{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "85a0ea68-1042-4997-8532-199438cfd75c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "전체 피처명에서 10개만 추출: ['tBodyAcc-mean()-X', 'tBodyAcc-mean()-Y', 'tBodyAcc-mean()-Z', 'tBodyAcc-std()-X', 'tBodyAcc-std()-Y', 'tBodyAcc-std()-Z', 'tBodyAcc-mad()-X', 'tBodyAcc-mad()-Y', 'tBodyAcc-mad()-Z', 'tBodyAcc-max()-X']\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "\n",
    "# features.txt 파일에는 피처 이름 index와 피처명이 공백으로 분리되어 있음\n",
    "# 이를 DataFrame으로 로드\n",
    "feature_name_df = pd.read_csv('C:/Users/niceq/Documents/DataScience/Python ML Guide/human_activity/features.txt',\n",
    "                               sep='\\s+', header=None, names=['column_index', 'column_name'])\n",
    "\n",
    "# 피처명 index를 제거하고, 피처명만 리스트 객체로 생성한 뒤 샘플로 10개만 추출\n",
    "feature_name = feature_name_df.iloc[:, 1].values.tolist()\n",
    "print('전체 피처명에서 10개만 추출:', feature_name[:10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "0ec3f58b-1caf-4762-afe7-4b9d315810ab",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "column_index    42\n",
      "dtype: int64\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>column_index</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>column_name</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>fBodyAcc-bandsEnergy()-1,16</th>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>fBodyAcc-bandsEnergy()-1,24</th>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>fBodyAcc-bandsEnergy()-1,8</th>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>fBodyAcc-bandsEnergy()-17,24</th>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>fBodyAcc-bandsEnergy()-17,32</th>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                              column_index\n",
       "column_name                               \n",
       "fBodyAcc-bandsEnergy()-1,16              3\n",
       "fBodyAcc-bandsEnergy()-1,24              3\n",
       "fBodyAcc-bandsEnergy()-1,8               3\n",
       "fBodyAcc-bandsEnergy()-17,24             3\n",
       "fBodyAcc-bandsEnergy()-17,32             3"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 중복된 피처명 파악하기\n",
    "feature_dup_df = feature_name_df.groupby('column_name').count()\n",
    "print(feature_dup_df[feature_dup_df['column_index'] > 1].count())\n",
    "feature_dup_df[feature_dup_df['column_index'] > 1].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "2b235ebe-5e69-4243-8a1e-de21d6416e1a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 중복된 피처명에 _1 또는 _2 추가하는 함수\n",
    "def get_new_feature_name_df(old_feature_name_df):\n",
    "    feature_dup_df = pd.DataFrame(data=old_feature_name_df.groupby('column_name').cumcount(),\n",
    "                                  columns=['dup_cnt'])\n",
    "    feature_dup_df = feature_dup_df.reset_index()\n",
    "    new_feature_name_df = pd.merge(old_feature_name_df.reset_index(), feature_dup_df, how='outer')\n",
    "    new_feature_name_df['column_name'] = new_feature_name_df[['column_name', 'dup_cnt']].apply(lambda x : x[0]+'_'+str(x[1])\n",
    "                                        if x[1] > 0 else x[0], axis=1)\n",
    "    new_feature_name_df = new_feature_name_df.drop(['index'], axis=1)\n",
    "    return new_feature_name_df    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "b87f373c-b3d8-4f1d-9788-00859b2830d7",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\niceq\\AppData\\Local\\Temp\\ipykernel_15092\\3854546761.py:8: FutureWarning: Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n",
      "  if x[1] > 0 else x[0], axis=1)\n",
      "C:\\Users\\niceq\\AppData\\Local\\Temp\\ipykernel_15092\\3854546761.py:7: FutureWarning: Series.__getitem__ treating keys as positions is deprecated. In a future version, integer keys will always be treated as labels (consistent with DataFrame behavior). To access a value by position, use `ser.iloc[pos]`\n",
      "  new_feature_name_df['column_name'] = new_feature_name_df[['column_name', 'dup_cnt']].apply(lambda x : x[0]+'_'+str(x[1])\n"
     ]
    }
   ],
   "source": [
    "# get_human_dataset 함수 생성\n",
    "import pandas as pd\n",
    "\n",
    "def get_human_dataset():\n",
    "\n",
    "    # 각 데이터 파일은 공백으로 분리되어 있으므로 read_csv에서 공백 문자를 sep로 할당\n",
    "    feature_name_df = pd.read_csv('../human_activity/features.txt',\n",
