Complete Feature Selection.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "13550d20",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.neural_network import MLPClassifier\n",
    "from sklearn.feature_selection import VarianceThreshold\n",
    "from sklearn.feature_selection import f_classif\n",
    "from sklearn.feature_selection import chi2\n",
    "from sklearn.feature_selection import SelectKBest\n",
    "from sklearn.feature_selection import SequentialFeatureSelector\n",
    "from mlxtend.feature_selection import ExhaustiveFeatureSelector as EFS\n",
    "from sklearn.feature_selection import RFE\n",
    "from sklearn.linear_model import Lasso\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.feature_selection import SelectFromModel\n",
    "from sklearn.metrics import accuracy_score\n",
    "\n",
    "import warnings\n",
    "warnings.filterwarnings ('ignore')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "fa94a184",
   "metadata": {},
   "outputs": [],
   "source": [
    "data= pd.read_csv('F:\\IT Learning\\My Projects\\Data Science And ML Projects\\Human Activity Recognition with Smartphones\\Human Activity Reco. with smartphone data.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "28259b90",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>tBodyAcc-mean()-X</th>\n",
       "      <th>tBodyAcc-mean()-Y</th>\n",
       "      <th>tBodyAcc-mean()-Z</th>\n",
       "      <th>tBodyAcc-std()-X</th>\n",
       "      <th>tBodyAcc-std()-Y</th>\n",
       "      <th>tBodyAcc-std()-Z</th>\n",
       "      <th>tBodyAcc-mad()-X</th>\n",
       "      <th>tBodyAcc-mad()-Y</th>\n",
       "      <th>tBodyAcc-mad()-Z</th>\n",
       "      <th>tBodyAcc-max()-X</th>\n",
       "      <th>...</th>\n",
       "      <th>fBodyBodyGyroJerkMag-kurtosis()</th>\n",
       "      <th>angle(tBodyAccMean,gravity)</th>\n",
       "      <th>angle(tBodyAccJerkMean),gravityMean)</th>\n",
       "      <th>angle(tBodyGyroMean,gravityMean)</th>\n",
       "      <th>angle(tBodyGyroJerkMean,gravityMean)</th>\n",
       "      <th>angle(X,gravityMean)</th>\n",
       "      <th>angle(Y,gravityMean)</th>\n",
       "      <th>angle(Z,gravityMean)</th>\n",
       "      <th>subject</th>\n",
       "      <th>Activity</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.288585</td>\n",
       "      <td>-0.020294</td>\n",
       "      <td>-0.132905</td>\n",
       "      <td>-0.995279</td>\n",
       "      <td>-0.983111</td>\n",
       "      <td>-0.913526</td>\n",
       "      <td>-0.995112</td>\n",
       "      <td>-0.983185</td>\n",
       "      <td>-0.923527</td>\n",
       "      <td>-0.934724</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.710304</td>\n",
       "      <td>-0.112754</td>\n",
       "      <td>0.030400</td>\n",
       "      <td>-0.464761</td>\n",
       "      <td>-0.018446</td>\n",
       "      <td>-0.841247</td>\n",
       "      <td>0.179941</td>\n",
       "      <td>-0.058627</td>\n",
       "      <td>1</td>\n",
       "      <td>STANDING</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.278419</td>\n",
       "      <td>-0.016411</td>\n",
       "      <td>-0.123520</td>\n",
       "      <td>-0.998245</td>\n",
       "      <td>-0.975300</td>\n",
       "      <td>-0.960322</td>\n",
       "      <td>-0.998807</td>\n",
       "      <td>-0.974914</td>\n",
       "      <td>-0.957686</td>\n",
       "      <td>-0.943068</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.861499</td>\n",
       "      <td>0.053477</td>\n",
       "      <td>-0.007435</td>\n",
       "      <td>-0.732626</td>\n",
       "      <td>0.703511</td>\n",
       "      <td>-0.844788</td>\n",
       "      <td>0.180289</td>\n",
       "      <td>-0.054317</td>\n",
       "      <td>1</td>\n",
       "      <td>STANDING</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.279653</td>\n",
       "      <td>-0.019467</td>\n",
       "      <td>-0.113462</td>\n",
       "      <td>-0.995380</td>\n",
       "      <td>-0.967187</td>\n",
       "      <td>-0.978944</td>\n",
       "      <td>-0.996520</td>\n",
       "      <td>-0.963668</td>\n",
       "      <td>-0.977469</td>\n",
       "      <td>-0.938692</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.760104</td>\n",
       "      <td>-0.118559</td>\n",
       "      <td>0.177899</td>\n",
       "      <td>0.100699</td>\n",
       "      <td>0.808529</td>\n",
       "      <td>-0.848933</td>\n",
       "      <td>0.180637</td>\n",
       "      <td>-0.049118</td>\n",
       "      <td>1</td>\n",
       "      <td>STANDING</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.279174</td>\n",
       "      <td>-0.026201</td>\n",
       "      <td>-0.123283</td>\n",
       "      <td>-0.996091</td>\n",
       "      <td>-0.983403</td>\n",
       "      <td>-0.990675</td>\n",
       "      <td>-0.997099</td>\n",
       "      <td>-0.982750</td>\n",
       "      <td>-0.989302</td>\n",
       "      <td>-0.938692</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.482845</td>\n",
       "      <td>-0.036788</td>\n",
       "      <td>-0.012892</td>\n",
       "      <td>0.640011</td>\n",
       "      <td>-0.485366</td>\n",
       "      <td>-0.848649</td>\n",
       "      <td>0.181935</td>\n",
       "      <td>-0.047663</td>\n",
       "      <td>1</td>\n",
       "      <td>STANDING</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.276629</td>\n",
       "      <td>-0.016570</td>\n",
       "      <td>-0.115362</td>\n",
       "      <td>-0.998139</td>\n",
       "      <td>-0.980817</td>\n",
       "      <td>-0.990482</td>\n",
       "      <td>-0.998321</td>\n",
       "      <td>-0.979672</td>\n",
       "      <td>-0.990441</td>\n",
       "      <td>-0.942469</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.699205</td>\n",
       "      <td>0.123320</td>\n",
       "      <td>0.122542</td>\n",
       "      <td>0.693578</td>\n",
       "      <td>-0.615971</td>\n",
       "      <td>-0.847865</td>\n",
       "      <td>0.185151</td>\n",
       "      <td>-0.043892</td>\n",
       "      <td>1</td>\n",
       "      <td>STANDING</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>7347</th>\n",
       "      <td>0.299665</td>\n",
       "      <td>-0.057193</td>\n",
       "      <td>-0.181233</td>\n",
       "      <td>-0.195387</td>\n",
       "      <td>0.039905</td>\n",
       "      <td>0.077078</td>\n",
       "      <td>-0.282301</td>\n",
       "      <td>0.043616</td>\n",
       "      <td>0.060410</td>\n",
       "      <td>0.210795</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.880324</td>\n",
       "      <td>-0.190437</td>\n",
       "      <td>0.829718</td>\n",
       "      <td>0.206972</td>\n",
       "      <td>-0.425619</td>\n",
       "      <td>-0.791883</td>\n",
       "      <td>0.238604</td>\n",
       "      <td>0.049819</td>\n",
       "      <td>30</td>\n",
       "      <td>WALKING_UPSTAIRS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7348</th>\n",
       "      <td>0.273853</td>\n",
       "      <td>-0.007749</td>\n",
       "      <td>-0.147468</td>\n",
       "      <td>-0.235309</td>\n",
       "      <td>0.004816</td>\n",
       "      <td>0.059280</td>\n",
       "      <td>-0.322552</td>\n",
       "      <td>-0.029456</td>\n",
       "      <td>0.080585</td>\n",
       "      <td>0.117440</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.680744</td>\n",
       "      <td>0.064907</td>\n",
       "      <td>0.875679</td>\n",
       "      <td>-0.879033</td>\n",
       "      <td>0.400219</td>\n",
       "      <td>-0.771840</td>\n",
       "      <td>0.252676</td>\n",
       "      <td>0.050053</td>\n",
       "      <td>30</td>\n",
       "      <td>WALKING_UPSTAIRS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7349</th>\n",
       "      <td>0.273387</td>\n",
       "      <td>-0.017011</td>\n",
       "      <td>-0.045022</td>\n",
       "      <td>-0.218218</td>\n",
       "      <td>-0.103822</td>\n",
       "      <td>0.274533</td>\n",
       "      <td>-0.304515</td>\n",
       "      <td>-0.098913</td>\n",
       "      <td>0.332584</td>\n",
       "      <td>0.043999</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.304029</td>\n",
       "      <td>0.052806</td>\n",
       "      <td>-0.266724</td>\n",
       "      <td>0.864404</td>\n",
       "      <td>0.701169</td>\n",
       "      <td>-0.779133</td>\n",
       "      <td>0.249145</td>\n",
       "      <td>0.040811</td>\n",
       "      <td>30</td>\n",
       "      <td>WALKING_UPSTAIRS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7350</th>\n",
       "      <td>0.289654</td>\n",
       "      <td>-0.018843</td>\n",
       "      <td>-0.158281</td>\n",
       "      <td>-0.219139</td>\n",
