{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "5e4ce795",
   "metadata": {
    "papermill": {
     "duration": 0.033432,
     "end_time": "2022-05-11T11:03:04.321959",
     "exception": false,
     "start_time": "2022-05-11T11:03:04.288527",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Problem statement\n",
    "\n",
    "The May edition of the 2022 Tabular Playground series binary classification problem that includes a number of different feature interactions. This competition is an opportunity to explore various methods for identifying and exploiting these feature interactions."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "af70a983",
   "metadata": {
    "papermill": {
     "duration": 0.032628,
     "end_time": "2022-05-11T11:03:04.386417",
     "exception": false,
     "start_time": "2022-05-11T11:03:04.353789",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Import libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "a8932043",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:04.453540Z",
     "iopub.status.busy": "2022-05-11T11:03:04.452968Z",
     "iopub.status.idle": "2022-05-11T11:03:05.559143Z",
     "shell.execute_reply": "2022-05-11T11:03:05.558125Z"
    },
    "papermill": {
     "duration": 1.143269,
     "end_time": "2022-05-11T11:03:05.561715",
     "exception": false,
     "start_time": "2022-05-11T11:03:04.418446",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "66d2b4ae",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:05.627534Z",
     "iopub.status.busy": "2022-05-11T11:03:05.627253Z",
     "iopub.status.idle": "2022-05-11T11:03:05.633896Z",
     "shell.execute_reply": "2022-05-11T11:03:05.633045Z"
    },
    "papermill": {
     "duration": 0.043253,
     "end_time": "2022-05-11T11:03:05.637363",
     "exception": false,
     "start_time": "2022-05-11T11:03:05.594110",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "../coal-price-data/binary_classification/sample_submission.csv\n",
      "../coal-price-data/binary_classification/train.csv\n",
      "../coal-price-data/binary_classification/test.csv\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "\n",
    "path = \"../coal-price-data/binary_classification\"\n",
    "for dirname, _, filenames in os.walk(path):\n",
    "    for filename in filenames:\n",
    "        print(os.path.join(dirname, filename))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "be1e26a5",
   "metadata": {
    "papermill": {
     "duration": 0.035619,
     "end_time": "2022-05-11T11:03:05.708148",
     "exception": false,
     "start_time": "2022-05-11T11:03:05.672529",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Read files"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "1c56f757",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:05.776270Z",
     "iopub.status.busy": "2022-05-11T11:03:05.775581Z",
     "iopub.status.idle": "2022-05-11T11:03:21.346102Z",
     "shell.execute_reply": "2022-05-11T11:03:21.345294Z"
    },
    "papermill": {
     "duration": 15.60683,
     "end_time": "2022-05-11T11:03:21.348390",
     "exception": false,
     "start_time": "2022-05-11T11:03:05.741560",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "train = pd.read_csv(f\"{path}/train.csv\")\n",
    "test = pd.read_csv(f\"{path}/test.csv\")\n",
    "submission = pd.read_csv(f\"{path}/sample_submission.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "7dc3af51",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:21.416502Z",
     "iopub.status.busy": "2022-05-11T11:03:21.416126Z",
     "iopub.status.idle": "2022-05-11T11:03:21.717153Z",
     "shell.execute_reply": "2022-05-11T11:03:21.716495Z"
    },
    "papermill": {
     "duration": 0.338273,
     "end_time": "2022-05-11T11:03:21.719304",
     "exception": false,
     "start_time": "2022-05-11T11:03:21.381031",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>f_00</th>\n",
       "      <th>f_01</th>\n",
       "      <th>f_02</th>\n",
       "      <th>f_03</th>\n",
       "      <th>f_04</th>\n",
       "      <th>f_05</th>\n",
       "      <th>f_06</th>\n",
       "      <th>f_07</th>\n",
       "      <th>f_08</th>\n",
       "      <th>...</th>\n",
       "      <th>f_22</th>\n",
       "      <th>f_23</th>\n",
       "      <th>f_24</th>\n",
       "      <th>f_25</th>\n",
       "      <th>f_26</th>\n",
       "      <th>f_27</th>\n",
       "      <th>f_28</th>\n",
       "      <th>f_29</th>\n",
       "      <th>f_30</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>-1.373246</td>\n",
       "      <td>0.238887</td>\n",
       "      <td>-0.243376</td>\n",
       "      <td>0.567405</td>\n",
       "      <td>-0.647715</td>\n",
       "      <td>0.839326</td>\n",
       "      <td>0.113133</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>...</td>\n",
       "      <td>-2.540739</td>\n",
       "      <td>0.766952</td>\n",
       "      <td>-2.730628</td>\n",
       "      <td>-0.208177</td>\n",
       "      <td>1.363402</td>\n",
       "      <td>ABABDADBAB</td>\n",
       "      <td>67.609153</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1.697021</td>\n",
       "      <td>-1.710322</td>\n",
       "      <td>-2.230332</td>\n",
       "      <td>-0.545661</td>\n",
       "      <td>1.113173</td>\n",
       "      <td>-1.552175</td>\n",
       "      <td>0.447825</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>2.278315</td>\n",
       "      <td>-0.633658</td>\n",
       "      <td>-1.217077</td>\n",
       "      <td>-3.782194</td>\n",
       "      <td>-0.058316</td>\n",
       "      <td>ACACCADCEB</td>\n",
       "      <td>377.096415</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>1.681726</td>\n",
       "      <td>0.616746</td>\n",
       "      <td>-1.027689</td>\n",
       "      <td>0.810492</td>\n",
       "      <td>-0.609086</td>\n",
       "      <td>0.113965</td>\n",
       "      <td>-0.708660</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>-1.385775</td>\n",
       "      <td>-0.520558</td>\n",
       "      <td>-0.009121</td>\n",
       "      <td>2.788536</td>\n",
       "      <td>-3.703488</td>\n",
       "      <td>AAAEABCKAD</td>\n",
       "      <td>-195.599702</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>-0.118172</td>\n",
       "      <td>-0.587835</td>\n",
       "      <td>-0.804638</td>\n",
       "      <td>2.086822</td>\n",
       "      <td>0.371005</td>\n",
       "      <td>-0.128831</td>\n",
       "      <td>-0.282575</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>0.572594</td>\n",
       "      <td>-1.653213</td>\n",
       "      <td>1.686035</td>\n",
       "      <td>-2.533098</td>\n",
       "      <td>-0.608601</td>\n",
       "      <td>BDBBAACBCB</td>\n",
       "      <td>210.826205</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>1.148481</td>\n",
       "      <td>-0.176567</td>\n",
       "      <td>-0.664871</td>\n",
       "      <td>-1.101343</td>\n",
       "      <td>0.467875</td>\n",
       "      <td>0.500117</td>\n",
       "      <td>0.407515</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>-3.912929</td>\n",
       "      <td>-1.430366</td>\n",
       "      <td>2.127649</td>\n",
       "      <td>-3.306784</td>\n",
       "      <td>4.371371</td>\n",
       "      <td>BDBCBBCHFE</td>\n",
       "      <td>-217.211798</td>\n",
       "      <td>0</td>\n",
       "      <td>1</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",
       "      <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>899995</th>\n",
       "      <td>899995</td>\n",
       "      <td>1.380145</td>\n",
       "      <td>-0.038884</td>\n",
       "      <td>0.597111</td>\n",
       "      <td>0.854560</td>\n",
       "      <td>0.684301</td>\n",
       "      <td>-1.058618</td>\n",
       "      <td>1.310699</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>-1.594744</td>\n",
       "      <td>0.522019</td>\n",
       "      <td>0.833047</td>\n",
       "      <td>2.714125</td>\n",
       "      <td>1.290094</td>\n",
       "      <td>BABBCBBBED</td>\n",
       "      <td>455.033851</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>899996</th>\n",
       "      <td>899996</td>\n",
       "      <td>-1.369789</td>\n",
       "      <td>0.044841</td>\n",
       "      <td>0.015458</td>\n",
       "      <td>0.376565</td>\n",
       "      <td>-0.380529</td>\n",
       "      <td>-0.830815</td>\n",
       "      <td>-1.798458</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>2.413899</td>\n",
       "      <td>-0.674942</td>\n",
       "      <td>-0.412111</td>\n",
       "      <td>-0.030436</td>\n",
       "      <td>-3.144047</td>\n",
       "      <td>BBBGBBDQBE</td>\n",
       "      <td>134.703577</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>899997</th>\n",
       "      <td>899997</td>\n",
       "      <td>1.386201</td>\n",
       "      <td>-0.961150</td>\n",
       "      <td>0.725994</td>\n",
       "      <td>-0.132844</td>\n",
       "      <td>0.873911</td>\n",
       "      <td>-0.245339</td>\n",
       "      <td>-1.045786</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.151930</td>\n",
       "      <td>-4.560773</td>\n",
       "      <td>-1.249154</td>\n",
       "      <td>1.793535</td>\n",
       "      <td>2.253696</td>\n",
       "      <td>AEBEDBBHBA</td>\n",
       "      <td>-99.536313</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>899998</th>\n",
       "      <td>899998</td>\n",
       "      <td>-1.590572</td>\n",
       "      <td>-0.509938</td>\n",
       "      <td>-1.715397</td>\n",
       "      <td>-0.249988</td>\n",
       "      <td>1.359933</td>\n",
       "      <td>1.650808</td>\n",
       "      <td>-0.058592</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>2.423670</td>\n",
       "      <td>2.110008</td>\n",
       "      <td>0.561271</td>\n",
       "      <td>-2.149610</td>\n",
       "      <td>1.019982</td>\n",
       "      <td>ADBAAADDAE</td>\n",
       "      <td>47.823039</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>899999</th>\n",
       "      <td>899999</td>\n",
       "      <td>-0.636210</td>\n",
       "      <td>-0.425986</td>\n",
       "      <td>-1.826699</td>\n",
       "      <td>-0.598797</td>\n",
       "      <td>1.589577</td>\n",
       "      <td>-0.482298</td>\n",
       "      <td>-0.214093</td>\n",
       "      <td>7</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>1.340696</td>\n",
       "      <td>3.762351</td>\n",
       "      <td>1.797137</td>\n",
       "      <td>-0.412837</td>\n",
       "      <td>2.090440</td>\n",
       "      <td>BCAACADSCE</td>\n",
       "      <td>-44.559296</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>900000 rows × 33 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            id      f_00      f_01      f_02      f_03      f_04      f_05  \\\n",
       "0            0 -1.373246  0.238887 -0.243376  0.567405 -0.647715  0.839326   \n",
       "1            1  1.697021 -1.710322 -2.230332 -0.545661  1.113173 -1.552175   \n",
       "2            2  1.681726  0.616746 -1.027689  0.810492 -0.609086  0.113965   \n",
       "3            3 -0.118172 -0.587835 -0.804638  2.086822  0.371005 -0.128831   \n",
       "4            4  1.148481 -0.176567 -0.664871 -1.101343  0.467875  0.500117   \n",
       "...        ...       ...       ...       ...       ...       ...       ...   \n",
       "899995  899995  1.380145 -0.038884  0.597111  0.854560  0.684301 -1.058618   \n",
       "899996  899996 -1.369789  0.044841  0.015458  0.376565 -0.380529 -0.830815   \n",
       "899997  899997  1.386201 -0.961150  0.725994 -0.132844  0.873911 -0.245339   \n",
       "899998  899998 -1.590572 -0.509938 -1.715397 -0.249988  1.359933  1.650808   \n",
       "899999  899999 -0.636210 -0.425986 -1.826699 -0.598797  1.589577 -0.482298   \n",
       "\n",
       "            f_06  f_07  f_08  ...      f_22      f_23      f_24      f_25  \\\n",
       "0       0.113133     1     5  ... -2.540739  0.766952 -2.730628 -0.208177   \n",
