{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "c5def04f",
   "metadata": {},
   "source": [
    "<img src = \"DB.jpeg\">"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "97d27415",
   "metadata": {},
   "source": [
    "### 1. 패키지(Package)\n",
    "- 설치하기 : pip install 패키지명\n",
    "- 로딩하기 : import 패키지명 as 애칭(별명)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "2a98cc43",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 패키지 로딩하기\n",
    "import seaborn as sns # 데이터 시각화(Data Visualization)\n",
    "import pandas  as pd  # 데이터 읽어오기, 핸들링, 분석   "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "428e4d2b",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 예제 데이터 : diamonds\n",
    "diamonds = sns.load_dataset(\"diamonds\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "27273539",
   "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>carat</th>\n",
       "      <th>cut</th>\n",
       "      <th>color</th>\n",
       "      <th>clarity</th>\n",
       "      <th>depth</th>\n",
       "      <th>table</th>\n",
       "      <th>price</th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "      <th>z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.23</td>\n",
       "      <td>Ideal</td>\n",
       "      <td>E</td>\n",
       "      <td>SI2</td>\n",
       "      <td>61.5</td>\n",
       "      <td>55.0</td>\n",
       "      <td>326</td>\n",
       "      <td>3.95</td>\n",
       "      <td>3.98</td>\n",
       "      <td>2.43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.21</td>\n",
       "      <td>Premium</td>\n",
       "      <td>E</td>\n",
       "      <td>SI1</td>\n",
       "      <td>59.8</td>\n",
       "      <td>61.0</td>\n",
       "      <td>326</td>\n",
       "      <td>3.89</td>\n",
       "      <td>3.84</td>\n",
       "      <td>2.31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.23</td>\n",
       "      <td>Good</td>\n",
       "      <td>E</td>\n",
       "      <td>VS1</td>\n",
       "      <td>56.9</td>\n",
       "      <td>65.0</td>\n",
       "      <td>327</td>\n",
       "      <td>4.05</td>\n",
       "      <td>4.07</td>\n",
       "      <td>2.31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.29</td>\n",
       "      <td>Premium</td>\n",
       "      <td>I</td>\n",
       "      <td>VS2</td>\n",
       "      <td>62.4</td>\n",
       "      <td>58.0</td>\n",
       "      <td>334</td>\n",
       "      <td>4.20</td>\n",
       "      <td>4.23</td>\n",
       "      <td>2.63</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.31</td>\n",
       "      <td>Good</td>\n",
       "      <td>J</td>\n",
       "      <td>SI2</td>\n",
       "      <td>63.3</td>\n",
       "      <td>58.0</td>\n",
       "      <td>335</td>\n",
       "      <td>4.34</td>\n",
       "      <td>4.35</td>\n",
       "      <td>2.75</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   carat      cut color clarity  depth  table  price     x     y     z\n",
       "0   0.23    Ideal     E     SI2   61.5   55.0    326  3.95  3.98  2.43\n",
       "1   0.21  Premium     E     SI1   59.8   61.0    326  3.89  3.84  2.31\n",
       "2   0.23     Good     E     VS1   56.9   65.0    327  4.05  4.07  2.31\n",
       "3   0.29  Premium     I     VS2   62.4   58.0    334  4.20  4.23  2.63\n",
       "4   0.31     Good     J     SI2   63.3   58.0    335  4.34  4.35  2.75"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 데이터의 일부 보기\n",
    "# data.head(n = 5)\n",
    "diamonds.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e584b421",
   "metadata": {},
   "source": [
    "### 2. 연산자(Operator)\n",
    "- 산술 연산자\n",
    "- 할당 연산자\n",
    "- 비교 연산자\n",
    "- 논리 연산자"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "b6519086",
   "metadata": {},
   "outputs": [],
   "source": [
    "# (1) 산술 연산자\n",
    "# +, -, *, /, %, //, **\n",
    "# 기존에 없었던 새로운 열을 만들 때에 사용"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "848eb0ee",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "7"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "3 + 4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "ed6c8c47",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-1"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "3 - 4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "1ea5d465",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "12"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "3 * 4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "ee9311f7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.75"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "3 / 4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "36938f4b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "13 % 4 # 나머지"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "affebe7c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "13 // 4 # 몫"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "62a08d19",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "28561"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "13 ** 4 # 거듭제곱"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "5d73f886",
   "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>carat</th>\n",
       "      <th>cut</th>\n",
       "      <th>color</th>\n",
       "      <th>clarity</th>\n",
       "      <th>depth</th>\n",
       "      <th>table</th>\n",
       "      <th>price</th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "      <th>z</th>\n",
       "      <th>xyz_mean</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.23</td>\n",
       "      <td>Ideal</td>\n",
       "      <td>E</td>\n",
       "      <td>SI2</td>\n",
       "      <td>61.5</td>\n",
       "      <td>55.0</td>\n",
       "      <td>326</td>\n",
       "      <td>3.95</td>\n",
       "      <td>3.98</td>\n",
       "      <td>2.43</td>\n",
       "      <td>3.453333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.21</td>\n",
       "      <td>Premium</td>\n",
       "      <td>E</td>\n",
       "      <td>SI1</td>\n",
       "      <td>59.8</td>\n",
       "      <td>61.0</td>\n",
       "      <td>326</td>\n",
       "      <td>3.89</td>\n",
       "      <td>3.84</td>\n",
       "      <td>2.31</td>\n",
       "      <td>3.346667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.23</td>\n",
