{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "c6458055",
   "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>night_call_dura_rate</th>\n",
       "      <th>l3m_night_call_dura_rate</th>\n",
       "      <th>l6m_night_call_dura_rate</th>\n",
       "      <th>night_call_cnt_rate</th>\n",
       "      <th>l3m_night_call_cnt_rate</th>\n",
       "      <th>l6m_night_call_cnt_rate</th>\n",
       "      <th>called_cnt_rate</th>\n",
       "      <th>l3m_called_cnt_rate</th>\n",
       "      <th>l6m_called_cnt_rate</th>\n",
       "      <th>contact_ratio</th>\n",
       "      <th>...</th>\n",
       "      <th>rcn_chnl_id</th>\n",
       "      <th>rcn_chnl_typ</th>\n",
       "      <th>rcn_mode</th>\n",
       "      <th>user_star_val</th>\n",
       "      <th>star_evalu_tm</th>\n",
       "      <th>is_fam_v_ntw</th>\n",
       "      <th>is_camp_user</th>\n",
       "      <th>is_camp_area_user</th>\n",
       "      <th>row_num</th>\n",
       "      <th>label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.2726</td>\n",
       "      <td>0.5082</td>\n",
       "      <td>5.5138</td>\n",
       "      <td>3.1250</td>\n",
       "      <td>2.1277</td>\n",
       "      <td>4.6512</td>\n",
       "      <td>87.5000</td>\n",
       "      <td>88.2979</td>\n",
       "      <td>84.3023</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>30507</td>\n",
       "      <td>3</td>\n",
       "      <td>4.0</td>\n",
       "      <td>198.0</td>\n",
       "      <td>202110</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>29833</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>8.4315</td>\n",
       "      <td>3.6997</td>\n",
       "      <td>2.0436</td>\n",
       "      <td>6.9767</td>\n",
       "      <td>2.0305</td>\n",
       "      <td>1.3298</td>\n",
       "      <td>76.7442</td>\n",
       "      <td>72.0812</td>\n",
       "      <td>67.8191</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>GZ_GZPY0612038</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4.0</td>\n",
       "      <td>91.0</td>\n",
       "      <td>202207</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>18121</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5.0105</td>\n",
       "      <td>4.7252</td>\n",
       "      <td>3.5456</td>\n",
       "      <td>7.6923</td>\n",
       "      <td>7.3684</td>\n",
       "      <td>5.4526</td>\n",
       "      <td>49.0385</td>\n",
       "      <td>55.5263</td>\n",
       "      <td>56.4885</td>\n",
       "      <td>7</td>\n",
       "      <td>...</td>\n",
       "      <td>218568</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>8372</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.4925</td>\n",
       "      <td>0.6083</td>\n",
       "      <td>2.8386</td>\n",
       "      <td>3.8462</td>\n",
       "      <td>2.2222</td>\n",
       "      <td>5.6604</td>\n",
       "      <td>19.2308</td>\n",
       "      <td>46.6667</td>\n",
       "      <td>52.8302</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>2.25E+18</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4.0</td>\n",
       "      <td>133.0</td>\n",
       "      <td>202112</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>32780</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.7424</td>\n",
       "      <td>0.6146</td>\n",
       "      <td>0.9135</td>\n",
       "      <td>0.6472</td>\n",
       "      <td>0.4854</td>\n",
       "      <td>0.3784</td>\n",
       "      <td>37.5405</td>\n",
       "      <td>38.4709</td>\n",
       "      <td>40.6486</td>\n",
       "      <td>15</td>\n",
       "      <td>...</td>\n",
       "      <td>BASS1_ST</td>\n",
       "      <td>9999</td>\n",
       "      <td>99.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3509</td>\n",
       "      <td>0</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>39138</th>\n",
       "      <td>0.6517</td>\n",
       "      <td>1.4560</td>\n",
       "      <td>2.2093</td>\n",
       "      <td>2.5510</td>\n",
       "      <td>3.0505</td>\n",
       "      <td>4.3779</td>\n",
       "      <td>44.6429</td>\n",
       "      <td>47.2831</td>\n",
       "      <td>49.9078</td>\n",
       "      <td>20</td>\n",
       "      <td>...</td>\n",
       "      <td>112000259</td>\n",
       "      <td>3</td>\n",
       "      <td>99.0</td>\n",
       "      <td>311.0</td>\n",
       "      <td>202202</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3193</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39139</th>\n",
       "      <td>0.3208</td>\n",
       "      <td>0.2805</td>\n",
       "      <td>0.5318</td>\n",
       "      <td>0.7299</td>\n",
       "      <td>0.7317</td>\n",
       "      <td>0.9901</td>\n",
       "      <td>27.7372</td>\n",
       "      <td>30.4878</td>\n",
       "      <td>30.5831</td>\n",
       "      <td>9</td>\n",
       "      <td>...</td>\n",
       "      <td>27031001</td>\n",
       "      <td>1002</td>\n",
       "      <td>4.0</td>\n",
       "      <td>203.0</td>\n",
       "      <td>202110</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>46717</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39140</th>\n",
       "      <td>1.3945</td>\n",
       "      <td>4.3936</td>\n",
       "      <td>3.6663</td>\n",
       "      <td>1.8519</td>\n",
       "      <td>2.1277</td>\n",
       "      <td>2.4476</td>\n",
       "      <td>68.5185</td>\n",
       "      <td>64.7754</td>\n",
       "      <td>63.4615</td>\n",
       "      <td>5</td>\n",
       "      <td>...</td>\n",
       "      <td>NX.01.06.03.100</td>\n",
       "      <td>2104</td>\n",
       "      <td>4.0</td>\n",
       "      <td>119.0</td>\n",
       "      <td>202107</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>46379</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39141</th>\n",
       "      <td>1.3134</td>\n",
       "      <td>0.8997</td>\n",
       "      <td>0.8586</td>\n",
       "      <td>0.3226</td>\n",
       "      <td>0.3333</td>\n",
       "      <td>0.7042</td>\n",
       "      <td>64.1935</td>\n",
       "      <td>62.5000</td>\n",
       "      <td>63.8833</td>\n",
       "      <td>14</td>\n",
       "      <td>...</td>\n",
       "      <td>HB.TS.13.01.G1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4.0</td>\n",
       "      <td>163.0</td>\n",
       "      <td>202111</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>12670</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39142</th>\n",
       "      <td>3.2597</td>\n",
       "      <td>5.8913</td>\n",
       "      <td>5.7781</td>\n",
       "      <td>7.1429</td>\n",
       "      <td>4.4444</td>\n",
       "      <td>6.3559</td>\n",
       "      <td>43.8776</td>\n",
       "      <td>37.7778</td>\n",
       "      <td>35.5932</td>\n",
       "      <td>8</td>\n",
       "      <td>...</td>\n",
       "      <td>10191125</td>\n",
       "      <td>2103</td>\n",
       "      <td>99.0</td>\n",
       "      <td>250.0</td>\n",
       "      <td>202111</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>43570</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>39143 rows × 85 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       night_call_dura_rate  l3m_night_call_dura_rate  \\\n",
       "0                    1.2726                    0.5082   \n",
       "1                    8.4315                    3.6997   \n",
       "2                    5.0105                    4.7252   \n",
       "3                    1.4925                    0.6083   \n",
       "4                    0.7424                    0.6146   \n",
       "...                     ...                       ...   \n",