       "1       0.447825     1     3  ...  2.278315 -0.633658 -1.217077 -3.782194   \n",
       "2      -0.708660     1     0  ... -1.385775 -0.520558 -0.009121  2.788536   \n",
       "3      -0.282575     3     2  ...  0.572594 -1.653213  1.686035 -2.533098   \n",
       "4       0.407515     3     3  ... -3.912929 -1.430366  2.127649 -3.306784   \n",
       "...          ...   ...   ...  ...       ...       ...       ...       ...   \n",
       "899995  1.310699     2     1  ... -1.594744  0.522019  0.833047  2.714125   \n",
       "899996 -1.798458     4     1  ...  2.413899 -0.674942 -0.412111 -0.030436   \n",
       "899997 -1.045786     0     0  ... -0.151930 -4.560773 -1.249154  1.793535   \n",
       "899998 -0.058592     0     2  ...  2.423670  2.110008  0.561271 -2.149610   \n",
       "899999 -0.214093     7     1  ...  1.340696  3.762351  1.797137 -0.412837   \n",
       "\n",
       "            f_26        f_27        f_28  f_29  f_30  target  \n",
       "0       1.363402  ABABDADBAB   67.609153     0     0       0  \n",
       "1      -0.058316  ACACCADCEB  377.096415     0     0       1  \n",
       "2      -3.703488  AAAEABCKAD -195.599702     0     2       1  \n",
       "3      -0.608601  BDBBAACBCB  210.826205     0     0       1  \n",
       "4       4.371371  BDBCBBCHFE -217.211798     0     1       1  \n",
       "...          ...         ...         ...   ...   ...     ...  \n",
       "899995  1.290094  BABBCBBBED  455.033851     0     2       1  \n",
       "899996 -3.144047  BBBGBBDQBE  134.703577     0     1       0  \n",
       "899997  2.253696  AEBEDBBHBA  -99.536313     0     1       0  \n",
       "899998  1.019982  ADBAAADDAE   47.823039     1     2       0  \n",
       "899999  2.090440  BCAACADSCE  -44.559296     0     2       1  \n",
       "\n",
       "[900000 rows x 33 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "56d9b5e5",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:21.789492Z",
     "iopub.status.busy": "2022-05-11T11:03:21.788702Z",
     "iopub.status.idle": "2022-05-11T11:03:22.024768Z",
     "shell.execute_reply": "2022-05-11T11:03:22.023935Z"
    },
    "papermill": {
     "duration": 0.272034,
     "end_time": "2022-05-11T11:03:22.026588",
     "exception": false,
     "start_time": "2022-05-11T11:03:21.754554",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>f_00</th>\n",
       "      <th>f_01</th>\n",
       "      <th>f_02</th>\n",
       "      <th>f_03</th>\n",
       "      <th>f_04</th>\n",
       "      <th>f_05</th>\n",
       "      <th>f_06</th>\n",
       "      <th>f_07</th>\n",
       "      <th>f_08</th>\n",
       "      <th>...</th>\n",
       "      <th>f_21</th>\n",
       "      <th>f_22</th>\n",
       "      <th>f_23</th>\n",
       "      <th>f_24</th>\n",
       "      <th>f_25</th>\n",
       "      <th>f_26</th>\n",
       "      <th>f_27</th>\n",
       "      <th>f_28</th>\n",
       "      <th>f_29</th>\n",
       "      <th>f_30</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>900000</td>\n",
       "      <td>0.442517</td>\n",
       "      <td>0.174380</td>\n",
       "      <td>-0.999816</td>\n",
       "      <td>0.762741</td>\n",
       "      <td>0.186778</td>\n",
       "      <td>-1.074775</td>\n",
       "      <td>0.501888</td>\n",
       "      <td>6</td>\n",
       "      <td>6</td>\n",
       "      <td>...</td>\n",
       "      <td>-1.006400</td>\n",
       "      <td>-1.193879</td>\n",
       "      <td>-2.435736</td>\n",
       "      <td>-2.427430</td>\n",
       "      <td>-1.966887</td>\n",
       "      <td>5.734205</td>\n",
       "      <td>BAAABADLAC</td>\n",
       "      <td>99.478419</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>900001</td>\n",
       "      <td>-0.605598</td>\n",
       "      <td>-0.305715</td>\n",
       "      <td>0.627667</td>\n",
       "      <td>-0.578898</td>\n",
       "      <td>-1.750931</td>\n",
       "      <td>1.355550</td>\n",
       "      <td>-0.190911</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>2.382405</td>\n",
       "      <td>0.149442</td>\n",
       "      <td>1.883322</td>\n",
       "      <td>-2.848714</td>\n",
       "      <td>-0.725155</td>\n",
       "      <td>3.194219</td>\n",
       "      <td>AFABBAEGCB</td>\n",
       "      <td>-65.993825</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>900002</td>\n",
       "      <td>0.303990</td>\n",
       "      <td>2.445110</td>\n",
       "      <td>0.246515</td>\n",
       "      <td>0.818248</td>\n",
       "      <td>0.359731</td>\n",
       "      <td>-1.331845</td>\n",
       "      <td>1.358622</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>-7.026098</td>\n",
       "      <td>1.312277</td>\n",
       "      <td>-5.157192</td>\n",
       "      <td>1.714005</td>\n",
       "      <td>0.585032</td>\n",
       "      <td>0.066898</td>\n",
       "      <td>BBACABBKEE</td>\n",
       "      <td>-87.405622</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>900003</td>\n",
       "      <td>0.154053</td>\n",
       "      <td>0.260126</td>\n",
       "      <td>-1.367092</td>\n",
       "      <td>-0.093175</td>\n",
       "      <td>-1.111034</td>\n",
       "      <td>-0.948481</td>\n",
       "      <td>1.119220</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.594532</td>\n",
       "      <td>-3.939475</td>\n",
       "      <td>1.754570</td>\n",
       "      <td>-2.364007</td>\n",
       "      <td>-1.003320</td>\n",
       "      <td>3.893099</td>\n",
       "      <td>AEBEAACQCC</td>\n",
       "      <td>-281.293460</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>900004</td>\n",
       "      <td>-1.651904</td>\n",
       "      <td>-0.424266</td>\n",
       "      <td>-0.667356</td>\n",
       "      <td>-0.322124</td>\n",
       "      <td>-0.089462</td>\n",
       "      <td>0.181705</td>\n",
       "      <td>1.784983</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>0.084906</td>\n",
       "      <td>-0.985736</td>\n",
       "      <td>-0.130467</td>\n",
       "      <td>-3.557893</td>\n",
       "      <td>1.210687</td>\n",
       "      <td>1.861884</td>\n",
       "      <td>AEBBBBDABF</td>\n",
       "      <td>25.629415</td>\n",
       "      <td>0</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>699995</th>\n",
       "      <td>1599995</td>\n",
       "      <td>0.640110</td>\n",
       "      <td>0.897808</td>\n",
       "      <td>-0.523956</td>\n",
       "      <td>1.563760</td>\n",
       "      <td>-0.092281</td>\n",
       "      <td>-0.610867</td>\n",
       "      <td>0.535426</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>2.604048</td>\n",
       "      <td>1.122867</td>\n",
       "      <td>0.518110</td>\n",
       "      <td>1.243837</td>\n",
       "      <td>0.575111</td>\n",
       "      <td>0.076372</td>\n",
       "      <td>BCBCEBHMCD</td>\n",
       "      <td>204.186539</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699996</th>\n",
       "      <td>1599996</td>\n",
       "      <td>-0.191771</td>\n",
       "      <td>-0.035246</td>\n",
       "      <td>-0.118533</td>\n",
       "      <td>0.584750</td>\n",
       "      <td>2.126977</td>\n",
       "      <td>0.568659</td>\n",
       "      <td>-0.052663</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>3.029857</td>\n",
       "      <td>1.384682</td>\n",
       "      <td>-1.135740</td>\n",
       "      <td>2.982713</td>\n",
       "      <td>-1.511760</td>\n",
       "      <td>2.225218</td>\n",
       "      <td>BAABCADQFC</td>\n",
       "      <td>-97.694591</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699997</th>\n",
       "      <td>1599997</td>\n",
       "      <td>-0.331704</td>\n",
       "      <td>-0.328845</td>\n",
       "      <td>-1.185503</td>\n",
       "      <td>1.022128</td>\n",
       "      <td>-0.483099</td>\n",
       "      <td>-0.107146</td>\n",
       "      <td>-0.968281</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>4.021273</td>\n",
       "      <td>-1.845266</td>\n",
       "      <td>1.096011</td>\n",
       "      <td>-2.734508</td>\n",
       "      <td>-4.885955</td>\n",
       "      <td>-2.248739</td>\n",
       "      <td>AAAJCBGQBA</td>\n",
       "      <td>130.622745</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699998</th>\n",
       "      <td>1599998</td>\n",
       "      <td>-2.031073</td>\n",
       "      <td>-1.238398</td>\n",
       "      <td>0.964699</td>\n",
       "      <td>-1.045950</td>\n",
       "      <td>0.906064</td>\n",
       "      <td>0.634301</td>\n",
       "      <td>-0.707474</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>1.453864</td>\n",
       "      <td>-1.696606</td>\n",
       "      <td>1.018995</td>\n",
       "      <td>1.973697</td>\n",
       "      <td>-0.353068</td>\n",
       "      <td>-3.333449</td>\n",
       "      <td>BCBBCABNDE</td>\n",
       "      <td>-364.625148</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699999</th>\n",
       "      <td>1599999</td>\n",
       "      <td>-0.085906</td>\n",
       "      <td>-0.002124</td>\n",
       "      <td>2.227375</td>\n",
       "      <td>0.217145</td>\n",
       "      <td>3.179153</td>\n",
       "      <td>-1.660188</td>\n",
       "      <td>0.891989</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>-3.549082</td>\n",
       "      <td>-4.325318</td>\n",
       "      <td>-5.017221</td>\n",
       "      <td>0.251268</td>\n",
       "      <td>-3.236026</td>\n",
       "      <td>-0.362070</td>\n",
       "      <td>AFBEBACHFF</td>\n",
       "      <td>-155.417342</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>700000 rows × 32 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "             id      f_00      f_01      f_02      f_03      f_04      f_05  \\\n",
       "0        900000  0.442517  0.174380 -0.999816  0.762741  0.186778 -1.074775   \n",
       "1        900001 -0.605598 -0.305715  0.627667 -0.578898 -1.750931  1.355550   \n",
       "2        900002  0.303990  2.445110  0.246515  0.818248  0.359731 -1.331845   \n",
       "3        900003  0.154053  0.260126 -1.367092 -0.093175 -1.111034 -0.948481   \n",
       "4        900004 -1.651904 -0.424266 -0.667356 -0.322124 -0.089462  0.181705   \n",
       "...         ...       ...       ...       ...       ...       ...       ...   \n",
       "699995  1599995  0.640110  0.897808 -0.523956  1.563760 -0.092281 -0.610867   \n",
       "699996  1599996 -0.191771 -0.035246 -0.118533  0.584750  2.126977  0.568659   \n",
       "699997  1599997 -0.331704 -0.328845 -1.185503  1.022128 -0.483099 -0.107146   \n",
       "699998  1599998 -2.031073 -1.238398  0.964699 -1.045950  0.906064  0.634301   \n",
       "699999  1599999 -0.085906 -0.002124  2.227375  0.217145  3.179153 -1.660188   \n",
       "\n",
       "            f_06  f_07  f_08  ...      f_21      f_22      f_23      f_24  \\\n",
       "0       0.501888     6     6  ... -1.006400 -1.193879 -2.435736 -2.427430   \n",
       "1      -0.190911     1     3  ...  2.382405  0.149442  1.883322 -2.848714   \n",
       "2       1.358622     3     3  ... -7.026098  1.312277 -5.157192  1.714005   \n",
       "3       1.119220     0     0  ... -0.594532 -3.939475  1.754570 -2.364007   \n",
       "4       1.784983     2     2  ...  0.084906 -0.985736 -0.130467 -3.557893   \n",
       "...          ...   ...   ...  ...       ...       ...       ...       ...   \n",
       "699995  0.535426     0     1  ...  2.604048  1.122867  0.518110  1.243837   \n",
       "699996 -0.052663     4     3  ...  3.029857  1.384682 -1.135740  2.982713   \n",
       "699997 -0.968281     1     1  ...  4.021273 -1.845266  1.096011 -2.734508   \n",
       "699998 -0.707474     5     1  ...  1.453864 -1.696606  1.018995  1.973697   \n",
       "699999  0.891989     0     3  ... -3.549082 -4.325318 -5.017221  0.251268   \n",
       "\n",
       "            f_25      f_26        f_27        f_28  f_29  f_30  \n",