       "      <td>Good</td>\n",
       "      <td>E</td>\n",
       "      <td>VS1</td>\n",
       "      <td>56.9</td>\n",
       "      <td>65.0</td>\n",
       "      <td>327</td>\n",
       "      <td>4.05</td>\n",
       "      <td>4.07</td>\n",
       "      <td>2.31</td>\n",
       "      <td>3.476667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.29</td>\n",
       "      <td>Premium</td>\n",
       "      <td>I</td>\n",
       "      <td>VS2</td>\n",
       "      <td>62.4</td>\n",
       "      <td>58.0</td>\n",
       "      <td>334</td>\n",
       "      <td>4.20</td>\n",
       "      <td>4.23</td>\n",
       "      <td>2.63</td>\n",
       "      <td>3.686667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.31</td>\n",
       "      <td>Good</td>\n",
       "      <td>J</td>\n",
       "      <td>SI2</td>\n",
       "      <td>63.3</td>\n",
       "      <td>58.0</td>\n",
       "      <td>335</td>\n",
       "      <td>4.34</td>\n",
       "      <td>4.35</td>\n",
       "      <td>2.75</td>\n",
       "      <td>3.813333</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   carat      cut color clarity  depth  table  price     x     y     z  \\\n",
       "0   0.23    Ideal     E     SI2   61.5   55.0    326  3.95  3.98  2.43   \n",
       "1   0.21  Premium     E     SI1   59.8   61.0    326  3.89  3.84  2.31   \n",
       "2   0.23     Good     E     VS1   56.9   65.0    327  4.05  4.07  2.31   \n",
       "3   0.29  Premium     I     VS2   62.4   58.0    334  4.20  4.23  2.63   \n",
       "4   0.31     Good     J     SI2   63.3   58.0    335  4.34  4.35  2.75   \n",
       "\n",
       "   xyz_mean  \n",
       "0  3.453333  \n",
       "1  3.346667  \n",
       "2  3.476667  \n",
       "3  3.686667  \n",
       "4  3.813333  "
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# xyz_mean : 새로운 열의 이름\n",
    "# (x + y + z)/3 \n",
    "# 평균 : 데이터를 다 더 하고, 자유로도 나눈 값\n",
    "\n",
    "diamonds[\"xyz_mean\"] = (diamonds[\"x\"] + diamonds[\"y\"] + diamonds[\"z\"])/3\n",
    "diamonds.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "7a5d0f43",
   "metadata": {},
   "outputs": [],
   "source": [
    "# (2) 할당 연산자\n",
    "# = \n",
    "# 저장하는 기능"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "33c7faa7",
   "metadata": {},
   "outputs": [],
   "source": [
    "age = 29"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "57c34868",
   "metadata": {},
   "outputs": [],
   "source": [
    "# age : data, RAM에 저장됨"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "50180350",
   "metadata": {},
   "outputs": [],
   "source": [
    "name = \"허민\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "c2123757",
   "metadata": {},
   "outputs": [],
   "source": [
    "# name : data, RAM에 저장됨"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "d2e8ea2e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# (3) 비교 연산자\n",
    "# >, >=, <, <=, ==, !=\n",
    "# 전체 데이터 중에서 조건에 맞는 데이터를 추출\n",
    "# 행 기준"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "c099fe16",
   "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>carat</th>\n",
       "      <th>cut</th>\n",
       "      <th>color</th>\n",
       "      <th>clarity</th>\n",
       "      <th>depth</th>\n",
       "      <th>table</th>\n",
       "      <th>price</th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "      <th>z</th>\n",
       "      <th>xyz_mean</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>25998</th>\n",
       "      <td>4.01</td>\n",
       "      <td>Premium</td>\n",
       "      <td>I</td>\n",
       "      <td>I1</td>\n",
       "      <td>61.0</td>\n",
       "      <td>61.0</td>\n",
       "      <td>15223</td>\n",
       "      <td>10.14</td>\n",
       "      <td>10.10</td>\n",
       "      <td>6.17</td>\n",
       "      <td>8.803333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25999</th>\n",
       "      <td>4.01</td>\n",
       "      <td>Premium</td>\n",
       "      <td>J</td>\n",
       "      <td>I1</td>\n",
       "      <td>62.5</td>\n",
       "      <td>62.0</td>\n",
       "      <td>15223</td>\n",
       "      <td>10.02</td>\n",
       "      <td>9.94</td>\n",
       "      <td>6.24</td>\n",
       "      <td>8.733333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26444</th>\n",
       "      <td>4.00</td>\n",
       "      <td>Very Good</td>\n",
       "      <td>I</td>\n",
       "      <td>I1</td>\n",
       "      <td>63.3</td>\n",
       "      <td>58.0</td>\n",
       "      <td>15984</td>\n",
       "      <td>10.01</td>\n",
       "      <td>9.94</td>\n",
       "      <td>6.31</td>\n",
       "      <td>8.753333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27130</th>\n",
       "      <td>4.13</td>\n",
       "      <td>Fair</td>\n",
       "      <td>H</td>\n",
       "      <td>I1</td>\n",
       "      <td>64.8</td>\n",
       "      <td>61.0</td>\n",
       "      <td>17329</td>\n",
       "      <td>10.00</td>\n",
       "      <td>9.85</td>\n",
       "      <td>6.43</td>\n",
       "      <td>8.760000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27415</th>\n",
       "      <td>5.01</td>\n",
       "      <td>Fair</td>\n",
       "      <td>J</td>\n",
       "      <td>I1</td>\n",
       "      <td>65.5</td>\n",
       "      <td>59.0</td>\n",
       "      <td>18018</td>\n",
       "      <td>10.74</td>\n",
       "      <td>10.54</td>\n",
       "      <td>6.98</td>\n",
       "      <td>9.420000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27630</th>\n",
       "      <td>4.50</td>\n",
       "      <td>Fair</td>\n",
       "      <td>J</td>\n",
       "      <td>I1</td>\n",
       "      <td>65.8</td>\n",
       "      <td>58.0</td>\n",
       "      <td>18531</td>\n",
       "      <td>10.23</td>\n",
       "      <td>10.16</td>\n",
       "      <td>6.72</td>\n",
       "      <td>9.036667</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       carat        cut color clarity  depth  table  price      x      y  \\\n",
       "25998   4.01    Premium     I      I1   61.0   61.0  15223  10.14  10.10   \n",
       "25999   4.01    Premium     J      I1   62.5   62.0  15223  10.02   9.94   \n",
       "26444   4.00  Very Good     I      I1   63.3   58.0  15984  10.01   9.94   \n",