       "      <td>-0.111412</td>\n",
       "      <td>0.268893</td>\n",
       "      <td>-0.310487</td>\n",
       "      <td>-0.068200</td>\n",
       "      <td>0.319473</td>\n",
       "      <td>0.101702</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.344314</td>\n",
       "      <td>-0.101360</td>\n",
       "      <td>0.700740</td>\n",
       "      <td>0.936674</td>\n",
       "      <td>-0.589479</td>\n",
       "      <td>-0.785181</td>\n",
       "      <td>0.246432</td>\n",
       "      <td>0.025339</td>\n",
       "      <td>30</td>\n",
       "      <td>WALKING_UPSTAIRS</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7351</th>\n",
       "      <td>0.351503</td>\n",
       "      <td>-0.012423</td>\n",
       "      <td>-0.203867</td>\n",
       "      <td>-0.269270</td>\n",
       "      <td>-0.087212</td>\n",
       "      <td>0.177404</td>\n",
       "      <td>-0.377404</td>\n",
       "      <td>-0.038678</td>\n",
       "      <td>0.229430</td>\n",
       "      <td>0.269013</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.740738</td>\n",
       "      <td>-0.280088</td>\n",
       "      <td>-0.007739</td>\n",
       "      <td>-0.056088</td>\n",
       "      <td>-0.616956</td>\n",
       "      <td>-0.783267</td>\n",
       "      <td>0.246809</td>\n",
       "      <td>0.036695</td>\n",
       "      <td>30</td>\n",
       "      <td>WALKING_UPSTAIRS</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>7352 rows × 563 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      tBodyAcc-mean()-X  tBodyAcc-mean()-Y  tBodyAcc-mean()-Z  \\\n",
       "0              0.288585          -0.020294          -0.132905   \n",
       "1              0.278419          -0.016411          -0.123520   \n",
       "2              0.279653          -0.019467          -0.113462   \n",
       "3              0.279174          -0.026201          -0.123283   \n",
       "4              0.276629          -0.016570          -0.115362   \n",
       "...                 ...                ...                ...   \n",
       "7347           0.299665          -0.057193          -0.181233   \n",
       "7348           0.273853          -0.007749          -0.147468   \n",
       "7349           0.273387          -0.017011          -0.045022   \n",
       "7350           0.289654          -0.018843          -0.158281   \n",
       "7351           0.351503          -0.012423          -0.203867   \n",
       "\n",
       "      tBodyAcc-std()-X  tBodyAcc-std()-Y  tBodyAcc-std()-Z  tBodyAcc-mad()-X  \\\n",
       "0            -0.995279         -0.983111         -0.913526         -0.995112   \n",
       "1            -0.998245         -0.975300         -0.960322         -0.998807   \n",
       "2            -0.995380         -0.967187         -0.978944         -0.996520   \n",
       "3            -0.996091         -0.983403         -0.990675         -0.997099   \n",
       "4            -0.998139         -0.980817         -0.990482         -0.998321   \n",
       "...                ...               ...               ...               ...   \n",
       "7347         -0.195387          0.039905          0.077078         -0.282301   \n",
       "7348         -0.235309          0.004816          0.059280         -0.322552   \n",
       "7349         -0.218218         -0.103822          0.274533         -0.304515   \n",
       "7350         -0.219139         -0.111412          0.268893         -0.310487   \n",
       "7351         -0.269270         -0.087212          0.177404         -0.377404   \n",
       "\n",
       "      tBodyAcc-mad()-Y  tBodyAcc-mad()-Z  tBodyAcc-max()-X  ...  \\\n",
       "0            -0.983185         -0.923527         -0.934724  ...   \n",
       "1            -0.974914         -0.957686         -0.943068  ...   \n",
       "2            -0.963668         -0.977469         -0.938692  ...   \n",
       "3            -0.982750         -0.989302         -0.938692  ...   \n",
       "4            -0.979672         -0.990441         -0.942469  ...   \n",
       "...                ...               ...               ...  ...   \n",
       "7347          0.043616          0.060410          0.210795  ...   \n",
       "7348         -0.029456          0.080585          0.117440  ...   \n",
       "7349         -0.098913          0.332584          0.043999  ...   \n",
       "7350         -0.068200          0.319473          0.101702  ...   \n",
       "7351         -0.038678          0.229430          0.269013  ...   \n",
       "\n",
       "      fBodyBodyGyroJerkMag-kurtosis()  angle(tBodyAccMean,gravity)  \\\n",
       "0                           -0.710304                    -0.112754   \n",
       "1                           -0.861499                     0.053477   \n",
       "2                           -0.760104                    -0.118559   \n",
       "3                           -0.482845                    -0.036788   \n",
       "4                           -0.699205                     0.123320   \n",
       "...                               ...                          ...   \n",
       "7347                        -0.880324                    -0.190437   \n",
       "7348                        -0.680744                     0.064907   \n",
       "7349                        -0.304029                     0.052806   \n",
       "7350                        -0.344314                    -0.101360   \n",
       "7351                        -0.740738                    -0.280088   \n",
       "\n",
       "      angle(tBodyAccJerkMean),gravityMean)  angle(tBodyGyroMean,gravityMean)  \\\n",
       "0                                 0.030400                         -0.464761   \n",
       "1                                -0.007435                         -0.732626   \n",
       "2                                 0.177899                          0.100699   \n",
       "3                                -0.012892                          0.640011   \n",
       "4                                 0.122542                          0.693578   \n",
       "...                                    ...                               ...   \n",
       "7347                              0.829718                          0.206972   \n",
       "7348                              0.875679                         -0.879033   \n",
       "7349                             -0.266724                          0.864404   \n",
       "7350                              0.700740                          0.936674   \n",
       "7351                             -0.007739                         -0.056088   \n",
       "\n",
       "      angle(tBodyGyroJerkMean,gravityMean)  angle(X,gravityMean)  \\\n",
       "0                                -0.018446             -0.841247   \n",
       "1                                 0.703511             -0.844788   \n",
       "2                                 0.808529             -0.848933   \n",
       "3                                -0.485366             -0.848649   \n",
       "4                                -0.615971             -0.847865   \n",
       "...                                    ...                   ...   \n",
       "7347                             -0.425619             -0.791883   \n",
       "7348                              0.400219             -0.771840   \n",
       "7349                              0.701169             -0.779133   \n",
       "7350                             -0.589479             -0.785181   \n",
       "7351                             -0.616956             -0.783267   \n",
       "\n",
       "      angle(Y,gravityMean)  angle(Z,gravityMean)  subject          Activity  \n",
       "0                 0.179941             -0.058627        1          STANDING  \n",
       "1                 0.180289             -0.054317        1          STANDING  \n",
       "2                 0.180637             -0.049118        1          STANDING  \n",
       "3                 0.181935             -0.047663        1          STANDING  \n",
       "4                 0.185151             -0.043892        1          STANDING  \n",
       "...                    ...                   ...      ...               ...  \n",
       "7347              0.238604              0.049819       30  WALKING_UPSTAIRS  \n",
       "7348              0.252676              0.050053       30  WALKING_UPSTAIRS  \n",
       "7349              0.249145              0.040811       30  WALKING_UPSTAIRS  \n",
       "7350              0.246432              0.025339       30  WALKING_UPSTAIRS  \n",
       "7351              0.246809              0.036695       30  WALKING_UPSTAIRS  \n",
       "\n",