       "0      -1.966887  5.734205  BAAABADLAC   99.478419     0     0  \n",
       "1      -0.725155  3.194219  AFABBAEGCB  -65.993825     1     0  \n",
       "2       0.585032  0.066898  BBACABBKEE  -87.405622     0     1  \n",
       "3      -1.003320  3.893099  AEBEAACQCC -281.293460     0     0  \n",
       "4       1.210687  1.861884  AEBBBBDABF   25.629415     0     2  \n",
       "...          ...       ...         ...         ...   ...   ...  \n",
       "699995  0.575111  0.076372  BCBCEBHMCD  204.186539     0     0  \n",
       "699996 -1.511760  2.225218  BAABCADQFC  -97.694591     0     2  \n",
       "699997 -4.885955 -2.248739  AAAJCBGQBA  130.622745     1     0  \n",
       "699998 -0.353068 -3.333449  BCBBCABNDE -364.625148     0     0  \n",
       "699999 -3.236026 -0.362070  AFBEBACHFF -155.417342     0     1  \n",
       "\n",
       "[700000 rows x 32 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "d6f2b103",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:22.097149Z",
     "iopub.status.busy": "2022-05-11T11:03:22.096385Z",
     "iopub.status.idle": "2022-05-11T11:03:22.108954Z",
     "shell.execute_reply": "2022-05-11T11:03:22.107976Z"
    },
    "papermill": {
     "duration": 0.049962,
     "end_time": "2022-05-11T11:03:22.110994",
     "exception": false,
     "start_time": "2022-05-11T11:03:22.061032",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>900000</td>\n",
       "      <td>0.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>900001</td>\n",
       "      <td>0.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>900002</td>\n",
       "      <td>0.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>900003</td>\n",
       "      <td>0.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>900004</td>\n",
       "      <td>0.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699995</th>\n",
       "      <td>1599995</td>\n",
       "      <td>0.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699996</th>\n",
       "      <td>1599996</td>\n",
       "      <td>0.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699997</th>\n",
       "      <td>1599997</td>\n",
       "      <td>0.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699998</th>\n",
       "      <td>1599998</td>\n",
       "      <td>0.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699999</th>\n",
       "      <td>1599999</td>\n",
       "      <td>0.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>700000 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "             id  target\n",
       "0        900000     0.5\n",
       "1        900001     0.5\n",
       "2        900002     0.5\n",
       "3        900003     0.5\n",
       "4        900004     0.5\n",
       "...         ...     ...\n",
       "699995  1599995     0.5\n",
       "699996  1599996     0.5\n",
       "699997  1599997     0.5\n",
       "699998  1599998     0.5\n",
       "699999  1599999     0.5\n",
       "\n",
       "[700000 rows x 2 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "submission"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "52d8140f",
   "metadata": {
    "papermill": {
     "duration": 0.035034,
     "end_time": "2022-05-11T11:03:22.180689",
     "exception": false,
     "start_time": "2022-05-11T11:03:22.145655",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Analyse"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "68db965c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:22.251536Z",
     "iopub.status.busy": "2022-05-11T11:03:22.251122Z",
     "iopub.status.idle": "2022-05-11T11:03:22.429558Z",
     "shell.execute_reply": "2022-05-11T11:03:22.428055Z"
    },
    "papermill": {
     "duration": 0.216562,
     "end_time": "2022-05-11T11:03:22.431705",
     "exception": false,
     "start_time": "2022-05-11T11:03:22.215143",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 900000 entries, 0 to 899999\n",
      "Data columns (total 33 columns):\n",
      " #   Column  Non-Null Count   Dtype  \n",
      "---  ------  --------------   -----  \n",
      " 0   id      900000 non-null  int64  \n",
      " 1   f_00    900000 non-null  float64\n",
      " 2   f_01    900000 non-null  float64\n",
      " 3   f_02    900000 non-null  float64\n",
      " 4   f_03    900000 non-null  float64\n",
      " 5   f_04    900000 non-null  float64\n",
      " 6   f_05    900000 non-null  float64\n",
      " 7   f_06    900000 non-null  float64\n",
      " 8   f_07    900000 non-null  int64  \n",
      " 9   f_08    900000 non-null  int64  \n",
      " 10  f_09    900000 non-null  int64  \n",
      " 11  f_10    900000 non-null  int64  \n",
      " 12  f_11    900000 non-null  int64  \n",
      " 13  f_12    900000 non-null  int64  \n",
      " 14  f_13    900000 non-null  int64  \n",
      " 15  f_14    900000 non-null  int64  \n",
      " 16  f_15    900000 non-null  int64  \n",
      " 17  f_16    900000 non-null  int64  \n",
      " 18  f_17    900000 non-null  int64  \n",
      " 19  f_18    900000 non-null  int64  \n",
      " 20  f_19    900000 non-null  float64\n",
      " 21  f_20    900000 non-null  float64\n",
      " 22  f_21    900000 non-null  float64\n",
      " 23  f_22    900000 non-null  float64\n",
      " 24  f_23    900000 non-null  float64\n",
      " 25  f_24    900000 non-null  float64\n",
      " 26  f_25    900000 non-null  float64\n",
      " 27  f_26    900000 non-null  float64\n",
      " 28  f_27    900000 non-null  object \n",
      " 29  f_28    900000 non-null  float64\n",
      " 30  f_29    900000 non-null  int64  \n",
      " 31  f_30    900000 non-null  int64  \n",
      " 32  target  900000 non-null  int64  \n",
      "dtypes: float64(16), int64(16), object(1)\n",
      "memory usage: 226.6+ MB\n"
     ]
    }
   ],
   "source": [
    "train.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "ac090171",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:22.505768Z",
     "iopub.status.busy": "2022-05-11T11:03:22.505490Z",
     "iopub.status.idle": "2022-05-11T11:03:23.698698Z",
     "shell.execute_reply": "2022-05-11T11:03:23.697778Z"
    },
    "papermill": {
     "duration": 1.231653,
     "end_time": "2022-05-11T11:03:23.700854",
     "exception": false,
     "start_time": "2022-05-11T11:03:22.469201",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>f_00</th>\n",
       "      <th>f_01</th>\n",
       "      <th>f_02</th>\n",
       "      <th>f_03</th>\n",
       "      <th>f_04</th>\n",
       "      <th>f_05</th>\n",
       "      <th>f_06</th>\n",
       "      <th>f_07</th>\n",
       "      <th>f_08</th>\n",
       "      <th>...</th>\n",
       "      <th>f_21</th>\n",
       "      <th>f_22</th>\n",
       "      <th>f_23</th>\n",
       "      <th>f_24</th>\n",
       "      <th>f_25</th>\n",
       "      <th>f_26</th>\n",
       "      <th>f_28</th>\n",
       "      <th>f_29</th>\n",
       "      <th>f_30</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>900000.000000</td>\n",
       "      <td>900000.000000</td>\n",
       "      <td>900000.000000</td>\n",
       "      <td>900000.000000</td>\n",
       "      <td>900000.000000</td>\n",
       "      <td>900000.000000</td>\n",
       "      <td>900000.000000</td>\n",
       "      <td>900000.000000</td>\n",
       "      <td>900000.000000</td>\n",
       "      <td>900000.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>900000.000000</td>\n",
       "      <td>900000.000000</td>\n",
       "      <td>900000.000000</td>\n",
       "      <td>900000.000000</td>\n",
       "      <td>900000.000000</td>\n",
       "      <td>900000.000000</td>\n",
       "      <td>900000.000000</td>\n",
       "      <td>900000.000000</td>\n",
       "      <td>900000.000000</td>\n",
       "      <td>900000.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>449999.500000</td>\n",
       "      <td>-0.000286</td>\n",
       "      <td>0.001165</td>\n",
       "      <td>0.001174</td>\n",
       "      <td>-0.001368</td>\n",
       "      <td>-0.000571</td>\n",
       "      <td>0.000284</td>\n",
       "      <td>-0.000709</td>\n",
       "      <td>2.031460</td>\n",
       "      <td>2.057998</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.156307</td>\n",
       "      <td>-0.009273</td>\n",
       "      <td>-0.369459</td>\n",
       "      <td>-0.342738</td>\n",
       "      <td>0.176549</td>\n",
       "      <td>0.357591</td>\n",
       "      <td>-0.380876</td>\n",
       "      <td>0.345661</td>\n",
       "      <td>1.002654</td>\n",
       "      <td>0.486488</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>259807.765473</td>\n",
       "      <td>0.998888</td>\n",
       "      <td>0.999193</td>\n",
       "      <td>1.000514</td>\n",
       "      <td>1.000175</td>\n",
       "      <td>1.000167</td>\n",
       "      <td>0.999875</td>\n",
       "      <td>0.999942</td>\n",
       "      <td>1.656172</td>\n",
       "      <td>1.590955</td>\n",
       "      <td>...</td>\n",
       "      <td>2.484706</td>\n",
       "      <td>2.450797</td>\n",
       "      <td>2.453405</td>\n",
       "      <td>2.386941</td>\n",
       "      <td>2.416959</td>\n",
       "      <td>2.476020</td>\n",
       "      <td>238.773054</td>\n",
       "      <td>0.475584</td>\n",
       "      <td>0.818989</td>\n",
       "      <td>0.499818</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>-4.599856</td>\n",
       "      <td>-4.682199</td>\n",
       "      <td>-4.642676</td>\n",
       "      <td>-4.658816</td>\n",
       "      <td>-4.748501</td>\n",
       "      <td>-4.750214</td>\n",
       "      <td>-4.842919</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>-13.310146</td>\n",
       "      <td>-11.853530</td>\n",
       "      <td>-12.301097</td>\n",
       "      <td>-11.416189</td>\n",
       "      <td>-11.918306</td>\n",
       "      <td>-14.300577</td>\n",
       "      <td>-1229.753052</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>224999.750000</td>\n",
       "      <td>-0.675490</td>\n",
       "      <td>-0.675162</td>\n",
       "      <td>-0.674369</td>\n",
       "      <td>-0.676114</td>\n",
       "      <td>-0.675909</td>\n",
       "      <td>-0.673437</td>\n",
       "      <td>-0.674876</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>-1.820063</td>\n",
       "      <td>-1.645585</td>\n",
       "      <td>-2.019739</td>\n",
       "      <td>-1.955956</td>\n",
       "      <td>-1.440424</td>\n",
       "      <td>-1.261598</td>\n",
       "      <td>-159.427418</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>449999.500000</td>\n",
       "      <td>0.001144</td>\n",
       "      <td>0.002014</td>\n",
       "      <td>0.002218</td>\n",
       "      <td>-0.002227</td>\n",
       "      <td>-0.001662</td>\n",
       "      <td>-0.000438</td>\n",
       "      <td>-0.001492</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.152668</td>\n",
       "      <td>0.030850</td>\n",
       "      <td>-0.390966</td>\n",
       "      <td>-0.340746</td>\n",
       "      <td>0.160912</td>\n",
       "      <td>0.404212</td>\n",
       "      <td>-0.519808</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>674999.250000</td>\n",
       "      <td>0.674337</td>\n",
       "      <td>0.675021</td>\n",
       "      <td>0.677505</td>\n",
       "      <td>0.672544</td>\n",
       "      <td>0.673789</td>\n",
       "      <td>0.675028</td>\n",
       "      <td>0.674749</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.507071</td>\n",
       "      <td>1.661676</td>\n",
       "      <td>1.255408</td>\n",
       "      <td>1.266673</td>\n",
       "      <td>1.795928</td>\n",
       "      <td>2.028219</td>\n",
       "      <td>158.987357</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>899999.000000</td>\n",
       "      <td>4.749301</td>\n",
       "      <td>4.815699</td>\n",
       "      <td>4.961982</td>\n",
       "      <td>4.454920</td>\n",
       "      <td>4.948983</td>\n",
       "      <td>4.971881</td>\n",
       "      <td>4.822668</td>\n",