       "27130   4.13       Fair     H      I1   64.8   61.0  17329  10.00   9.85   \n",
       "27415   5.01       Fair     J      I1   65.5   59.0  18018  10.74  10.54   \n",
       "27630   4.50       Fair     J      I1   65.8   58.0  18531  10.23  10.16   \n",
       "\n",
       "          z  xyz_mean  \n",
       "25998  6.17  8.803333  \n",
       "25999  6.24  8.733333  \n",
       "26444  6.31  8.753333  \n",
       "27130  6.43  8.760000  \n",
       "27415  6.98  9.420000  \n",
       "27630  6.72  9.036667  "
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# i. carat(무게)가 4 이상인 다이아몬드\n",
    "# data.loc[행, :]\n",
    "\n",
    "diamonds.loc[diamonds[\"carat\"] >= 4 , :]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "4bc27c14",
   "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>carat</th>\n",
       "      <th>cut</th>\n",
       "      <th>color</th>\n",
       "      <th>clarity</th>\n",
       "      <th>depth</th>\n",
       "      <th>table</th>\n",
       "      <th>price</th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "      <th>z</th>\n",
       "      <th>xyz_mean</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.23</td>\n",
       "      <td>Good</td>\n",
       "      <td>E</td>\n",
       "      <td>VS1</td>\n",
       "      <td>56.9</td>\n",
       "      <td>65.0</td>\n",
       "      <td>327</td>\n",
       "      <td>4.05</td>\n",
       "      <td>4.07</td>\n",
       "      <td>2.31</td>\n",
       "      <td>3.476667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.31</td>\n",
       "      <td>Good</td>\n",
       "      <td>J</td>\n",
       "      <td>SI2</td>\n",
       "      <td>63.3</td>\n",
       "      <td>58.0</td>\n",
       "      <td>335</td>\n",
       "      <td>4.34</td>\n",
       "      <td>4.35</td>\n",
       "      <td>2.75</td>\n",
       "      <td>3.813333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>0.30</td>\n",
       "      <td>Good</td>\n",
       "      <td>J</td>\n",
       "      <td>SI1</td>\n",
       "      <td>64.0</td>\n",
       "      <td>55.0</td>\n",
       "      <td>339</td>\n",
       "      <td>4.25</td>\n",
       "      <td>4.28</td>\n",
       "      <td>2.73</td>\n",
       "      <td>3.753333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>0.30</td>\n",
       "      <td>Good</td>\n",
       "      <td>J</td>\n",
       "      <td>SI1</td>\n",
       "      <td>63.4</td>\n",
       "      <td>54.0</td>\n",
       "      <td>351</td>\n",
       "      <td>4.23</td>\n",
       "      <td>4.29</td>\n",
       "      <td>2.70</td>\n",
       "      <td>3.740000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>0.30</td>\n",
       "      <td>Good</td>\n",
       "      <td>J</td>\n",
       "      <td>SI1</td>\n",
       "      <td>63.8</td>\n",
       "      <td>56.0</td>\n",
       "      <td>351</td>\n",
       "      <td>4.23</td>\n",
       "      <td>4.26</td>\n",
       "      <td>2.71</td>\n",
       "      <td>3.733333</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>53913</th>\n",
       "      <td>0.80</td>\n",
       "      <td>Good</td>\n",
       "      <td>G</td>\n",
       "      <td>VS2</td>\n",
       "      <td>64.2</td>\n",
       "      <td>58.0</td>\n",
       "      <td>2753</td>\n",
       "      <td>5.84</td>\n",
       "      <td>5.81</td>\n",
       "      <td>3.74</td>\n",
       "      <td>5.130000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>53914</th>\n",
       "      <td>0.84</td>\n",
       "      <td>Good</td>\n",
       "      <td>I</td>\n",
       "      <td>VS1</td>\n",
       "      <td>63.7</td>\n",
       "      <td>59.0</td>\n",
       "      <td>2753</td>\n",
       "      <td>5.94</td>\n",
       "      <td>5.90</td>\n",
       "      <td>3.77</td>\n",
       "      <td>5.203333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>53916</th>\n",
       "      <td>0.74</td>\n",
       "      <td>Good</td>\n",
       "      <td>D</td>\n",
       "      <td>SI1</td>\n",
       "      <td>63.1</td>\n",
       "      <td>59.0</td>\n",
       "      <td>2753</td>\n",
       "      <td>5.71</td>\n",
       "      <td>5.74</td>\n",
       "      <td>3.61</td>\n",
       "      <td>5.020000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>53927</th>\n",
       "      <td>0.79</td>\n",
       "      <td>Good</td>\n",
       "      <td>F</td>\n",
       "      <td>SI1</td>\n",
       "      <td>58.1</td>\n",
       "      <td>59.0</td>\n",
       "      <td>2756</td>\n",
       "      <td>6.06</td>\n",
       "      <td>6.13</td>\n",
       "      <td>3.54</td>\n",
       "      <td>5.243333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>53936</th>\n",
       "      <td>0.72</td>\n",
       "      <td>Good</td>\n",
       "      <td>D</td>\n",
       "      <td>SI1</td>\n",
       "      <td>63.1</td>\n",
       "      <td>55.0</td>\n",
       "      <td>2757</td>\n",
       "      <td>5.69</td>\n",
       "      <td>5.75</td>\n",
       "      <td>3.61</td>\n",
       "      <td>5.016667</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4906 rows × 11 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       carat   cut color clarity  depth  table  price     x     y     z  \\\n",
       "2       0.23  Good     E     VS1   56.9   65.0    327  4.05  4.07  2.31   \n",
       "4       0.31  Good     J     SI2   63.3   58.0    335  4.34  4.35  2.75   \n",
       "10      0.30  Good     J     SI1   64.0   55.0    339  4.25  4.28  2.73   \n",
       "17      0.30  Good     J     SI1   63.4   54.0    351  4.23  4.29  2.70   \n",
       "18      0.30  Good     J     SI1   63.8   56.0    351  4.23  4.26  2.71   \n",
       "...      ...   ...   ...     ...    ...    ...    ...   ...   ...   ...   \n",
       "53913   0.80  Good     G     VS2   64.2   58.0   2753  5.84  5.81  3.74   \n",
       "53914   0.84  Good     I     VS1   63.7   59.0   2753  5.94  5.90  3.77   \n",
       "53916   0.74  Good     D     SI1   63.1   59.0   2753  5.71  5.74  3.61   \n",
       "53927   0.79  Good     F     SI1   58.1   59.0   2756  6.06  6.13  3.54   \n",
       "53936   0.72  Good     D     SI1   63.1   55.0   2757  5.69  5.75  3.61   \n",
       "\n",
       "       xyz_mean  \n",
       "2      3.476667  \n",
