CMTR_CHURN_PR_V3_.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "730bb6cf-50ef-49cb-9c01-2a886b290094",
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "df1 = pd.read_csv(\"E:/dasein_py/Data Analysis/招商银行/cleaned_features_v3.csv\", index_col = 0, header =0)\n",
    "df2 = pd.read_csv(\"E:/dasein_py/Data Analysis/招商银行/cleaned_test_v3.csv\", index_col = 0, header =0)\n",
    "lbl = pd.read_csv(\"E:/dasein_py/Data Analysis/招商银行/cleaned_labels_v3.csv\", index_col = 0, header =0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "a558b198-9389-484d-8670-982750836d04",
   "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>AGN_CNT_RCT_12_MON</th>\n",
       "      <th>ICO_CUR_MON_ACM_TRX_TM</th>\n",
       "      <th>NB_RCT_3_MON_LGN_TMS_AGV</th>\n",
       "      <th>AGN_CUR_YEAR_AMT</th>\n",
       "      <th>AGN_CUR_YEAR_WAG_AMT</th>\n",
       "      <th>AGN_AGR_LATEST_AGN_AMT</th>\n",
       "      <th>ICO_CUR_MON_ACM_TRX_AMT</th>\n",
       "      <th>COUNTER_CUR_YEAR_CNT_AMT</th>\n",
       "      <th>PUB_TO_PRV_TRX_AMT_CUR_YEAR</th>\n",
       "      <th>MON_12_EXT_SAM_TRSF_IN_AMT</th>\n",
       "      <th>...</th>\n",
       "      <th>WTHR_OPN_ONL_ICO</th>\n",
       "      <th>EMP_NBR</th>\n",
       "      <th>REG_CPT</th>\n",
       "      <th>SHH_BCK</th>\n",
       "      <th>HLD_DMS_CCY_ACT_NBR</th>\n",
       "      <th>REG_DT</th>\n",
       "      <th>LGP_HLD_CARD_LVL</th>\n",
       "      <th>OPN_TM</th>\n",
       "      <th>NB_CTC_HLD_IDV_AIO_CARD_SITU</th>\n",
       "      <th>HLD_FGN_CCY_ACT_NBR</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2472.0</td>\n",
       "      <td>72.0</td>\n",
       "      <td>425.3</td>\n",
       "      <td>12015888.3</td>\n",
       "      <td>8816593.9</td>\n",
       "      <td>674873.7</td>\n",
       "      <td>25879985.3</td>\n",
       "      <td>2.0</td>\n",
       "      <td>660732.0</td>\n",
       "      <td>262372474.2</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.200000e+09</td>\n",
       "      <td>0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>1708.45</td>\n",
       "      <td>0</td>\n",
       "      <td>416.84</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2282.0</td>\n",
       "      <td>222.0</td>\n",
       "      <td>175.3</td>\n",
       "      <td>11776572.4</td>\n",
       "      <td>8816593.9</td>\n",
       "      <td>1964626.4</td>\n",
       "      <td>14755499.8</td>\n",
       "      <td>2.0</td>\n",
       "      <td>126608.3</td>\n",
       "      <td>2.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1002.0</td>\n",
       "      <td>5.000002e+06</td>\n",
       "      <td>0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>199.42</td>\n",
       "      <td>1</td>\n",
       "      <td>195.87</td>\n",
       "      <td>1</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2472.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>175.3</td>\n",
       "      <td>12015888.3</td>\n",
       "      <td>8816593.9</td>\n",
       "      <td>4599822.3</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.000000e+08</td>\n",
       "      <td>1</td>\n",
       "      <td>12.0</td>\n",
       "      <td>1135.55</td>\n",
       "      <td>1</td>\n",
       "      <td>1122.00</td>\n",
       "      <td>-1</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2472.0</td>\n",
       "      <td>92.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>12015888.3</td>\n",
       "      <td>8816593.9</td>\n",
       "      <td>674873.7</td>\n",
       "      <td>9622952.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>2.0</td>\n",
       "      <td>5.000020e+05</td>\n",
       "      <td>2</td>\n",
       "      <td>12.0</td>\n",
       "      <td>98.45</td>\n",
       "      <td>-1</td>\n",
       "      <td>92.00</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2472.0</td>\n",
       "      <td>92.0</td>\n",
       "      <td>175.3</td>\n",
       "      <td>12015888.3</td>\n",
       "      <td>8816593.9</td>\n",
       "      <td>674873.7</td>\n",
       "      <td>9622952.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2802.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.000000e+08</td>\n",
       "      <td>1</td>\n",
       "      <td>12.0</td>\n",
       "      <td>702.97</td>\n",
       "      <td>-1</td>\n",
       "      <td>355.87</td>\n",
       "      <td>2</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 48 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   AGN_CNT_RCT_12_MON  ICO_CUR_MON_ACM_TRX_TM  NB_RCT_3_MON_LGN_TMS_AGV  \\\n",
       "0              2472.0                    72.0                     425.3   \n",
       "1              2282.0                   222.0                     175.3   \n",
       "2              2472.0                     2.0                     175.3   \n",
       "3              2472.0                    92.0                      22.0   \n",
       "4              2472.0                    92.0                     175.3   \n",
       "\n",
       "   AGN_CUR_YEAR_AMT  AGN_CUR_YEAR_WAG_AMT  AGN_AGR_LATEST_AGN_AMT  \\\n",
       "0        12015888.3             8816593.9                674873.7   \n",
       "1        11776572.4             8816593.9               1964626.4   \n",
       "2        12015888.3             8816593.9               4599822.3   \n",
       "3        12015888.3             8816593.9                674873.7   \n",
       "4        12015888.3             8816593.9                674873.7   \n",
       "\n",
       "   ICO_CUR_MON_ACM_TRX_AMT  COUNTER_CUR_YEAR_CNT_AMT  \\\n",
       "0               25879985.3                       2.0   \n",
       "1               14755499.8                       2.0   \n",
       "2                      2.0                       2.0   \n",
       "3                9622952.0                       2.0   \n",
       "4                9622952.0                       2.0   \n",
       "\n",
       "   PUB_TO_PRV_TRX_AMT_CUR_YEAR  MON_12_EXT_SAM_TRSF_IN_AMT  ...  \\\n",
       "0                     660732.0                 262372474.2  ...   \n",
       "1                     126608.3                         2.0  ...   \n",
       "2                          2.0                         2.0  ...   \n",
       "3                          2.0                         2.0  ...   \n",
       "4                       2802.0                         2.0  ...   \n",
       "\n",
       "   WTHR_OPN_ONL_ICO  EMP_NBR       REG_CPT  SHH_BCK  HLD_DMS_CCY_ACT_NBR  \\\n",
       "0                 0      2.0  1.200000e+09        0                 12.0   \n",
       "1                 0   1002.0  5.000002e+06        0                 22.0   \n",
       "2                 0      2.0  1.000000e+08        1                 12.0   \n",
       "3                 1      2.0  5.000020e+05        2                 12.0   \n",
       "4                 1      2.0  1.000000e+08        1                 12.0   \n",
       "\n",
       "    REG_DT  LGP_HLD_CARD_LVL   OPN_TM  NB_CTC_HLD_IDV_AIO_CARD_SITU  \\\n",
       "0  1708.45                 0   416.84                             0   \n",
       "1   199.42                 1   195.87                             1   \n",
       "2  1135.55                 1  1122.00                            -1   \n",
       "3    98.45                -1    92.00                             2   \n",
       "4   702.97                -1   355.87                             2   \n",
       "\n",
       "   HLD_FGN_CCY_ACT_NBR  \n",
       "0                  2.0  \n",
       "1                  2.0  \n",
       "2                  2.0  \n",
       "3                  2.0  \n",
       "4                  2.0  \n",
       "\n",
       "[5 rows x 48 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "cdca1a0a-d582-46b1-8b13-39c78aba48ee",
   "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>AGN_CNT_RCT_12_MON</th>\n",
       "      <th>ICO_CUR_MON_ACM_TRX_TM</th>\n",