       "[7352 rows x 563 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "6cf84a9c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(7352, 563)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "6dc4a67f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>tBodyAcc-mean()-X</th>\n",
       "      <th>tBodyAcc-mean()-Y</th>\n",
       "      <th>tBodyAcc-mean()-Z</th>\n",
       "      <th>tBodyAcc-std()-X</th>\n",
       "      <th>tBodyAcc-std()-Y</th>\n",
       "      <th>tBodyAcc-std()-Z</th>\n",
       "      <th>tBodyAcc-mad()-X</th>\n",
       "      <th>tBodyAcc-mad()-Y</th>\n",
       "      <th>tBodyAcc-mad()-Z</th>\n",
       "      <th>tBodyAcc-max()-X</th>\n",
       "      <th>...</th>\n",
       "      <th>fBodyBodyGyroJerkMag-skewness()</th>\n",
       "      <th>fBodyBodyGyroJerkMag-kurtosis()</th>\n",
       "      <th>angle(tBodyAccMean,gravity)</th>\n",
       "      <th>angle(tBodyAccJerkMean),gravityMean)</th>\n",
       "      <th>angle(tBodyGyroMean,gravityMean)</th>\n",
       "      <th>angle(tBodyGyroJerkMean,gravityMean)</th>\n",
       "      <th>angle(X,gravityMean)</th>\n",
       "      <th>angle(Y,gravityMean)</th>\n",
       "      <th>angle(Z,gravityMean)</th>\n",
       "      <th>subject</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>7352.000000</td>\n",
       "      <td>7352.000000</td>\n",
       "      <td>7352.000000</td>\n",
       "      <td>7352.000000</td>\n",
       "      <td>7352.000000</td>\n",
       "      <td>7352.000000</td>\n",
       "      <td>7352.000000</td>\n",
       "      <td>7352.000000</td>\n",
       "      <td>7352.000000</td>\n",
       "      <td>7352.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>7352.000000</td>\n",
       "      <td>7352.000000</td>\n",
       "      <td>7352.000000</td>\n",
       "      <td>7352.000000</td>\n",
       "      <td>7352.000000</td>\n",
       "      <td>7352.000000</td>\n",
       "      <td>7352.000000</td>\n",
       "      <td>7352.000000</td>\n",
       "      <td>7352.000000</td>\n",
       "      <td>7352.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.274488</td>\n",
       "      <td>-0.017695</td>\n",
       "      <td>-0.109141</td>\n",
       "      <td>-0.605438</td>\n",
       "      <td>-0.510938</td>\n",
       "      <td>-0.604754</td>\n",
       "      <td>-0.630512</td>\n",
       "      <td>-0.526907</td>\n",
       "      <td>-0.606150</td>\n",
       "      <td>-0.468604</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.307009</td>\n",
       "      <td>-0.625294</td>\n",
       "      <td>0.008684</td>\n",
       "      <td>0.002186</td>\n",
       "      <td>0.008726</td>\n",
       "      <td>-0.005981</td>\n",
       "      <td>-0.489547</td>\n",
       "      <td>0.058593</td>\n",
       "      <td>-0.056515</td>\n",
       "      <td>17.413085</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.070261</td>\n",
       "      <td>0.040811</td>\n",
       "      <td>0.056635</td>\n",
       "      <td>0.448734</td>\n",
       "      <td>0.502645</td>\n",
       "      <td>0.418687</td>\n",
       "      <td>0.424073</td>\n",
       "      <td>0.485942</td>\n",
       "      <td>0.414122</td>\n",
       "      <td>0.544547</td>\n",
       "      <td>...</td>\n",
       "      <td>0.321011</td>\n",
       "      <td>0.307584</td>\n",
       "      <td>0.336787</td>\n",
       "      <td>0.448306</td>\n",
       "      <td>0.608303</td>\n",
       "      <td>0.477975</td>\n",
       "      <td>0.511807</td>\n",
       "      <td>0.297480</td>\n",
       "      <td>0.279122</td>\n",
       "      <td>8.975143</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-0.999873</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.995357</td>\n",
       "      <td>-0.999765</td>\n",
       "      <td>-0.976580</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.262975</td>\n",
       "      <td>-0.024863</td>\n",
       "      <td>-0.120993</td>\n",
       "      <td>-0.992754</td>\n",
       "      <td>-0.978129</td>\n",
       "      <td>-0.980233</td>\n",
       "      <td>-0.993591</td>\n",
       "      <td>-0.978162</td>\n",
       "      <td>-0.980251</td>\n",
       "      <td>-0.936219</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.542602</td>\n",
       "      <td>-0.845573</td>\n",
       "      <td>-0.121527</td>\n",
       "      <td>-0.289549</td>\n",
       "      <td>-0.482273</td>\n",
       "      <td>-0.376341</td>\n",
       "      <td>-0.812065</td>\n",
       "      <td>-0.017885</td>\n",
       "      <td>-0.143414</td>\n",
       "      <td>8.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.277193</td>\n",
       "      <td>-0.017219</td>\n",
       "      <td>-0.108676</td>\n",
       "      <td>-0.946196</td>\n",
       "      <td>-0.851897</td>\n",
       "      <td>-0.859365</td>\n",
       "      <td>-0.950709</td>\n",
       "      <td>-0.857328</td>\n",
       "      <td>-0.857143</td>\n",
       "      <td>-0.881637</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.343685</td>\n",
       "      <td>-0.711692</td>\n",
       "      <td>0.009509</td>\n",
       "      <td>0.008943</td>\n",
       "      <td>0.008735</td>\n",
       "      <td>-0.000368</td>\n",
       "      <td>-0.709417</td>\n",
       "      <td>0.182071</td>\n",
       "      <td>0.003181</td>\n",
       "      <td>19.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>0.288461</td>\n",
       "      <td>-0.010783</td>\n",
       "      <td>-0.097794</td>\n",
       "      <td>-0.242813</td>\n",
       "      <td>-0.034231</td>\n",
       "      <td>-0.262415</td>\n",
       "      <td>-0.292680</td>\n",
       "      <td>-0.066701</td>\n",
       "      <td>-0.265671</td>\n",
       "      <td>-0.017129</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.126979</td>\n",
       "      <td>-0.503878</td>\n",
       "      <td>0.150865</td>\n",
       "      <td>0.292861</td>\n",
       "      <td>0.506187</td>\n",
       "      <td>0.359368</td>\n",
       "      <td>-0.509079</td>\n",
       "      <td>0.248353</td>\n",
       "      <td>0.107659</td>\n",
       "      <td>26.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.916238</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.967664</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.989538</td>\n",
       "      <td>0.956845</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.998702</td>\n",
       "      <td>0.996078</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.478157</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>30.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 562 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       tBodyAcc-mean()-X  tBodyAcc-mean()-Y  tBodyAcc-mean()-Z  \\\n",
       "count        7352.000000        7352.000000        7352.000000   \n",
       "mean            0.274488          -0.017695          -0.109141   \n",
       "std             0.070261           0.040811           0.056635   \n",
       "min            -1.000000          -1.000000          -1.000000   \n",
       "25%             0.262975          -0.024863          -0.120993   \n",
       "50%             0.277193          -0.017219          -0.108676   \n",
       "75%             0.288461          -0.010783          -0.097794   \n",
       "max             1.000000           1.000000           1.000000   \n",
       "\n",
       "       tBodyAcc-std()-X  tBodyAcc-std()-Y  tBodyAcc-std()-Z  tBodyAcc-mad()-X  \\\n",
       "count       7352.000000       7352.000000       7352.000000       7352.000000   \n",
       "mean          -0.605438         -0.510938         -0.604754         -0.630512   \n",
       "std            0.448734          0.502645          0.418687          0.424073   \n",
       "min           -1.000000         -0.999873         -1.000000         -1.000000   \n",
       "25%           -0.992754         -0.978129         -0.980233         -0.993591   \n",
       "50%           -0.946196         -0.851897         -0.859365         -0.950709   \n",
       "75%           -0.242813         -0.034231         -0.262415         -0.292680   \n",
       "max            1.000000          0.916238          1.000000          1.000000   \n",
       "\n",
       "       tBodyAcc-mad()-Y  tBodyAcc-mad()-Z  tBodyAcc-max()-X  ...  \\\n",
       "count       7352.000000       7352.000000       7352.000000  ...   \n",
       "mean          -0.526907         -0.606150         -0.468604  ...   \n",
       "std            0.485942          0.414122          0.544547  ...   \n",
       "min           -1.000000         -1.000000         -1.000000  ...   \n",
       "25%           -0.978162         -0.980251         -0.936219  ...   \n",
       "50%           -0.857328         -0.857143         -0.881637  ...   \n",
