoNut2DnHLm2rgTpJb1Z4KPAP8RNI4kvu+3wicTnJ3yamSdgSQ9H7gYZK7U15CcjvhnwL/Bvw6vScOadvPpp/xJDAa+E/gDJI7K64jvZPlD4HfAp8iuWnXBcCVXfy9zUqLCE+ecjEBl5HcCfHMgrLtSe5AF8CxBeX/kpZ9IZ2fTnKv6XcUrfOEtN2J6fx2wEskNzErbLcT8CKwuKDsPSQ37xpT1PYM4A1gp3T+tPQztq/0NvS05U3eE7c8+mn7m4hYDjwKLIyI6QXlz5Dcl2WPdG/8aOCbEfFa4Yoi4lfA31h7z+4RQH/gv4ravcS6D7CAZC/9dXad670AAAGRSURBVGCypG3bJ5JfCduSPOnJrFv5BliWN0uLg5hkz7nUv+VXgXcCe5IMr5S7x/vfgEHp+w+R3DL3LyXa/bNofi+gH7C8zHp3K1Nu1mUc4pY3q8uUv12mHNYe+ym37OqCum2AtyKi1Pq2LpoX8BzlHyP3vx30yaxLOMStN3g2fd2H5OEfxT5UUP4CsK2k3SLi+aJ2exbNPwfUkjyD9a2u6qzZhvCYuG3xIuJFoAW4qPjSd0nHk4T45LToPpKDkOcVtfsA6z9HdBrJgdCzij9T0s5d0nmzTnhP3HqLc0mCvFXSt0kev3cQcDFwY0TcB8kT0yVNIgn8HUjOatkdaCR5fNfB7SuMiMck3UbycOc90/oq4FiSJ637cWrW7Rzi1itExBOSDgEmAl8H+gBPAReRPGC30LkkB0tPB75AckD088ARFIR46kySc9VPT9+/QPK8xq90yxcxK+In+5iZ5ZjHxM3McswhbmaWYw5xM7Mcc4ibmeWYQ9zMLMcc4mZmOeYQNzPLMYe4mVmOOcTNzHLs/wCvNqN71HdE8QAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 테스트 데이터셋(2018년)의 선수들의 SLG를 예측\n",
    "Lasso_SLG = SLG_linear_models['Lasso'].predict(SLG_test.iloc[:,-5:])\n",
    "Ridge_SLG = SLG_linear_models['Ridge'].predict(SLG_test.iloc[:,-5:])\n",
    "RF_SLG = SLG_RF_models['RF'].predict(SLG_test.iloc[:,-5:])\n",
    "XGB_SLG = XGB_SLG_gridsearch.predict(SLG_test.iloc[:,-5:])\n",
    "\n",
    "# test데이터 WRMSE 계산\n",
    "wrmse_score_SLG = [wrmse(SLG_test['SLG'], SLG_test['AB'], Lasso_SLG),\n",
    "                   wrmse(SLG_test['SLG'], SLG_test['AB'], Ridge_SLG), \n",
    "                   wrmse(SLG_test['SLG'], SLG_test['AB'], RF_SLG),\n",
    "                   wrmse(SLG_test['SLG'], SLG_test['AB'], XGB_SLG)]\n",
    "\n",
    "x_lab = ['Lasso', 'Ridge', 'RF', 'XGB']\n",
    "\n",
    "plt.bar(x_lab, wrmse_score_SLG)\n",
    "plt.title('WRMSE of SLG', fontsize=20)\n",
    "plt.xlabel('model', fontsize=18)\n",
    "plt.ylabel('', fontsize=18)\n",
    "plt.ylim(0, 0.9)\n",
    "\n",
    "# 막대그래프 위에 값을 표시해준다.\n",
    "for i, v in enumerate(wrmse_score_SLG):\n",
    "    plt.text(i-0.1, v + 0.01, str(np.round(v,3))) # x 좌표, y 좌표, 텍스트를 표현한다.\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1.4.3. 결과 해석과 평가"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x432 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(15,6)) # 그래프의 크기 지정\n",
    "\n",
    "plt.subplot(1,2,1) \n",
    "plt.barh(OBP_train.iloc[:,-5:].columns, OBP_RF_models['RF'].feature_importances_) \n",
    "plt.title('Feature importance of RF in OBP')\n",
    "\n",
    "plt.subplot(1,2,2) \n",
    "plt.barh(SLG_train.iloc[:,-5:].columns,SLG_RF_models['RF'].feature_importances_)\n",
    "plt.title('Feature importance of RF in SLG')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Alpha :  0.0001\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>lag1_OBP</th>\n",
       "      <th>lag2_OBP</th>\n",
       "      <th>lag3_OBP</th>\n",
       "      <th>mean_OBP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>coefficient</th>\n",
       "      <td>0.003195</td>\n",
       "      <td>0.018249</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.864913</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  age  lag1_OBP  lag2_OBP  lag3_OBP  mean_OBP\n",
       "coefficient  0.003195  0.018249       0.0       0.0  0.864913"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Alpha :  0.0001\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>lag1_SLG</th>\n",
       "      <th>lag2_SLG</th>\n",
       "      <th>lag3_SLG</th>\n",
       "      <th>mean_SLG</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>coefficient</th>\n",
       "      <td>0.0049</td>\n",
       "      <td>0.081209</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>0.836453</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                age  lag1_SLG  lag2_SLG  lag3_SLG  mean_SLG\n",
       "coefficient  0.0049  0.081209       0.0      -0.0  0.836453"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "print('Alpha : ', OBP_linear_models['Lasso'].alpha) # Lasso + GridSearchCV -> alpha값 출력\n",
    "# Lasso model의 선형 계수 값 출력\n",
    "display(pd.DataFrame(OBP_linear_models['Lasso'].coef_.reshape(-1, 5), columns=OBP_train.iloc[:,-5:].columns, index=['coefficient']))\n",
    "\n",
    "print('Alpha : ', SLG_linear_models['Lasso'].alpha)\n",
    "display(pd.DataFrame(SLG_linear_models['Lasso'].coef_.reshape(-1, 5), columns=SLG_train.iloc[:,-5:].columns, index=['coefficient']))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      ".."