       "      <th>NB_RCT_3_MON_LGN_TMS_AGV</th>\n",
       "      <th>AGN_CUR_YEAR_AMT</th>\n",
       "      <th>AGN_CUR_YEAR_WAG_AMT</th>\n",
       "      <th>AGN_AGR_LATEST_AGN_AMT</th>\n",
       "      <th>ICO_CUR_MON_ACM_TRX_AMT</th>\n",
       "      <th>COUNTER_CUR_YEAR_CNT_AMT</th>\n",
       "      <th>PUB_TO_PRV_TRX_AMT_CUR_YEAR</th>\n",
       "      <th>MON_12_EXT_SAM_TRSF_IN_AMT</th>\n",
       "      <th>...</th>\n",
       "      <th>WTHR_OPN_ONL_ICO</th>\n",
       "      <th>EMP_NBR</th>\n",
       "      <th>REG_CPT</th>\n",
       "      <th>SHH_BCK</th>\n",
       "      <th>HLD_DMS_CCY_ACT_NBR</th>\n",
       "      <th>REG_DT</th>\n",
       "      <th>LGP_HLD_CARD_LVL</th>\n",
       "      <th>OPN_TM</th>\n",
       "      <th>NB_CTC_HLD_IDV_AIO_CARD_SITU</th>\n",
       "      <th>HLD_FGN_CCY_ACT_NBR</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>23662.0</td>\n",
       "      <td>92.0</td>\n",
       "      <td>172.0</td>\n",
       "      <td>11812311.6</td>\n",
       "      <td>8745226.1</td>\n",
       "      <td>135692.0</td>\n",
       "      <td>9444134.2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>594825002.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>26622.0</td>\n",
       "      <td>1.000000e+08</td>\n",
       "      <td>0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>242461.35</td>\n",
       "      <td>0</td>\n",
       "      <td>1588.13</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2492.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>172.0</td>\n",
       "      <td>11812311.6</td>\n",
       "      <td>8745226.1</td>\n",
       "      <td>703149.6</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1502.0</td>\n",
       "      <td>3.800000e+08</td>\n",
       "      <td>1</td>\n",
       "      <td>12.0</td>\n",
       "      <td>432.00</td>\n",
       "      <td>0</td>\n",
       "      <td>82.65</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1672.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>48.7</td>\n",
       "      <td>992125.6</td>\n",
       "      <td>8745226.1</td>\n",
       "      <td>992125.6</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.000000e+08</td>\n",
       "      <td>0</td>\n",
       "      <td>42.0</td>\n",
       "      <td>705.23</td>\n",
       "      <td>-1</td>\n",
       "      <td>512.65</td>\n",
       "      <td>1</td>\n",
       "      <td>22.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>5432.0</td>\n",
       "      <td>102.0</td>\n",
       "      <td>88.7</td>\n",
       "      <td>46729796.3</td>\n",
       "      <td>46729796.3</td>\n",
       "      <td>7356752.4</td>\n",
       "      <td>8048976.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2154106.4</td>\n",
       "      <td>2.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>432.0</td>\n",
       "      <td>5.000002e+06</td>\n",
       "      <td>2</td>\n",
       "      <td>12.0</td>\n",
       "      <td>442.00</td>\n",
       "      <td>1</td>\n",
       "      <td>432.00</td>\n",
       "      <td>1</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>11842.0</td>\n",
       "      <td>782.0</td>\n",
       "      <td>1545.3</td>\n",
       "      <td>27085791.9</td>\n",
       "      <td>8745226.1</td>\n",
       "      <td>135002.0</td>\n",
       "      <td>81516420.9</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2421499.6</td>\n",
       "      <td>2.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>902.0</td>\n",
       "      <td>1.131689e+09</td>\n",
       "      <td>1</td>\n",
       "      <td>12.0</td>\n",
       "      <td>3747.48</td>\n",
       "      <td>-1</td>\n",
       "      <td>3200.06</td>\n",
       "      <td>1</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 48 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   AGN_CNT_RCT_12_MON  ICO_CUR_MON_ACM_TRX_TM  NB_RCT_3_MON_LGN_TMS_AGV  \\\n",
       "0             23662.0                    92.0                     172.0   \n",
       "1              2492.0                     2.0                     172.0   \n",
       "2              1672.0                     2.0                      48.7   \n",
       "3              5432.0                   102.0                      88.7   \n",
       "4             11842.0                   782.0                    1545.3   \n",
       "\n",
       "   AGN_CUR_YEAR_AMT  AGN_CUR_YEAR_WAG_AMT  AGN_AGR_LATEST_AGN_AMT  \\\n",
       "0        11812311.6             8745226.1                135692.0   \n",
       "1        11812311.6             8745226.1                703149.6   \n",
       "2          992125.6             8745226.1                992125.6   \n",
       "3        46729796.3            46729796.3               7356752.4   \n",
       "4        27085791.9             8745226.1                135002.0   \n",
       "\n",
       "   ICO_CUR_MON_ACM_TRX_AMT  COUNTER_CUR_YEAR_CNT_AMT  \\\n",
       "0                9444134.2                       2.0   \n",
       "1                      2.0                       2.0   \n",
       "2                      2.0                       2.0   \n",
       "3                8048976.0                       2.0   \n",
       "4               81516420.9                       2.0   \n",
       "\n",
       "   PUB_TO_PRV_TRX_AMT_CUR_YEAR  MON_12_EXT_SAM_TRSF_IN_AMT  ...  \\\n",
       "0                          2.0                 594825002.0  ...   \n",
       "1                          2.0                         2.0  ...   \n",
       "2                          2.0                         2.0  ...   \n",
       "3                    2154106.4                         2.0  ...   \n",
       "4                    2421499.6                         2.0  ...   \n",
       "\n",
       "   WTHR_OPN_ONL_ICO  EMP_NBR       REG_CPT  SHH_BCK  HLD_DMS_CCY_ACT_NBR  \\\n",
       "0                 0  26622.0  1.000000e+08        0                 12.0   \n",
       "1                 0   1502.0  3.800000e+08        1                 12.0   \n",
       "2                 1      2.0  1.000000e+08        0                 42.0   \n",
       "3                 0    432.0  5.000002e+06        2                 12.0   \n",
       "4                 0    902.0  1.131689e+09        1                 12.0   \n",
       "\n",
       "      REG_DT  LGP_HLD_CARD_LVL   OPN_TM  NB_CTC_HLD_IDV_AIO_CARD_SITU  \\\n",
       "0  242461.35                 0  1588.13                             0   \n",
       "1     432.00                 0    82.65                             0   \n",
       "2     705.23                -1   512.65                             1   \n",
       "3     442.00                 1   432.00                             1   \n",
       "4    3747.48                -1  3200.06                             1   \n",
       "\n",
       "   HLD_FGN_CCY_ACT_NBR  \n",
       "0                  2.0  \n",
       "1                  2.0  \n",
       "2                 22.0  \n",
       "3                  2.0  \n",
       "4                  2.0  \n",
       "\n",
       "[5 rows x 48 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "fef6fb63-25d3-46ce-b1fe-0a8f905a8ebb",
   "metadata": {},
   "outputs": [],
   "source": [
    "label = lbl.values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "5b122ef2-74df-4d8f-a117-e313ec4d97e6",
   "metadata": {},
   "outputs": [],
   "source": [
    "from xgboost.sklearn import XGBClassifier\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "scaler = StandardScaler(copy=False)\n",
    "df2_features = scaler.fit_transform(df2)\n",
    "df1_features = scaler.fit_transform(df1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "711ee1fe-6c64-419c-bb9b-e226ed152772",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([[-0.01771666, -0.04036806,  0.13334904, ..., -0.42572884,\n",
       "         -1.18894007, -0.23009299],\n",
       "        [-0.01797979, -0.02722852, -0.20762554, ..., -0.79782908,\n",