       "4      3.813333  \n",
       "10     3.753333  \n",
       "17     3.740000  \n",
       "18     3.733333  \n",
       "...         ...  \n",
       "53913  5.130000  \n",
       "53914  5.203333  \n",
       "53916  5.020000  \n",
       "53927  5.243333  \n",
       "53936  5.016667  \n",
       "\n",
       "[4906 rows x 11 columns]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# ii. cut(품질)이 \"Good\"인 다이아몬드\n",
    "# data.loc[행, :]\n",
    "\n",
    "diamonds.loc[diamonds[\"cut\"] == \"Good\" , :]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "4e3c4e8e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# (4) 논리 연산자\n",
    "# &, |\n",
    "# 조건을 2개 이상 줄 때\n",
    "\n",
    "# & : and : 2개 이상의 조건을 모두 만족하는 데이터\n",
    "# | : or  : 2개 이상의 조건 중에서 하나만 만족해도 데이터"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "02abd635",
   "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>carat</th>\n",
       "      <th>cut</th>\n",
       "      <th>color</th>\n",
       "      <th>clarity</th>\n",
       "      <th>depth</th>\n",
       "      <th>table</th>\n",
       "      <th>price</th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "      <th>z</th>\n",
       "      <th>xyz_mean</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>22831</th>\n",
       "      <td>3.00</td>\n",
       "      <td>Good</td>\n",
       "      <td>I</td>\n",
       "      <td>I1</td>\n",
       "      <td>57.0</td>\n",
       "      <td>64.0</td>\n",
       "      <td>10863</td>\n",
       "      <td>9.38</td>\n",
       "      <td>9.31</td>\n",
       "      <td>5.33</td>\n",
       "      <td>8.006667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23539</th>\n",
       "      <td>3.00</td>\n",
       "      <td>Good</td>\n",
       "      <td>E</td>\n",
       "      <td>I1</td>\n",
       "      <td>64.2</td>\n",
       "      <td>65.0</td>\n",
       "      <td>11548</td>\n",
       "      <td>9.08</td>\n",
       "      <td>8.96</td>\n",
       "      <td>5.79</td>\n",
       "      <td>7.943333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25850</th>\n",
       "      <td>3.00</td>\n",
       "      <td>Good</td>\n",
       "      <td>J</td>\n",
       "      <td>SI2</td>\n",
       "      <td>59.3</td>\n",
       "      <td>64.0</td>\n",
       "      <td>14918</td>\n",
       "      <td>9.32</td>\n",
       "      <td>9.19</td>\n",
       "      <td>5.50</td>\n",
       "      <td>8.003333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27517</th>\n",
       "      <td>3.01</td>\n",
       "      <td>Good</td>\n",
       "      <td>I</td>\n",
       "      <td>SI2</td>\n",
       "      <td>63.9</td>\n",
       "      <td>60.0</td>\n",
       "      <td>18242</td>\n",
       "      <td>9.06</td>\n",
       "      <td>9.01</td>\n",
       "      <td>5.77</td>\n",
       "      <td>7.946667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27518</th>\n",
       "      <td>3.01</td>\n",
       "      <td>Good</td>\n",
       "      <td>I</td>\n",
       "      <td>SI2</td>\n",
       "      <td>63.9</td>\n",
       "      <td>60.0</td>\n",
       "      <td>18242</td>\n",
       "      <td>9.06</td>\n",
       "      <td>9.01</td>\n",
       "      <td>5.77</td>\n",
       "      <td>7.946667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27649</th>\n",
       "      <td>3.01</td>\n",
       "      <td>Good</td>\n",
       "      <td>H</td>\n",
       "      <td>SI2</td>\n",
       "      <td>57.6</td>\n",
       "      <td>64.0</td>\n",
       "      <td>18593</td>\n",
       "      <td>9.44</td>\n",
       "      <td>9.38</td>\n",
       "      <td>5.42</td>\n",
       "      <td>8.080000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       carat   cut color clarity  depth  table  price     x     y     z  \\\n",
       "22831   3.00  Good     I      I1   57.0   64.0  10863  9.38  9.31  5.33   \n",
       "23539   3.00  Good     E      I1   64.2   65.0  11548  9.08  8.96  5.79   \n",
       "25850   3.00  Good     J     SI2   59.3   64.0  14918  9.32  9.19  5.50   \n",
       "27517   3.01  Good     I     SI2   63.9   60.0  18242  9.06  9.01  5.77   \n",
       "27518   3.01  Good     I     SI2   63.9   60.0  18242  9.06  9.01  5.77   \n",
       "27649   3.01  Good     H     SI2   57.6   64.0  18593  9.44  9.38  5.42   \n",
       "\n",
       "       xyz_mean  \n",
       "22831  8.006667  \n",
       "23539  7.943333  \n",
       "25850  8.003333  \n",
       "27517  7.946667  \n",
       "27518  7.946667  \n",
       "27649  8.080000  "
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# i. carat은 3이상이고, cut은 \"Good\"인 데이터\n",
    "diamonds.loc[(diamonds[\"carat\"] >= 3) & (diamonds[\"cut\"] == \"Good\") , :]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "227ea216",
   "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>carat</th>\n",
       "      <th>cut</th>\n",
       "      <th>color</th>\n",
       "      <th>clarity</th>\n",
       "      <th>depth</th>\n",
       "      <th>table</th>\n",
       "      <th>price</th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "      <th>z</th>\n",
       "      <th>xyz_mean</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.23</td>\n",
       "      <td>Good</td>\n",
       "      <td>E</td>\n",
       "      <td>VS1</td>\n",
       "      <td>56.9</td>\n",
       "      <td>65.0</td>\n",
       "      <td>327</td>\n",
       "      <td>4.05</td>\n",
       "      <td>4.07</td>\n",
       "      <td>2.31</td>\n",
       "      <td>3.476667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.31</td>\n",
       "      <td>Good</td>\n",
       "      <td>J</td>\n",
       "      <td>SI2</td>\n",
       "      <td>63.3</td>\n",
       "      <td>58.0</td>\n",
       "      <td>335</td>\n",
       "      <td>4.34</td>\n",
       "      <td>4.35</td>\n",
       "      <td>2.75</td>\n",
       "      <td>3.813333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>0.30</td>\n",
       "      <td>Good</td>\n",
       "      <td>J</td>\n",
       "      <td>SI1</td>\n",
       "      <td>64.0</td>\n",
       "      <td>55.0</td>\n",
       "      <td>339</td>\n",
       "      <td>4.25</td>\n",
       "      <td>4.28</td>\n",
       "      <td>2.73</td>\n",