       "39138                0.6517                    1.4560   \n",
       "39139                0.3208                    0.2805   \n",
       "39140                1.3945                    4.3936   \n",
       "39141                1.3134                    0.8997   \n",
       "39142                3.2597                    5.8913   \n",
       "\n",
       "       l6m_night_call_dura_rate  night_call_cnt_rate  l3m_night_call_cnt_rate  \\\n",
       "0                        5.5138               3.1250                   2.1277   \n",
       "1                        2.0436               6.9767                   2.0305   \n",
       "2                        3.5456               7.6923                   7.3684   \n",
       "3                        2.8386               3.8462                   2.2222   \n",
       "4                        0.9135               0.6472                   0.4854   \n",
       "...                         ...                  ...                      ...   \n",
       "39138                    2.2093               2.5510                   3.0505   \n",
       "39139                    0.5318               0.7299                   0.7317   \n",
       "39140                    3.6663               1.8519                   2.1277   \n",
       "39141                    0.8586               0.3226                   0.3333   \n",
       "39142                    5.7781               7.1429                   4.4444   \n",
       "\n",
       "       l6m_night_call_cnt_rate  called_cnt_rate  l3m_called_cnt_rate  \\\n",
       "0                       4.6512          87.5000              88.2979   \n",
       "1                       1.3298          76.7442              72.0812   \n",
       "2                       5.4526          49.0385              55.5263   \n",
       "3                       5.6604          19.2308              46.6667   \n",
       "4                       0.3784          37.5405              38.4709   \n",
       "...                        ...              ...                  ...   \n",
       "39138                   4.3779          44.6429              47.2831   \n",
       "39139                   0.9901          27.7372              30.4878   \n",
       "39140                   2.4476          68.5185              64.7754   \n",
       "39141                   0.7042          64.1935              62.5000   \n",
       "39142                   6.3559          43.8776              37.7778   \n",
       "\n",
       "       l6m_called_cnt_rate  contact_ratio  ...      rcn_chnl_id  rcn_chnl_typ  \\\n",
       "0                  84.3023              1  ...            30507             3   \n",
       "1                  67.8191              3  ...   GZ_GZPY0612038           NaN   \n",
       "2                  56.4885              7  ...           218568           NaN   \n",
       "3                  52.8302              0  ...         2.25E+18           NaN   \n",
       "4                  40.6486             15  ...         BASS1_ST          9999   \n",
       "...                    ...            ...  ...              ...           ...   \n",
       "39138              49.9078             20  ...        112000259             3   \n",
       "39139              30.5831              9  ...         27031001          1002   \n",
       "39140              63.4615              5  ...  NX.01.06.03.100          2104   \n",
       "39141              63.8833             14  ...   HB.TS.13.01.G1           NaN   \n",
       "39142              35.5932              8  ...         10191125          2103   \n",
       "\n",
       "       rcn_mode  user_star_val  star_evalu_tm  is_fam_v_ntw  is_camp_user  \\\n",
       "0           4.0          198.0         202110             0             0   \n",
       "1           4.0           91.0         202207             0             0   \n",
       "2           4.0            NaN             -3             1             1   \n",
       "3           4.0          133.0         202112             1             1   \n",
       "4          99.0            NaN             -3             0             0   \n",
       "...         ...            ...            ...           ...           ...   \n",
       "39138      99.0          311.0         202202             0             0   \n",
       "39139       4.0          203.0         202110             0             0   \n",
       "39140       4.0          119.0         202107             0             0   \n",
       "39141       4.0          163.0         202111             0             0   \n",
       "39142      99.0          250.0         202111             1             0   \n",
       "\n",
       "       is_camp_area_user  row_num  label  \n",
       "0                      0    29833      0  \n",
       "1                      0    18121      0  \n",
       "2                      0     8372      0  \n",
       "3                      0    32780      0  \n",
       "4                      0     3509      0  \n",
       "...                  ...      ...    ...  \n",
       "39138                  0     3193      0  \n",
       "39139                  0    46717      0  \n",
       "39140                  0    46379      0  \n",
       "39141                  0    12670      0  \n",
       "39142                  0    43570      0  \n",
       "\n",
       "[39143 rows x 85 columns]"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import os\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "data1=pd.read_csv('csvdata/train_a_label.csv', encoding='gbk')\n",
    "data2=pd.read_csv('csvdata/train_b.csv')\n",
    "data3=pd.read_csv('csvdata/test_a.csv', encoding='gbk')\n",
    "data4=pd.read_csv('csvdata/test_b.csv')\n",
    "data1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "deadly-torture",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "#补0\n",
    "data1=data1.fillna(-1)\n",
    "data2=data2.fillna(-1)\n",
    "data3=data3.fillna(-1)\n",
    "data4=data4.fillna(-1)\n",
    "\n",
    "data1=data1[['row_num'] + data1.drop(labels=['row_num'],axis=1).columns.tolist() ] \n",
    "data2=data2[['row_num'] + data2.drop(labels=['row_num'],axis=1).columns.tolist() ] \n",
    "data3=data3[['row_num'] + data3.drop(labels=['row_num'],axis=1).columns.tolist() ] \n",
    "data4=data4[['row_num'] + data4.drop(labels=['row_num'],axis=1).columns.tolist() ] \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "narrow-feedback",
   "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>row_num</th>\n",
       "      <th>label</th>\n",
       "      <th>user_star_val</th>\n",
       "      <th>night_call_dura_rate</th>\n",
       "      <th>night_call_cnt_rate</th>\n",
       "      <th>age</th>\n",
       "      <th>cust_star</th>\n",
       "      <th>opp_belo_cnt</th>\n",
       "      <th>rcn_mode</th>\n",
       "      <th>l6m_night_call_cnt_rate</th>\n",
       "      <th>night_percent_six</th>\n",
       "      <th>brand_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>29833</td>\n",
       "      <td>0</td>\n",
       "      <td>198.0</td>\n",
       "      <td>1.2726</td>\n",
       "      <td>3.1250</td>\n",
       "      <td>2</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4.6512</td>\n",
       "      <td>5.11</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>18121</td>\n",
       "      <td>0</td>\n",
       "      <td>91.0</td>\n",
       "      <td>8.4315</td>\n",
       "      <td>6.9767</td>\n",
       "      <td>1</td>\n",
       "      <td>6.0</td>\n",
       "      <td>3</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1.3298</td>\n",