       "      <td>15.000000</td>\n",
       "      <td>16.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>14.455426</td>\n",
       "      <td>11.344080</td>\n",
       "      <td>12.247100</td>\n",
       "      <td>12.389844</td>\n",
       "      <td>12.529179</td>\n",
       "      <td>12.913041</td>\n",
       "      <td>1229.562577</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 32 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                  id           f_00           f_01           f_02  \\\n",
       "count  900000.000000  900000.000000  900000.000000  900000.000000   \n",
       "mean   449999.500000      -0.000286       0.001165       0.001174   \n",
       "std    259807.765473       0.998888       0.999193       1.000514   \n",
       "min         0.000000      -4.599856      -4.682199      -4.642676   \n",
       "25%    224999.750000      -0.675490      -0.675162      -0.674369   \n",
       "50%    449999.500000       0.001144       0.002014       0.002218   \n",
       "75%    674999.250000       0.674337       0.675021       0.677505   \n",
       "max    899999.000000       4.749301       4.815699       4.961982   \n",
       "\n",
       "                f_03           f_04           f_05           f_06  \\\n",
       "count  900000.000000  900000.000000  900000.000000  900000.000000   \n",
       "mean       -0.001368      -0.000571       0.000284      -0.000709   \n",
       "std         1.000175       1.000167       0.999875       0.999942   \n",
       "min        -4.658816      -4.748501      -4.750214      -4.842919   \n",
       "25%        -0.676114      -0.675909      -0.673437      -0.674876   \n",
       "50%        -0.002227      -0.001662      -0.000438      -0.001492   \n",
       "75%         0.672544       0.673789       0.675028       0.674749   \n",
       "max         4.454920       4.948983       4.971881       4.822668   \n",
       "\n",
       "                f_07           f_08  ...           f_21           f_22  \\\n",
       "count  900000.000000  900000.000000  ...  900000.000000  900000.000000   \n",
       "mean        2.031460       2.057998  ...      -0.156307      -0.009273   \n",
       "std         1.656172       1.590955  ...       2.484706       2.450797   \n",
       "min         0.000000       0.000000  ...     -13.310146     -11.853530   \n",
       "25%         1.000000       1.000000  ...      -1.820063      -1.645585   \n",
       "50%         2.000000       2.000000  ...      -0.152668       0.030850   \n",
       "75%         3.000000       3.000000  ...       1.507071       1.661676   \n",
       "max        15.000000      16.000000  ...      14.455426      11.344080   \n",
       "\n",
       "                f_23           f_24           f_25           f_26  \\\n",
       "count  900000.000000  900000.000000  900000.000000  900000.000000   \n",
       "mean       -0.369459      -0.342738       0.176549       0.357591   \n",
       "std         2.453405       2.386941       2.416959       2.476020   \n",
       "min       -12.301097     -11.416189     -11.918306     -14.300577   \n",
       "25%        -2.019739      -1.955956      -1.440424      -1.261598   \n",
       "50%        -0.390966      -0.340746       0.160912       0.404212   \n",
       "75%         1.255408       1.266673       1.795928       2.028219   \n",
       "max        12.247100      12.389844      12.529179      12.913041   \n",
       "\n",
       "                f_28           f_29           f_30         target  \n",
       "count  900000.000000  900000.000000  900000.000000  900000.000000  \n",
       "mean       -0.380876       0.345661       1.002654       0.486488  \n",
       "std       238.773054       0.475584       0.818989       0.499818  \n",
       "min     -1229.753052       0.000000       0.000000       0.000000  \n",
       "25%      -159.427418       0.000000       0.000000       0.000000  \n",
       "50%        -0.519808       0.000000       1.000000       0.000000  \n",
       "75%       158.987357       1.000000       2.000000       1.000000  \n",
       "max      1229.562577       1.000000       2.000000       1.000000  \n",
       "\n",
       "[8 rows x 32 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "56e154be",
   "metadata": {
    "papermill": {
     "duration": 0.035465,
     "end_time": "2022-05-11T11:03:23.773992",
     "exception": false,
     "start_time": "2022-05-11T11:03:23.738527",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Analyse target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "8ff4e8b1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:23.846653Z",
     "iopub.status.busy": "2022-05-11T11:03:23.846387Z",
     "iopub.status.idle": "2022-05-11T11:03:26.891259Z",
     "shell.execute_reply": "2022-05-11T11:03:26.890221Z"
    },
    "papermill": {
     "duration": 3.083778,
     "end_time": "2022-05-11T11:03:26.893405",
     "exception": false,
     "start_time": "2022-05-11T11:03:23.809627",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.7/site-packages/seaborn/distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).\n",
      "  warnings.warn(msg, FutureWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='target', ylabel='Density'>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.distplot(train['target'])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "89084ac0",
   "metadata": {
    "papermill": {
     "duration": 0.038491,
     "end_time": "2022-05-11T11:03:26.971134",
     "exception": false,
     "start_time": "2022-05-11T11:03:26.932643",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Define target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "fb918316",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:27.049570Z",
     "iopub.status.busy": "2022-05-11T11:03:27.049053Z",
     "iopub.status.idle": "2022-05-11T11:03:27.055599Z",
     "shell.execute_reply": "2022-05-11T11:03:27.054810Z"
    },
    "papermill": {
     "duration": 0.049053,
     "end_time": "2022-05-11T11:03:27.057883",
     "exception": false,
     "start_time": "2022-05-11T11:03:27.008830",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0         0\n",
       "1         1\n",
       "2         1\n",
       "3         1\n",
       "4         1\n",
       "         ..\n",
       "899995    1\n",
       "899996    0\n",
       "899997    0\n",
       "899998    0\n",
       "899999    1\n",
       "Name: target, Length: 900000, dtype: int64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "target = train['target']\n",
    "target"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d388de97",
   "metadata": {
    "papermill": {
     "duration": 0.037479,
     "end_time": "2022-05-11T11:03:27.134251",
     "exception": false,
     "start_time": "2022-05-11T11:03:27.096772",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Combine train and test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "06fe1a2d",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:27.213073Z",
     "iopub.status.busy": "2022-05-11T11:03:27.212416Z",
     "iopub.status.idle": "2022-05-11T11:03:28.484296Z",
     "shell.execute_reply": "2022-05-11T11:03:28.483417Z"
    },
    "papermill": {
     "duration": 1.313462,
     "end_time": "2022-05-11T11:03:28.486506",
     "exception": false,
     "start_time": "2022-05-11T11:03:27.173044",
     "status": "completed"
    },
    "tags": []
   },
   "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>f_00</th>\n",
       "      <th>f_01</th>\n",
       "      <th>f_02</th>\n",
       "      <th>f_03</th>\n",
       "      <th>f_04</th>\n",
       "      <th>f_05</th>\n",
       "      <th>f_06</th>\n",
       "      <th>f_07</th>\n",
       "      <th>f_08</th>\n",
       "      <th>f_09</th>\n",
       "      <th>...</th>\n",
       "      <th>f_20</th>\n",
       "      <th>f_21</th>\n",
       "      <th>f_22</th>\n",
       "      <th>f_23</th>\n",
       "      <th>f_24</th>\n",
       "      <th>f_25</th>\n",
       "      <th>f_26</th>\n",
       "      <th>f_28</th>\n",
       "      <th>f_29</th>\n",
       "      <th>f_30</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-1.373246</td>\n",
       "      <td>0.238887</td>\n",
       "      <td>-0.243376</td>\n",
       "      <td>0.567405</td>\n",
       "      <td>-0.647715</td>\n",
       "      <td>0.839326</td>\n",
       "      <td>0.113133</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.919717</td>\n",
       "      <td>3.058541</td>\n",
       "      <td>-2.540739</td>\n",
       "      <td>0.766952</td>\n",
       "      <td>-2.730628</td>\n",
       "      <td>-0.208177</td>\n",
       "      <td>1.363402</td>\n",
       "      <td>67.609153</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.697021</td>\n",
       "      <td>-1.710322</td>\n",
       "      <td>-2.230332</td>\n",
       "      <td>-0.545661</td>\n",
       "      <td>1.113173</td>\n",
       "      <td>-1.552175</td>\n",
       "      <td>0.447825</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>...</td>\n",
       "      <td>-1.075434</td>\n",
       "      <td>2.179050</td>\n",
       "      <td>2.278315</td>\n",
       "      <td>-0.633658</td>\n",
       "      <td>-1.217077</td>\n",
       "      <td>-3.782194</td>\n",
       "      <td>-0.058316</td>\n",
       "      <td>377.096415</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.681726</td>\n",
       "      <td>0.616746</td>\n",
       "      <td>-1.027689</td>\n",
       "      <td>0.810492</td>\n",
       "      <td>-0.609086</td>\n",
       "      <td>0.113965</td>\n",
       "      <td>-0.708660</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>-3.485342</td>\n",
       "      <td>-0.784235</td>\n",
       "      <td>-1.385775</td>\n",
       "      <td>-0.520558</td>\n",
       "      <td>-0.009121</td>\n",
       "      <td>2.788536</td>\n",
       "      <td>-3.703488</td>\n",
       "      <td>-195.599702</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-0.118172</td>\n",
       "      <td>-0.587835</td>\n",
       "      <td>-0.804638</td>\n",
       "      <td>2.086822</td>\n",
       "      <td>0.371005</td>\n",
       "      <td>-0.128831</td>\n",
       "      <td>-0.282575</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>-2.100177</td>\n",
       "      <td>-2.343819</td>\n",
       "      <td>0.572594</td>\n",
       "      <td>-1.653213</td>\n",
       "      <td>1.686035</td>\n",
       "      <td>-2.533098</td>\n",
       "      <td>-0.608601</td>\n",
       "      <td>210.826205</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.148481</td>\n",
       "      <td>-0.176567</td>\n",
       "      <td>-0.664871</td>\n",
       "      <td>-1.101343</td>\n",
       "      <td>0.467875</td>\n",
       "      <td>0.500117</td>\n",
       "      <td>0.407515</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.605033</td>\n",
       "      <td>1.133665</td>\n",
       "      <td>-3.912929</td>\n",
       "      <td>-1.430366</td>\n",
       "      <td>2.127649</td>\n",
       "      <td>-3.306784</td>\n",
       "      <td>4.371371</td>\n",
       "      <td>-217.211798</td>\n",
       "      <td>0</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",
       "      <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>699995</th>\n",
       "      <td>0.640110</td>\n",
       "      <td>0.897808</td>\n",
       "      <td>-0.523956</td>\n",
       "      <td>1.563760</td>\n",
       "      <td>-0.092281</td>\n",
       "      <td>-0.610867</td>\n",
       "      <td>0.535426</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "      <td>...</td>\n",
       "      <td>-2.185190</td>\n",
       "      <td>2.604048</td>\n",
       "      <td>1.122867</td>\n",
       "      <td>0.518110</td>\n",
       "      <td>1.243837</td>\n",
       "      <td>0.575111</td>\n",
       "      <td>0.076372</td>\n",
       "      <td>204.186539</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699996</th>\n",
       "      <td>-0.191771</td>\n",