       "      <td>3.753333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>0.30</td>\n",
       "      <td>Good</td>\n",
       "      <td>J</td>\n",
       "      <td>SI1</td>\n",
       "      <td>63.4</td>\n",
       "      <td>54.0</td>\n",
       "      <td>351</td>\n",
       "      <td>4.23</td>\n",
       "      <td>4.29</td>\n",
       "      <td>2.70</td>\n",
       "      <td>3.740000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>0.30</td>\n",
       "      <td>Good</td>\n",
       "      <td>J</td>\n",
       "      <td>SI1</td>\n",
       "      <td>63.8</td>\n",
       "      <td>56.0</td>\n",
       "      <td>351</td>\n",
       "      <td>4.23</td>\n",
       "      <td>4.26</td>\n",
       "      <td>2.71</td>\n",
       "      <td>3.733333</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>53913</th>\n",
       "      <td>0.80</td>\n",
       "      <td>Good</td>\n",
       "      <td>G</td>\n",
       "      <td>VS2</td>\n",
       "      <td>64.2</td>\n",
       "      <td>58.0</td>\n",
       "      <td>2753</td>\n",
       "      <td>5.84</td>\n",
       "      <td>5.81</td>\n",
       "      <td>3.74</td>\n",
       "      <td>5.130000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>53914</th>\n",
       "      <td>0.84</td>\n",
       "      <td>Good</td>\n",
       "      <td>I</td>\n",
       "      <td>VS1</td>\n",
       "      <td>63.7</td>\n",
       "      <td>59.0</td>\n",
       "      <td>2753</td>\n",
       "      <td>5.94</td>\n",
       "      <td>5.90</td>\n",
       "      <td>3.77</td>\n",
       "      <td>5.203333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>53916</th>\n",
       "      <td>0.74</td>\n",
       "      <td>Good</td>\n",
       "      <td>D</td>\n",
       "      <td>SI1</td>\n",
       "      <td>63.1</td>\n",
       "      <td>59.0</td>\n",
       "      <td>2753</td>\n",
       "      <td>5.71</td>\n",
       "      <td>5.74</td>\n",
       "      <td>3.61</td>\n",
       "      <td>5.020000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>53927</th>\n",
       "      <td>0.79</td>\n",
       "      <td>Good</td>\n",
       "      <td>F</td>\n",
       "      <td>SI1</td>\n",
       "      <td>58.1</td>\n",
       "      <td>59.0</td>\n",
       "      <td>2756</td>\n",
       "      <td>6.06</td>\n",
       "      <td>6.13</td>\n",
       "      <td>3.54</td>\n",
       "      <td>5.243333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>53936</th>\n",
       "      <td>0.72</td>\n",
       "      <td>Good</td>\n",
       "      <td>D</td>\n",
       "      <td>SI1</td>\n",
       "      <td>63.1</td>\n",
       "      <td>55.0</td>\n",
       "      <td>2757</td>\n",
       "      <td>5.69</td>\n",
       "      <td>5.75</td>\n",
       "      <td>3.61</td>\n",
       "      <td>5.016667</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4940 rows × 11 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       carat   cut color clarity  depth  table  price     x     y     z  \\\n",
       "2       0.23  Good     E     VS1   56.9   65.0    327  4.05  4.07  2.31   \n",
       "4       0.31  Good     J     SI2   63.3   58.0    335  4.34  4.35  2.75   \n",
       "10      0.30  Good     J     SI1   64.0   55.0    339  4.25  4.28  2.73   \n",
       "17      0.30  Good     J     SI1   63.4   54.0    351  4.23  4.29  2.70   \n",
       "18      0.30  Good     J     SI1   63.8   56.0    351  4.23  4.26  2.71   \n",
       "...      ...   ...   ...     ...    ...    ...    ...   ...   ...   ...   \n",
       "53913   0.80  Good     G     VS2   64.2   58.0   2753  5.84  5.81  3.74   \n",
       "53914   0.84  Good     I     VS1   63.7   59.0   2753  5.94  5.90  3.77   \n",
       "53916   0.74  Good     D     SI1   63.1   59.0   2753  5.71  5.74  3.61   \n",
       "53927   0.79  Good     F     SI1   58.1   59.0   2756  6.06  6.13  3.54   \n",
       "53936   0.72  Good     D     SI1   63.1   55.0   2757  5.69  5.75  3.61   \n",
       "\n",
       "       xyz_mean  \n",
       "2      3.476667  \n",
       "4      3.813333  \n",
       "10     3.753333  \n",
       "17     3.740000  \n",
       "18     3.733333  \n",
       "...         ...  \n",
       "53913  5.130000  \n",
       "53914  5.203333  \n",
       "53916  5.020000  \n",
       "53927  5.243333  \n",
       "53936  5.016667  \n",
       "\n",
       "[4940 rows x 11 columns]"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# ii. carat은 3이상이거나 cut은 \"Good\"인 데이터\n",
    "diamonds.loc[(diamonds[\"carat\"] >= 3) | (diamonds[\"cut\"] == \"Good\") , :]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2a06be26",
   "metadata": {},
   "source": [
    "### 3. 데이터의 유형(Type of Data)\n",
    "- 수치형 : Numerical : 정수형(integer, int)\n",
    "- 수치형 : Numerical : 실수형(float)\n",
    "- 문자형 : String, Object\n",
    "- bool형 : Boolean   : True, False"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "a6c835b6",
   "metadata": {},
   "outputs": [],
   "source": [
    "# (1) 수치형(정수형)\n",
    "x1 = 10"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "c3f1c4b3",
   "metadata": {},
   "outputs": [],
   "source": [
    "# x1   : data\n",
    "# type : int"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "8ec6f923",
   "metadata": {},
   "outputs": [],
   "source": [
    "x2 = 10.2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "2674a877",
   "metadata": {},
   "outputs": [],
   "source": [
    "# x2   : data\n",
    "# type : float"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "094fedfd",
   "metadata": {},
   "outputs": [],
   "source": [
    "x3 = '인생은 고통의 바다이다.'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "710d289c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# x3   : data\n",
    "# type : object"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "f2b55c5e",
   "metadata": {},
   "outputs": [],
   "source": [
    "x4 = \"문제가 문제가 아니라 문제를 대하는 나의 태도가 문제다.\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "3feefd1e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# x4   : data\n",
    "# type : object"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "8beedebe",
   "metadata": {},
   "outputs": [],
   "source": [
    "x5 = True"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "3e738c86",
   "metadata": {},
   "outputs": [],
   "source": [