       "75%           -0.066701         -0.265671         -0.017129  ...   \n",
       "max            0.967664          1.000000          1.000000  ...   \n",
       "\n",
       "       fBodyBodyGyroJerkMag-skewness()  fBodyBodyGyroJerkMag-kurtosis()  \\\n",
       "count                      7352.000000                      7352.000000   \n",
       "mean                         -0.307009                        -0.625294   \n",
       "std                           0.321011                         0.307584   \n",
       "min                          -0.995357                        -0.999765   \n",
       "25%                          -0.542602                        -0.845573   \n",
       "50%                          -0.343685                        -0.711692   \n",
       "75%                          -0.126979                        -0.503878   \n",
       "max                           0.989538                         0.956845   \n",
       "\n",
       "       angle(tBodyAccMean,gravity)  angle(tBodyAccJerkMean),gravityMean)  \\\n",
       "count                  7352.000000                           7352.000000   \n",
       "mean                      0.008684                              0.002186   \n",
       "std                       0.336787                              0.448306   \n",
       "min                      -0.976580                             -1.000000   \n",
       "25%                      -0.121527                             -0.289549   \n",
       "50%                       0.009509                              0.008943   \n",
       "75%                       0.150865                              0.292861   \n",
       "max                       1.000000                              1.000000   \n",
       "\n",
       "       angle(tBodyGyroMean,gravityMean)  angle(tBodyGyroJerkMean,gravityMean)  \\\n",
       "count                       7352.000000                           7352.000000   \n",
       "mean                           0.008726                             -0.005981   \n",
       "std                            0.608303                              0.477975   \n",
       "min                           -1.000000                             -1.000000   \n",
       "25%                           -0.482273                             -0.376341   \n",
       "50%                            0.008735                             -0.000368   \n",
       "75%                            0.506187                              0.359368   \n",
       "max                            0.998702                              0.996078   \n",
       "\n",
       "       angle(X,gravityMean)  angle(Y,gravityMean)  angle(Z,gravityMean)  \\\n",
       "count           7352.000000           7352.000000           7352.000000   \n",
       "mean              -0.489547              0.058593             -0.056515   \n",
       "std                0.511807              0.297480              0.279122   \n",
       "min               -1.000000             -1.000000             -1.000000   \n",
       "25%               -0.812065             -0.017885             -0.143414   \n",
       "50%               -0.709417              0.182071              0.003181   \n",
       "75%               -0.509079              0.248353              0.107659   \n",
       "max                1.000000              0.478157              1.000000   \n",
       "\n",
       "           subject  \n",
       "count  7352.000000  \n",
       "mean     17.413085  \n",
       "std       8.975143  \n",
       "min       1.000000  \n",
       "25%       8.000000  \n",
       "50%      19.000000  \n",
       "75%      26.000000  \n",
       "max      30.000000  \n",
       "\n",
       "[8 rows x 562 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "c135b5a4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 7352 entries, 0 to 7351\n",
      "Columns: 563 entries, tBodyAcc-mean()-X to Activity\n",
      "dtypes: float64(561), int64(1), object(1)\n",
      "memory usage: 31.6+ MB\n"
     ]
    }
   ],
   "source": [
    "data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "931cf089",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['tBodyAcc-mean()-X',\n",
       " 'tBodyAcc-mean()-Y',\n",
       " 'tBodyAcc-mean()-Z',\n",
       " 'tBodyAcc-std()-X',\n",
       " 'tBodyAcc-std()-Y',\n",
       " 'tBodyAcc-std()-Z',\n",
       " 'tBodyAcc-mad()-X',\n",
       " 'tBodyAcc-mad()-Y',\n",
       " 'tBodyAcc-mad()-Z',\n",
       " 'tBodyAcc-max()-X',\n",
       " 'tBodyAcc-max()-Y',\n",
       " 'tBodyAcc-max()-Z',\n",
       " 'tBodyAcc-min()-X',\n",
       " 'tBodyAcc-min()-Y',\n",
       " 'tBodyAcc-min()-Z',\n",
       " 'tBodyAcc-sma()',\n",
       " 'tBodyAcc-energy()-X',\n",
       " 'tBodyAcc-energy()-Y',\n",
       " 'tBodyAcc-energy()-Z',\n",
       " 'tBodyAcc-iqr()-X',\n",
       " 'tBodyAcc-iqr()-Y',\n",
       " 'tBodyAcc-iqr()-Z',\n",
       " 'tBodyAcc-entropy()-X',\n",
       " 'tBodyAcc-entropy()-Y',\n",
       " 'tBodyAcc-entropy()-Z',\n",
       " 'tBodyAcc-arCoeff()-X,1',\n",
       " 'tBodyAcc-arCoeff()-X,2',\n",
       " 'tBodyAcc-arCoeff()-X,3',\n",
       " 'tBodyAcc-arCoeff()-X,4',\n",
       " 'tBodyAcc-arCoeff()-Y,1',\n",
       " 'tBodyAcc-arCoeff()-Y,2',\n",
       " 'tBodyAcc-arCoeff()-Y,3',\n",
       " 'tBodyAcc-arCoeff()-Y,4',\n",
       " 'tBodyAcc-arCoeff()-Z,1',\n",
       " 'tBodyAcc-arCoeff()-Z,2',\n",
       " 'tBodyAcc-arCoeff()-Z,3',\n",
       " 'tBodyAcc-arCoeff()-Z,4',\n",
       " 'tBodyAcc-correlation()-X,Y',\n",
       " 'tBodyAcc-correlation()-X,Z',\n",
       " 'tBodyAcc-correlation()-Y,Z',\n",
       " 'tGravityAcc-mean()-X',\n",
       " 'tGravityAcc-mean()-Y',\n",
       " 'tGravityAcc-mean()-Z',\n",
       " 'tGravityAcc-std()-X',\n",
       " 'tGravityAcc-std()-Y',\n",
       " 'tGravityAcc-std()-Z',\n",
       " 'tGravityAcc-mad()-X',\n",
       " 'tGravityAcc-mad()-Y',\n",
       " 'tGravityAcc-mad()-Z',\n",
       " 'tGravityAcc-max()-X',\n",
       " 'tGravityAcc-max()-Y',\n",
       " 'tGravityAcc-max()-Z',\n",
       " 'tGravityAcc-min()-X',\n",
       " 'tGravityAcc-min()-Y',\n",
       " 'tGravityAcc-min()-Z',\n",
       " 'tGravityAcc-sma()',\n",
       " 'tGravityAcc-energy()-X',\n",
       " 'tGravityAcc-energy()-Y',\n",
       " 'tGravityAcc-energy()-Z',\n",
       " 'tGravityAcc-iqr()-X',\n",
       " 'tGravityAcc-iqr()-Y',\n",
       " 'tGravityAcc-iqr()-Z',\n",
       " 'tGravityAcc-entropy()-X',\n",
       " 'tGravityAcc-entropy()-Y',\n",
       " 'tGravityAcc-entropy()-Z',\n",
       " 'tGravityAcc-arCoeff()-X,1',\n",
       " 'tGravityAcc-arCoeff()-X,2',\n",
       " 'tGravityAcc-arCoeff()-X,3',\n",
       " 'tGravityAcc-arCoeff()-X,4',\n",
       " 'tGravityAcc-arCoeff()-Y,1',\n",
       " 'tGravityAcc-arCoeff()-Y,2',\n",
       " 'tGravityAcc-arCoeff()-Y,3',\n",
       " 'tGravityAcc-arCoeff()-Y,4',\n",
       " 'tGravityAcc-arCoeff()-Z,1',\n",
       " 'tGravityAcc-arCoeff()-Z,2',\n",
       " 'tGravityAcc-arCoeff()-Z,3',\n",
       " 'tGravityAcc-arCoeff()-Z,4',\n",
       " 'tGravityAcc-correlation()-X,Y',\n",
       " 'tGravityAcc-correlation()-X,Z',\n",
       " 'tGravityAcc-correlation()-Y,Z',\n",
       " 'tBodyAccJerk-mean()-X',\n",
       " 'tBodyAccJerk-mean()-Y',\n",
       " 'tBodyAccJerk-mean()-Z',\n",
       " 'tBodyAccJerk-std()-X',\n",
       " 'tBodyAccJerk-std()-Y',\n",
       " 'tBodyAccJerk-std()-Z',\n",
       " 'tBodyAccJerk-mad()-X',\n",
       " 'tBodyAccJerk-mad()-Y',\n",
       " 'tBodyAccJerk-mad()-Z',\n",
       " 'tBodyAccJerk-max()-X',\n",
       " 'tBodyAccJerk-max()-Y',\n",
       " 'tBodyAccJerk-max()-Z',\n",
       " 'tBodyAccJerk-min()-X',\n",
       " 'tBodyAccJerk-min()-Y',\n",
       " 'tBodyAccJerk-min()-Z',\n",
       " 'tBodyAccJerk-sma()',\n",
       " 'tBodyAccJerk-energy()-X',\n",
       " 'tBodyAccJerk-energy()-Y',\n",
       " 'tBodyAccJerk-energy()-Z',\n",
       " 'tBodyAccJerk-iqr()-X',\n",
       " 'tBodyAccJerk-iqr()-Y',\n",
       " 'tBodyAccJerk-iqr()-Z',\n",
       " 'tBodyAccJerk-entropy()-X',\n",
       " 'tBodyAccJerk-entropy()-Y',\n",
       " 'tBodyAccJerk-entropy()-Z',\n",
       " 'tBodyAccJerk-arCoeff()-X,1',\n",
       " 'tBodyAccJerk-arCoeff()-X,2',\n",
       " 'tBodyAccJerk-arCoeff()-X,3',\n",
       " 'tBodyAccJerk-arCoeff()-X,4',\n",
       " 'tBodyAccJerk-arCoeff()-Y,1',\n",
       " 'tBodyAccJerk-arCoeff()-Y,2',\n",
       " 'tBodyAccJerk-arCoeff()-Y,3',\n",
       " 'tBodyAccJerk-arCoeff()-Y,4',\n",
       " 'tBodyAccJerk-arCoeff()-Z,1',\n",
       " 'tBodyAccJerk-arCoeff()-Z,2',\n",
       " 'tBodyAccJerk-arCoeff()-Z,3',\n",
       " 'tBodyAccJerk-arCoeff()-Z,4',\n",
       " 'tBodyAccJerk-correlation()-X,Y',\n",
       " 'tBodyAccJerk-correlation()-X,Z',\n",
       " 'tBodyAccJerk-correlation()-Y,Z',\n",
       " 'tBodyGyro-mean()-X',\n",