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x345.6 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "from sklearn.linear_model import lars_path # LASSO의 계산 측면에서의 단점을 극복\n",
    "\n",
    "plt.figure(figsize=(15,4.8)) # 그래프 크기 지정\n",
    "\n",
    "plt.subplot(1,2,1) \n",
    "# OBP 모델의 alpha 값의 변화에 따른 계수의 변화를 alpha, coefs에 저장한다.\n",
    "alphas, _, coefs = lars_path(OBP_train.iloc[:,-5:].values, OBP_train['OBP'], method='lasso', verbose=True)\n",
    "xx = np.sum(np.abs(coefs.T), axis=1)# 피처별 alpha 값에 따른 선형 모델 계수의 절댓값의 합 \n",
    "xx /= xx[-1]# 계수의 절댓값 중 가장 큰 값으로 alpha에 따른 피처의 계수의 합을 나눈다. \n",
    "\n",
    "plt.plot(xx, coefs.T)\n",
    "plt.xlabel('|coef| / max|coef|')\n",
    "plt.ylabel('Coefficients')\n",
    "plt.title('OBP LASSO Path')\n",
    "plt.axis('tight')\n",
    "plt.legend(OBP_train.iloc[:,-5:].columns) \n",
    "\n",
    "\n",
    "plt.subplot(1,2,2)\n",
    "# SLG 모델에서 alpha 값의 변화에 따른 계수의 변화를 alpha, coefs에 저장한다.\n",
    "alphas, _, coefs = lars_path(SLG_train.iloc[:,-5:].values, SLG_train['SLG'], method='lasso', verbose=True)\n",
    "xx = np.sum(np.abs(coefs.T), axis=1)\n",
    "xx /= xx[-1]\n",
    "\n",
    "plt.plot(xx, coefs.T)\n",
    "plt.xlabel('|coef| / max|coef|')\n",
    "plt.ylabel('Coefficients')\n",
    "plt.title('SLG LASSO Path')\n",
    "plt.axis('tight')\n",
    "plt.legend(OBP_train.iloc[:,-5:].columns)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1.5. 성능 향상을 위한 방법\n",
    "### 1.5.1. 앙상블"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "OBP model averaging:  0.3324574652010582\n",
      "SLG model averaging:  0.6684541138633259\n"
     ]
    }
   ],
   "source": [
    "print('OBP model averaging: ',\n",
    "      wrmse(OBP_test['OBP'], OBP_test['AB'], (Lasso_OBP + RF_OBP) / 2))\n",
    "print('SLG model averaging: ',\n",
    "      wrmse(SLG_test['SLG'], OBP_test['AB'], (Lasso_SLG + RF_SLG) / 2))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1.5.2. df 단순화"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\ipykernel_launcher.py:18: FutureWarning: Indexing with multiple keys (implicitly converted to a tuple of keys) will be deprecated, use a list instead.\n"
     ]
    }
   ],
   "source": [
    "# 전처리된 데이터를 다른 곳에 저장\n",
    "sum_hf_yr_OBP_origin = sum_hf_yr_OBP.copy()\n",
    "\n",
    "# 희생타\n",
    "regular_season_df['SF'] = regular_season_df[['H','BB','HBP']].sum(axis=1) / regular_season_df['OBP'] \n",
    "                          - regular_season_df[['AB','BB','HBP']].sum(axis=1)\n",
    "regular_season_df['SF'].fillna(0, inplace = True)\n",
    "regular_season_df['SF'] = regular_season_df['SF'].apply(lambda x : round(x,0))\n",
    "\n",
    "# 한 타수당 평균 희생타 \n",
    "regular_season_df['SF_1'] = regular_season_df['SF'] / regular_season_df['AB']\n",
    "regular_season_df_SF = regular_season_df[['batter_name','year','SF_1']]\n",
    "\n",
    "# 연도별 선수의 시즌 전반기 출루율과 관련된 성적 + BB, RBI 추가\n",
    "sum_hf_yr_OBP = day_by_day_df.loc[day_by_day_df['date'] <= 7.18].groupby(['batter_name','year'])['AB','H','BB','HBP','RBI', '2B', '3B', 'HR'].sum().reset_index()\n",
    "sum_hf_yr_OBP = sum_hf_yr_OBP.merge(regular_season_df_SF, how = 'left',on=['batter_name','year'])\n",
    "\n",
    "# 한 타수당 평균 희생타 \n",
    "sum_hf_yr_OBP['SF'] = (sum_hf_yr_OBP['SF_1']*sum_hf_yr_OBP['AB']).apply(lambda x: round(x,0))\n",
    "sum_hf_yr_OBP.drop('SF_1',axis = 1, inplace = True)\n",
    "\n",
    "# 전반기 OBP(출루율 계산)\n",
    "sum_hf_yr_OBP['OBP'] = sum_hf_yr_OBP[['H', 'BB', 'HBP']].sum(axis = 1) / sum_hf_yr_OBP[['AB', 'BB', 'HBP','SF']].sum(axis = 1)\n",
    "sum_hf_yr_OBP['OBP'].fillna(0, inplace = True)\n",
    "\n",
    "# TB \n",
    "sum_hf_yr_OBP['TB'] =  sum_hf_yr_OBP['H'] + sum_hf_yr_OBP['2B']*2 + sum_hf_yr_OBP['3B']*3 + sum_hf_yr_OBP['HR']*4\n",
    "sum_hf_yr_OBP = sum_hf_yr_OBP[['batter_name','year','AB','OBP', 'BB', 'TB', 'RBI']]\n",
    "\n",
    "# 나이\n",
    "sum_hf_yr_OBP = sum_hf_yr_OBP.merge(regular_season_df[['batter_name','year','age']], how = 'left', on=['batter_name','year'])\n",
    "\n",
    "# 평균 OBP \n",
    "sum_hf_yr_OBP = sum_hf_yr_OBP.merge(player_OBP_mean[['batter_name', 'mean_OBP']], how ='left', on=\"batter_name\")\n",