    "# x5   : data\n",
    "# type : bool"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "b1f4492b",
   "metadata": {},
   "outputs": [],
   "source": [
    "x6 = False"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "51f6e31a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# x6   : data\n",
    "# type : bool"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "189d166c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 53940 entries, 0 to 53939\n",
      "Data columns (total 11 columns):\n",
      " #   Column    Non-Null Count  Dtype   \n",
      "---  ------    --------------  -----   \n",
      " 0   carat     53940 non-null  float64 \n",
      " 1   cut       53940 non-null  category\n",
      " 2   color     53940 non-null  category\n",
      " 3   clarity   53940 non-null  category\n",
      " 4   depth     53940 non-null  float64 \n",
      " 5   table     53940 non-null  float64 \n",
      " 6   price     53940 non-null  int64   \n",
      " 7   x         53940 non-null  float64 \n",
      " 8   y         53940 non-null  float64 \n",
      " 9   z         53940 non-null  float64 \n",
      " 10  xyz_mean  53940 non-null  float64 \n",
      "dtypes: category(3), float64(7), int64(1)\n",
      "memory usage: 3.4 MB\n"
     ]
    }
   ],
   "source": [
    "# 데이터의 정보(Information) 보기\n",
    "# data.info()\n",
    "diamonds.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "93736c7f",
   "metadata": {},
   "source": [
    "### 4. 데이터(Data)\n",
    "- 리스트(list) *****\n",
    "- 튜플(tuple)\n",
    "- 딕셔너리(dictionary)\n",
    "- 시리즈(series)\n",
    "- 데이터프레임(DataFrame) *****"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "b550f5bd",
   "metadata": {},
   "outputs": [],
   "source": [
    "# (1) 리스트(List)\n",
    "# 가장 많이 사용하는 데이터 형태 중에 하나\n",
    "# 활용도\n",
    "# - 함수의 파라미터 설정에 2개 이상을 저장할 때\n",
    "# - 슬라이싱(Slicing)\n",
    "\n",
    "# 리스트 안에 있는 값은 수정이 가능함"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "cd96b2e7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# i. 리스트 만들기\n",
    "# [값, 값, ...]                   : 1차원 구조\n",
    "# [[값, 값, ...], [값, 값, ...]] : 2차원 구조"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "4c4d01da",
   "metadata": {},
   "outputs": [],
   "source": [
    "major = [\"통계학\", \"컴퓨터공학\", \"컴퓨터과학\", \"컴퓨터공학\", \"경제학\", \"수학\", \"컴퓨터공학\", \"수학\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "6736c42f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# major : data : list\n",
    "# type  : object"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "f2fb8b45",
   "metadata": {},
   "outputs": [],
   "source": [
    "sleep = [6, 8, 7, 6, 6]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "db0d0b68",
   "metadata": {},
   "outputs": [],
   "source": [
    "# sleep : data : list\n",
    "# type  : int"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "4dae2e48",
   "metadata": {},
   "outputs": [],
   "source": [
    "smoke = [False, False, True, False, False]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "b664826e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# smoke : data : list\n",
    "# type  : bool"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "d09b77e6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "10"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# ii. 리스트 슬라이싱\n",
    "# list[index]\n",
    "# index : 위치, 행(row), 행의 이름(row name)\n",
    "# 파이썬에서는 첫 번째 위치를 0\n",
    "sleep[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "4a9a2ad3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[10, 8]"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sleep[:2] # 파이썬 관점 : 0, 1번째를 슬라이싱"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "754a4c22",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[7, 6, 6]"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sleep[2:] # 파이썬 관점 : 2, 3, ... 끝까지 슬라이싱"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "2b7b934a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[10, 7, 6]"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sleep[::2] # 한 칸씩 건너 뛰면서 슬라이싱"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "1ba8575b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "6"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sleep[-1] # 제일 오른 쪽에 있는 값"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "aac44a81",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[10, 8, 7, 6, 6]"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# iii. 리스트의 값 수정하기\n",
    "sleep[0] = 10\n",
    "sleep"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ab23c3a7",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "72dc5a86",
   "metadata": {},
   "outputs": [],
   "source": [
    "# (2) 튜플(Tuple)\n",
    "# 리스트와 거의 비슷함\n",
    "# 값이 수정 불가\n",
    "# 초기값을 설정, 어떤 값이 변경되면 안될 때"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "42e19b5b",
   "metadata": {},
   "outputs": [],
   "source": [
    "# i. 튜플 만들기\n",
    "# (값, 값, ....)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "b5157de2",
   "metadata": {},
   "outputs": [],
   "source": [
    "address = (\"분당\", \"부천\", \"서울\", \"부천\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "id": "9720ef05",
   "metadata": {},
   "outputs": [],
   "source": [
    "# address : data : tuple\n",
    "# type    : object"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "dc5b34bf",
   "metadata": {},
   "outputs": [],
   "source": [
    "cyear = (17, 5, 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "8c2ef4a3",
   "metadata": {},
   "outputs": [],
   "source": [
    "# cyear : data : tuple\n",
    "# type  : int"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "02800693",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "28d08eb1",
   "metadata": {},
   "outputs": [],
   "source": [
    "# (3) 딕셔너리(Dictionary)\n",
    "# 키(key)와 값(value)로 이루어진 데이터 형태"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "9a411062",
   "metadata": {},
   "outputs": [],
   "source": [
    "# i. 딕셔너리 만들기\n",
    "# {\"key1\" : [value1, value2, ...],\n",
    "#  \"key2\" : [value1, value2, ...]}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "3e75dc5c",
   "metadata": {},
   "outputs": [],
   "source": [
    "survey = {\"id\"     : [1, 2, 3, 4],\n",
    "          \"nation\" : [\"한국\", \"스위스\", \"한국\", \"미국\"],\n",