       "      <td>-0.035246</td>\n",
       "      <td>-0.118533</td>\n",
       "      <td>0.584750</td>\n",
       "      <td>2.126977</td>\n",
       "      <td>0.568659</td>\n",
       "      <td>-0.052663</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.239552</td>\n",
       "      <td>3.029857</td>\n",
       "      <td>1.384682</td>\n",
       "      <td>-1.135740</td>\n",
       "      <td>2.982713</td>\n",
       "      <td>-1.511760</td>\n",
       "      <td>2.225218</td>\n",
       "      <td>-97.694591</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699997</th>\n",
       "      <td>-0.331704</td>\n",
       "      <td>-0.328845</td>\n",
       "      <td>-1.185503</td>\n",
       "      <td>1.022128</td>\n",
       "      <td>-0.483099</td>\n",
       "      <td>-0.107146</td>\n",
       "      <td>-0.968281</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.922626</td>\n",
       "      <td>4.021273</td>\n",
       "      <td>-1.845266</td>\n",
       "      <td>1.096011</td>\n",
       "      <td>-2.734508</td>\n",
       "      <td>-4.885955</td>\n",
       "      <td>-2.248739</td>\n",
       "      <td>130.622745</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699998</th>\n",
       "      <td>-2.031073</td>\n",
       "      <td>-1.238398</td>\n",
       "      <td>0.964699</td>\n",
       "      <td>-1.045950</td>\n",
       "      <td>0.906064</td>\n",
       "      <td>0.634301</td>\n",
       "      <td>-0.707474</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>-3.079996</td>\n",
       "      <td>1.453864</td>\n",
       "      <td>-1.696606</td>\n",
       "      <td>1.018995</td>\n",
       "      <td>1.973697</td>\n",
       "      <td>-0.353068</td>\n",
       "      <td>-3.333449</td>\n",
       "      <td>-364.625148</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699999</th>\n",
       "      <td>-0.085906</td>\n",
       "      <td>-0.002124</td>\n",
       "      <td>2.227375</td>\n",
       "      <td>0.217145</td>\n",
       "      <td>3.179153</td>\n",
       "      <td>-1.660188</td>\n",
       "      <td>0.891989</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>...</td>\n",
       "      <td>-2.128546</td>\n",
       "      <td>-3.549082</td>\n",
       "      <td>-4.325318</td>\n",
       "      <td>-5.017221</td>\n",
       "      <td>0.251268</td>\n",
       "      <td>-3.236026</td>\n",
       "      <td>-0.362070</td>\n",
       "      <td>-155.417342</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1600000 rows × 30 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            f_00      f_01      f_02      f_03      f_04      f_05      f_06  \\\n",
       "0      -1.373246  0.238887 -0.243376  0.567405 -0.647715  0.839326  0.113133   \n",
       "1       1.697021 -1.710322 -2.230332 -0.545661  1.113173 -1.552175  0.447825   \n",
       "2       1.681726  0.616746 -1.027689  0.810492 -0.609086  0.113965 -0.708660   \n",
       "3      -0.118172 -0.587835 -0.804638  2.086822  0.371005 -0.128831 -0.282575   \n",
       "4       1.148481 -0.176567 -0.664871 -1.101343  0.467875  0.500117  0.407515   \n",
       "...          ...       ...       ...       ...       ...       ...       ...   \n",
       "699995  0.640110  0.897808 -0.523956  1.563760 -0.092281 -0.610867  0.535426   \n",
       "699996 -0.191771 -0.035246 -0.118533  0.584750  2.126977  0.568659 -0.052663   \n",
       "699997 -0.331704 -0.328845 -1.185503  1.022128 -0.483099 -0.107146 -0.968281   \n",
       "699998 -2.031073 -1.238398  0.964699 -1.045950  0.906064  0.634301 -0.707474   \n",
       "699999 -0.085906 -0.002124  2.227375  0.217145  3.179153 -1.660188  0.891989   \n",
       "\n",
       "        f_07  f_08  f_09  ...      f_20      f_21      f_22      f_23  \\\n",
       "0          1     5     1  ... -0.919717  3.058541 -2.540739  0.766952   \n",
       "1          1     3     4  ... -1.075434  2.179050  2.278315 -0.633658   \n",
       "2          1     0     2  ... -3.485342 -0.784235 -1.385775 -0.520558   \n",
       "3          3     2     1  ... -2.100177 -2.343819  0.572594 -1.653213   \n",
       "4          3     3     0  ...  0.605033  1.133665 -3.912929 -1.430366   \n",
       "...      ...   ...   ...  ...       ...       ...       ...       ...   \n",
       "699995     0     1     6  ... -2.185190  2.604048  1.122867  0.518110   \n",
       "699996     4     3     4  ... -0.239552  3.029857  1.384682 -1.135740   \n",
       "699997     1     1     2  ... -0.922626  4.021273 -1.845266  1.096011   \n",
       "699998     5     1     1  ... -3.079996  1.453864 -1.696606  1.018995   \n",
       "699999     0     3     4  ... -2.128546 -3.549082 -4.325318 -5.017221   \n",
       "\n",
       "            f_24      f_25      f_26        f_28  f_29  f_30  \n",
       "0      -2.730628 -0.208177  1.363402   67.609153     0     0  \n",
       "1      -1.217077 -3.782194 -0.058316  377.096415     0     0  \n",
       "2      -0.009121  2.788536 -3.703488 -195.599702     0     2  \n",
       "3       1.686035 -2.533098 -0.608601  210.826205     0     0  \n",
       "4       2.127649 -3.306784  4.371371 -217.211798     0     1  \n",
       "...          ...       ...       ...         ...   ...   ...  \n",
       "699995  1.243837  0.575111  0.076372  204.186539     0     0  \n",
       "699996  2.982713 -1.511760  2.225218  -97.694591     0     2  \n",
       "699997 -2.734508 -4.885955 -2.248739  130.622745     1     0  \n",
       "699998  1.973697 -0.353068 -3.333449 -364.625148     0     0  \n",
       "699999  0.251268 -3.236026 -0.362070 -155.417342     0     1  \n",
       "\n",
       "[1600000 rows x 30 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "combi = train.drop(['target'], axis=1).append(test)\n",
    "combi = combi.drop(['id', 'f_27'], axis=1)\n",
    "combi"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "aa697977",
   "metadata": {
    "papermill": {
     "duration": 0.039281,
     "end_time": "2022-05-11T11:03:28.565424",
     "exception": false,
     "start_time": "2022-05-11T11:03:28.526143",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Heatmap"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "0e948e76",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:28.645338Z",
     "iopub.status.busy": "2022-05-11T11:03:28.645031Z",
     "iopub.status.idle": "2022-05-11T11:03:33.606584Z",
     "shell.execute_reply": "2022-05-11T11:03:33.605587Z"
    },
    "papermill": {
     "duration": 5.004322,
     "end_time": "2022-05-11T11:03:33.608988",
     "exception": false,
     "start_time": "2022-05-11T11:03:28.604666",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 864x648 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "corr = combi.corr()\n",
    "f, ax = plt.subplots(figsize=(12, 9))\n",
    "sns.heatmap(corr, vmax=.8, square=True);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "ba6957d3",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:33.692201Z",
     "iopub.status.busy": "2022-05-11T11:03:33.691895Z",
     "iopub.status.idle": "2022-05-11T11:03:33.715345Z",
     "shell.execute_reply": "2022-05-11T11:03:33.714306Z"
    },
    "papermill": {
     "duration": 0.06877,
     "end_time": "2022-05-11T11:03:33.718205",
     "exception": false,
     "start_time": "2022-05-11T11:03:33.649435",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "          f_00      f_01      f_02      f_03      f_04      f_05      f_06  \\\n",
      "f_00  1.000000 -0.000373 -0.000155 -0.001402 -0.000391 -0.000088 -0.001257   \n",
      "f_01 -0.000373  1.000000  0.001066  0.000231 -0.001221  0.000028 -0.000963   \n",
      "f_02 -0.000155  0.001066  1.000000 -0.000307  0.000768 -0.000394  0.000661   \n",
      "f_03 -0.001402  0.000231 -0.000307  1.000000  0.000483  0.001895 -0.000237   \n",
      "f_04 -0.000391 -0.001221  0.000768  0.000483  1.000000  0.000198 -0.000347   \n",
      "f_05 -0.000088  0.000028 -0.000394  0.001895  0.000198  1.000000  0.001312   \n",
      "f_06 -0.001257 -0.000963  0.000661 -0.000237 -0.000347  0.001312  1.000000   \n",
      "f_07  0.000268 -0.001054  0.000925  0.000644  0.000317  0.000282 -0.000048   \n",
      "f_08 -0.000945 -0.000522 -0.000284 -0.000512  0.000721 -0.000602  0.000229   \n",
      "f_09  0.000175 -0.000363  0.000052  0.000678  0.000846  0.000830  0.000046   \n",
      "f_10  0.000347  0.000363  0.000580 -0.000808 -0.002530 -0.000209 -0.000022   \n",
      "f_11  0.001084  0.000897 -0.000922  0.000700  0.001119 -0.000094 -0.000209   \n",
      "f_12  0.000300 -0.000526  0.001041  0.000740  0.001370  0.001240  0.000957   \n",
      "f_13  0.001492  0.000129 -0.001560 -0.001747 -0.000624  0.000479  0.000286   \n",
      "f_14  0.001599  0.000820  0.001278 -0.000388  0.000224  0.000056 -0.000079   \n",
      "f_15 -0.000687 -0.000014  0.001568 -0.001294  0.000272  0.000727  0.000612   \n",
      "f_16  0.000163 -0.000759 -0.000873  0.000486 -0.000711 -0.000264 -0.000025   \n",
      "f_17 -0.000202 -0.000345  0.000392  0.001029 -0.000427  0.000930  0.000511   \n",
      "f_18 -0.000226 -0.000116 -0.000205  0.000235  0.001201  0.000152  0.000143   \n",
      "f_19 -0.000310 -0.000941 -0.000755  0.000652 -0.000401  0.000635  0.000661   \n",
      "f_20 -0.000489  0.001159  0.000051  0.000124  0.000223  0.000278 -0.000120   \n",
      "f_21  0.000768 -0.000546 -0.000196  0.000156  0.000082  0.000051 -0.000620   \n",
      "f_22 -0.001141 -0.000207 -0.000636  0.000725  0.000627  0.000474 -0.000243   \n",
      "f_23  0.000197 -0.000510  0.000123  0.000361 -0.001822 -0.000784 -0.001081   \n",
      "f_24  0.001522 -0.000183 -0.000447  0.001403  0.000876 -0.000349 -0.001327   \n",
      "f_25  0.000285  0.000097 -0.000667  0.001246 -0.001457  0.000513  0.001279   \n",
      "f_26 -0.000172  0.000420  0.000305 -0.000089 -0.000656  0.000433  0.000436   \n",
      "f_28  0.188822  0.194247  0.208815  0.328754  0.169644  0.296369  0.165917   \n",
      "f_29 -0.000032 -0.000232 -0.000377  0.000161  0.000141 -0.000608  0.000858   \n",
      "f_30 -0.000781  0.000817 -0.000630 -0.000484 -0.000664 -0.000723  0.000495   \n",
      "\n",
      "          f_07      f_08      f_09  ...      f_20      f_21      f_22  \\\n",
      "f_00  0.000268 -0.000945  0.000175  ... -0.000489  0.000768 -0.001141   \n",
      "f_01 -0.001054 -0.000522 -0.000363  ...  0.001159 -0.000546 -0.000207   \n",
      "f_02  0.000925 -0.000284  0.000052  ...  0.000051 -0.000196 -0.000636   \n",
      "f_03  0.000644 -0.000512  0.000678  ...  0.000124  0.000156  0.000725   \n",
      "f_04  0.000317  0.000721  0.000846  ...  0.000223  0.000082  0.000627   \n",
      "f_05  0.000282 -0.000602  0.000830  ...  0.000278  0.000051  0.000474   \n",
      "f_06 -0.000048  0.000229  0.000046  ... -0.000120 -0.000620 -0.000243   \n",
      "f_07  1.000000  0.113097  0.006419  ... -0.002478  0.001269  0.000464   \n",
      "f_08  0.113097  1.000000 -0.067602  ... -0.004145  0.004364 -0.001753   \n",
      "f_09  0.006419 -0.067602  1.000000  ... -0.004613  0.005410 -0.001343   \n",
      "f_10 -0.089812 -0.085315 -0.050998  ...  0.003826 -0.003314  0.000885   \n",
      "f_11 -0.134704 -0.102443  0.007286  ...  0.004513 -0.005434  0.002350   \n",
      "f_12  0.093957  0.011274  0.035231  ... -0.000851 -0.000410 -0.001399   \n",
      "f_13  0.059271  0.038777 -0.047612  ...  0.002026 -0.001728  0.000846   \n",
      "f_14 -0.061668 -0.043743  0.032393  ...  0.001488 -0.002593 -0.001102   \n",
      "f_15  0.055368  0.010021 -0.000042  ... -0.002765  0.003701 -0.001018   \n",
      "f_16  0.062274  0.049848 -0.019949  ...  0.001838 -0.001320  0.001152   \n",
      "f_17 -0.149490 -0.049167  0.005606  ...  0.001073  0.000038 -0.000294   \n",
      "f_18  0.026738  0.066641 -0.051665  ... -0.001864  0.000212  0.000678   \n",
      "f_19 -0.003340 -0.005489 -0.010161  ... -0.081401  0.027210 -0.070250   \n",
      "f_20 -0.002478 -0.004145 -0.004613  ...  1.000000 -0.012057 -0.063454   \n",