       "         -0.56876373, -0.23009299],\n",
       "        [-0.01771666, -0.04649984, -0.20762554, ...,  0.76171837,\n",
       "         -1.80911642, -0.23009299],\n",
       "        ...,\n",
       "        [ 0.00867952,  0.05248468, -0.20762554, ...,  2.46359244,\n",
       "         -1.80911642, -0.23009299],\n",
       "        [-0.01771666, -0.04562387, -0.27118321, ..., -0.26875194,\n",
       "         -1.18894007, -0.23009299],\n",
       "        [-0.01771666, -0.04387193, -0.12579164, ...,  0.63298115,\n",
       "          2.532118  , -0.23009299]]),\n",
       " array([[ 0.10232026, -0.12387589, -0.29241471, ...,  1.56024628,\n",
       "         -1.1976317 , -0.16766289],\n",
       "        [-0.06773752, -0.15788593, -0.29241471, ..., -0.98796441,\n",
       "         -1.1976317 , -0.16766289],\n",
       "        [-0.07432455, -0.15788593, -0.53567716, ..., -0.26013634,\n",
       "         -0.53231156,  1.2934516 ],\n",
       "        ...,\n",
       "        [-0.0817952 , -0.08608696, -0.02271498, ..., -0.10399183,\n",
       "          0.79832873, -0.16766289],\n",
       "        [-0.08380344, -0.00673021,  0.41784061, ..., -1.06768697,\n",
       "          0.13300858, -0.16766289],\n",
       "        [ 0.01813483, -0.03696135, -0.01620431, ...,  1.8070477 ,\n",
       "          0.13300858, -0.16766289]]))"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1_features, df2_features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "0102171e-069e-4112-85f5-631e1ab87a3a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[-0.01771666, -0.04212   , -0.37129334, ...,  0.40428524,\n",
       "        -0.56876373, -0.23009299],\n",
       "       [-0.00688675, -0.0193448 ,  0.16976512, ...,  0.08433662,\n",
       "         0.05141262,  0.94220602],\n",
       "       [-0.02094347, -0.03511224, -0.13479337, ...,  2.10181475,\n",
       "         1.29176531, -0.23009299],\n",
       "       ...,\n",
       "       [-0.02023717, -0.04124403, -0.18034758, ..., -0.90809348,\n",
       "         1.29176531, -0.23009299],\n",
       "       [-0.01771666, -0.04649984, -0.42121202, ..., -1.03955869,\n",
       "         1.29176531, -0.23009299],\n",
       "       [-0.01771666, -0.03861612, -0.41671116, ..., -0.07861826,\n",
       "         1.29176531, -0.23009299]])"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split #数据集训练集划分\n",
    "x_train,x_test,y_train,y_test=train_test_split(df1_features,label,test_size=.2,random_state=22)\n",
    "x_train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "40a0769e-1350-4f32-9631-33063c134ddf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 0, ..., 1, 1, 0], dtype=int64)"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_train.reshape(-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "e360649b-fe92-4050-9285-8dab491db2e7",
   "metadata": {},
   "outputs": [],
   "source": [
    "from pytorch_tabnet.tab_model import TabNetClassifier, TabNetRegressor\n",
    "from pytorch_tabnet.pretraining import TabNetPretrainer\n",
    "import torch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "05867243-5dd8-4552-963e-df9d0ab4fa48",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Device used : cpu\n",
      "epoch 0  | loss: 655.35333| val_0_unsup_loss: 5.044311298413062e+19|  0:00:02s\n",
      "epoch 1  | loss: 17.48018| val_0_unsup_loss: 1.006651213611008e+16|  0:00:05s\n",
      "epoch 2  | loss: 1.84422 | val_0_unsup_loss: 2.5346904116166656e+16|  0:00:08s\n",
      "epoch 3  | loss: 1.06343 | val_0_unsup_loss: 1.789790181654528e+17|  0:00:11s\n",
      "epoch 4  | loss: 1.0783  | val_0_unsup_loss: 2.806378661098291e+16|  0:00:13s\n",
      "epoch 5  | loss: 1.04342 | val_0_unsup_loss: 5.267322551507354e+16|  0:00:16s\n",
      "epoch 6  | loss: 1.03608 | val_0_unsup_loss: 1040009150857216.0|  0:00:19s\n",
      "epoch 7  | loss: 1.03378 | val_0_unsup_loss: 6721049366364160.0|  0:00:22s\n",
      "epoch 8  | loss: 1.04402 | val_0_unsup_loss: 2.9546870308991926e+19|  0:00:25s\n",
      "epoch 9  | loss: 1.0561  | val_0_unsup_loss: 5.157704592292577e+18|  0:00:27s\n",
      "epoch 10 | loss: 1.03691 | val_0_unsup_loss: 3.6109418709070643e+18|  0:00:30s\n",
      "epoch 11 | loss: 1.03819 | val_0_unsup_loss: 1.4984565576284766e+19|  0:00:33s\n",
      "epoch 12 | loss: 1.03456 | val_0_unsup_loss: 2.2736422993657856e+16|  0:00:36s\n",
      "epoch 13 | loss: 1.03696 | val_0_unsup_loss: 2.50242511405056e+16|  0:00:38s\n",
      "epoch 14 | loss: 1.02655 | val_0_unsup_loss: 1.3291912230422446e+18|  0:00:41s\n",
      "epoch 15 | loss: 1.0211  | val_0_unsup_loss: 7.281385187940762e+17|  0:00:44s\n",
      "epoch 16 | loss: 1.0122  | val_0_unsup_loss: 1.618817978961232e+18|  0:00:47s\n",
      "\n",
      "Early stopping occurred at epoch 16 with best_epoch = 6 and best_val_0_unsup_loss = 1040009150857216.0\n",
      "Best weights from best epoch are automatically used!\n",
      "Device used : cpu\n",
      "Loading weights from unsupervised pretraining\n",
      "epoch 0  | loss: 0.63346 | train_auc: 0.59469 | valid_auc: 0.49343 |  0:00:02s\n",
      "epoch 1  | loss: 0.53143 | train_auc: 0.6492  | valid_auc: 0.52278 |  0:00:05s\n",
      "epoch 2  | loss: 0.52202 | train_auc: 0.67001 | valid_auc: 0.5633  |  0:00:08s\n",
      "epoch 3  | loss: 0.5142  | train_auc: 0.68331 | valid_auc: 0.53604 |  0:00:11s\n",
      "epoch 4  | loss: 0.5039  | train_auc: 0.66571 | valid_auc: 0.50033 |  0:00:14s\n",
      "epoch 5  | loss: 0.49148 | train_auc: 0.68686 | valid_auc: 0.50327 |  0:00:17s\n",
      "epoch 6  | loss: 0.47438 | train_auc: 0.73552 | valid_auc: 0.51687 |  0:00:19s\n",
      "epoch 7  | loss: 0.47583 | train_auc: 0.68535 | valid_auc: 0.54898 |  0:00:22s\n",
      "epoch 8  | loss: 0.45955 | train_auc: 0.58826 | valid_auc: 0.49706 |  0:00:25s\n",
      "epoch 9  | loss: 0.44769 | train_auc: 0.63717 | valid_auc: 0.50035 |  0:00:28s\n",
      "epoch 10 | loss: 0.43235 | train_auc: 0.57046 | valid_auc: 0.50065 |  0:00:30s\n",
      "epoch 11 | loss: 0.41672 | train_auc: 0.65155 | valid_auc: 0.51918 |  0:00:33s\n",
      "epoch 12 | loss: 0.41257 | train_auc: 0.66125 | valid_auc: 0.59177 |  0:00:36s\n",
      "epoch 13 | loss: 0.41337 | train_auc: 0.67083 | valid_auc: 0.55861 |  0:00:39s\n",
      "epoch 14 | loss: 0.40831 | train_auc: 0.65318 | valid_auc: 0.55624 |  0:00:41s\n",
      "epoch 15 | loss: 0.40664 | train_auc: 0.66728 | valid_auc: 0.50613 |  0:00:44s\n",
      "epoch 16 | loss: 0.40737 | train_auc: 0.679   | valid_auc: 0.54809 |  0:00:47s\n",
      "epoch 17 | loss: 0.40756 | train_auc: 0.67769 | valid_auc: 0.54467 |  0:00:50s\n",
      "epoch 18 | loss: 0.40515 | train_auc: 0.68776 | valid_auc: 0.49919 |  0:00:53s\n",
      "epoch 19 | loss: 0.40622 | train_auc: 0.6852  | valid_auc: 0.53226 |  0:00:55s\n",
      "epoch 20 | loss: 0.41053 | train_auc: 0.65981 | valid_auc: 0.52287 |  0:00:58s\n",
      "epoch 21 | loss: 0.41248 | train_auc: 0.64519 | valid_auc: 0.49839 |  0:01:01s\n",
      "epoch 22 | loss: 0.41319 | train_auc: 0.66758 | valid_auc: 0.48926 |  0:01:04s\n",
      "\n",
      "Early stopping occurred at epoch 22 with best_epoch = 12 and best_valid_auc = 0.59177\n",
      "Best weights from best epoch are automatically used!\n"
     ]
    }
   ],
   "source": [
    "# TabNetPretrainer 预训练模型\n",
    "unsupervised_model = TabNetPretrainer(\n",
    "    optimizer_fn=torch.optim.Adam,\n",
    "    optimizer_params=dict(lr=2e-2),\n",
    "    mask_type='sparsemax' # \"sparsemax\"\n",
    ")\n",
    "\n",
    "unsupervised_model.fit(\n",
    "    X_train=x_train,\n",
    "    eval_set=[df1.values],\n",
    "    pretraining_ratio=0.8,\n",
    ")\n",
    "\n",
    "clf = TabNetClassifier(\n",
    "    optimizer_fn=torch.optim.Adam,\n",
    "    optimizer_params=dict(lr=2e-2),\n",
    "    scheduler_params={\"step_size\":10, # how to use learning rate scheduler\n",
    "                      \"gamma\":0.9},\n",
    "    scheduler_fn=torch.optim.lr_scheduler.StepLR,\n",