    "          \"car\"    : [\"제네시스\", \"아반떼\", \"아이오닉5\", \"A4\"]}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "a24ad163",
   "metadata": {},
   "outputs": [],
   "source": [
    "# survey     : data : dictionary\n",
    "# key        : id, nation, car\n",
    "# value(id) : 1, 2, 3, 4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "14bb4879",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dict_items([('id', [1, 2, 3, 4]), ('nation', ['한국', '스위스', '한국', '미국']), ('car', ['제네시스', '아반떼', '아이오닉5', 'A4'])])"
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# items : key + value\n",
    "survey.items()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4e22b4a9",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "167da52e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# (4) 시리즈(Series)\n",
    "# 행과 열로 데이터 있는 데이터에서\n",
    "# 하나의 행 또는 하나의 열을 슬라이싱하면"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f87cb2c6",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "id": "b40d9fae",
   "metadata": {},
   "outputs": [],
   "source": [
    "# (5) 데이터프레임(DataFrame)\n",
    "# 행과 열로 구성되어 있음 : 2차원 구조\n",
    "# 열마다 같은 데이터 유형을 가져되고, 안 가져되 됨\n",
    "\n",
    "# 참고로\n",
    "# 모든 열이 하나의 데이터 유형만 가지는 행과 열로 된 것 : 행렬"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "ea28a219",
   "metadata": {},
   "outputs": [],
   "source": [
    "# i. 데이터 프레임 만들기\n",
    "# pandas.DataFrame(딕셔너리)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "1a845a2f",
   "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>id</th>\n",
       "      <th>nation</th>\n",
       "      <th>car</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>한국</td>\n",
       "      <td>제네시스</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>스위스</td>\n",
       "      <td>아반떼</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>한국</td>\n",
       "      <td>아이오닉5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>미국</td>\n",
       "      <td>A4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   id nation    car\n",
       "0   1     한국   제네시스\n",
       "1   2    스위스    아반떼\n",
       "2   3     한국  아이오닉5\n",
       "3   4     미국     A4"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame(survey)\n",
    "df # 데이터 보기 : 데이터의 양이 적을 때에 사용함"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c94645f1",
   "metadata": {},
   "source": [
    "### 5. 데이터 읽어오기\n",
    "- txt\n",
    "- csv : comma separated value\n",
    "- excel\n",
    "- pickle\n",
    "- etc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "id": "8a3f41f3",
   "metadata": {},
   "outputs": [],
   "source": [
    "# (1) txt\n",
    "# pandas.read_table(filepath_or_buffer = \"드라이브:/폴더/파일명.txt\",\n",
    "#                   sep                = 구분자,\n",
    "#                   header             = ,\n",
    "#                   encoding           = \"EUC-KR\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "06c99e7d",
   "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>id</th>\n",
       "      <th>food</th>\n",
       "      <th>drink</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>피자</td>\n",
       "      <td>소주</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>돼지갈비</td>\n",
       "      <td>소주</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>삼겹살</td>\n",
       "      <td>콜라</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>닭갈비</td>\n",
       "      <td>소주</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   id  food drink\n",
       "0   1    피자    소주\n",
       "1   2  돼지갈비    소주\n",
       "2   3   삼겹살    콜라\n",
       "3   4   닭갈비    소주"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# i. 구분자(Separater) : 공백(blank)\n",
    "blank = pd.read_table(filepath_or_buffer = \"d:/DB/blank.txt\",\n",
    "                      sep                = \" \",\n",
    "                      header             = 0)\n",
    "blank # DataFrame : 행과 열로 되어 있음"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "332256ef",
   "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>id</th>\n",
       "      <th>hobby</th>\n",
       "      <th>money</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>야구</td>\n",
       "      <td>50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>축구</td>\n",
       "      <td>100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>애니메이션</td>\n",
       "      <td>70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>영화보기</td>\n",
       "      <td>80</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>그림그리기</td>\n",
       "      <td>70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6</td>\n",
       "      <td>영화보기</td>\n",
       "      <td>80</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7</td>\n",
       "      <td>책사기</td>\n",
       "      <td>300</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   id  hobby  money\n",
       "0   1     야구     50\n",
       "1   2     축구    100\n",
       "2   3  애니메이션     70\n",
       "3   4   영화보기     80\n",
       "4   5  그림그리기     70\n",
       "5   6   영화보기     80\n",
       "6   7    책사기    300"
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# ii. 구분자(Separater) : 콤마(comma)\n",
    "comma = pd.read_table(filepath_or_buffer = \"d:/DB/comma.txt\",\n",
    "                      sep                = \",\",\n",
    "                      header             = 0)\n",
    "comma"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "e7fa1fb0",
   "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>id</th>\n",
       "      <th>weight</th>\n",
       "      <th>height</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>70</td>\n",
       "      <td>175</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>48</td>\n",
       "      <td>158</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>60</td>\n",
       "      <td>170</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>70</td>\n",
       "      <td>180</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>110</td>\n",
       "      <td>195</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   id  weight  height\n",
       "0   1      70     175\n",
       "1   2      48     158\n",
       "2   3      60     170\n",
       "3   4      70     180\n",
       "4   5     110     195"