       " 'tBodyGyro-mean()-Y',\n",
       " 'tBodyGyro-mean()-Z',\n",
       " 'tBodyGyro-std()-X',\n",
       " 'tBodyGyro-std()-Y',\n",
       " 'tBodyGyro-std()-Z',\n",
       " 'tBodyGyro-mad()-X',\n",
       " 'tBodyGyro-mad()-Y',\n",
       " 'tBodyGyro-mad()-Z',\n",
       " 'tBodyGyro-max()-X',\n",
       " 'tBodyGyro-max()-Y',\n",
       " 'tBodyGyro-max()-Z',\n",
       " 'tBodyGyro-min()-X',\n",
       " 'tBodyGyro-min()-Y',\n",
       " 'tBodyGyro-min()-Z',\n",
       " 'tBodyGyro-sma()',\n",
       " 'tBodyGyro-energy()-X',\n",
       " 'tBodyGyro-energy()-Y',\n",
       " 'tBodyGyro-energy()-Z',\n",
       " 'tBodyGyro-iqr()-X',\n",
       " 'tBodyGyro-iqr()-Y',\n",
       " 'tBodyGyro-iqr()-Z',\n",
       " 'tBodyGyro-entropy()-X',\n",
       " 'tBodyGyro-entropy()-Y',\n",
       " 'tBodyGyro-entropy()-Z',\n",
       " 'tBodyGyro-arCoeff()-X,1',\n",
       " 'tBodyGyro-arCoeff()-X,2',\n",
       " 'tBodyGyro-arCoeff()-X,3',\n",
       " 'tBodyGyro-arCoeff()-X,4',\n",
       " 'tBodyGyro-arCoeff()-Y,1',\n",
       " 'tBodyGyro-arCoeff()-Y,2',\n",
       " 'tBodyGyro-arCoeff()-Y,3',\n",
       " 'tBodyGyro-arCoeff()-Y,4',\n",
       " 'tBodyGyro-arCoeff()-Z,1',\n",
       " 'tBodyGyro-arCoeff()-Z,2',\n",
       " 'tBodyGyro-arCoeff()-Z,3',\n",
       " 'tBodyGyro-arCoeff()-Z,4',\n",
       " 'tBodyGyro-correlation()-X,Y',\n",
       " 'tBodyGyro-correlation()-X,Z',\n",
       " 'tBodyGyro-correlation()-Y,Z',\n",
       " 'tBodyGyroJerk-mean()-X',\n",
       " 'tBodyGyroJerk-mean()-Y',\n",
       " 'tBodyGyroJerk-mean()-Z',\n",
       " 'tBodyGyroJerk-std()-X',\n",
       " 'tBodyGyroJerk-std()-Y',\n",
       " 'tBodyGyroJerk-std()-Z',\n",
       " 'tBodyGyroJerk-mad()-X',\n",
       " 'tBodyGyroJerk-mad()-Y',\n",
       " 'tBodyGyroJerk-mad()-Z',\n",
       " 'tBodyGyroJerk-max()-X',\n",
       " 'tBodyGyroJerk-max()-Y',\n",
       " 'tBodyGyroJerk-max()-Z',\n",
       " 'tBodyGyroJerk-min()-X',\n",
       " 'tBodyGyroJerk-min()-Y',\n",
       " 'tBodyGyroJerk-min()-Z',\n",
       " 'tBodyGyroJerk-sma()',\n",
       " 'tBodyGyroJerk-energy()-X',\n",
       " 'tBodyGyroJerk-energy()-Y',\n",
       " 'tBodyGyroJerk-energy()-Z',\n",
       " 'tBodyGyroJerk-iqr()-X',\n",
       " 'tBodyGyroJerk-iqr()-Y',\n",
       " 'tBodyGyroJerk-iqr()-Z',\n",
       " 'tBodyGyroJerk-entropy()-X',\n",
       " 'tBodyGyroJerk-entropy()-Y',\n",
       " 'tBodyGyroJerk-entropy()-Z',\n",
       " 'tBodyGyroJerk-arCoeff()-X,1',\n",
       " 'tBodyGyroJerk-arCoeff()-X,2',\n",
       " 'tBodyGyroJerk-arCoeff()-X,3',\n",
       " 'tBodyGyroJerk-arCoeff()-X,4',\n",
       " 'tBodyGyroJerk-arCoeff()-Y,1',\n",
       " 'tBodyGyroJerk-arCoeff()-Y,2',\n",
       " 'tBodyGyroJerk-arCoeff()-Y,3',\n",
       " 'tBodyGyroJerk-arCoeff()-Y,4',\n",
       " 'tBodyGyroJerk-arCoeff()-Z,1',\n",
       " 'tBodyGyroJerk-arCoeff()-Z,2',\n",
       " 'tBodyGyroJerk-arCoeff()-Z,3',\n",
       " 'tBodyGyroJerk-arCoeff()-Z,4',\n",
       " 'tBodyGyroJerk-correlation()-X,Y',\n",
       " 'tBodyGyroJerk-correlation()-X,Z',\n",
       " 'tBodyGyroJerk-correlation()-Y,Z',\n",
       " 'tBodyAccMag-mean()',\n",
       " 'tBodyAccMag-std()',\n",
       " 'tBodyAccMag-mad()',\n",
       " 'tBodyAccMag-max()',\n",
       " 'tBodyAccMag-min()',\n",
       " 'tBodyAccMag-sma()',\n",
       " 'tBodyAccMag-energy()',\n",
       " 'tBodyAccMag-iqr()',\n",
       " 'tBodyAccMag-entropy()',\n",
       " 'tBodyAccMag-arCoeff()1',\n",
       " 'tBodyAccMag-arCoeff()2',\n",
       " 'tBodyAccMag-arCoeff()3',\n",
       " 'tBodyAccMag-arCoeff()4',\n",
       " 'tGravityAccMag-mean()',\n",
       " 'tGravityAccMag-std()',\n",
       " 'tGravityAccMag-mad()',\n",
       " 'tGravityAccMag-max()',\n",
       " 'tGravityAccMag-min()',\n",
       " 'tGravityAccMag-sma()',\n",
       " 'tGravityAccMag-energy()',\n",
       " 'tGravityAccMag-iqr()',\n",
       " 'tGravityAccMag-entropy()',\n",
       " 'tGravityAccMag-arCoeff()1',\n",
       " 'tGravityAccMag-arCoeff()2',\n",
       " 'tGravityAccMag-arCoeff()3',\n",
       " 'tGravityAccMag-arCoeff()4',\n",
       " 'tBodyAccJerkMag-mean()',\n",
       " 'tBodyAccJerkMag-std()',\n",
       " 'tBodyAccJerkMag-mad()',\n",
       " 'tBodyAccJerkMag-max()',\n",
       " 'tBodyAccJerkMag-min()',\n",
       " 'tBodyAccJerkMag-sma()',\n",
       " 'tBodyAccJerkMag-energy()',\n",
       " 'tBodyAccJerkMag-iqr()',\n",
       " 'tBodyAccJerkMag-entropy()',\n",
       " 'tBodyAccJerkMag-arCoeff()1',\n",
       " 'tBodyAccJerkMag-arCoeff()2',\n",
       " 'tBodyAccJerkMag-arCoeff()3',\n",
       " 'tBodyAccJerkMag-arCoeff()4',\n",
       " 'tBodyGyroMag-mean()',\n",
       " 'tBodyGyroMag-std()',\n",
       " 'tBodyGyroMag-mad()',\n",
       " 'tBodyGyroMag-max()',\n",
       " 'tBodyGyroMag-min()',\n",
       " 'tBodyGyroMag-sma()',\n",
       " 'tBodyGyroMag-energy()',\n",
       " 'tBodyGyroMag-iqr()',\n",
       " 'tBodyGyroMag-entropy()',\n",
       " 'tBodyGyroMag-arCoeff()1',\n",
       " 'tBodyGyroMag-arCoeff()2',\n",
       " 'tBodyGyroMag-arCoeff()3',\n",
       " 'tBodyGyroMag-arCoeff()4',\n",
       " 'tBodyGyroJerkMag-mean()',\n",
       " 'tBodyGyroJerkMag-std()',\n",
       " 'tBodyGyroJerkMag-mad()',\n",
       " 'tBodyGyroJerkMag-max()',\n",
       " 'tBodyGyroJerkMag-min()',\n",
       " 'tBodyGyroJerkMag-sma()',\n",
       " 'tBodyGyroJerkMag-energy()',\n",
       " 'tBodyGyroJerkMag-iqr()',\n",
       " 'tBodyGyroJerkMag-entropy()',\n",
       " 'tBodyGyroJerkMag-arCoeff()1',\n",
       " 'tBodyGyroJerkMag-arCoeff()2',\n",
       " 'tBodyGyroJerkMag-arCoeff()3',\n",
       " 'tBodyGyroJerkMag-arCoeff()4',\n",
       " 'fBodyAcc-mean()-X',\n",
       " 'fBodyAcc-mean()-Y',\n",
       " 'fBodyAcc-mean()-Z',\n",
       " 'fBodyAcc-std()-X',\n",
       " 'fBodyAcc-std()-Y',\n",
       " 'fBodyAcc-std()-Z',\n",
       " 'fBodyAcc-mad()-X',\n",
       " 'fBodyAcc-mad()-Y',\n",
       " 'fBodyAcc-mad()-Z',\n",
       " 'fBodyAcc-max()-X',\n",
       " 'fBodyAcc-max()-Y',\n",
       " 'fBodyAcc-max()-Z',\n",
       " 'fBodyAcc-min()-X',\n",
       " 'fBodyAcc-min()-Y',\n",
       " 'fBodyAcc-min()-Z',\n",
       " 'fBodyAcc-sma()',\n",
       " 'fBodyAcc-energy()-X',\n",
       " 'fBodyAcc-energy()-Y',\n",
       " 'fBodyAcc-energy()-Z',\n",
       " 'fBodyAcc-iqr()-X',\n",
       " 'fBodyAcc-iqr()-Y',\n",
       " 'fBodyAcc-iqr()-Z',\n",
       " 'fBodyAcc-entropy()-X',\n",
       " 'fBodyAcc-entropy()-Y',\n",
       " 'fBodyAcc-entropy()-Z',\n",
       " 'fBodyAcc-maxInds-X',\n",
       " 'fBodyAcc-maxInds-Y',\n",
       " 'fBodyAcc-maxInds-Z',\n",
       " 'fBodyAcc-meanFreq()-X',\n",
       " 'fBodyAcc-meanFreq()-Y',\n",
       " 'fBodyAcc-meanFreq()-Z',\n",
       " 'fBodyAcc-skewness()-X',\n",
       " 'fBodyAcc-kurtosis()-X',\n",
       " 'fBodyAcc-skewness()-Y',\n",
       " 'fBodyAcc-kurtosis()-Y',\n",
       " 'fBodyAcc-skewness()-Z',\n",
       " 'fBodyAcc-kurtosis()-Z',\n",
       " 'fBodyAcc-bandsEnergy()-1,8',\n",
       " 'fBodyAcc-bandsEnergy()-9,16',\n",
       " 'fBodyAcc-bandsEnergy()-17,24',\n",
       " 'fBodyAcc-bandsEnergy()-25,32',\n",
       " 'fBodyAcc-bandsEnergy()-33,40',\n",
       " 'fBodyAcc-bandsEnergy()-41,48',\n",
       " 'fBodyAcc-bandsEnergy()-49,56',\n",
       " 'fBodyAcc-bandsEnergy()-57,64',\n",
       " 'fBodyAcc-bandsEnergy()-1,16',\n",
       " 'fBodyAcc-bandsEnergy()-17,32',\n",
       " 'fBodyAcc-bandsEnergy()-33,48',\n",
       " 'fBodyAcc-bandsEnergy()-49,64',\n",
       " 'fBodyAcc-bandsEnergy()-1,24',\n",
       " 'fBodyAcc-bandsEnergy()-25,48',\n",
       " 'fBodyAcc-bandsEnergy()-1,8.1',\n",
       " 'fBodyAcc-bandsEnergy()-9,16.1',\n",
       " 'fBodyAcc-bandsEnergy()-17,24.1',\n",
       " 'fBodyAcc-bandsEnergy()-25,32.1',\n",
       " 'fBodyAcc-bandsEnergy()-33,40.1',\n",
       " 'fBodyAcc-bandsEnergy()-41,48.1',\n",
       " 'fBodyAcc-bandsEnergy()-49,56.1',\n",
       " 'fBodyAcc-bandsEnergy()-57,64.1',\n",
       " 'fBodyAcc-bandsEnergy()-1,16.1',\n",
       " 'fBodyAcc-bandsEnergy()-17,32.1',\n",
       " 'fBodyAcc-bandsEnergy()-33,48.1',\n",
       " 'fBodyAcc-bandsEnergy()-49,64.1',\n",
       " 'fBodyAcc-bandsEnergy()-1,24.1',\n",
       " 'fBodyAcc-bandsEnergy()-25,48.1',\n",
       " 'fBodyAcc-bandsEnergy()-1,8.2',\n",
       " 'fBodyAcc-bandsEnergy()-9,16.2',\n",
       " 'fBodyAcc-bandsEnergy()-17,24.2',\n",
       " 'fBodyAcc-bandsEnergy()-25,32.2',\n",
       " 'fBodyAcc-bandsEnergy()-33,40.2',\n",
       " 'fBodyAcc-bandsEnergy()-41,48.2',\n",
       " 'fBodyAcc-bandsEnergy()-49,56.2',\n",
       " 'fBodyAcc-bandsEnergy()-57,64.2',\n",
       " 'fBodyAcc-bandsEnergy()-1,16.2',\n",
       " 'fBodyAcc-bandsEnergy()-17,32.2',\n",
       " 'fBodyAcc-bandsEnergy()-33,48.2',\n",
       " 'fBodyAcc-bandsEnergy()-49,64.2',\n",
       " 'fBodyAcc-bandsEnergy()-1,24.2',\n",