       "      <td>17.64</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8372</td>\n",
       "      <td>0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>5.0105</td>\n",
       "      <td>7.6923</td>\n",
       "      <td>4</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>3</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.4526</td>\n",
       "      <td>12.70</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>32780</td>\n",
       "      <td>0</td>\n",
       "      <td>133.0</td>\n",
       "      <td>1.4925</td>\n",
       "      <td>3.8462</td>\n",
       "      <td>2</td>\n",
       "      <td>7.0</td>\n",
       "      <td>3</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.6604</td>\n",
       "      <td>2.83</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3509</td>\n",
       "      <td>0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0.7424</td>\n",
       "      <td>0.6472</td>\n",
       "      <td>6</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>3</td>\n",
       "      <td>99.0</td>\n",
       "      <td>0.3784</td>\n",
       "      <td>6.18</td>\n",
       "      <td>1</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39138</th>\n",
       "      <td>3193</td>\n",
       "      <td>0</td>\n",
       "      <td>311.0</td>\n",
       "      <td>0.6517</td>\n",
       "      <td>2.5510</td>\n",
       "      <td>5</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3</td>\n",
       "      <td>99.0</td>\n",
       "      <td>4.3779</td>\n",
       "      <td>11.52</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39139</th>\n",
       "      <td>46717</td>\n",
       "      <td>0</td>\n",
       "      <td>203.0</td>\n",
       "      <td>0.3208</td>\n",
       "      <td>0.7299</td>\n",
       "      <td>3</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.9901</td>\n",
       "      <td>11.19</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39140</th>\n",
       "      <td>46379</td>\n",
       "      <td>0</td>\n",
       "      <td>119.0</td>\n",
       "      <td>1.3945</td>\n",
       "      <td>1.8519</td>\n",
       "      <td>3</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4</td>\n",
       "      <td>4.0</td>\n",
       "      <td>2.4476</td>\n",
       "      <td>30.93</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39141</th>\n",
       "      <td>12670</td>\n",
       "      <td>0</td>\n",
       "      <td>163.0</td>\n",
       "      <td>1.3134</td>\n",
       "      <td>0.3226</td>\n",
       "      <td>6</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.7042</td>\n",
       "      <td>36.48</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39142</th>\n",
       "      <td>43570</td>\n",
       "      <td>0</td>\n",
       "      <td>250.0</td>\n",
       "      <td>3.2597</td>\n",
       "      <td>7.1429</td>\n",
       "      <td>4</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5</td>\n",
       "      <td>99.0</td>\n",
       "      <td>6.3559</td>\n",
       "      <td>24.18</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>39143 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       row_num  label  user_star_val  night_call_dura_rate  \\\n",
       "0        29833      0          198.0                1.2726   \n",
       "1        18121      0           91.0                8.4315   \n",
       "2         8372      0           -1.0                5.0105   \n",
       "3        32780      0          133.0                1.4925   \n",
       "4         3509      0           -1.0                0.7424   \n",
       "...        ...    ...            ...                   ...   \n",
       "39138     3193      0          311.0                0.6517   \n",
       "39139    46717      0          203.0                0.3208   \n",
       "39140    46379      0          119.0                1.3945   \n",
       "39141    12670      0          163.0                1.3134   \n",
       "39142    43570      0          250.0                3.2597   \n",
       "\n",
       "       night_call_cnt_rate  age  cust_star  opp_belo_cnt  rcn_mode  \\\n",
       "0                   3.1250    2        4.0             5       4.0   \n",
       "1                   6.9767    1        6.0             3       4.0   \n",
       "2                   7.6923    4       -1.0             3       4.0   \n",
       "3                   3.8462    2        7.0             3       4.0   \n",
       "4                   0.6472    6       -1.0             3      99.0   \n",
       "...                    ...  ...        ...           ...       ...   \n",
       "39138               2.5510    5        4.0             3      99.0   \n",
       "39139               0.7299    3        5.0             4       4.0   \n",
       "39140               1.8519    3        5.0             4       4.0   \n",
       "39141               0.3226    6        5.0             2       4.0   \n",
       "39142               7.1429    4        5.0             5      99.0   \n",
       "\n",
       "       l6m_night_call_cnt_rate  night_percent_six  brand_id  \n",
       "0                       4.6512               5.11         2  \n",
       "1                       1.3298              17.64         2  \n",
       "2                       5.4526              12.70         2  \n",
       "3                       5.6604               2.83         1  \n",
       "4                       0.3784               6.18         1  \n",
       "...                        ...                ...       ...  \n",
       "39138                   4.3779              11.52         2  \n",
       "39139                   0.9901              11.19         1  \n",
       "39140                   2.4476              30.93         1  \n",
       "39141                   0.7042              36.48         1  \n",
       "39142                   6.3559              24.18         1  \n",
       "\n",
       "[39143 rows x 12 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#data1=data1.drop(labels=['pretty_num_typ','rcn_chnl_id','rcn_chnl_typ','star_evalu_tm','star_evalu_tm', 'top5_call_dura_rate', 'l6m_once_numbers_rate', 'once_numbers_rate', 'l6m_contact_ratio', 'l3m_top10_call_cnt_rate', 'l3m_top5_call_cnt_rate', 'l6m_top10_call_dura_rate', 'l3m_is_same_imei_msisdn_cnt_gtr2', 'top10_call_dura_rate', 'ocpn_code', 'top5_call_cnt_rate', 'top10_opp_belo_cnt', 'educat_degree_code', 'l6m_top10_opp_belo_cnt', 'l3m_once_numbers_rate', 'l3m_top10_opp_belo_cnt', 'l3m_contact_ratio', 'l6m_top5_call_dura_rate', 'pre3m_top10_diff_num', 'age_lvl', 'top10_diff_num', 'same_idcard_msisdn_cnt', 'pre3m_top5_diff_num', 'l3m_id_cnt', 'l3m_top10_call_dura_rate', 'pre2m_top10_diff_num', 'top10_call_cnt_rate', 'contact_ratio', 'top5_opp_belo_cnt', 'is_pretty_num', 'l3m_top5_opp_belo_cnt', 'pre2m_top5_diff_num', 'l1m_is_same_imei_msisdn_cnt_gtr2', 'sex', 'same_imei_msisdn_hr_cnt', 'l6m_top5_opp_belo_cnt', 'is_fam_v_ntw', 'top5_diff_num', 'is_camp_user', 'idty_typ', 'zuche_six_total_dur', 'vip_lvl'],axis=1)\n",
    "data1=data1[['row_num','label','user_star_val','night_call_dura_rate', 'night_call_cnt_rate', 'age', 'cust_star', 'opp_belo_cnt', 'rcn_mode', 'l6m_night_call_cnt_rate', 'night_percent_six', 'brand_id']]\n",
    "#, 'star_evalu_tm', 'l3m_called_cnt_rate', 'night_percent_current', 'l6m_called_cnt_rate', 'l3m_night_call_dura_rate'\n",
    "data1['age']=data1['age']//10\n",
    "data1.to_csv(path_or_buf='csvclear/train_a_label.csv', index=None) \n",
    "\n",
    "\n",