    "sum_hf_yr_OBP = sum_hf_yr_OBP.loc[~sum_hf_yr_OBP['mean_OBP'].isna()].reset_index(drop=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 각 변수에 대한 1년 전 성적 생성\n",
    "sum_hf_yr_OBP = lag_function(sum_hf_yr_OBP, \"BB\", 1)\n",
    "sum_hf_yr_OBP = lag_function(sum_hf_yr_OBP, \"TB\", 1)\n",
    "sum_hf_yr_OBP = lag_function(sum_hf_yr_OBP, \"RBI\", 1)\n",
    "sum_hf_yr_OBP = lag_function(sum_hf_yr_OBP, \"OBP\", 1)\n",
    "\n",
    "sum_hf_yr_OBP = sum_hf_yr_OBP.dropna() # 결측치 포함한 행 제거\n",
    "\n",
    "# 변수 리스트 지정\n",
    "feature_list_1 = ['age', 'lag1_OBP', 'mean_OBP']\n",
    "feature_list_2 = ['age', 'lag1_BB', 'lag1_TB', 'lag1_RBI','lag1_OBP', 'mean_OBP']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 학습시킬 데이터 30타수 이상만 학습\n",
    "sum_hf_yr_OBP= sum_hf_yr_OBP.loc[sum_hf_yr_OBP['AB']>=30] \n",
    "\n",
    "# 2018년 test로 나누고 나머지는 학습\n",
    "OBP_train = sum_hf_yr_OBP.loc[sum_hf_yr_OBP['year'] != 2018]\n",
    "OBP_test = sum_hf_yr_OBP.loc[sum_hf_yr_OBP['year'] == 2018]\n",
    "\n",
    "# grid search를 이용해 학습한다.\n",
    "OBP_RF_models_1 = {\n",
    "    'RF': GridSearchCV(\n",
    "        RandomForestRegressor(random_state=42), param_grid=RF_params, n_jobs=-1).fit(OBP_train.loc[:,feature_list_1], OBP_train['OBP']).best_estimator_}\n",
    "\n",
    "OBP_RF_models_2 = {\n",
    "    'RF': GridSearchCV(\n",
    "        RandomForestRegressor(random_state=42), param_grid=RF_params, n_jobs=-1).fit(OBP_train.loc[:,feature_list_2], OBP_train['OBP']).best_estimator_}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 예측\n",
    "RF_OBP_1 = OBP_RF_models_1['RF'].predict(OBP_test.loc[:,feature_list_1])\n",
    "RF_OBP_2 = OBP_RF_models_2['RF'].predict(OBP_test.loc[:,feature_list_2])\n",
    "\n",
    "# wrmse 계산\n",
    "wrmse_score = [wrmse(OBP_test['OBP'],OBP_test['AB'],RF_OBP_1) ,\n",
    "               wrmse(OBP_test['OBP'],OBP_test['AB'],RF_OBP_2)]\n",
    "x_lab = ['simple', 'complicate']\n",
    "\n",
    "plt.bar(x_lab, wrmse_score)\n",
    "plt.title('WRMSE of OBP', fontsize=20)\n",
    "plt.xlabel('model', fontsize=18)\n",
    "plt.ylabel('', fontsize=18)\n",
    "plt.ylim(0,0.5)\n",
    "# 막대그래프 위에 값을 표시해준다.\n",
    "for i, v in enumerate(wrmse_score):\n",
    "    plt.text(i-0.1, v + 0.01, str(np.round(v,3))) # x 좌표, y좌표, 텍스트 표시\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 최종 제출을 위한 원래 데이터 복구 \n",
    "sum_hf_yr_OBP = sum_hf_yr_OBP_origin.copy()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1.5.3. 테스트 데이터 정제"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_id</th>\n",
       "      <th>batter_name</th>\n",
       "      <th>year</th>\n",
       "      <th>year_born</th>\n",
       "      <th>age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2019</td>\n",
       "      <td>1992년 08월 11일</td>\n",
       "      <td>27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>강구성</td>\n",
       "      <td>2019</td>\n",
       "      <td>1993년 06월 09일</td>\n",
       "      <td>26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>강민국</td>\n",
       "      <td>2019</td>\n",
       "      <td>1992년 01월 10일</td>\n",
       "      <td>27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>강민호</td>\n",
       "      <td>2019</td>\n",
       "      <td>1985년 08월 18일</td>\n",
       "      <td>34</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>강백호</td>\n",
       "      <td>2019</td>\n",
       "      <td>1999년 07월 29일</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   batter_id batter_name  year      year_born  age\n",
       "0          1         강경학  2019  1992년 08월 11일   27\n",
       "1          2         강구성  2019  1993년 06월 09일   26\n",
       "2          3         강민국  2019  1992년 01월 10일   27\n",
       "3          4         강민호  2019  1985년 08월 18일   34\n",
       "4          5         강백호  2019  1999년 07월 29일   20"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "submission = pd.read_csv('./input/submission.csv')\n",
    "submission['year'] = 2019 # 연도 기입\n",
    "\n",
    "batter_year_born = regular_season_df[['batter_id','batter_name','year_born']].copy() # 2019년의 Age(나이) 계산\n",
    "batter_year_born = batter_year_born.drop_duplicates().reset_index(drop=True) # 중복선수 제거\n",
    "\n",