    "                               sep='\\s+', header=None, names=['column_index', 'column_name'])\n",
    "    # 중복된 피처명을 수정하는 get_new_feature_name_df()를 이용, 신규 피처명 DF 생성\n",
    "    new_feature_name_df = get_new_feature_name_df(feature_name_df)\n",
    "\n",
    "    # DF에 피처명을 칼럼으로 부여하기 위헤 리스트 객체로 다시 변환\n",
    "    feature_name = new_feature_name_df.iloc[:, 1].values.tolist()\n",
    "\n",
    "    # 학습 피처 데이터세트와 테스트 피처 데이터를 DF로 로딩. 칼럼명은 feature_name 적용\n",
    "    X_train = pd.read_csv('../human_activity/train/X_train.txt', sep='\\s+', names=feature_name)\n",
    "    X_test = pd.read_csv('../human_activity/test/X_test.txt', sep='\\s+', names=feature_name)\n",
    "\n",
    "    # 학습 레이블과 테스트 레이블 데이터를 DF로 로딩하고 칼럼명은 action 부여\n",
    "    y_train = pd.read_csv('../human_activity/train/y_train.txt', sep='\\s+', header=None,names=['action'])\n",
    "    y_test = pd.read_csv('../human_activity/test/y_test.txt', sep='\\s+', header=None, names=['action'])\n",
    "\n",
    "    # 로드된 학습/테스트용 DF 모두 반환\n",
    "    return X_train, X_test, y_train, y_test\n",
    "\n",
    "X_train, X_test, y_train, y_test = get_human_dataset()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "2dfe1e75-4f0b-4a9f-a566-19d7c8c31b3c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "## 학습 피처 데이터셋 ##\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 7352 entries, 0 to 7351\n",
      "Columns: 561 entries, tBodyAcc-mean()-X to angle(Z,gravityMean)\n",
      "dtypes: float64(561)\n",
      "memory usage: 31.5 MB\n",
      "None\n"
     ]
    }
   ],
   "source": [
    "print('## 학습 피처 데이터셋 ##')\n",
    "print(X_train.info())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "b27fc01e-48a7-42a9-9c4a-730a9cf2b532",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "action\n",
      "6    1407\n",
      "5    1374\n",
      "4    1286\n",
      "1    1226\n",
      "2    1073\n",
      "3     986\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "print(y_train['action'].value_counts())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "5924d2e7-f069-4e1f-b44e-7375af471a45",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "결정 트리 예측 정확도: 0.8548\n",
      "DecisionTreeClassifier 기본 하이퍼 파라미터:\n",
      " {'ccp_alpha': 0.0, 'class_weight': None, 'criterion': 'gini', 'max_depth': None, 'max_features': None, 'max_leaf_nodes': None, 'min_impurity_decrease': 0.0, 'min_samples_leaf': 1, 'min_samples_split': 2, 'min_weight_fraction_leaf': 0.0, 'monotonic_cst': None, 'random_state': 156, 'splitter': 'best'}\n"
     ]
    }
   ],
   "source": [
    "# 동작 예측 분류 수행\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.metrics import accuracy_score\n",
    "\n",
    "# 예제 반복 시마다 동일한 예측 결과 도출을 위해 random_state 설정\n",
    "dt_clf = DecisionTreeClassifier(random_state=156)\n",
    "dt_clf.fit(X_train, y_train)\n",
    "pred = dt_clf.predict(X_test)\n",
    "accuracy = accuracy_score(y_test, pred)\n",
    "print('결정 트리 예측 정확도: {0:.4f}'.format(accuracy))\n",
    "\n",
    "# DecisionTreeClassifier의 하이퍼 파라미터 추출\n",
    "print('DecisionTreeClassifier 기본 하이퍼 파라미터:\\n', dt_clf.get_params())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "b778c0af-0c36-46f4-b216-f57e04915bb0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 5 folds for each of 7 candidates, totalling 35 fits\n",
      "GridSearchCV 최고 평균 정확도 수치: 0.8549\n",
      "GridSearchCV 최적 하이퍼 파라미터: {'max_depth': 8, 'min_samples_split': 16}\n"
     ]
    }
   ],
   "source": [
    "# 트리 깊이가 예측 정확도에 주는 영향 측정\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "params = {\n",
    "    'max_depth' : [6, 8, 10, 12, 16, 20, 24],\n",
    "    'min_samples_split' : [16]\n",
    "}\n",
    "\n",
    "grid_cv = GridSearchCV(dt_clf, param_grid=params, scoring='accuracy', cv=5, verbose=1)\n",
    "grid_cv.fit(X_train, y_train)\n",
    "print('GridSearchCV 최고 평균 정확도 수치: {0:.4f}'.format(grid_cv.best_score_))\n",
    "print('GridSearchCV 최적 하이퍼 파라미터:', grid_cv.best_params_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "66a4b840-92ae-417a-9b8e-9340f7656ff4",
   "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>param_max_depth</th>\n",
       "      <th>mean_test_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>0.847662</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>8</td>\n",