    "#data3=data3.drop(labels=['pretty_num_typ','rcn_chnl_id','rcn_chnl_typ','star_evalu_tm', 'top5_call_dura_rate', 'l6m_once_numbers_rate', 'once_numbers_rate', 'l6m_contact_ratio', 'l3m_top10_call_cnt_rate', 'l3m_top5_call_cnt_rate', 'l6m_top10_call_dura_rate', 'l3m_is_same_imei_msisdn_cnt_gtr2', 'top10_call_dura_rate', 'ocpn_code', 'top5_call_cnt_rate', 'top10_opp_belo_cnt', 'educat_degree_code', 'l6m_top10_opp_belo_cnt', 'l3m_once_numbers_rate', 'l3m_top10_opp_belo_cnt', 'l3m_contact_ratio', 'l6m_top5_call_dura_rate', 'pre3m_top10_diff_num', 'age_lvl', 'top10_diff_num', 'same_idcard_msisdn_cnt', 'pre3m_top5_diff_num', 'l3m_id_cnt', 'l3m_top10_call_dura_rate', 'pre2m_top10_diff_num', 'top10_call_cnt_rate', 'contact_ratio', 'top5_opp_belo_cnt', 'is_pretty_num', 'l3m_top5_opp_belo_cnt', 'pre2m_top5_diff_num', 'l1m_is_same_imei_msisdn_cnt_gtr2', 'sex', 'same_imei_msisdn_hr_cnt', 'l6m_top5_opp_belo_cnt', 'is_fam_v_ntw', 'top5_diff_num', 'is_camp_user', 'idty_typ', 'zuche_six_total_dur', 'vip_lvl'],axis=1)\n",
    "data3=data3[['row_num','user_star_val', 'star_evalu_tm','night_call_dura_rate', 'night_call_cnt_rate', 'age', 'cust_star', 'opp_belo_cnt', 'rcn_mode', 'l6m_night_call_cnt_rate', 'night_percent_six', 'brand_id']]\n",
    "#data3=data3[['row_num'] + data3.drop(labels=['row_num'],axis=1).columns.tolist() ]  \n",
    "data3['age']=data3['age']//10\n",
    "\n",
    "data3.to_csv(path_or_buf='csvclear/test_a.csv', index=None)  \n",
    "data1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "supposed-composer",
   "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>row_num</th>\n",
       "      <th>label</th>\n",
       "      <th>user_star_val</th>\n",
       "      <th>night_call_dura_rate</th>\n",
       "      <th>night_call_cnt_rate</th>\n",
       "      <th>age</th>\n",
       "      <th>cust_star</th>\n",
       "      <th>opp_belo_cnt</th>\n",
       "      <th>rcn_mode</th>\n",
       "      <th>l6m_night_call_cnt_rate</th>\n",
       "      <th>night_percent_six</th>\n",
       "      <th>brand_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>29833</td>\n",
       "      <td>0</td>\n",
       "      <td>198.0</td>\n",
       "      <td>1.2726</td>\n",
       "      <td>3.1250</td>\n",
       "      <td>2</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4.6512</td>\n",
       "      <td>5.11</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>18121</td>\n",
       "      <td>0</td>\n",
       "      <td>91.0</td>\n",
       "      <td>8.4315</td>\n",
       "      <td>6.9767</td>\n",
       "      <td>1</td>\n",
       "      <td>6.0</td>\n",
       "      <td>3</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1.3298</td>\n",
       "      <td>17.64</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8372</td>\n",
       "      <td>0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>5.0105</td>\n",
       "      <td>7.6923</td>\n",
       "      <td>4</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>3</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.4526</td>\n",
       "      <td>12.70</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>32780</td>\n",
       "      <td>0</td>\n",
       "      <td>133.0</td>\n",
       "      <td>1.4925</td>\n",
       "      <td>3.8462</td>\n",
       "      <td>2</td>\n",
       "      <td>7.0</td>\n",
       "      <td>3</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.6604</td>\n",
       "      <td>2.83</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3509</td>\n",
       "      <td>0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0.7424</td>\n",
       "      <td>0.6472</td>\n",
       "      <td>6</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>3</td>\n",
       "      <td>99.0</td>\n",
       "      <td>0.3784</td>\n",
       "      <td>6.18</td>\n",
       "      <td>1</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39138</th>\n",
       "      <td>3193</td>\n",
       "      <td>0</td>\n",
       "      <td>311.0</td>\n",
       "      <td>0.6517</td>\n",
       "      <td>2.5510</td>\n",
       "      <td>5</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3</td>\n",
       "      <td>99.0</td>\n",
       "      <td>4.3779</td>\n",
       "      <td>11.52</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39139</th>\n",
       "      <td>46717</td>\n",
       "      <td>0</td>\n",
       "      <td>203.0</td>\n",
       "      <td>0.3208</td>\n",
       "      <td>0.7299</td>\n",
       "      <td>3</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.9901</td>\n",
       "      <td>11.19</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39140</th>\n",
       "      <td>46379</td>\n",
       "      <td>0</td>\n",
       "      <td>119.0</td>\n",
       "      <td>1.3945</td>\n",
       "      <td>1.8519</td>\n",
       "      <td>3</td>\n",
       "      <td>5.0</td>\n",
       "      <td>4</td>\n",
       "      <td>4.0</td>\n",
       "      <td>2.4476</td>\n",
       "      <td>30.93</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39141</th>\n",
       "      <td>12670</td>\n",
       "      <td>0</td>\n",
       "      <td>163.0</td>\n",
       "      <td>1.3134</td>\n",
       "      <td>0.3226</td>\n",
       "      <td>6</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.7042</td>\n",
       "      <td>36.48</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39142</th>\n",
       "      <td>43570</td>\n",
       "      <td>0</td>\n",
       "      <td>250.0</td>\n",
       "      <td>3.2597</td>\n",
       "      <td>7.1429</td>\n",
       "      <td>4</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5</td>\n",
       "      <td>99.0</td>\n",
       "      <td>6.3559</td>\n",
       "      <td>24.18</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>39143 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       row_num  label  user_star_val  night_call_dura_rate  \\\n",
       "0        29833      0          198.0                1.2726   \n",
       "1        18121      0           91.0                8.4315   \n",
       "2         8372      0           -1.0                5.0105   \n",
       "3        32780      0          133.0                1.4925   \n",
       "4         3509      0           -1.0                0.7424   \n",
       "...        ...    ...            ...                   ...   \n",
       "39138     3193      0          311.0                0.6517   \n",
       "39139    46717      0          203.0                0.3208   \n",
       "39140    46379      0          119.0                1.3945   \n",
       "39141    12670      0          163.0                1.3134   \n",
       "39142    43570      0          250.0                3.2597   \n",
       "\n",
       "       night_call_cnt_rate  age  cust_star  opp_belo_cnt  rcn_mode  \\\n",
       "0                   3.1250    2        4.0             5       4.0   \n",
       "1                   6.9767    1        6.0             3       4.0   \n",
       "2                   7.6923    4       -1.0             3       4.0   \n",
       "3                   3.8462    2        7.0             3       4.0   \n",
       "4                   0.6472    6       -1.0             3      99.0   \n",
       "...                    ...  ...        ...           ...       ...   \n",
       "39138               2.5510    5        4.0             3      99.0   \n",
       "39139               0.7299    3        5.0             4       4.0   \n",
       "39140               1.8519    3        5.0             4       4.0   \n",
       "39141               0.3226    6        5.0             2       4.0   \n",
       "39142               7.1429    4        5.0             5      99.0   \n",
       "\n",
       "       l6m_night_call_cnt_rate  night_percent_six  brand_id  \n",