    "    mask_type='sparsemax' # This will be overwritten if using pretrain model\n",
    ")\n",
    "\n",
    "clf.fit(x_train, y_train.reshape(-1),\n",
    "    eval_set= [(x_train, y_train.reshape(-1)), (df1.values, lbl.values.reshape(-1))],\n",
    "    eval_name=['train', 'valid'],\n",
    "    eval_metric=['auc'],\n",
    "    from_unsupervised=unsupervised_model\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "de8a9c5e-5366-49b9-9379-4a7aaba1eb88",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.96832305, 0.9685319 , 0.94283664, ..., 0.950373  , 0.97888523,\n",
       "       0.97209686], dtype=float32)"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predict_proba = clf.predict_proba(x_test)\n",
    "predict_proba[:,0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "2c41fbe7-88e1-46de-891d-44e3778662c6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.6511318268787747"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics import roc_curve, auc\n",
    "false_positive_rate, true_positive_rate, thresholds = roc_curve(y_test.reshape(-1), predict_proba[:,1])\n",
    "auc(false_positive_rate, true_positive_rate)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "db29ffc6-5847-4a59-bfda-bb34aee82f2b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.6511318268787747"
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predict_proba2 = clf.predict_proba(x_test)\n",
    "false_positive_rate, true_positive_rate, thresholds = roc_curve(y_test.reshape(-1), predict_proba2[:,1])\n",
    "auc(false_positive_rate, true_positive_rate)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "26882e2f-a9bb-41c5-8951-6b7da79580b5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.74      1.00      0.85      5914\n",
      "           1       0.00      0.00      0.00      2086\n",
      "\n",
      "    accuracy                           0.74      8000\n",
      "   macro avg       0.37      0.50      0.43      8000\n",
      "weighted avg       0.55      0.74      0.63      8000\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "D:\\anaconda3\\lib\\site-packages\\sklearn\\metrics\\_classification.py:1318: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n",
      "D:\\anaconda3\\lib\\site-packages\\sklearn\\metrics\\_classification.py:1318: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n",
      "D:\\anaconda3\\lib\\site-packages\\sklearn\\metrics\\_classification.py:1318: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n"
     ]
    }
   ],
   "source": [
    "y_pred = clf.predict(x_test)\n",
    "target_names = ['class 0', 'class 1', 'class 2']\n",
    "print(classification_report(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "355f5fd9-ae77-4589-b8d8-bf2bb9f7d392",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.decomposition import PCA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "96690025-07cf-4c3e-a514-077cb6266267",
   "metadata": {},
   "outputs": [],
   "source": [
    "pca = PCA(n_components=15)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "766c1a47-1e23-4cba-a57d-bb53ffc2811c",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train2 = pca.fit_transform(df1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "18723d06-0173-46ad-9792-fd818ae4f2f9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[-2.43485860e+09, -9.79041901e+08,  3.53320372e+08, ...,\n",
       "         1.69800686e+07, -2.25714355e+07, -4.64186443e+06],\n",
       "       [-2.60326552e+09, -1.20454133e+09,  8.68250383e+08, ...,\n",
       "        -1.52891318e+07,  2.49463735e+07, -4.31176019e+06],\n",
       "       [-2.68028228e+09, -1.20485478e+09,  8.54260903e+08, ...,\n",
       "        -6.92020453e+06,  1.85919676e+06, -6.11148416e+06],\n",
       "       ...,\n",
       "       [-1.83277407e+09,  1.97828903e+08, -1.41091945e+09, ...,\n",
       "        -2.56263370e+07,  1.64018130e+07,  1.97540606e+07],\n",
       "       [-2.69602533e+09, -1.20535081e+09,  8.69142156e+08, ...,\n",
       "        -7.76629505e+06,  3.55282768e+06, -5.94794662e+06],\n",
       "       [-2.49502542e+09, -6.73593810e+08, -1.75264765e+08, ...,\n",
       "         2.45673520e+07, -3.89305184e+07,  6.36896835e+06]])"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_train2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "41865aaa-7f24-48bf-a2ee-871f19883638",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[-0.01340227, -0.01963732,  0.01192276, ...,  0.04434032,\n",
       "        -0.07542411, -0.01812773],\n",
       "       [-0.01432923, -0.02416032,  0.02929903, ..., -0.03992475,\n",
       "         0.08336014, -0.01683858],\n",
       "       [-0.01475316, -0.0241666 ,  0.02882695, ..., -0.01807084,\n",
       "         0.00621264, -0.02386699],\n",
       "       ...,\n",
       "       [-0.01008819,  0.00396799, -0.04761134, ..., -0.06691846,\n",
       "         0.05480787,  0.07714491],\n",
       "       [-0.01483982, -0.02417655,  0.02932912, ..., -0.02028025,\n",
       "         0.01187204, -0.02322833],\n",
       "       [-0.01373345, -0.01351074, -0.00591429, ...,  0.06415312,\n",
       "        -0.1300892 ,  0.02487253]])"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "features2 = scaler.fit_transform(x_train2)\n",
    "features2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "f40649d8-4eae-4579-98a6-addb1b879a66",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train2,x_test2,y_train2,y_test2 =train_test_split(features2,label,test_size=.2,random_state=22)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "8f3312e8-3892-43df-ad2c-1d1e950c63fb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0],\n",
       "       [0],\n",
       "       [0],\n",
       "       ...,\n",
       "       [0],\n",
       "       [1],\n",
       "       [0]], dtype=int64)"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "label"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "58f0c43c-32a0-4cbc-8547-27b53c558998",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Device used : cpu\n",
      "epoch 0  | loss: 520.54109| val_0_unsup_loss: 1.40954 |  0:00:02s\n",
      "epoch 1  | loss: 611.17195| val_0_unsup_loss: 1.87714 |  0:00:04s\n",
      "epoch 2  | loss: 411.79755| val_0_unsup_loss: 1.9529  |  0:00:06s\n",
      "epoch 3  | loss: 371.55147| val_0_unsup_loss: 2.14971 |  0:00:08s\n",
      "epoch 4  | loss: 296.11923| val_0_unsup_loss: 1.8425  |  0:00:10s\n",
      "epoch 5  | loss: 411.97911| val_0_unsup_loss: 2.48366 |  0:00:12s\n",
      "epoch 6  | loss: 417.03189| val_0_unsup_loss: 2.99035 |  0:00:14s\n",
      "epoch 7  | loss: 372.76401| val_0_unsup_loss: 2.71654 |  0:00:16s\n",
      "epoch 8  | loss: 385.54724| val_0_unsup_loss: 3.37694 |  0:00:18s\n",
      "epoch 9  | loss: 469.75974| val_0_unsup_loss: 2.40193 |  0:00:20s\n",
      "epoch 10 | loss: 314.84748| val_0_unsup_loss: 3.56644 |  0:00:22s\n",
      "\n",
      "Early stopping occurred at epoch 10 with best_epoch = 0 and best_val_0_unsup_loss = 1.40954\n",
      "Best weights from best epoch are automatically used!\n",
      "Device used : cpu\n",
      "Loading weights from unsupervised pretraining\n",
      "epoch 0  | loss: 0.78046 | train_auc: 0.4932  | valid_auc: 0.4913  |  0:00:02s\n",
      "epoch 1  | loss: 0.7781  | train_auc: 0.56835 | valid_auc: 0.56577 |  0:00:04s\n",
      "epoch 2  | loss: 0.77733 | train_auc: 0.57439 | valid_auc: 0.57156 |  0:00:06s\n",
      "epoch 3  | loss: 0.78039 | train_auc: 0.58641 | valid_auc: 0.58313 |  0:00:08s\n",
      "epoch 4  | loss: 0.77017 | train_auc: 0.59281 | valid_auc: 0.59023 |  0:00:10s\n",
      "epoch 5  | loss: 0.78008 | train_auc: 0.55829 | valid_auc: 0.55525 |  0:00:12s\n",
      "epoch 6  | loss: 0.77408 | train_auc: 0.48578 | valid_auc: 0.48367 |  0:00:14s\n",
      "epoch 7  | loss: 0.77283 | train_auc: 0.57681 | valid_auc: 0.57386 |  0:00:16s\n",
      "epoch 8  | loss: 0.76308 | train_auc: 0.58549 | valid_auc: 0.58236 |  0:00:18s\n",