       " 'fBodyAcc-bandsEnergy()-25,48.2',\n",
       " 'fBodyAccJerk-mean()-X',\n",
       " 'fBodyAccJerk-mean()-Y',\n",
       " 'fBodyAccJerk-mean()-Z',\n",
       " 'fBodyAccJerk-std()-X',\n",
       " 'fBodyAccJerk-std()-Y',\n",
       " 'fBodyAccJerk-std()-Z',\n",
       " 'fBodyAccJerk-mad()-X',\n",
       " 'fBodyAccJerk-mad()-Y',\n",
       " 'fBodyAccJerk-mad()-Z',\n",
       " 'fBodyAccJerk-max()-X',\n",
       " 'fBodyAccJerk-max()-Y',\n",
       " 'fBodyAccJerk-max()-Z',\n",
       " 'fBodyAccJerk-min()-X',\n",
       " 'fBodyAccJerk-min()-Y',\n",
       " 'fBodyAccJerk-min()-Z',\n",
       " 'fBodyAccJerk-sma()',\n",
       " 'fBodyAccJerk-energy()-X',\n",
       " 'fBodyAccJerk-energy()-Y',\n",
       " 'fBodyAccJerk-energy()-Z',\n",
       " 'fBodyAccJerk-iqr()-X',\n",
       " 'fBodyAccJerk-iqr()-Y',\n",
       " 'fBodyAccJerk-iqr()-Z',\n",
       " 'fBodyAccJerk-entropy()-X',\n",
       " 'fBodyAccJerk-entropy()-Y',\n",
       " 'fBodyAccJerk-entropy()-Z',\n",
       " 'fBodyAccJerk-maxInds-X',\n",
       " 'fBodyAccJerk-maxInds-Y',\n",
       " 'fBodyAccJerk-maxInds-Z',\n",
       " 'fBodyAccJerk-meanFreq()-X',\n",
       " 'fBodyAccJerk-meanFreq()-Y',\n",
       " 'fBodyAccJerk-meanFreq()-Z',\n",
       " 'fBodyAccJerk-skewness()-X',\n",
       " 'fBodyAccJerk-kurtosis()-X',\n",
       " 'fBodyAccJerk-skewness()-Y',\n",
       " 'fBodyAccJerk-kurtosis()-Y',\n",
       " 'fBodyAccJerk-skewness()-Z',\n",
       " 'fBodyAccJerk-kurtosis()-Z',\n",
       " 'fBodyAccJerk-bandsEnergy()-1,8',\n",
       " 'fBodyAccJerk-bandsEnergy()-9,16',\n",
       " 'fBodyAccJerk-bandsEnergy()-17,24',\n",
       " 'fBodyAccJerk-bandsEnergy()-25,32',\n",
       " 'fBodyAccJerk-bandsEnergy()-33,40',\n",
       " 'fBodyAccJerk-bandsEnergy()-41,48',\n",
       " 'fBodyAccJerk-bandsEnergy()-49,56',\n",
       " 'fBodyAccJerk-bandsEnergy()-57,64',\n",
       " 'fBodyAccJerk-bandsEnergy()-1,16',\n",
       " 'fBodyAccJerk-bandsEnergy()-17,32',\n",
       " 'fBodyAccJerk-bandsEnergy()-33,48',\n",
       " 'fBodyAccJerk-bandsEnergy()-49,64',\n",
       " 'fBodyAccJerk-bandsEnergy()-1,24',\n",
       " 'fBodyAccJerk-bandsEnergy()-25,48',\n",
       " 'fBodyAccJerk-bandsEnergy()-1,8.1',\n",
       " 'fBodyAccJerk-bandsEnergy()-9,16.1',\n",
       " 'fBodyAccJerk-bandsEnergy()-17,24.1',\n",
       " 'fBodyAccJerk-bandsEnergy()-25,32.1',\n",
       " 'fBodyAccJerk-bandsEnergy()-33,40.1',\n",
       " 'fBodyAccJerk-bandsEnergy()-41,48.1',\n",
       " 'fBodyAccJerk-bandsEnergy()-49,56.1',\n",
       " 'fBodyAccJerk-bandsEnergy()-57,64.1',\n",
       " 'fBodyAccJerk-bandsEnergy()-1,16.1',\n",
       " 'fBodyAccJerk-bandsEnergy()-17,32.1',\n",
       " 'fBodyAccJerk-bandsEnergy()-33,48.1',\n",
       " 'fBodyAccJerk-bandsEnergy()-49,64.1',\n",
       " 'fBodyAccJerk-bandsEnergy()-1,24.1',\n",
       " 'fBodyAccJerk-bandsEnergy()-25,48.1',\n",
       " 'fBodyAccJerk-bandsEnergy()-1,8.2',\n",
       " 'fBodyAccJerk-bandsEnergy()-9,16.2',\n",
       " 'fBodyAccJerk-bandsEnergy()-17,24.2',\n",
       " 'fBodyAccJerk-bandsEnergy()-25,32.2',\n",
       " 'fBodyAccJerk-bandsEnergy()-33,40.2',\n",
       " 'fBodyAccJerk-bandsEnergy()-41,48.2',\n",
       " 'fBodyAccJerk-bandsEnergy()-49,56.2',\n",
       " 'fBodyAccJerk-bandsEnergy()-57,64.2',\n",
       " 'fBodyAccJerk-bandsEnergy()-1,16.2',\n",
       " 'fBodyAccJerk-bandsEnergy()-17,32.2',\n",
       " 'fBodyAccJerk-bandsEnergy()-33,48.2',\n",
       " 'fBodyAccJerk-bandsEnergy()-49,64.2',\n",
       " 'fBodyAccJerk-bandsEnergy()-1,24.2',\n",
       " 'fBodyAccJerk-bandsEnergy()-25,48.2',\n",
       " 'fBodyGyro-mean()-X',\n",
       " 'fBodyGyro-mean()-Y',\n",
       " 'fBodyGyro-mean()-Z',\n",
       " 'fBodyGyro-std()-X',\n",
       " 'fBodyGyro-std()-Y',\n",
       " 'fBodyGyro-std()-Z',\n",
       " 'fBodyGyro-mad()-X',\n",
       " 'fBodyGyro-mad()-Y',\n",
       " 'fBodyGyro-mad()-Z',\n",
       " 'fBodyGyro-max()-X',\n",
       " 'fBodyGyro-max()-Y',\n",
       " 'fBodyGyro-max()-Z',\n",
       " 'fBodyGyro-min()-X',\n",
       " 'fBodyGyro-min()-Y',\n",
       " 'fBodyGyro-min()-Z',\n",
       " 'fBodyGyro-sma()',\n",
       " 'fBodyGyro-energy()-X',\n",
       " 'fBodyGyro-energy()-Y',\n",
       " 'fBodyGyro-energy()-Z',\n",
       " 'fBodyGyro-iqr()-X',\n",
       " 'fBodyGyro-iqr()-Y',\n",
       " 'fBodyGyro-iqr()-Z',\n",
       " 'fBodyGyro-entropy()-X',\n",
       " 'fBodyGyro-entropy()-Y',\n",
       " 'fBodyGyro-entropy()-Z',\n",
       " 'fBodyGyro-maxInds-X',\n",
       " 'fBodyGyro-maxInds-Y',\n",
       " 'fBodyGyro-maxInds-Z',\n",
       " 'fBodyGyro-meanFreq()-X',\n",
       " 'fBodyGyro-meanFreq()-Y',\n",
       " 'fBodyGyro-meanFreq()-Z',\n",
       " 'fBodyGyro-skewness()-X',\n",
       " 'fBodyGyro-kurtosis()-X',\n",
       " 'fBodyGyro-skewness()-Y',\n",
       " 'fBodyGyro-kurtosis()-Y',\n",
       " 'fBodyGyro-skewness()-Z',\n",
       " 'fBodyGyro-kurtosis()-Z',\n",
       " 'fBodyGyro-bandsEnergy()-1,8',\n",
       " 'fBodyGyro-bandsEnergy()-9,16',\n",
       " 'fBodyGyro-bandsEnergy()-17,24',\n",
       " 'fBodyGyro-bandsEnergy()-25,32',\n",
       " 'fBodyGyro-bandsEnergy()-33,40',\n",
       " 'fBodyGyro-bandsEnergy()-41,48',\n",
       " 'fBodyGyro-bandsEnergy()-49,56',\n",
       " 'fBodyGyro-bandsEnergy()-57,64',\n",
       " 'fBodyGyro-bandsEnergy()-1,16',\n",
       " 'fBodyGyro-bandsEnergy()-17,32',\n",
       " 'fBodyGyro-bandsEnergy()-33,48',\n",
       " 'fBodyGyro-bandsEnergy()-49,64',\n",
       " 'fBodyGyro-bandsEnergy()-1,24',\n",
       " 'fBodyGyro-bandsEnergy()-25,48',\n",
       " 'fBodyGyro-bandsEnergy()-1,8.1',\n",
       " 'fBodyGyro-bandsEnergy()-9,16.1',\n",
       " 'fBodyGyro-bandsEnergy()-17,24.1',\n",
       " 'fBodyGyro-bandsEnergy()-25,32.1',\n",
       " 'fBodyGyro-bandsEnergy()-33,40.1',\n",
       " 'fBodyGyro-bandsEnergy()-41,48.1',\n",
       " 'fBodyGyro-bandsEnergy()-49,56.1',\n",
       " 'fBodyGyro-bandsEnergy()-57,64.1',\n",
       " 'fBodyGyro-bandsEnergy()-1,16.1',\n",
       " 'fBodyGyro-bandsEnergy()-17,32.1',\n",
       " 'fBodyGyro-bandsEnergy()-33,48.1',\n",
       " 'fBodyGyro-bandsEnergy()-49,64.1',\n",
       " 'fBodyGyro-bandsEnergy()-1,24.1',\n",
       " 'fBodyGyro-bandsEnergy()-25,48.1',\n",
       " 'fBodyGyro-bandsEnergy()-1,8.2',\n",
       " 'fBodyGyro-bandsEnergy()-9,16.2',\n",
       " 'fBodyGyro-bandsEnergy()-17,24.2',\n",
       " 'fBodyGyro-bandsEnergy()-25,32.2',\n",
       " 'fBodyGyro-bandsEnergy()-33,40.2',\n",
       " 'fBodyGyro-bandsEnergy()-41,48.2',\n",
       " 'fBodyGyro-bandsEnergy()-49,56.2',\n",
       " 'fBodyGyro-bandsEnergy()-57,64.2',\n",
       " 'fBodyGyro-bandsEnergy()-1,16.2',\n",
       " 'fBodyGyro-bandsEnergy()-17,32.2',\n",
       " 'fBodyGyro-bandsEnergy()-33,48.2',\n",
       " 'fBodyGyro-bandsEnergy()-49,64.2',\n",
       " 'fBodyGyro-bandsEnergy()-1,24.2',\n",
       " 'fBodyGyro-bandsEnergy()-25,48.2',\n",
       " 'fBodyAccMag-mean()',\n",
       " 'fBodyAccMag-std()',\n",
       " 'fBodyAccMag-mad()',\n",
       " 'fBodyAccMag-max()',\n",
       " 'fBodyAccMag-min()',\n",
       " 'fBodyAccMag-sma()',\n",
       " 'fBodyAccMag-energy()',\n",
       " 'fBodyAccMag-iqr()',\n",
       " 'fBodyAccMag-entropy()',\n",
       " 'fBodyAccMag-maxInds',\n",
       " 'fBodyAccMag-meanFreq()',\n",
       " 'fBodyAccMag-skewness()',\n",
       " 'fBodyAccMag-kurtosis()',\n",
       " 'fBodyBodyAccJerkMag-mean()',\n",
       " 'fBodyBodyAccJerkMag-std()',\n",
       " 'fBodyBodyAccJerkMag-mad()',\n",
       " 'fBodyBodyAccJerkMag-max()',\n",
       " 'fBodyBodyAccJerkMag-min()',\n",
       " 'fBodyBodyAccJerkMag-sma()',\n",
       " 'fBodyBodyAccJerkMag-energy()',\n",
       " 'fBodyBodyAccJerkMag-iqr()',\n",
       " 'fBodyBodyAccJerkMag-entropy()',\n",
       " 'fBodyBodyAccJerkMag-maxInds',\n",
       " 'fBodyBodyAccJerkMag-meanFreq()',\n",
       " 'fBodyBodyAccJerkMag-skewness()',\n",
       " 'fBodyBodyAccJerkMag-kurtosis()',\n",
       " 'fBodyBodyGyroMag-mean()',\n",
       " 'fBodyBodyGyroMag-std()',\n",
       " 'fBodyBodyGyroMag-mad()',\n",
       " 'fBodyBodyGyroMag-max()',\n",
       " 'fBodyBodyGyroMag-min()',\n",
       " 'fBodyBodyGyroMag-sma()',\n",
       " 'fBodyBodyGyroMag-energy()',\n",
       " 'fBodyBodyGyroMag-iqr()',\n",
       " 'fBodyBodyGyroMag-entropy()',\n",
       " 'fBodyBodyGyroMag-maxInds',\n",
       " 'fBodyBodyGyroMag-meanFreq()',\n",
       " 'fBodyBodyGyroMag-skewness()',\n",
       " 'fBodyBodyGyroMag-kurtosis()',\n",
       " 'fBodyBodyGyroJerkMag-mean()',\n",
       " 'fBodyBodyGyroJerkMag-std()',\n",
       " 'fBodyBodyGyroJerkMag-mad()',\n",
       " 'fBodyBodyGyroJerkMag-max()',\n",
       " 'fBodyBodyGyroJerkMag-min()',\n",
       " 'fBodyBodyGyroJerkMag-sma()',\n",
       " 'fBodyBodyGyroJerkMag-energy()',\n",
       " 'fBodyBodyGyroJerkMag-iqr()',\n",