       "0                       4.6512               5.11         2  \n",
       "1                       1.3298              17.64         2  \n",
       "2                       5.4526              12.70         2  \n",
       "3                       5.6604               2.83         1  \n",
       "4                       0.3784               6.18         1  \n",
       "...                        ...                ...       ...  \n",
       "39138                   4.3779              11.52         2  \n",
       "39139                   0.9901              11.19         1  \n",
       "39140                   2.4476              30.93         1  \n",
       "39141                   0.7042              36.48         1  \n",
       "39142                   6.3559              24.18         1  \n",
       "\n",
       "[39143 rows x 12 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "handy-custom",
   "metadata": {},
   "outputs": [],
   "source": [
    "def fun_flux(x):\n",
    "    x=x/1024\n",
    "    if x <= 100:\n",
    "        return 1\n",
    "    if x <= 500:\n",
    "        return 2\n",
    "    if x <= 1024:\n",
    "        return 3\n",
    "    if x <= 2048:\n",
    "        return 4\n",
    "    else:\n",
    "        return 5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "linear-divorce",
   "metadata": {},
   "outputs": [],
   "source": [
    "df2 = data2[['row_num','innet_dura','basic_package_prc','package_flux','in_set_voice_minu','pri_package_lvl','cur_eff_sale_cmpn_cnt','mon_stp_cnt','gsm_user_lvl','is_join_busi_typ_contr','user_status']]\n",
    "#,'become_group_user_memb_tm','term_os','mage_status','user_area_belo','group_indus_typ_code'\n",
    "#df2 = data2.drop(labels=['belo_camp_id','become_group_user_memb_tm', 'belo_group_cust_id', 'term_brand', 'term_mdl', 'charge_package_unify_code', 'befo_pri_package_code', 'basic_package_id', 'basic_package_eff_date', 'package_stp_date','is_exempt_prest_open_inter_roam ','is_hnet_bind','camp_lvl','cm_nadd_mkcase_cnt','pretty_num_typ_code','term_typ','is_mkcase_user','is_warnt_boot','is_fuse_brd','year_nadd_id','is_group_user','exit_typ','is_main_card_user','is_cm_ord_nolimit_and_eff','is_give_card','this_is_replace_package','is_join_term_contr','memb_typ','is_use_backup_sim_svc','owe_stp_days','become_group_user_memb_tm','mon_stp_cnt','gsm_user_lvl','is_join_busi_typ_contr','user_status','term_os','mage_status','user_area_belo','group_indus_typ_code','nation','ord_4g_package_user_id','stp_dura','last_one_stp_tm','is_ord_nolimit','brd_bdwth','msisdn_owe_stp_freq','innet_dura_lvl_code','is_urgent_boot','is_gsm_user','is_ass_card','in_set_sms_cnt','package_typ','ass_card_cnt','gsm_user_src','unique_flag','is_indv_cust_posb','is_fnet_bind','is_group_v_ntw_bind','is_bind_pay','cancl_date'],axis=1)\n",
    "#df2['pretty_num_typ_name'] = df2['pretty_num_typ_name'].str.replace('非靓号', '0')\n",
    "#if df2['pretty_num_typ_name'].str != '0':\n",
    "#    df2['pretty_num_typ_name']='1'\n",
    "    \n",
    "#df2['pretty_num_typ_name']=df2['pretty_num_typ_name'].astype(int) \n",
    "#if df2['stp_typ'].str != '9999':\n",
    "#    df2['stp_typ']='0'  \n",
    "#df2['stp_typ']=df2['stp_typ'].astype(int) \n",
    "#df2['cm_nadd_mkcase_cnt'] = df2['cm_nadd_mkcase_cnt'].str.replace(r'\\\\N','-1')\n",
    "#df2['cm_nadd_mkcase_cnt']=df2['cm_nadd_mkcase_cnt'].astype(int)\n",
    "df2['cur_eff_sale_cmpn_cnt'] = df2['cur_eff_sale_cmpn_cnt'].str.replace(r'\\\\N','-1')\n",
    "df2['cur_eff_sale_cmpn_cnt']=df2['cur_eff_sale_cmpn_cnt'].astype(int) \n",
    "df2['basic_package_prc'] = df2['basic_package_prc'].str.replace(r'\\\\N','-1')\n",
    "df2['basic_package_prc']=df2['basic_package_prc'].astype(int)\n",
    "\n",
    "#df2['user_status']=df2['user_status']-1000\n",
    "#df2['package_flux'] = df2['package_flux'].apply(lambda x: fun_flux(x))\n",
    "\n",
    "df2.to_csv(path_or_buf='csvclear/train_b.csv', index=None) \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "detected-teddy",
   "metadata": {},
   "outputs": [],
   "source": [
    "df4 = data4[['row_num','innet_dura','basic_package_prc','package_flux','in_set_voice_minu','pri_package_lvl','cur_eff_sale_cmpn_cnt','mon_stp_cnt','gsm_user_lvl','is_join_busi_typ_contr','user_status']]\n",
    "\n",
    "#df4 = data4.drop(labels=['belo_camp_id','become_group_user_memb_tm', 'belo_group_cust_id', 'term_brand', 'term_mdl', 'charge_package_unify_code', 'befo_pri_package_code', 'basic_package_id', 'basic_package_eff_date', 'package_stp_date','is_exempt_prest_open_inter_roam ','is_hnet_bind','camp_lvl','cm_nadd_mkcase_cnt','pretty_num_typ_code','term_typ','is_mkcase_user','is_warnt_boot','is_fuse_brd','year_nadd_id','is_group_user','exit_typ','is_main_card_user','is_cm_ord_nolimit_and_eff','is_give_card','this_is_replace_package','is_join_term_contr','memb_typ','is_use_backup_sim_svc','owe_stp_days','become_group_user_memb_tm','mon_stp_cnt','gsm_user_lvl','is_join_busi_typ_contr','user_status','term_os','mage_status','user_area_belo','group_indus_typ_code','nation','ord_4g_package_user_id','stp_dura','last_one_stp_tm','is_ord_nolimit','brd_bdwth','msisdn_owe_stp_freq','innet_dura_lvl_code','is_urgent_boot','is_gsm_user','is_ass_card','in_set_sms_cnt','package_typ','ass_card_cnt','gsm_user_src','unique_flag','is_indv_cust_posb','is_fnet_bind','is_group_v_ntw_bind','is_bind_pay','cancl_date'],axis=1)\n",
    "#df4['pretty_num_typ_name'] = df4['pretty_num_typ_name'].str.replace('非靓号', '0')\n",
    "#if df4['pretty_num_typ_name'].str != '0':\n",
    "#    df4['pretty_num_typ_name']='1'\n",
    "    \n",
    "#df4['pretty_num_typ_name']=df4['pretty_num_typ_name'].astype(int) \n",
    "#if df4['stp_typ'].str != '9999':\n",
    "#    df4['stp_typ']='0'  \n",
    "#df4['stp_typ']=df2['stp_typ'].astype(int) \n",
    "#df4['cm_nadd_mkcase_cnt'] = df4['cm_nadd_mkcase_cnt'].str.replace(r'\\\\N','-1')\n",
    "#df4['cm_nadd_mkcase_cnt']=df4['cm_nadd_mkcase_cnt'].astype(int)\n",
    "df4['cur_eff_sale_cmpn_cnt'] = df4['cur_eff_sale_cmpn_cnt'].str.replace(r'\\\\N','-1')\n",
    "df4['cur_eff_sale_cmpn_cnt']=df4['cur_eff_sale_cmpn_cnt'].astype(int) \n",
    "df4['basic_package_prc'] = df4['basic_package_prc'].str.replace(r'\\\\N','-1')\n",
    "df4['basic_package_prc']=df4['basic_package_prc'].astype(int)\n",
    "\n",
    "#df4['user_status']=df4['user_status']-1000\n",
    "#df4['package_flux'] = df4['package_flux'].apply(lambda x: fun_flux(x))\n",
    "\n",
    "df4.to_csv(path_or_buf='csvclear/test_b.csv', index=None)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "chronic-cisco",
   "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>row_num</th>\n",
       "      <th>innet_dura</th>\n",
       "      <th>basic_package_prc</th>\n",
       "      <th>package_flux</th>\n",
       "      <th>in_set_voice_minu</th>\n",
       "      <th>pri_package_lvl</th>\n",
       "      <th>cur_eff_sale_cmpn_cnt</th>\n",
       "      <th>mon_stp_cnt</th>\n",
       "      <th>gsm_user_lvl</th>\n",
       "      <th>is_join_busi_typ_contr</th>\n",
       "      <th>user_status</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5239</td>\n",
       "      <td>7</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>9000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5220</td>\n",
       "      <td>53</td>\n",
       "      <td>99</td>\n",
       "      <td>66560</td>\n",
       "      <td>1300</td>\n",
       "      <td>6.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>7.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>37261</td>\n",
       "      <td>36</td>\n",
       "      <td>128</td>\n",