       "      <td>0.854879</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10</td>\n",
       "      <td>0.852705</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>12</td>\n",
       "      <td>0.845768</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>16</td>\n",
       "      <td>0.847127</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>20</td>\n",
       "      <td>0.848624</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>24</td>\n",
       "      <td>0.848624</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   param_max_depth  mean_test_score\n",
       "0                6         0.847662\n",
       "1                8         0.854879\n",
       "2               10         0.852705\n",
       "3               12         0.845768\n",
       "4               16         0.847127\n",
       "5               20         0.848624\n",
       "6               24         0.848624"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 평균 정확도 수치 추출\n",
    "# GridSearchCV 객체의 cv_results_ 속성을 DF 로 생성\n",
    "cv_results_df = pd.DataFrame(grid_cv.cv_results_)\n",
    "\n",
    "#max_depth 파라미터 값과 그때의 테스트 세트, 학습 데이터 세트의 정확도 수치 추출\n",
    "cv_results_df[['param_max_depth', 'mean_test_score']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "101beb77-cbfe-4ffa-8316-19f8607e733a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "max_depth = 6 정확도: 0.8551\n",
      "max_depth = 8 정확도: 0.8717\n",
      "max_depth = 10 정확도: 0.8599\n",
      "max_depth = 12 정확도: 0.8571\n",
      "max_depth = 16 정확도: 0.8599\n",
      "max_depth = 20 정확도: 0.8565\n",
      "max_depth = 24 정확도: 0.8565\n"
     ]
    }
   ],
   "source": [
    "# 별도의 테스트 데이터 세트에서 min_samples_split은 16으로 고정하고 max_depth의 변화에 따른 값을 측정\n",
    "max_depths = [6, 8, 10, 12, 16, 20, 24]\n",
    "\n",
    "# max_depth 값을 변화시키면서 그때마다 학습과 테스트 세트에서의 예측 성능 측정\n",
    "for depth in max_depths:\n",
    "    dt_clf = DecisionTreeClassifier(max_depth=depth, min_samples_split=16, random_state=156)\n",
    "    dt_clf.fit(X_train, y_train)\n",
    "    pred = dt_clf.predict(X_test)\n",
    "    accuracy = accuracy_score(y_test, pred)\n",
    "    print('max_depth = {0} 정확도: {1:.4f}'.format(depth, accuracy))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "f1a4f711-c4d3-4972-b07c-acfaeb3816ff",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 5 folds for each of 8 candidates, totalling 40 fits\n",
      "GridSearchCV 최고 평균 정확도 수치: 0.8549\n",
      "GridSearchCV 최적 하이퍼 파라미터: {'max_depth': 8, 'min_samples_split': 16}\n"
     ]
    }
   ],
   "source": [
    "# max_depth와 min_samples_split을 같이 변경하면서 정확도 성능 튜닝\n",
    "params = {\n",
    "    'max_depth' : [8, 12, 16, 20],\n",
    "    'min_samples_split' : [16, 24]\n",
    "}\n",
    "\n",
    "grid_cv = GridSearchCV(dt_clf, param_grid=params, scoring='accuracy', cv=5, verbose=1)\n",
    "grid_cv.fit(X_train, y_train)\n",
    "print('GridSearchCV 최고 평균 정확도 수치: {0:.4f}'.format(grid_cv.best_score_))\n",
    "print('GridSearchCV 최적 하이퍼 파라미터:', grid_cv.best_params_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "1ec99b43-87b8-4e94-bfbd-e8cd8188b8e8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "결정 트리 예측 정확도: 0.8565\n"
     ]
    }
   ],
   "source": [
    "# best_estimator 이용해 예측 수행\n",
    "best_dt_clf = grid_cv.best_estimator_\n",
    "pred1 = best_dt_clf.predict(X_test)\n",
    "acccuracy = accuracy_score(y_test, pred1)\n",
    "print('결정 트리 예측 정확도: {0:.4f}'.format(accuracy))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "19870e9e-e696-4692-8ceb-fea2e27fb23b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 각 피처의 중요도 시각화하기\n",
    "import seaborn as sns\n",
    "\n",
    "ftr_importances_values = best_dt_clf.feature_importances_\n",
    "# Top 중요도로 정렬을 쉽게 하고, 시본(Seaborn)의 막대그래프로 쉽게 표현하기 위해 Series 변환\n",
    "ftr_importances = pd.Series(ftr_importances_values, index=X_train.columns)\n",
    "# 중요도 값 순으로 Series를 정렬\n",
    "ftr_top20 = ftr_importances.sort_values(ascending=False)[:20]\n",
    "plt.figure(figsize=(8, 6))\n",
    "plt.title('Feature Importances Top 20')\n",
    "sns.barplot(x=ftr_top20, y= ftr_top20.index)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "48a829b9-2eff-4ada-a4ea-7b7be231ffb5",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.11.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}