    "submission = submission.merge(batter_year_born, how='left', on=['batter_id', 'batter_name'])\n",
    "submission['age'] = submission['year'] - submission['year_born'].apply(lambda x: int(x[:4]))\n",
    "submission.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [],
   "source": [
    "submission_OBP = submission.copy()\n",
    "submission_SLG = submission.copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_id</th>\n",
       "      <th>batter_name</th>\n",
       "      <th>year</th>\n",
       "      <th>year_born</th>\n",
       "      <th>age</th>\n",
       "      <th>mean_OBP</th>\n",
       "      <th>lag1_OBP</th>\n",
       "      <th>lag2_OBP</th>\n",
       "      <th>lag3_OBP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2019</td>\n",
       "      <td>1992년 08월 11일</td>\n",
       "      <td>27</td>\n",
       "      <td>0.337880</td>\n",
       "      <td>0.423611</td>\n",
       "      <td>0.285714</td>\n",
       "      <td>0.222222</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>강구성</td>\n",
       "      <td>2019</td>\n",
       "      <td>1993년 06월 09일</td>\n",
       "      <td>26</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>강민국</td>\n",
       "      <td>2019</td>\n",
       "      <td>1992년 01월 10일</td>\n",
       "      <td>27</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>강민호</td>\n",
       "      <td>2019</td>\n",
       "      <td>1985년 08월 18일</td>\n",
       "      <td>34</td>\n",
       "      <td>0.358187</td>\n",
       "      <td>0.328990</td>\n",
       "      <td>0.386076</td>\n",
       "      <td>0.441860</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>강백호</td>\n",
       "      <td>2019</td>\n",
       "      <td>1999년 07월 29일</td>\n",
       "      <td>20</td>\n",
       "      <td>0.356164</td>\n",
       "      <td>0.355685</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   batter_id batter_name  year      year_born  age  mean_OBP  lag1_OBP  \\\n",
       "0          1         강경학  2019  1992년 08월 11일   27  0.337880  0.423611   \n",
       "1          2         강구성  2019  1993년 06월 09일   26       NaN       NaN   \n",
       "2          3         강민국  2019  1992년 01월 10일   27       NaN       NaN   \n",
       "3          4         강민호  2019  1985년 08월 18일   34  0.358187  0.328990   \n",
       "4          5         강백호  2019  1999년 07월 29일   20  0.356164  0.355685   \n",
       "\n",
       "   lag2_OBP  lag3_OBP  \n",
       "0  0.285714  0.222222  \n",
       "1       NaN       NaN  \n",
       "2       NaN       NaN  \n",
       "3  0.386076  0.441860  \n",
       "4       NaN       NaN  "
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 평균 성적 기입\n",
    "submission_OBP = submission_OBP.merge(sum_hf_yr_OBP[['batter_name','mean_OBP']].drop_duplicates().reset_index(drop=True), how='left', on='batter_name')\n",
    "\n",
    "#  과거 성적 값 채우기\n",
    "for i in [1,2,3]:\n",
    "    temp_lag_df = sum_hf_yr_OBP.loc[\n",
    "        (sum_hf_yr_OBP['year'] == (2019 - i)) &\n",
    "        (sum_hf_yr_OBP['AB']>=30),['batter_name','OBP']].copy()\n",
    "    temp_lag_df.rename(columns={'OBP':'lag'+str(i)+'_OBP'}, inplace=True)\n",
    "    submission_OBP = submission_OBP.merge(temp_lag_df, how='left', on='batter_name')\n",
    "\n",
    "submission_OBP.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['강구성', '강민국', '강상원', '고명성', '김응민', '김종덕', '김주찬', '김철호', '김태연',\n",
       "       '김태진', '김형준', '나원탁', '남태혁', '박광열', '박기혁', '백민기', '샌즈', '신범수',\n",
       "       '신성현', '양종민', '윤정우', '이동훈', '이범호', '이병휘', '이성곤', '이인행', '이종욱',\n",
       "       '이진영', '이창진', '장승현', '장시윤', '전민재', '전병우', '정경운', '정성훈', '조홍석',\n",
       "       '최원제', '홍창기'], dtype=object)"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "submission_OBP['batter_name'].loc[submission_OBP['mean_OBP'].isna()].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [],
   "source": [
    "for batter_name in [\"김주찬\", \"이범호\"]:\n",
    "     # 30타수 이상인 해당선수의 인덱스(Boolean)\n",
    "    cond_regular = (regular_season_df['AB'] >= 30) & (regular_season_df['batter_name'] == batter_name)\n",
    "    \n",
    "    # 타수를 고려해 평균 OBP 계산\n",