      "f_21  0.001269  0.004364  0.005410  ... -0.012057  1.000000 -0.155678   \n",
      "f_22  0.000464 -0.001753 -0.001343  ... -0.063454 -0.155678  1.000000   \n",
      "f_23  0.005402  0.002331  0.008653  ... -0.062111  0.116442 -0.088164   \n",
      "f_24  0.002533  0.003782  0.009826  ...  0.087198  0.054088 -0.016601   \n",
      "f_25 -0.001417 -0.002369 -0.005436  ... -0.062476 -0.084967  0.149289   \n",
      "f_26 -0.003336 -0.004363 -0.008274  ...  0.116582  0.139453 -0.035476   \n",
      "f_28  0.000336 -0.000379 -0.000692  ...  0.000399  0.000206 -0.000204   \n",
      "f_29 -0.048202  0.065008 -0.103734  ... -0.003260  0.003343  0.001211   \n",
      "f_30  0.000243  0.000014 -0.001397  ...  0.072440 -0.154615  0.315087   \n",
      "\n",
      "          f_23      f_24      f_25      f_26      f_28      f_29      f_30  \n",
      "f_00  0.000197  0.001522  0.000285 -0.000172  0.188822 -0.000032 -0.000781  \n",
      "f_01 -0.000510 -0.000183  0.000097  0.000420  0.194247 -0.000232  0.000817  \n",
      "f_02  0.000123 -0.000447 -0.000667  0.000305  0.208815 -0.000377 -0.000630  \n",
      "f_03  0.000361  0.001403  0.001246 -0.000089  0.328754  0.000161 -0.000484  \n",
      "f_04 -0.001822  0.000876 -0.001457 -0.000656  0.169644  0.000141 -0.000664  \n",
      "f_05 -0.000784 -0.000349  0.000513  0.000433  0.296369 -0.000608 -0.000723  \n",
      "f_06 -0.001081 -0.001327  0.001279  0.000436  0.165917  0.000858  0.000495  \n",
      "f_07  0.005402  0.002533 -0.001417 -0.003336  0.000336 -0.048202  0.000243  \n",
      "f_08  0.002331  0.003782 -0.002369 -0.004363 -0.000379  0.065008  0.000014  \n",
      "f_09  0.008653  0.009826 -0.005436 -0.008274 -0.000692 -0.103734 -0.001397  \n",
      "f_10 -0.003461 -0.003243  0.001780  0.004973 -0.000685  0.119974 -0.001564  \n",
      "f_11 -0.003118 -0.007147  0.002607  0.006271  0.000484  0.079092 -0.003122  \n",
      "f_12  0.003382  0.000881 -0.000297 -0.000923  0.000998 -0.111824 -0.001839  \n",
      "f_13 -0.002761 -0.002755  0.000574  0.003935 -0.000507  0.006873 -0.000301  \n",
      "f_14 -0.003426 -0.001403 -0.000042  0.003581  0.001091 -0.038155 -0.001668  \n",
      "f_15  0.005291  0.005004 -0.001737 -0.004642 -0.000461 -0.001241  0.000669  \n",
      "f_16 -0.002896 -0.003837  0.002054  0.004904 -0.001156  0.090912  0.000364  \n",
      "f_17 -0.001100 -0.001235 -0.000385  0.002392  0.000479 -0.077153  0.000416  \n",
      "f_18  0.001505  0.002620 -0.000008 -0.001464 -0.000377  0.158233  0.000114  \n",
      "f_19 -0.057858 -0.101625 -0.020306 -0.014043 -0.000726 -0.008606  0.096469  \n",
      "f_20 -0.062111  0.087198 -0.062476  0.116582  0.000399 -0.003260  0.072440  \n",
      "f_21  0.116442  0.054088 -0.084967  0.139453  0.000206  0.003343 -0.154615  \n",
      "f_22 -0.088164 -0.016601  0.149289 -0.035476 -0.000204  0.001211  0.315087  \n",
      "f_23  1.000000  0.011719 -0.231012  0.039106 -0.001049  0.009140 -0.171359  \n",
      "f_24  0.011719  1.000000 -0.086888  0.013721  0.000375  0.009089 -0.083660  \n",
      "f_25 -0.231012 -0.086888  1.000000  0.010003  0.000412 -0.004410  0.178792  \n",
      "f_26  0.039106  0.013721  0.010003  1.000000 -0.000673 -0.008045 -0.022952  \n",
      "f_28 -0.001049  0.000375  0.000412 -0.000673  1.000000 -0.000940 -0.000932  \n",
      "f_29  0.009140  0.009089 -0.004410 -0.008045 -0.000940  1.000000 -0.000315  \n",
      "f_30 -0.171359 -0.083660  0.178792 -0.022952 -0.000932 -0.000315  1.000000  \n",
      "\n",
      "[30 rows x 30 columns]\n"
     ]
    }
   ],
   "source": [
    "print(corr)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "513955a1",
   "metadata": {
    "papermill": {
     "duration": 0.040925,
     "end_time": "2022-05-11T11:03:33.801214",
     "exception": false,
     "start_time": "2022-05-11T11:03:33.760289",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Remove columns that have a high correlation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "830ae1b5",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:33.885247Z",
     "iopub.status.busy": "2022-05-11T11:03:33.884695Z",
     "iopub.status.idle": "2022-05-11T11:03:34.454640Z",
     "shell.execute_reply": "2022-05-11T11:03:34.453834Z"
    },
    "papermill": {
     "duration": 0.614369,
     "end_time": "2022-05-11T11:03:34.456908",
     "exception": false,
     "start_time": "2022-05-11T11:03:33.842539",
     "status": "completed"
    },
    "tags": []
   },
   "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>f_00</th>\n",
       "      <th>f_01</th>\n",
       "      <th>f_02</th>\n",
       "      <th>f_03</th>\n",
       "      <th>f_04</th>\n",
       "      <th>f_05</th>\n",
       "      <th>f_06</th>\n",
       "      <th>f_07</th>\n",
       "      <th>f_08</th>\n",
       "      <th>f_09</th>\n",
       "      <th>...</th>\n",
       "      <th>f_20</th>\n",
       "      <th>f_21</th>\n",
       "      <th>f_22</th>\n",
       "      <th>f_23</th>\n",
       "      <th>f_24</th>\n",
       "      <th>f_25</th>\n",
       "      <th>f_26</th>\n",
       "      <th>f_28</th>\n",
       "      <th>f_29</th>\n",
       "      <th>f_30</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-1.373246</td>\n",
       "      <td>0.238887</td>\n",
       "      <td>-0.243376</td>\n",
       "      <td>0.567405</td>\n",
       "      <td>-0.647715</td>\n",
       "      <td>0.839326</td>\n",
       "      <td>0.113133</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.919717</td>\n",
       "      <td>3.058541</td>\n",
       "      <td>-2.540739</td>\n",
       "      <td>0.766952</td>\n",
       "      <td>-2.730628</td>\n",
       "      <td>-0.208177</td>\n",
       "      <td>1.363402</td>\n",
       "      <td>67.609153</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.697021</td>\n",
       "      <td>-1.710322</td>\n",
       "      <td>-2.230332</td>\n",
       "      <td>-0.545661</td>\n",
       "      <td>1.113173</td>\n",
       "      <td>-1.552175</td>\n",
       "      <td>0.447825</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>...</td>\n",
       "      <td>-1.075434</td>\n",
       "      <td>2.179050</td>\n",
       "      <td>2.278315</td>\n",
       "      <td>-0.633658</td>\n",
       "      <td>-1.217077</td>\n",
       "      <td>-3.782194</td>\n",
       "      <td>-0.058316</td>\n",
       "      <td>377.096415</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.681726</td>\n",
       "      <td>0.616746</td>\n",
       "      <td>-1.027689</td>\n",
       "      <td>0.810492</td>\n",
       "      <td>-0.609086</td>\n",
       "      <td>0.113965</td>\n",
       "      <td>-0.708660</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>-3.485342</td>\n",
       "      <td>-0.784235</td>\n",
       "      <td>-1.385775</td>\n",
       "      <td>-0.520558</td>\n",
       "      <td>-0.009121</td>\n",
       "      <td>2.788536</td>\n",
       "      <td>-3.703488</td>\n",
       "      <td>-195.599702</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-0.118172</td>\n",
       "      <td>-0.587835</td>\n",
       "      <td>-0.804638</td>\n",
       "      <td>2.086822</td>\n",
       "      <td>0.371005</td>\n",
       "      <td>-0.128831</td>\n",
       "      <td>-0.282575</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>-2.100177</td>\n",
       "      <td>-2.343819</td>\n",
       "      <td>0.572594</td>\n",
       "      <td>-1.653213</td>\n",
       "      <td>1.686035</td>\n",
       "      <td>-2.533098</td>\n",
       "      <td>-0.608601</td>\n",
       "      <td>210.826205</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.148481</td>\n",
       "      <td>-0.176567</td>\n",
       "      <td>-0.664871</td>\n",
       "      <td>-1.101343</td>\n",
       "      <td>0.467875</td>\n",
       "      <td>0.500117</td>\n",
       "      <td>0.407515</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.605033</td>\n",
       "      <td>1.133665</td>\n",
       "      <td>-3.912929</td>\n",
       "      <td>-1.430366</td>\n",
       "      <td>2.127649</td>\n",
       "      <td>-3.306784</td>\n",
       "      <td>4.371371</td>\n",
       "      <td>-217.211798</td>\n",
       "      <td>0</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",
       "      <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>699995</th>\n",
       "      <td>0.640110</td>\n",
       "      <td>0.897808</td>\n",
       "      <td>-0.523956</td>\n",
       "      <td>1.563760</td>\n",
       "      <td>-0.092281</td>\n",
       "      <td>-0.610867</td>\n",
       "      <td>0.535426</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "      <td>...</td>\n",
       "      <td>-2.185190</td>\n",
       "      <td>2.604048</td>\n",
       "      <td>1.122867</td>\n",
       "      <td>0.518110</td>\n",
       "      <td>1.243837</td>\n",
       "      <td>0.575111</td>\n",
       "      <td>0.076372</td>\n",
       "      <td>204.186539</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699996</th>\n",
       "      <td>-0.191771</td>\n",
       "      <td>-0.035246</td>\n",
       "      <td>-0.118533</td>\n",
       "      <td>0.584750</td>\n",
       "      <td>2.126977</td>\n",
       "      <td>0.568659</td>\n",
       "      <td>-0.052663</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.239552</td>\n",
       "      <td>3.029857</td>\n",
       "      <td>1.384682</td>\n",
       "      <td>-1.135740</td>\n",
       "      <td>2.982713</td>\n",
       "      <td>-1.511760</td>\n",
       "      <td>2.225218</td>\n",
       "      <td>-97.694591</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699997</th>\n",
       "      <td>-0.331704</td>\n",
       "      <td>-0.328845</td>\n",
       "      <td>-1.185503</td>\n",
       "      <td>1.022128</td>\n",
       "      <td>-0.483099</td>\n",
       "      <td>-0.107146</td>\n",
       "      <td>-0.968281</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.922626</td>\n",
       "      <td>4.021273</td>\n",
       "      <td>-1.845266</td>\n",
       "      <td>1.096011</td>\n",
       "      <td>-2.734508</td>\n",
       "      <td>-4.885955</td>\n",
       "      <td>-2.248739</td>\n",
       "      <td>130.622745</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699998</th>\n",
       "      <td>-2.031073</td>\n",
       "      <td>-1.238398</td>\n",
       "      <td>0.964699</td>\n",
       "      <td>-1.045950</td>\n",
       "      <td>0.906064</td>\n",
       "      <td>0.634301</td>\n",
       "      <td>-0.707474</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>-3.079996</td>\n",
       "      <td>1.453864</td>\n",
       "      <td>-1.696606</td>\n",
       "      <td>1.018995</td>\n",
       "      <td>1.973697</td>\n",
       "      <td>-0.353068</td>\n",
       "      <td>-3.333449</td>\n",
       "      <td>-364.625148</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699999</th>\n",
       "      <td>-0.085906</td>\n",
       "      <td>-0.002124</td>\n",
       "      <td>2.227375</td>\n",
       "      <td>0.217145</td>\n",
       "      <td>3.179153</td>\n",
       "      <td>-1.660188</td>\n",
       "      <td>0.891989</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>...</td>\n",
       "      <td>-2.128546</td>\n",
       "      <td>-3.549082</td>\n",
       "      <td>-4.325318</td>\n",
       "      <td>-5.017221</td>\n",
       "      <td>0.251268</td>\n",
       "      <td>-3.236026</td>\n",
       "      <td>-0.362070</td>\n",
       "      <td>-155.417342</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1600000 rows × 30 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            f_00      f_01      f_02      f_03      f_04      f_05      f_06  \\\n",
       "0      -1.373246  0.238887 -0.243376  0.567405 -0.647715  0.839326  0.113133   \n",
       "1       1.697021 -1.710322 -2.230332 -0.545661  1.113173 -1.552175  0.447825   \n",
       "2       1.681726  0.616746 -1.027689  0.810492 -0.609086  0.113965 -0.708660   \n",
       "3      -0.118172 -0.587835 -0.804638  2.086822  0.371005 -0.128831 -0.282575   \n",