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# iii. 구분자(Separater) : 탭(tab)\n",
    "tab = pd.read_table(filepath_or_buffer = \"d:/DB/tab.txt\",\n",
    "                    sep                = \"\\t\",\n",
    "                    header             = 0)\n",
    "tab"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "id": "452ab9cd",
   "metadata": {},
   "outputs": [],
   "source": [
    "# (2) csv : comma separated value\n",
    "# 엑셀의 특수한 형태\n",
    "# pandas.read_csv(filepath_or_buffer = \"드라이브/폴더/파일명.csv\",\n",
    "#                 header             = ,\n",
    "#                 encoding           = \"EUC-KR\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "638da291",
   "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>id</th>\n",
       "      <th>idol</th>\n",
       "      <th>myear</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>차은우</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>박보검</td>\n",
       "      <td>29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>고윤정</td>\n",
       "      <td>31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>지효</td>\n",
       "      <td>31</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   id idol  myear\n",
       "0   1  차은우     30\n",
       "1   2  박보검     29\n",
       "2   3  고윤정     31\n",
       "3   4   지효     31"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hope = pd.read_csv(filepath_or_buffer = \"d:/DB/hope.csv\",\n",
    "                   header             = 0,\n",
    "                   encoding           = \"EUC-KR\")\n",
    "hope"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "b9522168",
   "metadata": {},
   "outputs": [],
   "source": [
    "# (3) 엑셀 : xls, xlsx\n",
    "# pandas.read_excle(io         = \"드라이브/폴더/파일명.xlsx\",\n",
    "#                   sheet_name = index or \"name\",\n",
    "#                   header     = )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "62d3436e",
   "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>id</th>\n",
       "      <th>books</th>\n",
       "      <th>author</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>김영하</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>박민규</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   id  books author\n",
       "0   1      2    NaN\n",
       "1   2      3    김영하\n",
       "2   3      1    박민규"
      ]
     },
     "execution_count": 96,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reading = pd.read_excel(io         = \"d:/DB/reading.xlsx\",\n",
    "                        sheet_name = 0,\n",
    "                        header     = 0)\n",
    "reading"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "id": "edd11f1f",
   "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>id</th>\n",
       "      <th>books</th>\n",
       "      <th>author</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>김영하</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>박민규</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   id  books author\n",
       "0   1      2    NaN\n",
       "1   2      3    김영하\n",
       "2   3      1    박민규"
      ]
     },
     "execution_count": 97,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reading = pd.read_excel(io         = \"d:/DB/reading.xlsx\",\n",
    "                        sheet_name = \"data\",\n",
    "                        header     = 0)\n",
    "reading"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "id": "30656a5c",
   "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>id</th>\n",
       "      <th>books</th>\n",
       "      <th>author</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>김영하</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>박민규</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   id  books author\n",
       "0   1      2    NaN\n",
       "1   2      3    김영하\n",
       "2   3      1    박민규"
      ]
     },
     "execution_count": 105,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# (4) pickle\n",
    "# pandas.read_pickle(filepath_of_buffer = \"드라이브/폴더/파일명.pickle\")\n",
    "reading2 = pd.read_pickle(filepath_or_buffer = \"d:/DB/reading_2024_0308_1716.pickle\")\n",
    "reading2"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2ad7e98f",
   "metadata": {},
   "source": [
    "### 6. 데이터 저장하기 \n",
    "- RAM -> HDD\n",
    "- txt\n",
    "- csv\n",
    "- excel\n",
    "- pickle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "id": "f2df1c6d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# (1) txt\n",
    "# data.to_csv(path_or_buf = \"드라이브/폴더/파일명.txt\",\n",
    "#             sep         = \" \" or \",\" or \"\\t\")\n",
    "\n",
    "reading.to_csv(path_or_buf = \"d:/DB/reading_2024_0308_1706.txt\",\n",
    "               sep         = \" \",\n",
    "               index       = False)\n",
    "\n",
    "# 참고\n",
    "# index         : 행의 이름\n",
    "# index = False : 행의 이름은 저장하지 마세요."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "id": "9c8cf8d5",
   "metadata": {},
   "outputs": [],
   "source": [
    "# (2) csv\n",
    "# data.to_csv(path_or_buf = \"드라이브/폴더/파일명.csv\")\n",
    "\n",
    "reading.to_csv(path_or_buf = \"d:/DB/reading_2024_0308_1710.csv\",\n",
    "               index       = False,\n",
    "               encoding    = \"EUC-KR\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "id": "268c7e59",
   "metadata": {},
   "outputs": [],
   "source": [
    "# (3) excel\n",
    "# data.to_excel(excel_writer = \"드라이브/폴더/파일명.xlsx\",\n",
    "#               sheet_name   = \"name\",\n",
    "#               index        = False)\n",
    "\n",
    "reading.to_excel(excel_writer = \"d:/DB/reading_2024_0308_1713.xlsx\",\n",
    "                 sheet_name   = \"data2\",\n",
    "                 index        = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "id": "a96d08af",
   "metadata": {},
   "outputs": [],
   "source": [
    "# (4) pickle\n",
    "# data.to_pickle(path = \"드라이브/폴더/파일명.pickle\")\n",
    "reading.to_pickle(path = \"d:/DB/reading_2024_0308_1716.pickle\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "93f2a66c",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "hide_input": false,
  "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": "3.11.5"
  },
  "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": 5
}