    "    mean_OBP = sum(regular_season_df.loc[cond_regular,'AB'] * regular_season_df.loc[cond_regular,'OBP']) / sum(regular_season_df.loc[cond_regular,'AB'])\n",
    "    submission_OBP.loc[(submission_OBP['batter_name'] == batter_name),'mean_OBP'] = mean_OBP\n",
    "    \n",
    "    # regular_season_Batter으로부터 1, 2, 3년 전 성적 구하기\n",
    "    cond_sub = submission_OBP['batter_name'] == batter_name\n",
    "    submission_OBP.loc[cond_sub,'lag1_OBP'] = regular_season_df.loc[(cond_regular) & (regular_season_df['year']==2018),'OBP'].values\n",
    "    submission_OBP.loc[cond_sub,'lag2_OBP'] = regular_season_df.loc[(cond_regular) & (regular_season_df['year']==2017),'OBP'].values\n",
    "    submission_OBP.loc[cond_sub,'lag3_OBP'] = regular_season_df.loc[(cond_regular) & (regular_season_df['year']==2016),'OBP'].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in np.where(submission_OBP['batter_name'].isin([\"고명성\",\"전민재\",\"김철호\",\"신범수\",\"이병휘\"])):\n",
    "    #submission_OBP.loc[i,'mean_OBP'] = season_OBP_mean.loc[season_OBP_mean['year']==2018,'mean_OBP'].values\n",
    "    submission_OBP.loc[i,'mean_OBP'] = \\\n",
    "        season_OBP_mean.loc[season_OBP_mean['year']==2018,'mean_OBP']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [],
   "source": [
    "for batter_name in [\"전병우\",\"샌즈\"]:\n",
    "    # 30 타수 이상인 해당 선수의 index 추출\n",
    "    cond_regular = (regular_season_df['AB']>=30) & (regular_season_df['batter_name']==batter_name) \n",
    "\n",
    "# 타수를 고려해 선수의 평균 OBP계산\n",
    "mean_OBP = sum(regular_season_df.loc[cond_regular,'AB'] * regular_season_df.loc[cond_regular,'OBP']) / sum(regular_season_df.loc[cond_regular,'AB'])\n",
    "    \n",
    "submission_OBP.loc[(submission_OBP['batter_name'] == batter_name),'mean_OBP'] = mean_OBP\n",
    "cond_sub = submission_OBP['batter_name'] == batter_name\n",
    "\n",
    "# 2018년 데이터로부터 2019년의 1년 전 성적 기입\n",
    "submission_OBP.loc[cond_sub,'lag1_OBP'] = regular_season_df.loc[(cond_regular)&(regular_season_df['year']==2018),'OBP'].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 평균 성적이 결측치인 선수들에 대해 평균 OBP의 하위 25% 성적 기입\n",
    "submission_OBP.loc[submission_OBP['mean_OBP'].isna(),'mean_OBP'] = np.quantile(player_OBP_mean['mean_OBP'],0.25)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_id</th>\n",
       "      <th>batter_name</th>\n",
       "      <th>year</th>\n",
       "      <th>year_born</th>\n",
       "      <th>age</th>\n",
       "      <th>mean_OBP</th>\n",
       "      <th>lag1_OBP</th>\n",
       "      <th>lag2_OBP</th>\n",
       "      <th>lag3_OBP</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2019</td>\n",
       "      <td>1992년 08월 11일</td>\n",
       "      <td>27</td>\n",
       "      <td>0.337880</td>\n",
       "      <td>0.423611</td>\n",
       "      <td>0.285714</td>\n",
       "      <td>0.222222</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>강구성</td>\n",
       "      <td>2019</td>\n",
       "      <td>1993년 06월 09일</td>\n",
       "      <td>26</td>\n",
       "      <td>0.304124</td>\n",
       "      <td>0.329991</td>\n",
       "      <td>0.330297</td>\n",
       "      <td>0.336224</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>강민국</td>\n",
       "      <td>2019</td>\n",
       "      <td>1992년 01월 10일</td>\n",
       "      <td>27</td>\n",
       "      <td>0.304124</td>\n",
       "      <td>0.329991</td>\n",
       "      <td>0.330297</td>\n",
       "      <td>0.336224</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>강민호</td>\n",
       "      <td>2019</td>\n",
       "      <td>1985년 08월 18일</td>\n",
       "      <td>34</td>\n",
       "      <td>0.358187</td>\n",
       "      <td>0.328990</td>\n",
       "      <td>0.386076</td>\n",
       "      <td>0.441860</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>강백호</td>\n",
       "      <td>2019</td>\n",
       "      <td>1999년 07월 29일</td>\n",
       "      <td>20</td>\n",
       "      <td>0.356164</td>\n",
       "      <td>0.355685</td>\n",
       "      <td>0.356317</td>\n",
       "      <td>0.362245</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   batter_id batter_name  year      year_born  age  mean_OBP  lag1_OBP  \\\n",