      "epoch 9  | loss: 0.76539 | train_auc: 0.52809 | valid_auc: 0.52513 |  0:00:20s\n",
      "epoch 10 | loss: 0.77301 | train_auc: 0.5629  | valid_auc: 0.56127 |  0:00:22s\n",
      "epoch 11 | loss: 0.76667 | train_auc: 0.53089 | valid_auc: 0.5285  |  0:00:24s\n",
      "epoch 12 | loss: 0.76313 | train_auc: 0.42783 | valid_auc: 0.42712 |  0:00:26s\n",
      "epoch 13 | loss: 0.77179 | train_auc: 0.45732 | valid_auc: 0.45538 |  0:00:28s\n",
      "epoch 14 | loss: 0.75925 | train_auc: 0.46186 | valid_auc: 0.4615  |  0:00:31s\n",
      "\n",
      "Early stopping occurred at epoch 14 with best_epoch = 4 and best_valid_auc = 0.59023\n",
      "Best weights from best epoch are automatically used!\n"
     ]
    }
   ],
   "source": [
    "# 调参\n",
    "# TabNetPretrainer 预训练模型\n",
    "unsupervised_model = TabNetPretrainer(\n",
    "    optimizer_fn=torch.optim.Adam,\n",
    "    optimizer_params=dict(lr=2e-5),\n",
    "    mask_type='sparsemax' # \"sparsemax\"\n",
    ")\n",
    "\n",
    "unsupervised_model.fit(\n",
    "    X_train=x_train2,\n",
    "    eval_set=[features2],\n",
    "    pretraining_ratio=0.8,\n",
    ")\n",
    "\n",
    "clf2 = TabNetClassifier(\n",
    "    optimizer_fn=torch.optim.Adam,\n",
    "    optimizer_params=dict(lr=2e-5),\n",
    "    scheduler_params={\"step_size\":10, # how to use learning rate scheduler\n",
    "                      \"gamma\":0.9},\n",
    "    scheduler_fn=torch.optim.lr_scheduler.StepLR,\n",
    "    mask_type='sparsemax' # This will be overwritten if using pretrain model\n",
    ")\n",
    "\n",
    "clf2.fit(x_train2, y_train2.reshape(-1),\n",
    "    eval_set= [(x_train2, y_train2.reshape(-1)), (features2, lbl.values.reshape(-1))],\n",
    "    eval_name=['train', 'valid'],\n",
    "    eval_metric=['auc'],\n",
    "    from_unsupervised=unsupervised_model\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "id": "40743967-71bc-4c80-8f3b-d8ccfedb652e",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import classification_report"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "7327d79d-1140-4c38-8922-f76408c363a9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.90      0.06      0.11      5914\n",
      "           1       0.27      0.98      0.42      2086\n",
      "\n",
      "    accuracy                           0.30      8000\n",
      "   macro avg       0.58      0.52      0.27      8000\n",
      "weighted avg       0.73      0.30      0.19      8000\n",
      "\n"
     ]
    }
   ],
   "source": [
    "y_pred2 = clf2.predict(x_test2)\n",
    "print(classification_report(y_test2.reshape(-1), y_pred2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "b9cba9aa-e9ab-4147-aa76-051b7c1bce9b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.5801404503216607"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predict_proba3 = clf2.predict_proba(x_test2)\n",
    "false_positive_rate, true_positive_rate, thresholds = roc_curve(y_test2.reshape(-1), predict_proba3[:,1])\n",
    "auc(false_positive_rate, true_positive_rate)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d4c20d16-c6b5-45e9-9121-e5ef33081e4d",
   "metadata": {},
   "source": [
    "### AutoGluon"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "id": "12bf36ab-7290-4444-83ff-6c76af1ae903",
   "metadata": {},
   "outputs": [],
   "source": [
    "from autogluon.tabular import TabularPredictor\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "id": "f9e1536d-120e-4df1-8d7d-a99859d38d3a",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Warning: path already exists! This predictor may overwrite an existing predictor! path=\"E:/dasein_py/Data Analysis/招商银行/agModels-predictClass/\"\n"
     ]
    },
    {
     "ename": "TypeError",
     "evalue": "import_optional_dependency() got an unexpected keyword argument 'errors'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[1;32mC:\\Users\\TRACYT~1\\AppData\\Local\\Temp/ipykernel_16856/126971473.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[0mtrain_data\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread_csv\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'E:/dasein_py/Data Analysis/招商银行/train.csv'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      2\u001b[0m \u001b[0msave_path\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;34m'E:/dasein_py/Data Analysis/招商银行/agModels-predictClass/'\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 3\u001b[1;33m \u001b[0mpredictor\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mTabularPredictor\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlabel\u001b[0m\u001b[1;33m=\u001b[0m \u001b[1;34m'LABEL'\u001b[0m \u001b[1;33m,\u001b[0m \u001b[0meval_metric\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'roc_auc'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mpath\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0msave_path\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtrain_data\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;32m~\\AppData\\Roaming\\Python\\Python39\\site-packages\\autogluon\\core\\utils\\decorators.py\u001b[0m in \u001b[0;36m_call\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m     28\u001b[0m         \u001b[1;32mdef\u001b[0m \u001b[0m_call\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\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     29\u001b[0m             \u001b[0mgargs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mgkwargs\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mg\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0mother_args\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 30\u001b[1;33m             \u001b[1;32mreturn\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0mgargs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mgkwargs\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     31\u001b[0m         \u001b[1;32mreturn\u001b[0m \u001b[0m_call\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     32\u001b[0m     \u001b[1;32mreturn\u001b[0m \u001b[0m_unpack_inner\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\AppData\\Roaming\\Python\\Python39\\site-packages\\autogluon\\tabular\\predictor\\predictor.py\u001b[0m in \u001b[0;36mfit\u001b[1;34m(self, train_data, tuning_data, time_limit, presets, hyperparameters, feature_metadata, infer_limit, infer_limit_batch_size, **kwargs)\u001b[0m\n\u001b[0;32m    795\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    796\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mtime_limit\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--> 797\u001b[1;33m             \u001b[0mmb_mem_usage_train_data\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mget_approximate_df_mem_usage\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtrain_data\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msample_ratio\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0.2\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msum\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m/\u001b[0m \u001b[1;36m1e6\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    798\u001b[0m             \u001b[0mnum_rows_train\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtrain_data\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    799\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mmb_mem_usage_train_data\u001b[0m \u001b[1;33m>=\u001b[0m \u001b[1;36m50\u001b[0m \u001b[1;32mor\u001b[0m \u001b[0mnum_rows_train\u001b[0m \u001b[1;33m>=\u001b[0m \u001b[1;36m100000\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\AppData\\Roaming\\Python\\Python39\\site-packages\\autogluon\\common\\utils\\pandas_utils.py\u001b[0m in \u001b[0;36minner\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m     20\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     21\u001b[0m                 \u001b[0mpackage_logger\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msetLevel\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmax\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m30\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mprevious_log_level\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---> 22\u001b[1;33m                 \u001b[1;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\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     23\u001b[0m             \u001b[1;32mfinally\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     24\u001b[0m                 \u001b[0mpackage_logger\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msetLevel\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mprevious_log_level\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\AppData\\Roaming\\Python\\Python39\\site-packages\\autogluon\\common\\utils\\pandas_utils.py\u001b[0m in \u001b[0;36mget_approximate_df_mem_usage\u001b[1;34m(df, sample_ratio)\u001b[0m\n\u001b[0;32m     48\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mcolumns_inexact\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     49\u001b[0m             \u001b[1;31m# this line causes NumExpr log, suspend_logging is used to hide the log.