       "      <td>40960</td>\n",
       "      <td>200</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>32634</td>\n",
       "      <td>257</td>\n",
       "      <td>98</td>\n",
       "      <td>20480</td>\n",
       "      <td>500</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-1</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>39782</td>\n",
       "      <td>215</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>20</td>\n",
       "      <td>0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9781</th>\n",
       "      <td>9304</td>\n",
       "      <td>69</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9782</th>\n",
       "      <td>38713</td>\n",
       "      <td>48</td>\n",
       "      <td>128</td>\n",
       "      <td>30720</td>\n",
       "      <td>500</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>6.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9783</th>\n",
       "      <td>41809</td>\n",
       "      <td>215</td>\n",
       "      <td>28</td>\n",
       "      <td>5120</td>\n",
       "      <td>80</td>\n",
       "      <td>0.0</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9784</th>\n",
       "      <td>2165</td>\n",
       "      <td>97</td>\n",
       "      <td>8</td>\n",
       "      <td>100</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9785</th>\n",
       "      <td>48929</td>\n",
       "      <td>225</td>\n",
       "      <td>18</td>\n",
       "      <td>1024</td>\n",
       "      <td>100</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1010</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>9786 rows × 11 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      row_num  innet_dura  basic_package_prc  package_flux  in_set_voice_minu  \\\n",
       "0        5239           7                 -1             0                  0   \n",
       "1        5220          53                 99         66560               1300   \n",
       "2       37261          36                128         40960                200   \n",
       "3       32634         257                 98         20480                500   \n",
       "4       39782         215                  0             0                  0   \n",
       "...       ...         ...                ...           ...                ...   \n",
       "9781     9304          69                  0             0                  0   \n",
       "9782    38713          48                128         30720                500   \n",
       "9783    41809         215                 28          5120                 80   \n",
       "9784     2165          97                  8           100                  0   \n",
       "9785    48929         225                 18          1024                100   \n",
       "\n",
       "      pri_package_lvl  cur_eff_sale_cmpn_cnt  mon_stp_cnt  gsm_user_lvl  \\\n",
       "0                 0.0                     -1            0          -1.0   \n",
       "1                 6.0                      1            1           7.0   \n",
       "2                 0.0                      4            0          -1.0   \n",
       "3                 0.0                     -1            1           1.0   \n",
       "4                 0.0                     20            0           7.0   \n",
       "...               ...                    ...          ...           ...   \n",
       "9781              0.0                      4            0          -1.0   \n",
       "9782              0.0                      1            1           6.0   \n",
       "9783              0.0                      8            0          -1.0   \n",
       "9784              0.0                      2            0           6.0   \n",
       "9785              0.0                     -1            0           1.0   \n",
       "\n",
       "      is_join_busi_typ_contr  user_status  \n",
       "0                          0         9000  \n",
       "1                          0         1010  \n",
       "2                          0         1010  \n",
       "3                          0         1010  \n",
       "4                          1         1010  \n",
       "...                      ...          ...  \n",
       "9781                       0         1010  \n",
       "9782                       0         1010  \n",
       "9783                       0         1010  \n",
       "9784                       0         1010  \n",
       "9785                       0         1010  \n",
       "\n",
       "[9786 rows x 11 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "invalid-parameter",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "数据清洗完成\n"
     ]
    }
   ],
   "source": [
    "print('数据清洗完成')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "timely-judges",
   "metadata": {},
   "outputs": [
    {
     "ename": "SyntaxError",
     "evalue": "Missing parentheses in call to 'print'. Did you mean print(cccc)? (<ipython-input-10-541b57d62b0e>, line 1)",
     "output_type": "error",
     "traceback": [
      "\u001b[0;36m  File \u001b[0;32m\"<ipython-input-10-541b57d62b0e>\"\u001b[0;36m, line \u001b[0;32m1\u001b[0m\n\u001b[0;31m    print cccc\u001b[0m\n\u001b[0m             ^\u001b[0m\n\u001b[0;31mSyntaxError\u001b[0m\u001b[0;31m:\u001b[0m Missing parentheses in call to 'print'. Did you mean print(cccc)?\n"
     ]
    }
   ],
   "source": [
    "print cccc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "broadband-pitch",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "cordless-intelligence",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\r\n",
      "    \"retcode\": 0,\r\n",
      "    \"retmsg\": \"Fate Flow CLI has been initialized successfully.\"\r\n",
      "}\r\n",
      "\r\n"
     ]
    }
   ],
   "source": [
    "!flow init --ip 10.43.159.182 --port 9380"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "dffd4c06",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\r\n",
      "    \"data\": {\r\n",
      "        \"board_url\": \"http://board:8080/index.html#/dashboard?job_id=20230424161428388177448&role=local&party_id=0\",\r\n",
      "        \"job_dsl_path\": \"/data/projects/fate/jobs/20230424161428388177448/job_dsl.json\",\r\n",
      "        \"job_id\": \"20230424161428388177448\",\r\n",
      "        \"job_runtime_conf_on_party_path\": \"/data/projects/fate/jobs/20230424161428388177448/local/job_runtime_on_party_conf.json\",\r\n",
      "        \"job_runtime_conf_path\": \"/data/projects/fate/jobs/20230424161428388177448/job_runtime_conf.json\",\r\n",
      "        \"logs_directory\": \"/data/projects/fate/logs/20230424161428388177448\",\r\n",
      "        \"model_info\": {\r\n",
      "            \"model_id\": \"local-0#model\",\r\n",
      "            \"model_version\": \"20230424161428388177448\"\r\n",
      "        },\r\n",
      "        \"namespace\": \"experiment\",\r\n",
      "        \"pipeline_dsl_path\": \"/data/projects/fate/jobs/20230424161428388177448/pipeline_dsl.json\",\r\n",
      "        \"table_name\": \"train_a_label\",\r\n",
      "        \"train_runtime_conf_path\": \"/data/projects/fate/jobs/20230424161428388177448/train_runtime_conf.json\"\r\n",
      "    },\r\n",
      "    \"jobId\": \"20230424161428388177448\",\r\n",
      "    \"retcode\": 0,\r\n",
      "    \"retmsg\": \"success\"\r\n",
      "}\r\n",
      "\r\n"
     ]
    }
   ],
   "source": [
    "!flow data upload -c /Examples/csvclear/upload_conf.json --drop"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "34470baf",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\r\n",
      "    \"data\": {\r\n",