       "0          1         강경학  2019  1992년 08월 11일   27  0.337880  0.423611   \n",
       "1          2         강구성  2019  1993년 06월 09일   26  0.304124  0.329991   \n",
       "2          3         강민국  2019  1992년 01월 10일   27  0.304124  0.329991   \n",
       "3          4         강민호  2019  1985년 08월 18일   34  0.358187  0.328990   \n",
       "4          5         강백호  2019  1999년 07월 29일   20  0.356164  0.355685   \n",
       "\n",
       "   lag2_OBP  lag3_OBP  \n",
       "0  0.285714  0.222222  \n",
       "1  0.330297  0.336224  \n",
       "2  0.330297  0.336224  \n",
       "3  0.386076  0.441860  \n",
       "4  0.356317  0.362245  "
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    " # i년 전 OBP 결측치 제거\n",
    "for i in [1,2,3]: \n",
    "    submission_OBP = lag_na_fill(submission_OBP, 'OBP', i, season_OBP_mean)\n",
    "submission_OBP.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 앞서 전처리한 데이터로 평균 SLG 값 기입\n",
    "submission_SLG = submission_SLG.merge(\n",
    "    sum_hf_yr_SLG[['batter_name','mean_SLG']].drop_duplicates().reset_index(drop=True),\n",
    "    how='left', on='batter_name')\n",
    "\n",
    "# 앞서 전처리한 데이터에서 과거 SLG 값 채우기\n",
    "for i in [1,2,3]:\n",
    "    temp_lag_df = sum_hf_yr_SLG.loc[(sum_hf_yr_SLG['year'] == (2019 - i)) &\n",
    "        (sum_hf_yr_SLG['AB']>=30),['batter_name','SLG']].copy()\n",
    "    \n",
    "    temp_lag_df.rename(columns={'SLG':'lag'+str(i)+'_SLG'}, inplace=True)\n",
    "    \n",
    "    submission_SLG = submission_SLG.merge(temp_lag_df, how='left', on='batter_name')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['강구성', '강민국', '강상원', '고명성', '김응민', '김종덕', '김주찬', '김철호', '김태연',\n",
       "       '김태진', '김형준', '나원탁', '남태혁', '박광열', '박기혁', '백민기', '샌즈', '신범수',\n",
       "       '신성현', '양종민', '윤정우', '이동훈', '이범호', '이병휘', '이성곤', '이인행', '이종욱',\n",
       "       '이진영', '이창진', '장승현', '장시윤', '전민재', '전병우', '정경운', '정성훈', '조홍석',\n",
       "       '최원제', '홍창기'], dtype=object)"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "submission_SLG['batter_name'].loc[submission_SLG['mean_SLG'].isna()].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [],
   "source": [
    "for batter_name in [\"김주찬\", \"이범호\"]:\n",
    "     # mean_SLG 계산\n",
    "    cond_regular = (regular_season_df['AB'] >= 30) & \\\n",
    "                   (regular_season_df['batter_name'] == batter_name)\n",
    "    \n",
    "    # 타수를 고려해 선수의 평균 SLG 계산\n",
    "    mean_SLG = sum(regular_season_df.loc[cond_regular,'AB'] * \\\n",
    "                   regular_season_df.loc[cond_regular,'SLG']) / \\\n",
    "               sum(regular_season_df.loc[cond_regular,'AB'])\n",
    "    \n",
    "    submission_SLG.loc[(submission_SLG['batter_name'] == batter_name), 'mean_SLG'] = \\\n",
    "        mean_SLG\n",
    "    \n",
    "    # regular_season_Batter으로부터 1, 2, 3년 전 성적 구하기\n",
    "    cond_sub = submission_SLG['batter_name'] == batter_name\n",
    "    \n",
    "    submission_SLG.loc[cond_sub,'lag1_SLG'] = regular_season_df.loc[\n",
    "        (cond_regular) & (regular_season_df['year'] == 2018),'SLG'].values\n",
    "    submission_SLG.loc[cond_sub,'lag2_SLG'] = regular_season_df.loc[\n",
    "        (cond_regular) & (regular_season_df['year'] == 2017),'SLG'].values\n",
    "    submission_SLG.loc[cond_sub,'lag3_SLG'] = regular_season_df.loc[\n",
    "        (cond_regular) & (regular_season_df['year'] == 2016),'SLG'].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in np.where(submission_SLG['batter_name'].isin(\n",
    "    [\"고명성\",\"전민재\",\"김철호\",\"신범수\",\"이병휘\"])):\n",
    "     # 위의 해당 선수들의 평균 SLG 평균값으로 대체\n",
    "    #submission_SLG.loc[i,'mean_SLG'] = season_SLG_mean.loc[season_SLG_mean['year']==2018,'mean_SLG'].values\n",
    "    submission_SLG.loc[i,'mean_SLG'] = \\\n",
    "        season_SLG_mean.loc[season_SLG_mean['year']==2018,'mean_SLG']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {},
   "outputs": [],
   "source": [
    "for batter_name in [\"전병우\",\"샌즈\"]:\n",
    "    \n",
    "    # 30타수 이상인 해당선수의 인덱스(Boolean) \n",
    "    cond_regular = (regular_season_df['AB']>=30)&\\\n",
    "(regular_season_df['batter_name']==batter_name)\n",
    "\n",
    "# 타수를 고려한 평균 SLG 계산\n",