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 50\u001b[1;33m             \u001b[0mmemory_usage_inexact\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mcolumns_inexact\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mhead\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnum_rows_sample\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmemory_usage\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdeep\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mcolumns_inexact\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m/\u001b[0m \u001b[0msample_ratio\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     51\u001b[0m             \u001b[0mmemory_usage\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmemory_usage_inexact\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcombine_first\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmemory_usage\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     52\u001b[0m         \u001b[1;32mreturn\u001b[0m \u001b[0mmemory_usage\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mD:\\anaconda3\\lib\\site-packages\\pandas\\core\\ops\\common.py\u001b[0m in \u001b[0;36mnew_method\u001b[1;34m(self, other)\u001b[0m\n\u001b[0;32m     63\u001b[0m                 \u001b[1;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcls\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     64\u001b[0m                     \u001b[1;32mbreak\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 65\u001b[1;33m                 \u001b[1;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mother\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcls\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     66\u001b[0m                     \u001b[1;32mreturn\u001b[0m \u001b[0mNotImplemented\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     67\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mD:\\anaconda3\\lib\\site-packages\\pandas\\core\\arraylike.py\u001b[0m in \u001b[0;36m__truediv__\u001b[1;34m(self, other)\u001b[0m\n\u001b[0;32m    111\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m__rsub__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mother\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    112\u001b[0m         \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_arith_method\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mother\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mroperator\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrsub\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 113\u001b[1;33m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    114\u001b[0m     \u001b[1;33m@\u001b[0m\u001b[0munpack_zerodim_and_defer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"__mul__\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    115\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m__mul__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mother\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;32mD:\\anaconda3\\lib\\site-packages\\pandas\\core\\series.py\u001b[0m in \u001b[0;36m_arith_method\u001b[1;34m(self, other, op)\u001b[0m\n\u001b[0;32m   4993\u001b[0m         \u001b[0mvalues\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mresult\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_values\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   4994\u001b[0m         \u001b[0mmask\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmissing\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmask_missing\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mto_replace\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 4995\u001b[1;33m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   4996\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mExtensionArray\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   4997\u001b[0m             \u001b[1;31m# dispatch to the EA's _pad_mask_inplace method\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mD:\\anaconda3\\lib\\site-packages\\pandas\\core\\ops\\array_ops.py\u001b[0m in \u001b[0;36marithmetic_op\u001b[1;34m(left, right, op)\u001b[0m\n\u001b[0;32m    187\u001b[0m     \u001b[0mNote\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mthe\u001b[0m \u001b[0mcaller\u001b[0m \u001b[1;32mis\u001b[0m \u001b[0mresponsible\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mensuring\u001b[0m \u001b[0mthat\u001b[0m \u001b[0mnumpy\u001b[0m \u001b[0mwarnings\u001b[0m \u001b[0mare\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    188\u001b[0m     \u001b[0msuppressed\u001b[0m \u001b[1;33m(\u001b[0m\u001b[1;32mwith\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0merrstate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mall\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m\"ignore\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mneeded\u001b[0m\u001b[1;33m.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 189\u001b[1;33m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    190\u001b[0m     \u001b[0mParameters\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    191\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[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[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mD:\\anaconda3\\lib\\site-packages\\pandas\\core\\ops\\array_ops.py\u001b[0m in \u001b[0;36m_na_arithmetic_op\u001b[1;34m(left, right, op, is_cmp)\u001b[0m\n\u001b[0;32m    137\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    138\u001b[0m     \u001b[0mIf\u001b[0m \u001b[0mnative\u001b[0m \u001b[0mtypes\u001b[0m \u001b[0mare\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mcompatible\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;32mtry\u001b[0m \u001b[0mcoercion\u001b[0m \u001b[0mto\u001b[0m \u001b[0mobject\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 139\u001b[1;33m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    140\u001b[0m     \u001b[0mParameters\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    141\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[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[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mD:\\anaconda3\\lib\\site-packages\\pandas\\core\\computation\\expressions.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m     17\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mpandas\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_typing\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mFuncType\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     18\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 19\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0mpandas\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcore\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcomputation\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcheck\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mNUMEXPR_INSTALLED\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     20\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mpandas\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcore\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mops\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mroperator\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     21\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mD:\\anaconda3\\lib\\site-packages\\pandas\\core\\computation\\check.