      "        \"board_url\": \"http://board:8080/index.html#/dashboard?job_id=20230424161429367145449&role=local&party_id=0\",\r\n",
      "        \"job_dsl_path\": \"/data/projects/fate/jobs/20230424161429367145449/job_dsl.json\",\r\n",
      "        \"job_id\": \"20230424161429367145449\",\r\n",
      "        \"job_runtime_conf_on_party_path\": \"/data/projects/fate/jobs/20230424161429367145449/local/job_runtime_on_party_conf.json\",\r\n",
      "        \"job_runtime_conf_path\": \"/data/projects/fate/jobs/20230424161429367145449/job_runtime_conf.json\",\r\n",
      "        \"logs_directory\": \"/data/projects/fate/logs/20230424161429367145449\",\r\n",
      "        \"model_info\": {\r\n",
      "            \"model_id\": \"local-0#model\",\r\n",
      "            \"model_version\": \"20230424161429367145449\"\r\n",
      "        },\r\n",
      "        \"namespace\": \"experiment\",\r\n",
      "        \"pipeline_dsl_path\": \"/data/projects/fate/jobs/20230424161429367145449/pipeline_dsl.json\",\r\n",
      "        \"table_name\": \"train_b\",\r\n",
      "        \"train_runtime_conf_path\": \"/data/projects/fate/jobs/20230424161429367145449/train_runtime_conf.json\"\r\n",
      "    },\r\n",
      "    \"jobId\": \"20230424161429367145449\",\r\n",
      "    \"retcode\": 0,\r\n",
      "    \"retmsg\": \"success\"\r\n",
      "}\r\n",
      "\r\n"
     ]
    }
   ],
   "source": [
    "!flow data upload -c /Examples/csvclear/upload_conf_host.json --drop"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "filled-princess",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\r\n",
      "    \"data\": {\r\n",
      "        \"count\": 39143,\r\n",
      "        \"exist\": 1,\r\n",
      "        \"namespace\": \"experiment\",\r\n",
      "        \"partition\": 4,\r\n",
      "        \"schema\": {\r\n",
      "            \"header\": \"label,user_star_val,night_call_dura_rate,night_call_cnt_rate,age,cust_star,opp_belo_cnt,rcn_mode,l6m_night_call_cnt_rate,night_percent_six,brand_id\",\r\n",
      "            \"sid\": \"row_num\"\r\n",
      "        },\r\n",
      "        \"table_name\": \"train_a_label\"\r\n",
      "    },\r\n",
      "    \"retcode\": 0,\r\n",
      "    \"retmsg\": \"success\"\r\n",
      "}\r\n",
      "\r\n"
     ]
    }
   ],
   "source": [
    "#查看表信息\n",
    "!flow table info -t train_a_label -n experiment\n",
    "#!flow table info -t train_a_label -n experiment"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "mighty-health",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\r\n",
      "    \"data\": {\r\n",
      "        \"board_url\": \"http://board:8080/index.html#/dashboard?job_id=20230424161430596799450&role=local&party_id=0\",\r\n",
      "        \"job_dsl_path\": \"/data/projects/fate/jobs/20230424161430596799450/job_dsl.json\",\r\n",
      "        \"job_id\": \"20230424161430596799450\",\r\n",
      "        \"job_runtime_conf_on_party_path\": \"/data/projects/fate/jobs/20230424161430596799450/local/job_runtime_on_party_conf.json\",\r\n",
      "        \"job_runtime_conf_path\": \"/data/projects/fate/jobs/20230424161430596799450/job_runtime_conf.json\",\r\n",
      "        \"logs_directory\": \"/data/projects/fate/logs/20230424161430596799450\",\r\n",
      "        \"model_info\": {\r\n",
      "            \"model_id\": \"local-0#model\",\r\n",
      "            \"model_version\": \"20230424161430596799450\"\r\n",
      "        },\r\n",
      "        \"namespace\": \"experiment\",\r\n",
      "        \"pipeline_dsl_path\": \"/data/projects/fate/jobs/20230424161430596799450/pipeline_dsl.json\",\r\n",
      "        \"table_name\": \"test_a\",\r\n",
      "        \"train_runtime_conf_path\": \"/data/projects/fate/jobs/20230424161430596799450/train_runtime_conf.json\"\r\n",
      "    },\r\n",
      "    \"jobId\": \"20230424161430596799450\",\r\n",
      "    \"retcode\": 0,\r\n",
      "    \"retmsg\": \"success\"\r\n",
      "}\r\n",
      "\r\n"
     ]
    }
   ],
   "source": [
    "#上传预测数据\n",
    "!flow data upload -c /Examples/csvclear/upload_testa_conf.json --drop"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "similar-teaching",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\r\n",
      "    \"data\": {\r\n",
      "        \"board_url\": \"http://board:8080/index.html#/dashboard?job_id=20230424161431222943451&role=local&party_id=0\",\r\n",
      "        \"job_dsl_path\": \"/data/projects/fate/jobs/20230424161431222943451/job_dsl.json\",\r\n",
      "        \"job_id\": \"20230424161431222943451\",\r\n",
      "        \"job_runtime_conf_on_party_path\": \"/data/projects/fate/jobs/20230424161431222943451/local/job_runtime_on_party_conf.json\",\r\n",
      "        \"job_runtime_conf_path\": \"/data/projects/fate/jobs/20230424161431222943451/job_runtime_conf.json\",\r\n",
      "        \"logs_directory\": \"/data/projects/fate/logs/20230424161431222943451\",\r\n",
      "        \"model_info\": {\r\n",
      "            \"model_id\": \"local-0#model\",\r\n",
      "            \"model_version\": \"20230424161431222943451\"\r\n",
      "        },\r\n",
      "        \"namespace\": \"experiment\",\r\n",
      "        \"pipeline_dsl_path\": \"/data/projects/fate/jobs/20230424161431222943451/pipeline_dsl.json\",\r\n",
      "        \"table_name\": \"test_b\",\r\n",
      "        \"train_runtime_conf_path\": \"/data/projects/fate/jobs/20230424161431222943451/train_runtime_conf.json\"\r\n",
      "    },\r\n",
      "    \"jobId\": \"20230424161431222943451\",\r\n",
      "    \"retcode\": 0,\r\n",
      "    \"retmsg\": \"success\"\r\n",
      "}\r\n",
      "\r\n"
     ]
    }
   ],
   "source": [
    "!flow data upload -c /Examples/csvclear/upload_testb_conf.json --drop"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "yellow-luxury",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\r\n",
      "    \"data\": {\r\n",
      "        \"count\": 9786,\r\n",
      "        \"exist\": 1,\r\n",
      "        \"namespace\": \"experiment\",\r\n",
      "        \"partition\": 4,\r\n",
      "        \"schema\": {\r\n",
      "            \"header\": \"user_star_val,star_evalu_tm,night_call_dura_rate,night_call_cnt_rate,age,cust_star,opp_belo_cnt,rcn_mode,l6m_night_call_cnt_rate,night_percent_six,brand_id\",\r\n",
      "            \"sid\": \"row_num\"\r\n",
      "        },\r\n",
      "        \"table_name\": \"test_a\"\r\n",
      "    },\r\n",
      "    \"retcode\": 0,\r\n",
      "    \"retmsg\": \"success\"\r\n",
      "}\r\n",
      "\r\n"
     ]
    }
   ],
   "source": [
    "#查看表信息\n",
    "!flow table info -t test_a -n experiment\n",
    "#!flow table info -t train_a_label -n experiment"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "artistic-drilling",
   "metadata": {},
   "outputs": [],
   "source": [
    "!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "hungry-eagle",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_conf = {\n",
    "  \"dsl_version\": 2,\n",
    "  \"initiator\": {\n",
    "    \"role\": \"guest\",\n",
    "    \"party_id\": 9999\n",
    "  },\n",
    "   \"job_parameters\": {\n",
    "   \"common\": {\n",
    "        \"work_mode\": 0 \n",
    "    }\n",
    "},\n",
    "  \"role\": {\n",
    "    \"host\": [10000],\n",
    "    \"guest\": [9999]\n",
    "  },\n",
    "  \"component_parameters\": {\n",
    "    \"common\": {\n",
    "      \"hetero_secure_boost_0\": {\n",
    "        \"task_type\": \"classification\",\n",
    "        \"objective_param\": {\n",
    "          \"objective\": \"cross_entropy\"\n",
    "        },\n",
    "        \"num_trees\": 1,\n",
    "        \"validation_freqs\": 1,\n",