    "mean_SLG = sum(regular_season_df.loc[cond_regular,'AB']*\n",
    "regular_season_df.loc[cond_regular,'SLG']) / sum(regular_season_df.loc[cond_regular,'AB'])\n",
    "\n",
    "# 해당 선수의 평균 SLG 값 기입\n",
    "submission_SLG.loc[(submission_SLG['batter_name'] == batter_name),\n",
    "'mean_SLG'] = mean_SLG\n",
    "\n",
    "# 해당 선수의 1년 전 SLG값 기입\n",
    "cond_sub = submission_SLG['batter_name'] == batter_name\n",
    "submission_SLG.loc[cond_sub,'lag1_SLG'] = regular_season_df.loc[(cond_regular)&\n",
    "(regular_season_df['year']==2018),'SLG'].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 평균 성적이 결측치인 선수들에 대해 평균 SLG의 하위 25% 성적 기입\n",
    "submission_SLG.loc[submission_SLG['mean_SLG'].isna(),'mean_SLG'] = \\\n",
    "    np.quantile(player_SLG_mean['mean_SLG'],0.25)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_id</th>\n",
       "      <th>batter_name</th>\n",
       "      <th>year</th>\n",
       "      <th>year_born</th>\n",
       "      <th>age</th>\n",
       "      <th>mean_SLG</th>\n",
       "      <th>lag1_SLG</th>\n",
       "      <th>lag2_SLG</th>\n",
       "      <th>lag3_SLG</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>2019</td>\n",
       "      <td>1992년 08월 11일</td>\n",
       "      <td>27</td>\n",
       "      <td>0.332527</td>\n",
       "      <td>0.523810</td>\n",
       "      <td>0.256098</td>\n",
       "      <td>0.222222</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>강구성</td>\n",
       "      <td>2019</td>\n",
       "      <td>1993년 06월 09일</td>\n",
       "      <td>26</td>\n",
       "      <td>0.326923</td>\n",
       "      <td>0.391429</td>\n",
       "      <td>0.385754</td>\n",
       "      <td>0.385397</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>강민국</td>\n",
       "      <td>2019</td>\n",
       "      <td>1992년 01월 10일</td>\n",
       "      <td>27</td>\n",
       "      <td>0.326923</td>\n",
       "      <td>0.391429</td>\n",
       "      <td>0.385754</td>\n",
       "      <td>0.385397</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>강민호</td>\n",
       "      <td>2019</td>\n",
       "      <td>1985년 08월 18일</td>\n",
       "      <td>34</td>\n",
       "      <td>0.466540</td>\n",
       "      <td>0.487273</td>\n",
       "      <td>0.548736</td>\n",
       "      <td>0.577689</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>강백호</td>\n",
       "      <td>2019</td>\n",
       "      <td>1999년 07월 29일</td>\n",
       "      <td>20</td>\n",
       "      <td>0.523719</td>\n",
       "      <td>0.532051</td>\n",
       "      <td>0.484152</td>\n",
       "      <td>0.483795</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   batter_id batter_name  year      year_born  age  mean_SLG  lag1_SLG  \\\n",
       "0          1         강경학  2019  1992년 08월 11일   27  0.332527  0.523810   \n",
       "1          2         강구성  2019  1993년 06월 09일   26  0.326923  0.391429   \n",
       "2          3         강민국  2019  1992년 01월 10일   27  0.326923  0.391429   \n",
       "3          4         강민호  2019  1985년 08월 18일   34  0.466540  0.487273   \n",
       "4          5         강백호  2019  1999년 07월 29일   20  0.523719  0.532051   \n",
       "\n",
       "   lag2_SLG  lag3_SLG  \n",
       "0  0.256098  0.222222  \n",
       "1  0.385754  0.385397  \n",
       "2  0.385754  0.385397  \n",
       "3  0.548736  0.577689  \n",
       "4  0.484152  0.483795  "
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "for i in [1,2,3]:\n",
    "    # i년 전 SLG 성적 결측치 처리\n",
    "    submission_SLG = lag_na_fill(submission_SLG, 'SLG', i, season_SLG_mean)\n",
    "submission_SLG.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Random Forests를 이용해 OBP 예측\n",
    "predict_OBP = OBP_RF_models['RF'].predict(submission_OBP.iloc[:,-5:]) \n",
    "# Lasso를 이용해 SLG 예측\n",
    "predict_SLG = SLG_linear_models ['Lasso'].predict(submission_SLG.iloc[:,-5:])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "<ipython-input-84-400b298e7ac7>:2: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  final_submission['OPS'] = predict_SLG + predict_OBP # OBP + SLG = OPS\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_id</th>\n",
       "      <th>batter_name</th>\n",