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mpandas\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcompat\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_optional\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mimport_optional_dependency\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      2\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 3\u001b[1;33m \u001b[0mne\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mimport_optional_dependency\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"numexpr\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0merrors\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m\"warn\"\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      4\u001b[0m \u001b[0mNUMEXPR_INSTALLED\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mne\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      5\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mNUMEXPR_INSTALLED\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mTypeError\u001b[0m: import_optional_dependency() got an unexpected keyword argument 'errors'"
     ]
    }
   ],
   "source": [
    "train_data = pd.read_csv('E:/dasein_py/Data Analysis/招商银行/train.csv')\n",
    "save_path = 'E:/dasein_py/Data Analysis/招商银行/agModels-predictClass/'\n",
    "predictor = TabularPredictor(label= 'LABEL' , eval_metric='roc_auc', path = save_path).fit(train_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "3c7621ff-be68-45b6-af58-fc370469ba28",
   "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>LABEL</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39995</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39996</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39997</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39998</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39999</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>40000 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       LABEL\n",
       "0          0\n",
       "1          0\n",
       "2          0\n",
       "3          1\n",
       "4          1\n",
       "...      ...\n",
       "39995      0\n",
       "39996      0\n",
       "39997      0\n",
       "39998      1\n",
       "39999      0\n",
       "\n",
       "[40000 rows x 1 columns]"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lbl"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "id": "9ea36f75-2c8e-4df4-8622-1012063311af",
   "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>LABEL</th>\n",
       "      <th>AGN_CNT_RCT_12_MON</th>\n",
       "      <th>ICO_CUR_MON_ACM_TRX_TM</th>\n",
       "      <th>NB_RCT_3_MON_LGN_TMS_AGV</th>\n",
       "      <th>AGN_CUR_YEAR_AMT</th>\n",
       "      <th>AGN_CUR_YEAR_WAG_AMT</th>\n",
       "      <th>AGN_AGR_LATEST_AGN_AMT</th>\n",
       "      <th>ICO_CUR_MON_ACM_TRX_AMT</th>\n",
       "      <th>COUNTER_CUR_YEAR_CNT_AMT</th>\n",
       "      <th>PUB_TO_PRV_TRX_AMT_CUR_YEAR</th>\n",
       "      <th>...</th>\n",
       "      <th>WTHR_OPN_ONL_ICO</th>\n",
       "      <th>EMP_NBR</th>\n",
       "      <th>REG_CPT</th>\n",
       "      <th>SHH_BCK</th>\n",
       "      <th>HLD_DMS_CCY_ACT_NBR</th>\n",
       "      <th>REG_DT</th>\n",
       "      <th>LGP_HLD_CARD_LVL</th>\n",
       "      <th>OPN_TM</th>\n",
       "      <th>NB_CTC_HLD_IDV_AIO_CARD_SITU</th>\n",
       "      <th>HLD_FGN_CCY_ACT_NBR</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>?</td>\n",
       "      <td>72</td>\n",
       "      <td>425.3</td>\n",
       "      <td>?</td>\n",
       "      <td>?</td>\n",
       "      <td>?</td>\n",
       "      <td>25879985.3</td>\n",
       "      <td>2</td>\n",
       "      <td>660732</td>\n",
       "      <td>...</td>\n",
       "      <td>B</td>\n",
       "      <td>2</td>\n",
       "      <td>1200000002</td>\n",
       "      <td>32</td>\n",
       "      <td>12</td>\n",
       "      <td>1708.45</td>\n",
       "      <td>?</td>\n",
       "      <td>416.84</td>\n",
       "      <td>?</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>2282</td>\n",
       "      <td>222</td>\n",
       "      <td>?</td>\n",
       "      <td>11776572.4</td>\n",
       "      <td>?</td>\n",
       "      <td>1964626.4</td>\n",
       "      <td>14755499.8</td>\n",
       "      <td>2</td>\n",
       "      <td>126608.3</td>\n",
       "      <td>...</td>\n",
       "      <td>B</td>\n",
       "      <td>1002</td>\n",
       "      <td>5000002</td>\n",
       "      <td>32</td>\n",
       "      <td>22</td>\n",
       "      <td>199.42</td>\n",
       "      <td>F</td>\n",
       "      <td>195.87</td>\n",
       "      <td>D</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>?</td>\n",
       "      <td>2</td>\n",
       "      <td>?</td>\n",
       "      <td>?</td>\n",
       "      <td>?</td>\n",
       "      <td>4599822.3</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>B</td>\n",
       "      <td>2</td>\n",
       "      <td>?</td>\n",
       "      <td>2</td>\n",
       "      <td>12</td>\n",
       "      <td>1135.55</td>\n",
       "      <td>F</td>\n",
       "      <td>1122</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>?</td>\n",
       "      <td>?</td>\n",
       "      <td>22</td>\n",
       "      <td>?</td>\n",
       "      <td>?</td>\n",
       "      <td>?</td>\n",
       "      <td>?</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>A</td>\n",
       "      <td>2</td>\n",
       "      <td>500002</td>\n",
       "      <td>12</td>\n",
       "      <td>12</td>\n",
       "      <td>98.45</td>\n",
       "      <td>NaN</td>\n",
       "      <td>92</td>\n",
       "      <td>C</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</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>A</td>\n",
       "      <td>2</td>\n",
       "      <td>?</td>\n",
       "      <td>2</td>\n",
       "      <td>12</td>\n",
       "      <td>?</td>\n",
       "      <td>NaN</td>\n",
       "      <td>355.87</td>\n",
       "      <td>C</td>\n",
       "      <td>2</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>39995</th>\n",
       "      <td>0</td>\n",
       "      <td>?</td>\n",
       "      <td>2</td>\n",
       "      <td>55.3</td>\n",
       "      <td>?</td>\n",
       "      <td>?</td>\n",
       "      <td>?</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>B</td>\n",
       "      <td>402</td>\n",
       "      <td>300000002</td>\n",
       "      <td>12</td>\n",
       "      <td>22</td>\n",
       "      <td>204.26</td>\n",
       "      <td>C</td>\n",
       "      <td>130.06</td>\n",
       "      <td>B</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39996</th>\n",
       "      <td>0</td>\n",
       "      <td>?</td>\n",
       "      <td>72</td>\n",
       "      <td>145.3</td>\n",
       "      <td>?</td>\n",
       "      <td>?</td>\n",
       "      <td>?</td>\n",
       "      <td>16431457.9</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>B</td>\n",
       "      <td>2</td>\n",
       "      <td>500000002</td>\n",
       "      <td>12</td>\n",
       "      <td>12</td>\n",
       "      <td>176.52</td>\n",
       "      <td>?</td>\n",
       "      <td>160.71</td>\n",
       "      <td>?</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39997</th>\n",
       "      <td>0</td>\n",
       "      <td>21532</td>\n",
       "      <td>1132</td>\n",
       "      <td>?</td>\n",
       "      <td>81027170.3</td>\n",