       " 'fBodyBodyGyroJerkMag-entropy()',\n",
       " 'fBodyBodyGyroJerkMag-maxInds',\n",
       " 'fBodyBodyGyroJerkMag-meanFreq()',\n",
       " 'fBodyBodyGyroJerkMag-skewness()',\n",
       " 'fBodyBodyGyroJerkMag-kurtosis()',\n",
       " 'angle(tBodyAccMean,gravity)',\n",
       " 'angle(tBodyAccJerkMean),gravityMean)',\n",
       " 'angle(tBodyGyroMean,gravityMean)',\n",
       " 'angle(tBodyGyroJerkMean,gravityMean)',\n",
       " 'angle(X,gravityMean)',\n",
       " 'angle(Y,gravityMean)',\n",
       " 'angle(Z,gravityMean)',\n",
       " 'subject',\n",
       " 'Activity']"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list(data.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "61449a39",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tBodyAcc-mean()-X       0\n",
       "tBodyAcc-mean()-Y       0\n",
       "tBodyAcc-mean()-Z       0\n",
       "tBodyAcc-std()-X        0\n",
       "tBodyAcc-std()-Y        0\n",
       "                       ..\n",
       "angle(X,gravityMean)    0\n",
       "angle(Y,gravityMean)    0\n",
       "angle(Z,gravityMean)    0\n",
       "subject                 0\n",
       "Activity                0\n",
       "Length: 563, dtype: int64"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "3cd83964",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot: >"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "data['Activity'].value_counts().sort_values().plot(kind = 'bar', color = 'pink')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "42355fcd",
   "metadata": {},
   "outputs": [],
   "source": [
    "data.drop('subject', axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "16940499",
   "metadata": {},
   "outputs": [],
   "source": [
    "encoder= LabelEncoder()\n",
    "data['Activity']=encoder.fit_transform(data['Activity'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "cd7ff549",
   "metadata": {},
   "outputs": [],
   "source": [
    "duplicate_columns = data.columns[data.T.duplicated()].tolist() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "dd320134",
   "metadata": {},
   "outputs": [],
   "source": [
    "data=data.drop(columns= duplicate_columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "c475d863",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(7352, 541)"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "1f9806b3",
   "metadata": {},
   "outputs": [],
   "source": [
    "X= data.drop('Activity', axis=1)\n",
    "y= data['Activity']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "320ad1fa",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3,random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "57be6539",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MLPClassifier()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MLPClassifier</label><div class=\"sk-toggleable__content\"><pre>MLPClassifier()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "MLPClassifier()"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model= MLPClassifier()\n",
    "model.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "1ada52a2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9814143245693563"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Model_Score_Raw_data=model.score(X_test,y_test)\n",
    "Model_Score_Raw_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "ae8f7cde",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9978624174115818"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.score(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "7d0c311c",
   "metadata": {},
   "outputs": [],
   "source": [
    "selector= VarianceThreshold(threshold=0.05)\n",
    "selected_features= selector.fit(X_train)\n",
    "X_train_high_variance= selector.transform(X_train)\n",
    "X_test_high_variance= selector.transform(X_test)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "32b3f37a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "347"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Total High Variance Features Only, Less than threshold features are already removed\n",
    "sum(selected_features.get_support())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "7319c562",
   "metadata": {},
   "outputs": [],
   "source": [
    "selected_indices=selected_features.get_support()\n",
    "selected_feature_names= X_train.columns[selected_indices]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "5b6a6fcf",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train_high_variance= pd.DataFrame(X_train_high_variance,columns= selected_feature_names)\n",
    "X_test_high_variance= pd.DataFrame(X_test_high_variance,columns= selected_feature_names)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "c6b7f542",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((5146, 347), (2206, 347))"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train_high_variance.shape, X_test_high_variance.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "cca8a5d6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-2 {color: black;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MLPClassifier()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MLPClassifier</label><div class=\"sk-toggleable__content\"><pre>MLPClassifier()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "MLPClassifier()"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model= MLPClassifier()\n",
    "model.fit(X_train_high_variance,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "8ba00eb7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.986400725294651"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Model_Score_After_vt=model.score(X_test_high_variance,y_test)\n",
    "Model_Score_After_vt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "2d1cb819",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5146, 347)"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train_high_variance.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "1ec9c207",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5146, 348)"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train_high_variance['Activity']= data['Activity']\n",
    "X_train_high_variance.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d59c730c",
   "metadata": {},
   "source": [
    "**Correlation Matrix Method:**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "5d032463",
   "metadata": {},
   "outputs": [],
   "source": [
    "threshold= 0.00001\n",
    "correlation_matrix= X_train_high_variance.corr()\n",
    "activity_corr= correlation_matrix['Activity']\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "a95649a2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Selected features:\n",
      "                                      tBodyAcc-std()-X  tBodyAcc-std()-Y  \\\n",
      "tBodyAcc-min()-X                             -0.967079         -0.937384   \n",
      "tBodyAcc-min()-Y                             -0.903597         -0.955939   \n",
      "tBodyAcc-min()-Z                             -0.826657         -0.837536   \n",
      "tBodyAcc-energy()-X                           0.949367          0.805397   \n",
      "tBodyAcc-arCoeff()-X,1                       -0.696417         -0.730736   \n",
      "...                                                ...               ...   \n",
      "angle(tBodyAccMean,gravity)                  -0.052114         -0.032088   \n",
      "angle(tBodyAccJerkMean),gravityMean)         -0.038631         -0.021792   \n",
      "angle(tBodyGyroMean,gravityMean)              0.037982          0.009565   \n",
      "angle(Y,gravityMean)                          0.473625          0.524676   \n",
      "angle(Z,gravityMean)                          0.397708          0.434379   \n",
      "\n",
      "                                      tBodyAcc-std()-Z  tBodyAcc-mad()-X  \\\n",
      "tBodyAcc-min()-X                             -0.863104         -0.962791   \n",
      "tBodyAcc-min()-Y                             -0.852754         -0.899359   \n",
      "tBodyAcc-min()-Z                             -0.938162         -0.820124   \n",
      "tBodyAcc-energy()-X                           0.715564          0.953457   \n",
      "tBodyAcc-arCoeff()-X,1                       -0.695279         -0.691184   \n",
      "...                                                ...               ...   \n",
      "angle(tBodyAccMean,gravity)                  -0.019793         -0.059446   \n",
      "angle(tBodyAccJerkMean),gravityMean)         -0.032353         -0.038839   \n",
      "angle(tBodyGyroMean,gravityMean)             -0.000667          0.038013   \n",
      "angle(Y,gravityMean)                          0.472982          0.469004   \n",
      "angle(Z,gravityMean)                          0.482210          0.393552   \n",
      "\n",