       "4       1.148481 -0.176567 -0.664871 -1.101343  0.467875  0.500117  0.407515   \n",
       "...          ...       ...       ...       ...       ...       ...       ...   \n",
       "699995  0.640110  0.897808 -0.523956  1.563760 -0.092281 -0.610867  0.535426   \n",
       "699996 -0.191771 -0.035246 -0.118533  0.584750  2.126977  0.568659 -0.052663   \n",
       "699997 -0.331704 -0.328845 -1.185503  1.022128 -0.483099 -0.107146 -0.968281   \n",
       "699998 -2.031073 -1.238398  0.964699 -1.045950  0.906064  0.634301 -0.707474   \n",
       "699999 -0.085906 -0.002124  2.227375  0.217145  3.179153 -1.660188  0.891989   \n",
       "\n",
       "        f_07  f_08  f_09  ...      f_20      f_21      f_22      f_23  \\\n",
       "0          1     5     1  ... -0.919717  3.058541 -2.540739  0.766952   \n",
       "1          1     3     4  ... -1.075434  2.179050  2.278315 -0.633658   \n",
       "2          1     0     2  ... -3.485342 -0.784235 -1.385775 -0.520558   \n",
       "3          3     2     1  ... -2.100177 -2.343819  0.572594 -1.653213   \n",
       "4          3     3     0  ...  0.605033  1.133665 -3.912929 -1.430366   \n",
       "...      ...   ...   ...  ...       ...       ...       ...       ...   \n",
       "699995     0     1     6  ... -2.185190  2.604048  1.122867  0.518110   \n",
       "699996     4     3     4  ... -0.239552  3.029857  1.384682 -1.135740   \n",
       "699997     1     1     2  ... -0.922626  4.021273 -1.845266  1.096011   \n",
       "699998     5     1     1  ... -3.079996  1.453864 -1.696606  1.018995   \n",
       "699999     0     3     4  ... -2.128546 -3.549082 -4.325318 -5.017221   \n",
       "\n",
       "            f_24      f_25      f_26        f_28  f_29  f_30  \n",
       "0      -2.730628 -0.208177  1.363402   67.609153     0     0  \n",
       "1      -1.217077 -3.782194 -0.058316  377.096415     0     0  \n",
       "2      -0.009121  2.788536 -3.703488 -195.599702     0     2  \n",
       "3       1.686035 -2.533098 -0.608601  210.826205     0     0  \n",
       "4       2.127649 -3.306784  4.371371 -217.211798     0     1  \n",
       "...          ...       ...       ...         ...   ...   ...  \n",
       "699995  1.243837  0.575111  0.076372  204.186539     0     0  \n",
       "699996  2.982713 -1.511760  2.225218  -97.694591     0     2  \n",
       "699997 -2.734508 -4.885955 -2.248739  130.622745     1     0  \n",
       "699998  1.973697 -0.353068 -3.333449 -364.625148     0     0  \n",
       "699999  0.251268 -3.236026 -0.362070 -155.417342     0     1  \n",
       "\n",
       "[1600000 rows x 30 columns]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "columns = np.full((corr.shape[0],), True, dtype=bool)\n",
    "for i in range(corr.shape[0]):\n",
    "    for j in range(i+1, corr.shape[0]):\n",
    "        if corr.iloc[i,j] >= 0.80:\n",
    "            if columns[j]:\n",
    "                columns[j] = False\n",
    "selected_columns = combi.columns[columns]\n",
    "combi = combi[selected_columns]\n",
    "combi"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8a8e289f",
   "metadata": {
    "papermill": {
     "duration": 0.041725,
     "end_time": "2022-05-11T11:03:34.540522",
     "exception": false,
     "start_time": "2022-05-11T11:03:34.498797",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Scale data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "d42bf25d",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:34.627208Z",
     "iopub.status.busy": "2022-05-11T11:03:34.626677Z",
     "iopub.status.idle": "2022-05-11T11:03:35.523105Z",
     "shell.execute_reply": "2022-05-11T11:03:35.522255Z"
    },
    "papermill": {
     "duration": 0.942607,
     "end_time": "2022-05-11T11:03:35.525139",
     "exception": false,
     "start_time": "2022-05-11T11:03:34.582532",
     "status": "completed"
    },
    "tags": []
   },
   "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>f_00</th>\n",
       "      <th>f_01</th>\n",
       "      <th>f_02</th>\n",
       "      <th>f_03</th>\n",
       "      <th>f_04</th>\n",
       "      <th>f_05</th>\n",
       "      <th>f_06</th>\n",
       "      <th>f_07</th>\n",
       "      <th>f_08</th>\n",
       "      <th>f_09</th>\n",
       "      <th>...</th>\n",
       "      <th>f_20</th>\n",
       "      <th>f_21</th>\n",
       "      <th>f_22</th>\n",
       "      <th>f_23</th>\n",
       "      <th>f_24</th>\n",
       "      <th>f_25</th>\n",
       "      <th>f_26</th>\n",
       "      <th>f_28</th>\n",
       "      <th>f_29</th>\n",
       "      <th>f_30</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.315238</td>\n",
       "      <td>0.530025</td>\n",
       "      <td>0.458038</td>\n",
       "      <td>0.546749</td>\n",
       "      <td>0.422871</td>\n",
       "      <td>0.591372</td>\n",
       "      <td>0.512752</td>\n",
       "      <td>0.0625</td>\n",
       "      <td>0.3125</td>\n",
       "      <td>0.0625</td>\n",
       "      <td>...</td>\n",
       "      <td>0.454761</td>\n",
       "      <td>0.589532</td>\n",
       "      <td>0.401455</td>\n",
       "      <td>0.532343</td>\n",
       "      <td>0.375916</td>\n",
       "      <td>0.507106</td>\n",
       "      <td>0.575593</td>\n",
       "      <td>0.527530</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.609890</td>\n",
       "      <td>0.329868</td>\n",
       "      <td>0.251164</td>\n",
       "      <td>0.430304</td>\n",
       "      <td>0.604453</td>\n",
       "      <td>0.354899</td>\n",
       "      <td>0.547380</td>\n",
       "      <td>0.0625</td>\n",
       "      <td>0.1875</td>\n",
       "      <td>0.2500</td>\n",
       "      <td>...</td>\n",
       "      <td>0.447912</td>\n",
       "      <td>0.557856</td>\n",
       "      <td>0.609194</td>\n",
       "      <td>0.475287</td>\n",
       "      <td>0.438386</td>\n",
       "      <td>0.368803</td>\n",
       "      <td>0.523351</td>\n",
       "      <td>0.653373</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.608423</td>\n",
       "      <td>0.568826</td>\n",
       "      <td>0.376379</td>\n",
       "      <td>0.572180</td>\n",
       "      <td>0.426854</td>\n",
       "      <td>0.519648</td>\n",
       "      <td>0.427730</td>\n",
       "      <td>0.0625</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.1250</td>\n",
       "      <td>...</td>\n",
       "      <td>0.341903</td>\n",
       "      <td>0.451131</td>\n",
       "      <td>0.451243</td>\n",
       "      <td>0.479894</td>\n",
       "      <td>0.488244</td>\n",
       "      <td>0.623069</td>\n",
       "      <td>0.389404</td>\n",
       "      <td>0.420505</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.435687</td>\n",
       "      <td>0.445132</td>\n",
       "      <td>0.399602</td>\n",
       "      <td>0.705705</td>\n",
       "      <td>0.527921</td>\n",
       "      <td>0.495640</td>\n",
       "      <td>0.471812</td>\n",
       "      <td>0.1875</td>\n",
       "      <td>0.1250</td>\n",
       "      <td>0.0625</td>\n",
       "      <td>...</td>\n",
       "      <td>0.402835</td>\n",
       "      <td>0.394961</td>\n",
       "      <td>0.535664</td>\n",
       "      <td>0.433754</td>\n",
       "      <td>0.558210</td>\n",
       "      <td>0.417139</td>\n",
       "      <td>0.503130</td>\n",
       "      <td>0.585764</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.557247</td>\n",
       "      <td>0.487364</td>\n",
       "      <td>0.414154</td>\n",
       "      <td>0.372170</td>\n",
       "      <td>0.537910</td>\n",
       "      <td>0.557831</td>\n",
       "      <td>0.543209</td>\n",
       "      <td>0.1875</td>\n",
       "      <td>0.1875</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.521833</td>\n",
       "      <td>0.520206</td>\n",
       "      <td>0.342303</td>\n",
       "      <td>0.442832</td>\n",
       "      <td>0.576437</td>\n",
       "      <td>0.387200</td>\n",
       "      <td>0.686125</td>\n",
       "      <td>0.411717</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.5</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>699995</th>\n",
       "      <td>0.508459</td>\n",
       "      <td>0.597687</td>\n",
       "      <td>0.428825</td>\n",
       "      <td>0.650984</td>\n",
       "      <td>0.480147</td>\n",
       "      <td>0.447976</td>\n",
       "      <td>0.556443</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.0625</td>\n",
       "      <td>0.3750</td>\n",
       "      <td>...</td>\n",
       "      <td>0.399095</td>\n",
       "      <td>0.573163</td>\n",
       "      <td>0.559385</td>\n",
       "      <td>0.522206</td>\n",
       "      <td>0.539958</td>\n",
       "      <td>0.537416</td>\n",
       "      <td>0.528300</td>\n",
       "      <td>0.583064</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699996</th>\n",
       "      <td>0.428624</td>\n",
       "      <td>0.501875</td>\n",
       "      <td>0.471036</td>\n",
       "      <td>0.548564</td>\n",
       "      <td>0.708996</td>\n",
       "      <td>0.564608</td>\n",
       "      <td>0.495599</td>\n",
       "      <td>0.2500</td>\n",
       "      <td>0.1875</td>\n",
       "      <td>0.2500</td>\n",
       "      <td>...</td>\n",
       "      <td>0.484681</td>\n",
       "      <td>0.588499</td>\n",
       "      <td>0.570671</td>\n",
       "      <td>0.454834</td>\n",
       "      <td>0.611729</td>\n",
       "      <td>0.456661</td>\n",
       "      <td>0.607262</td>\n",
       "      <td>0.460314</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699997</th>\n",
       "      <td>0.415195</td>\n",
       "      <td>0.471727</td>\n",
       "      <td>0.359948</td>\n",
       "      <td>0.594321</td>\n",
       "      <td>0.439846</td>\n",
       "      <td>0.497784</td>\n",
       "      <td>0.400869</td>\n",
       "      <td>0.0625</td>\n",
       "      <td>0.0625</td>\n",
       "      <td>0.1250</td>\n",
       "      <td>...</td>\n",
       "      <td>0.454633</td>\n",
       "      <td>0.624205</td>\n",
       "      <td>0.431435</td>\n",
       "      <td>0.545747</td>\n",
       "      <td>0.375756</td>\n",
       "      <td>0.326091</td>\n",
       "      <td>0.442861</td>\n",
       "      <td>0.553152</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699998</th>\n",
       "      <td>0.252107</td>\n",
       "      <td>0.378328</td>\n",
       "      <td>0.583818</td>\n",
       "      <td>0.377965</td>\n",
       "      <td>0.583096</td>\n",
       "      <td>0.571099</td>\n",
       "      <td>0.427852</td>\n",
       "      <td>0.3125</td>\n",
       "      <td>0.0625</td>\n",
       "      <td>0.0625</td>\n",
       "      <td>...</td>\n",
       "      <td>0.359734</td>\n",
       "      <td>0.531738</td>\n",
       "      <td>0.437844</td>\n",
       "      <td>0.542610</td>\n",
       "      <td>0.570083</td>\n",
       "      <td>0.501499</td>\n",
       "      <td>0.403001</td>\n",
       "      <td>0.351776</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699999</th>\n",
       "      <td>0.438784</td>\n",
       "      <td>0.505277</td>\n",
       "      <td>0.715283</td>\n",
       "      <td>0.510106</td>\n",
       "      <td>0.817496</td>\n",
       "      <td>0.344219</td>\n",
       "      <td>0.593333</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.1875</td>\n",
       "      <td>0.2500</td>\n",
       "      <td>...</td>\n",
       "      <td>0.401587</td>\n",
       "      <td>0.351553</td>\n",
       "      <td>0.324525</td>\n",
       "      <td>0.296717</td>\n",
       "      <td>0.498991</td>\n",
       "      <td>0.389938</td>\n",
       "      <td>0.512189</td>\n",
       "      <td>0.436843</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1600000 rows × 30 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            f_00      f_01      f_02      f_03      f_04      f_05      f_06  \\\n",
       "0       0.315238  0.530025  0.458038  0.546749  0.422871  0.591372  0.512752   \n",