       "      <td>?</td>\n",
       "      <td>12772212.7</td>\n",
       "      <td>596254539.9</td>\n",
       "      <td>2</td>\n",
       "      <td>484869.1</td>\n",
       "      <td>...</td>\n",
       "      <td>B</td>\n",
       "      <td>5002</td>\n",
       "      <td>500000002</td>\n",
       "      <td>32</td>\n",
       "      <td>12</td>\n",
       "      <td>2265.55</td>\n",
       "      <td>D</td>\n",
       "      <td>2132.65</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39998</th>\n",
       "      <td>1</td>\n",
       "      <td>?</td>\n",
       "      <td>12</td>\n",
       "      <td>128.7</td>\n",
       "      <td>?</td>\n",
       "      <td>?</td>\n",
       "      <td>?</td>\n",
       "      <td>488502</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>B</td>\n",
       "      <td>2</td>\n",
       "      <td>10000002</td>\n",
       "      <td>12</td>\n",
       "      <td>12</td>\n",
       "      <td>516.52</td>\n",
       "      <td>?</td>\n",
       "      <td>510.06</td>\n",
       "      <td>?</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39999</th>\n",
       "      <td>0</td>\n",
       "      <td>?</td>\n",
       "      <td>32</td>\n",
       "      <td>235.3</td>\n",
       "      <td>?</td>\n",
       "      <td>?</td>\n",
       "      <td>?</td>\n",
       "      <td>2740802</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>B</td>\n",
       "      <td>2002</td>\n",
       "      <td>1007800002</td>\n",
       "      <td>32</td>\n",
       "      <td>22</td>\n",
       "      <td>1945.87</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1045.55</td>\n",
       "      <td>A</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>40000 rows × 50 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       LABEL AGN_CNT_RCT_12_MON ICO_CUR_MON_ACM_TRX_TM  \\\n",
       "0          0                  ?                     72   \n",
       "1          0               2282                    222   \n",
       "2          0                  ?                      2   \n",
       "3          1                  ?                      ?   \n",
       "4          1                  ?                      ?   \n",
       "...      ...                ...                    ...   \n",
       "39995      0                  ?                      2   \n",
       "39996      0                  ?                     72   \n",
       "39997      0              21532                   1132   \n",
       "39998      1                  ?                     12   \n",
       "39999      0                  ?                     32   \n",
       "\n",
       "      NB_RCT_3_MON_LGN_TMS_AGV AGN_CUR_YEAR_AMT AGN_CUR_YEAR_WAG_AMT  \\\n",
       "0                        425.3                ?                    ?   \n",
       "1                            ?       11776572.4                    ?   \n",
       "2                            ?                ?                    ?   \n",
       "3                           22                ?                    ?   \n",
       "4                            ?                ?                    ?   \n",
       "...                        ...              ...                  ...   \n",
       "39995                     55.3                ?                    ?   \n",
       "39996                    145.3                ?                    ?   \n",
       "39997                        ?       81027170.3                    ?   \n",
       "39998                    128.7                ?                    ?   \n",
       "39999                    235.3                ?                    ?   \n",
       "\n",
       "      AGN_AGR_LATEST_AGN_AMT ICO_CUR_MON_ACM_TRX_AMT COUNTER_CUR_YEAR_CNT_AMT  \\\n",
       "0                          ?              25879985.3                        2   \n",
       "1                  1964626.4              14755499.8                        2   \n",
       "2                  4599822.3                       2                        2   \n",
       "3                          ?                       ?                        2   \n",
       "4                          ?                       ?                        ?   \n",
       "...                      ...                     ...                      ...   \n",
       "39995                      ?                       2                        2   \n",
       "39996                      ?              16431457.9                        2   \n",
       "39997             12772212.7             596254539.9                        2   \n",
       "39998                      ?                  488502                        2   \n",
       "39999                      ?                 2740802                        2   \n",
       "\n",
       "      PUB_TO_PRV_TRX_AMT_CUR_YEAR  ... WTHR_OPN_ONL_ICO EMP_NBR     REG_CPT  \\\n",
       "0                          660732  ...                B       2  1200000002   \n",
       "1                        126608.3  ...                B    1002     5000002   \n",
       "2                               2  ...                B       2           ?   \n",
       "3                               2  ...                A       2      500002   \n",
       "4                               ?  ...                A       2           ?   \n",
       "...                           ...  ...              ...     ...         ...   \n",
       "39995                           2  ...                B     402   300000002   \n",
       "39996                           2  ...                B       2   500000002   \n",
       "39997                    484869.1  ...                B    5002   500000002   \n",
       "39998                           2  ...                B       2    10000002   \n",
       "39999                           2  ...                B    2002  1007800002   \n",
       "\n",
       "      SHH_BCK HLD_DMS_CCY_ACT_NBR   REG_DT LGP_HLD_CARD_LVL   OPN_TM  \\\n",
       "0          32                  12  1708.45                ?   416.84   \n",
       "1          32                  22   199.42                F   195.87   \n",
       "2           2                  12  1135.55                F     1122   \n",
       "3          12                  12    98.45              NaN       92   \n",
       "4           2                  12        ?              NaN   355.87   \n",
       "...       ...                 ...      ...              ...      ...   \n",
       "39995      12                  22   204.26                C   130.06   \n",
       "39996      12                  12   176.52                ?   160.71   \n",
       "39997      32                  12  2265.55                D  2132.65   \n",
       "39998      12                  12   516.52                ?   510.06   \n",
       "39999      32                  22  1945.87              NaN  1045.55   \n",
       "\n",
       "      NB_CTC_HLD_IDV_AIO_CARD_SITU HLD_FGN_CCY_ACT_NBR  \n",
       "0                                ?                   2  \n",
       "1                                D                   2  \n",
       "2                              NaN                   2  \n",
       "3                                C                   2  \n",
       "4                                C                   2  \n",
       "...                            ...                 ...  \n",
       "39995                            B                   2  \n",
       "39996                            ?                   2  \n",
       "39997                          NaN                   2  \n",
       "39998                            ?                   2  \n",
       "39999                            A                   2  \n",
       "\n",
       "[40000 rows x 50 columns]"
      ]
     },
     "execution_count": 109,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "88539087-fea0-483c-96ea-7830f7d12a2c",
   "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}