       "      <th>OPS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>0.503957</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>강구성</td>\n",
       "      <td>0.687933</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>강민국</td>\n",
       "      <td>0.696609</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>강민호</td>\n",
       "      <td>0.958395</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>강백호</td>\n",
       "      <td>0.751592</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>8</td>\n",
       "      <td>강상원</td>\n",
       "      <td>0.661807</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>9</td>\n",
       "      <td>강승호</td>\n",
       "      <td>0.505642</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>11</td>\n",
       "      <td>강진성</td>\n",
       "      <td>0.656007</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>12</td>\n",
       "      <td>강한울</td>\n",
       "      <td>0.672859</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>16</td>\n",
       "      <td>고명성</td>\n",
       "      <td>0.640507</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   batter_id batter_name       OPS\n",
       "0          1         강경학  0.503957\n",
       "1          2         강구성  0.687933\n",
       "2          3         강민국  0.696609\n",
       "3          4         강민호  0.958395\n",
       "4          5         강백호  0.751592\n",
       "5          8         강상원  0.661807\n",
       "6          9         강승호  0.505642\n",
       "7         11         강진성  0.656007\n",
       "8         12         강한울  0.672859\n",
       "9         16         고명성  0.640507"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_submission = submission[['batter_id','batter_name']]\n",
    "final_submission['OPS'] = predict_SLG + predict_OBP # OBP + SLG = OPS \n",
    "final_submission.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "<ipython-input-88-db27b64caf8d>:1: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  final_submission['OPS'] = final_submission['OPS'] - 0.038\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>batter_id</th>\n",
       "      <th>batter_name</th>\n",
       "      <th>OPS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>강경학</td>\n",
       "      <td>0.465957</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>강구성</td>\n",
       "      <td>0.649933</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>강민국</td>\n",
       "      <td>0.658609</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>강민호</td>\n",
       "      <td>0.920395</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>강백호</td>\n",
       "      <td>0.713592</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>8</td>\n",
       "      <td>강상원</td>\n",
       "      <td>0.623807</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>9</td>\n",
       "      <td>강승호</td>\n",
       "      <td>0.467642</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>11</td>\n",
       "      <td>강진성</td>\n",
       "      <td>0.618007</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>12</td>\n",
       "      <td>강한울</td>\n",
       "      <td>0.634859</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>16</td>\n",
       "      <td>고명성</td>\n",
       "      <td>0.602507</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   batter_id batter_name       OPS\n",
       "0          1         강경학  0.465957\n",
       "1          2         강구성  0.649933\n",
       "2          3         강민국  0.658609\n",
       "3          4         강민호  0.920395\n",
       "4          5         강백호  0.713592\n",
       "5          8         강상원  0.623807\n",
       "6          9         강승호  0.467642\n",
       "7         11         강진성  0.618007\n",
       "8         12         강한울  0.634859\n",
       "9         16         고명성  0.602507"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "final_submission['OPS'] = final_submission['OPS'] - 0.038\n",
    "display(final_submission.head(10))\n",
    "final_submission.to_csv('submission.csv', index=False) # 최종 제출파일 생성"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.13"
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}