       "1       0.609890  0.329868  0.251164  0.430304  0.604453  0.354899  0.547380   \n",
       "2       0.608423  0.568826  0.376379  0.572180  0.426854  0.519648  0.427730   \n",
       "3       0.435687  0.445132  0.399602  0.705705  0.527921  0.495640  0.471812   \n",
       "4       0.557247  0.487364  0.414154  0.372170  0.537910  0.557831  0.543209   \n",
       "...          ...       ...       ...       ...       ...       ...       ...   \n",
       "699995  0.508459  0.597687  0.428825  0.650984  0.480147  0.447976  0.556443   \n",
       "699996  0.428624  0.501875  0.471036  0.548564  0.708996  0.564608  0.495599   \n",
       "699997  0.415195  0.471727  0.359948  0.594321  0.439846  0.497784  0.400869   \n",
       "699998  0.252107  0.378328  0.583818  0.377965  0.583096  0.571099  0.427852   \n",
       "699999  0.438784  0.505277  0.715283  0.510106  0.817496  0.344219  0.593333   \n",
       "\n",
       "          f_07    f_08    f_09  ...      f_20      f_21      f_22      f_23  \\\n",
       "0       0.0625  0.3125  0.0625  ...  0.454761  0.589532  0.401455  0.532343   \n",
       "1       0.0625  0.1875  0.2500  ...  0.447912  0.557856  0.609194  0.475287   \n",
       "2       0.0625  0.0000  0.1250  ...  0.341903  0.451131  0.451243  0.479894   \n",
       "3       0.1875  0.1250  0.0625  ...  0.402835  0.394961  0.535664  0.433754   \n",
       "4       0.1875  0.1875  0.0000  ...  0.521833  0.520206  0.342303  0.442832   \n",
       "...        ...     ...     ...  ...       ...       ...       ...       ...   \n",
       "699995  0.0000  0.0625  0.3750  ...  0.399095  0.573163  0.559385  0.522206   \n",
       "699996  0.2500  0.1875  0.2500  ...  0.484681  0.588499  0.570671  0.454834   \n",
       "699997  0.0625  0.0625  0.1250  ...  0.454633  0.624205  0.431435  0.545747   \n",
       "699998  0.3125  0.0625  0.0625  ...  0.359734  0.531738  0.437844  0.542610   \n",
       "699999  0.0000  0.1875  0.2500  ...  0.401587  0.351553  0.324525  0.296717   \n",
       "\n",
       "            f_24      f_25      f_26      f_28  f_29  f_30  \n",
       "0       0.375916  0.507106  0.575593  0.527530   0.0   0.0  \n",
       "1       0.438386  0.368803  0.523351  0.653373   0.0   0.0  \n",
       "2       0.488244  0.623069  0.389404  0.420505   0.0   1.0  \n",
       "3       0.558210  0.417139  0.503130  0.585764   0.0   0.0  \n",
       "4       0.576437  0.387200  0.686125  0.411717   0.0   0.5  \n",
       "...          ...       ...       ...       ...   ...   ...  \n",
       "699995  0.539958  0.537416  0.528300  0.583064   0.0   0.0  \n",
       "699996  0.611729  0.456661  0.607262  0.460314   0.0   1.0  \n",
       "699997  0.375756  0.326091  0.442861  0.553152   1.0   0.0  \n",
       "699998  0.570083  0.501499  0.403001  0.351776   0.0   0.0  \n",
       "699999  0.498991  0.389938  0.512189  0.436843   0.0   0.5  \n",
       "\n",
       "[1600000 rows x 30 columns]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "combi = (combi - combi.min()) / (combi.max() - combi.min())\n",
    "combi"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3d80cfe3",
   "metadata": {
    "papermill": {
     "duration": 0.042442,
     "end_time": "2022-05-11T11:03:35.610293",
     "exception": false,
     "start_time": "2022-05-11T11:03:35.567851",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Define X and y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "4d4770db",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:35.697945Z",
     "iopub.status.busy": "2022-05-11T11:03:35.697596Z",
     "iopub.status.idle": "2022-05-11T11:03:35.702099Z",
     "shell.execute_reply": "2022-05-11T11:03:35.701135Z"
    },
    "papermill": {
     "duration": 0.051241,
     "end_time": "2022-05-11T11:03:35.704229",
     "exception": false,
     "start_time": "2022-05-11T11:03:35.652988",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "y = target\n",
    "X = combi[: len(train)]\n",
    "X_test = combi[len(train) :]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5d8bb6c5",
   "metadata": {
    "papermill": {
     "duration": 0.043146,
     "end_time": "2022-05-11T11:03:35.790146",
     "exception": false,
     "start_time": "2022-05-11T11:03:35.747000",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Split dataset for training and validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "3bb874fb",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:35.878461Z",
     "iopub.status.busy": "2022-05-11T11:03:35.878177Z",
     "iopub.status.idle": "2022-05-11T11:03:36.552140Z",
     "shell.execute_reply": "2022-05-11T11:03:36.551242Z"
    },
    "papermill": {
     "duration": 0.721353,
     "end_time": "2022-05-11T11:03:36.554347",
     "exception": false,
     "start_time": "2022-05-11T11:03:35.832994",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((810000, 30), (90000, 30), (810000,), (90000,), (700000, 30))"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.1, random_state=42)\n",
    "X_train.shape, X_val.shape, y_train.shape,y_val.shape, X_test.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "383f9ee5",
   "metadata": {
    "papermill": {
     "duration": 0.04255,
     "end_time": "2022-05-11T11:03:36.640114",
     "exception": false,
     "start_time": "2022-05-11T11:03:36.597564",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Select model - Logistic Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "b1d9af4e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:36.727674Z",
     "iopub.status.busy": "2022-05-11T11:03:36.727395Z",
     "iopub.status.idle": "2022-05-11T11:03:45.348105Z",
     "shell.execute_reply": "2022-05-11T11:03:45.346914Z"
    },
    "papermill": {
     "duration": 8.667486,
     "end_time": "2022-05-11T11:03:45.350488",
     "exception": false,
     "start_time": "2022-05-11T11:03:36.683002",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.614883950617284\n"
     ]
    }
   ],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "model = LogisticRegression(random_state=42).fit(X_train, y_train)\n",
    "print(model.score(X_train, y_train))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ea710141",
   "metadata": {
    "papermill": {
     "duration": 0.043577,
     "end_time": "2022-05-11T11:03:45.437486",
     "exception": false,
     "start_time": "2022-05-11T11:03:45.393909",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Predict on validation set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "110776e9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:45.528247Z",
     "iopub.status.busy": "2022-05-11T11:03:45.527682Z",
     "iopub.status.idle": "2022-05-11T11:03:45.563979Z",
     "shell.execute_reply": "2022-05-11T11:03:45.563197Z"
    },
    "papermill": {
     "duration": 0.084883,
     "end_time": "2022-05-11T11:03:45.567687",
     "exception": false,
     "start_time": "2022-05-11T11:03:45.482804",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.6136444444444444\n"
     ]
    }
   ],
   "source": [
    "y_pred = model.predict(X_val)\n",
    "print(model.score(X_val, y_val))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4d6493b1",
   "metadata": {
    "papermill": {
     "duration": 0.050645,
     "end_time": "2022-05-11T11:03:45.700862",
     "exception": false,
     "start_time": "2022-05-11T11:03:45.650217",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Confusion matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "3e1a7d9c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:45.790395Z",
     "iopub.status.busy": "2022-05-11T11:03:45.790092Z",
     "iopub.status.idle": "2022-05-11T11:03:45.815750Z",
     "shell.execute_reply": "2022-05-11T11:03:45.815037Z"
    },
    "papermill": {
     "duration": 0.073088,
     "end_time": "2022-05-11T11:03:45.817848",
     "exception": false,
     "start_time": "2022-05-11T11:03:45.744760",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[30030 16191]\n",
      " [18581 25198]]\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import confusion_matrix\n",
    "\n",
    "print(confusion_matrix(y_val, y_pred))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "98219d25",
   "metadata": {
    "papermill": {
     "duration": 0.043722,
     "end_time": "2022-05-11T11:03:45.906025",
     "exception": false,
     "start_time": "2022-05-11T11:03:45.862303",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Predict on test set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "e3af5809",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:45.998329Z",
     "iopub.status.busy": "2022-05-11T11:03:45.997865Z",
     "iopub.status.idle": "2022-05-11T11:03:46.178067Z",
     "shell.execute_reply": "2022-05-11T11:03:46.176967Z"
    },
    "papermill": {
     "duration": 0.230467,
     "end_time": "2022-05-11T11:03:46.181754",
     "exception": false,
     "start_time": "2022-05-11T11:03:45.951287",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 1, 0, ..., 1, 0, 0])"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "preds = model.predict(X_test)\n",
    "preds = preds.astype(int)\n",
    "preds[preds < 0] = 0\n",
    "preds"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "542f7a58",
   "metadata": {
    "papermill": {
     "duration": 0.051137,
     "end_time": "2022-05-11T11:03:46.316333",
     "exception": false,
     "start_time": "2022-05-11T11:03:46.265196",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Submit"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "d9c151cc",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-05-11T11:03:46.407139Z",
     "iopub.status.busy": "2022-05-11T11:03:46.406885Z",
     "iopub.status.idle": "2022-05-11T11:03:47.731695Z",
     "shell.execute_reply": "2022-05-11T11:03:47.730883Z"
    },
    "papermill": {
     "duration": 1.372749,
     "end_time": "2022-05-11T11:03:47.733818",
     "exception": false,
     "start_time": "2022-05-11T11:03:46.361069",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>900000</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>900001</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>900002</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>900003</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>900004</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699995</th>\n",
       "      <td>1599995</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699996</th>\n",
       "      <td>1599996</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699997</th>\n",
       "      <td>1599997</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699998</th>\n",
       "      <td>1599998</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>699999</th>\n",
       "      <td>1599999</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>700000 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "             id  target\n",
       "0        900000       0\n",
       "1        900001       1\n",
       "2        900002       0\n",
       "3        900003       0\n",
       "4        900004       1\n",
       "...         ...     ...\n",
       "699995  1599995       1\n",
       "699996  1599996       1\n",
       "699997  1599997       1\n",
       "699998  1599998       0\n",
       "699999  1599999       0\n",
       "\n",
       "[700000 rows x 2 columns]"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "submission.target = preds\n",
    "submission.to_csv('submission.csv', index=False)\n",
    "submission = pd.read_csv(\"submission.csv\")\n",
    "submission"
   ]
  }
 ],
 "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": "3.12.1"
  },
  "papermill": {
   "default_parameters": {},
   "duration": 54.233478,
   "end_time": "2022-05-11T11:03:48.600102",
   "environment_variables": {},
   "exception": null,
   "input_path": "__notebook__.ipynb",
   "output_path": "__notebook__.ipynb",
   "parameters": {},
   "start_time": "2022-05-11T11:02:54.366624",
   "version": "2.3.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}