    "        \"encrypt_param\": {\n",
    "          \"method\": \"Paillier\"\n",
    "        },\n",
    "        \"tree_param\": {\n",
    "          \"max_depth\": 8\n",
    "        },\n",
    "        \"use_missing\": True\n",
    "      },\n",
    "      \"evaluation_0\": {\n",
    "        \"eval_type\": \"binary\"\n",
    "      }\n",
    "    },\n",
    "    \"role\": {\n",
    "      \"guest\": {\n",
    "        \"0\": {\n",
    "          \n",
    "          \"data_transform_0\": {\n",
    "            \"with_label\": True,\n",
    "            \"label_name\": \"label\",\n",
    "            \"label_type\": \"int\",\n",
    "            \"output_format\": \"dense\"\n",
    "          },\n",
    "          \"reader_0\": {\n",
    "            \"table\": {\n",
    "              \"name\": \"train_a_label\",\n",
    "              \"namespace\": \"experiment\"\n",
    "            }\n",
    "          }\n",
    "        }\n",
    "      },\n",
    "      \"host\": {\n",
    "        \"0\": {\n",
    "          \"data_transform_0\": {\n",
    "            \"with_label\": False\n",
    "          },\n",
    "          \"reader_0\": {\n",
    "            \"table\": {\n",
    "              \"name\": \"train_b\",\n",
    "              \"namespace\": \"experiment\"\n",
    "            }\n",
    "          }\n",
    "        }\n",
    "      }\n",
    "    }\n",
    "  }\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "loaded-ferry",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_dsl = {\n",
    "  \"components\": {\n",
    "    \"reader_0\": {\n",
    "      \"module\": \"Reader\",\n",
    "      \"output\": {\n",
    "        \"data\": [\"data\"]\n",
    "      }\n",
    "    },\n",
    "    \"data_transform_0\": {\n",
    "      \"module\": \"DataTransform\",\n",
    "      \"input\": {\n",
    "        \"data\": {\n",
    "          \"data\": [\"reader_0.data\"]\n",
    "        }\n",
    "      },\n",
    "      \"output\": {\n",
    "        \"data\": [\"data\"],\n",
    "        \"model\": [\"model\"]\n",
    "      }\n",
    "    },\n",
    "    \"intersection_0\": {\n",
    "      \"module\": \"Intersection\",\n",
    "      \"input\": {\n",
    "        \"data\": {\n",
    "          \"data\": [\"data_transform_0.data\"]\n",
    "        }\n",
    "      },\n",
    "      \"output\": {\n",
    "        \"data\": [\"data\"]\n",
    "      }\n",
    "    },        \n",
    "    \"hetero_secure_boost_0\": {\n",
    "      \"module\": \"HeteroSecureBoost\",\n",
    "      \"input\": {\n",
    "        \"data\": {\n",
    "          \"train_data\": [\"intersection_0.data\"]\n",
    "        }\n",
    "      },\n",
    "      \"output\": {\n",
    "        \"data\": [\"data\"],\n",
    "        \"model\": [\"model\"]\n",
    "      }\n",
    "    },\n",
    "    \"evaluation_0\": {\n",
    "      \"module\": \"Evaluation\",\n",
    "      \"input\": {\n",
    "        \"data\": {\n",
    "          \"data\": [\"hetero_secure_boost_0.data\"]\n",
    "        }\n",
    "      },\n",
    "      \"output\": {\n",
    "        \"data\": [\"data\"]\n",
    "      }\n",
    "    }\n",
    "  }\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "blind-bachelor",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'data': {'board_url': 'http://board:8080/index.html#/dashboard?job_id=20230424164733674031455&role=guest&party_id=9999', 'job_dsl_path': '/data/projects/fate/jobs/20230424164733674031455/job_dsl.json', 'job_id': '20230424164733674031455', 'job_runtime_conf_on_party_path': '/data/projects/fate/jobs/20230424164733674031455/guest/job_runtime_on_party_conf.json', 'job_runtime_conf_path': '/data/projects/fate/jobs/20230424164733674031455/job_runtime_conf.json', 'logs_directory': '/data/projects/fate/logs/20230424164733674031455', 'model_info': {'model_id': 'guest-9999#host-10000#model', 'model_version': '20230424164733674031455'}, 'pipeline_dsl_path': '/data/projects/fate/jobs/20230424164733674031455/pipeline_dsl.json', 'train_runtime_conf_path': '/data/projects/fate/jobs/20230424164733674031455/train_runtime_conf.json'}, 'jobId': '20230424164733674031455', 'retcode': 0, 'retmsg': 'success'}\n"
     ]
    }
   ],
   "source": [
    "#开始训练\n",
    "import requests\n",
    "post_data = {'job_dsl': train_dsl, 'job_runtime_conf': train_conf}\n",
    "response = requests.post(\"http://10.43.159.182:9380/v1/job/submit\", json=post_data)\n",
    "print(response.json())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "apparent-treasure",
   "metadata": {},
   "outputs": [],
   "source": [
    "#登录board_url查看模型训练结果"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "divine-smith",
   "metadata": {},
   "outputs": [],
   "source": [
    "#模型部署\n",
    "import requests\n",
    "config_data = {\n",
    "        \"job_parameters\": {\n",
    "            \"model_id\": \"guest-9999#host-10000#model\",\n",
    "            \"model_version\": \"20230424085041481989420\"\n",
    "        }\n",
    "    }\n",
    "response = requests.post(\"http://10.43.159.182:9380/v1/model/deploy\", json=config_data)\n",
    "\n",
    "print(response.json())\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "global-navigation",
   "metadata": {},
   "outputs": [],
   "source": [
    "predict_conf = {\n",
    "  \"dsl_version\": 2,\n",
    "  \"initiator\": {\n",
    "    \"role\": \"guest\",\n",
    "    \"party_id\": 9999\n",
    "  },\n",
    "  \"role\": {\n",
    "    \"host\": [10000],\n",
    "    \"guest\": [9999]\n",
    "  },\n",
    "    \"job_parameters\": {\n",
    "        \"common\": {\n",
    "            \"work_mode\": 0, \n",
    "            \"job_type\": \"predict\",\n",
    "            \"model_id\": \"guest-9999#host-10000#model\",\n",
    "            \"model_version\": \"20230424085832841569421\"\n",
    "        }\n",
    "    },\n",
    "    \"component_parameters\": {\n",
    "        \"role\": {\n",
    "            \"guest\": {\n",
    "                \"0\": {\n",
    "                    \"reader_0\": {\n",
    "                        \"table\": {\n",
    "                            \"name\": \"test_a\",\n",
    "                            \"namespace\": \"experiment\"\n",
    "                        }\n",
    "                    }\n",
    "                }\n",
    "            },\n",
    "            \"host\": {\n",
    "                \"0\": {\n",
    "                    \"reader_0\": {\n",
    "                        \"table\": {\n",
    "                            \"name\": \"test_b\",\n",
    "                            \"namespace\": \"experiment\"\n",
    "                        }\n",
    "                    }\n",
    "                }\n",
    "            }\n",
    "        }\n",
    "    }\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "affecting-accordance",
   "metadata": {},
   "outputs": [],
   "source": [
    "#预测数据\n",
    "post_data = {'job_runtime_conf': predict_conf}\n",
    "response = requests.post(\"http://10.43.159.182:9380/v1/job/submit\", json=post_data)\n",
    "print(response.json())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "thermal-guatemala",
   "metadata": {},
   "outputs": [],
   "source": [
    "#登录board_url查看模型预测结果"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fatal-palestine",
   "metadata": {},
   "outputs": [],
   "source": [
    "!flow component output-data -j 20230424085846677853422 -r guest -p 9999 -cpn hetero_secure_boost_0 --output-path ./"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "dental-million",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "detected-adventure",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}