      "                                      tBodyAcc-mad()-Y  tBodyAcc-mad()-Z  \\\n",
      "tBodyAcc-min()-X                             -0.932351         -0.859474   \n",
      "tBodyAcc-min()-Y                             -0.939299         -0.848019   \n",
      "tBodyAcc-min()-Z                             -0.828903         -0.920834   \n",
      "tBodyAcc-energy()-X                           0.796183          0.706158   \n",
      "tBodyAcc-arCoeff()-X,1                       -0.731556         -0.703787   \n",
      "...                                                ...               ...   \n",
      "angle(tBodyAccMean,gravity)                  -0.035637         -0.022428   \n",
      "angle(tBodyAccJerkMean),gravityMean)         -0.020567         -0.031113   \n",
      "angle(tBodyGyroMean,gravityMean)              0.006675         -0.005323   \n",
      "angle(Y,gravityMean)                          0.526429          0.474235   \n",
      "angle(Z,gravityMean)                          0.432468          0.478908   \n",
      "\n",
      "                                      tBodyAcc-max()-X  tBodyAcc-max()-Y  \\\n",
      "tBodyAcc-min()-X                             -0.943259         -0.903383   \n",
      "tBodyAcc-min()-Y                             -0.897574         -0.877444   \n",
      "tBodyAcc-min()-Z                             -0.836338         -0.815954   \n",
      "tBodyAcc-energy()-X                           0.914940          0.782201   \n",
      "tBodyAcc-arCoeff()-X,1                       -0.690142         -0.702469   \n",
      "...                                                ...               ...   \n",
      "angle(tBodyAccMean,gravity)                  -0.051110         -0.024739   \n",
      "angle(tBodyAccJerkMean),gravityMean)         -0.036956         -0.014950   \n",
      "angle(tBodyGyroMean,gravityMean)              0.042240          0.012705   \n",
      "angle(Y,gravityMean)                          0.482786          0.489963   \n",
      "angle(Z,gravityMean)                          0.408251          0.428149   \n",
      "\n",
      "                                      tBodyAcc-max()-Z  tBodyAcc-min()-X  ...  \\\n",
      "tBodyAcc-min()-X                             -0.864379          1.000000  ...   \n",
      "tBodyAcc-min()-Y                             -0.849696          0.911201  ...   \n",
      "tBodyAcc-min()-Z                             -0.834046          0.823711  ...   \n",
      "tBodyAcc-energy()-X                           0.717596         -0.887329  ...   \n",
      "tBodyAcc-arCoeff()-X,1                       -0.663843          0.695666  ...   \n",
      "...                                                ...               ...  ...   \n",
      "angle(tBodyAccMean,gravity)                  -0.003975          0.022641  ...   \n",
      "angle(tBodyAccJerkMean),gravityMean)         -0.032771          0.038985  ...   \n",
      "angle(tBodyGyroMean,gravityMean)             -0.012617         -0.020105  ...   \n",
      "angle(Y,gravityMean)                          0.461499         -0.473320  ...   \n",
      "angle(Z,gravityMean)                          0.417731         -0.397002  ...   \n",
      "\n",
      "                                      fBodyBodyGyroJerkMag-skewness()  \\\n",
      "tBodyAcc-min()-X                                            -0.166130   \n",
      "tBodyAcc-min()-Y                                            -0.206405   \n",
      "tBodyAcc-min()-Z                                            -0.150166   \n",
      "tBodyAcc-energy()-X                                          0.086497   \n",
      "tBodyAcc-arCoeff()-X,1                                      -0.241582   \n",
      "...                                                               ...   \n",
      "angle(tBodyAccMean,gravity)                                  0.009433   \n",
      "angle(tBodyAccJerkMean),gravityMean)                        -0.002988   \n",
      "angle(tBodyGyroMean,gravityMean)                             0.035931   \n",
      "angle(Y,gravityMean)                                         0.077225   \n",
      "angle(Z,gravityMean)                                         0.047252   \n",
      "\n",
      "                                      fBodyBodyGyroJerkMag-kurtosis()  \\\n",
      "tBodyAcc-min()-X                                            -0.132547   \n",
      "tBodyAcc-min()-Y                                            -0.176009   \n",
      "tBodyAcc-min()-Z                                            -0.118542   \n",
      "tBodyAcc-energy()-X                                          0.059062   \n",
      "tBodyAcc-arCoeff()-X,1                                      -0.199511   \n",
      "...                                                               ...   \n",
      "angle(tBodyAccMean,gravity)                                  0.008147   \n",
      "angle(tBodyAccJerkMean),gravityMean)                        -0.007813   \n",
      "angle(tBodyGyroMean,gravityMean)                             0.026406   \n",
      "angle(Y,gravityMean)                                         0.070555   \n",
      "angle(Z,gravityMean)                                         0.043901   \n",
      "\n",
      "                                      angle(tBodyAccMean,gravity)  \\\n",
      "tBodyAcc-min()-X                                         0.022641   \n",
      "tBodyAcc-min()-Y                                         0.022420   \n",
      "tBodyAcc-min()-Z                                         0.026680   \n",
      "tBodyAcc-energy()-X                                     -0.069958   \n",
      "tBodyAcc-arCoeff()-X,1                                   0.022107   \n",
      "...                                                           ...   \n",
      "angle(tBodyAccMean,gravity)                              1.000000   \n",
      "angle(tBodyAccJerkMean),gravityMean)                    -0.086703   \n",
      "angle(tBodyGyroMean,gravityMean)                         0.003277   \n",
      "angle(Y,gravityMean)                                    -0.008217   \n",
      "angle(Z,gravityMean)                                    -0.010504   \n",
      "\n",
      "                                      angle(tBodyAccJerkMean),gravityMean)  \\\n",
      "tBodyAcc-min()-X                                                  0.038985   \n",
      "tBodyAcc-min()-Y                                                  0.025464   \n",
      "tBodyAcc-min()-Z                                                  0.037001   \n",
      "tBodyAcc-energy()-X                                              -0.039607   \n",
      "tBodyAcc-arCoeff()-X,1                                            0.010733   \n",
      "...                                                                    ...   \n",
      "angle(tBodyAccMean,gravity)                                      -0.086703   \n",
      "angle(tBodyAccJerkMean),gravityMean)                              1.000000   \n",
      "angle(tBodyGyroMean,gravityMean)                                  0.015252   \n",
      "angle(Y,gravityMean)                                             -0.007186   \n",
      "angle(Z,gravityMean)                                             -0.018179   \n",
      "\n",
      "                                      angle(tBodyGyroMean,gravityMean)  \\\n",
      "tBodyAcc-min()-X                                             -0.020105   \n",
      "tBodyAcc-min()-Y                                             -0.022195   \n",
      "tBodyAcc-min()-Z                                             -0.036273   \n",
      "tBodyAcc-energy()-X                                           0.054150   \n",
      "tBodyAcc-arCoeff()-X,1                                       -0.008830   \n",
      "...                                                                ...   \n",
      "angle(tBodyAccMean,gravity)                                   0.003277   \n",
      "angle(tBodyAccJerkMean),gravityMean)                          0.015252   \n",
      "angle(tBodyGyroMean,gravityMean)                              1.000000   \n",
      "angle(Y,gravityMean)                                          0.003695   \n",
      "angle(Z,gravityMean)                                         -0.007246   \n",
      "\n",
      "                                      angle(tBodyGyroJerkMean,gravityMean)  \\\n",
      "tBodyAcc-min()-X                                                  0.040102   \n",
      "tBodyAcc-min()-Y                                                  0.053356   \n",
      "tBodyAcc-min()-Z                                                  0.042734   \n",
      "tBodyAcc-energy()-X                                              -0.052500   \n",
      "tBodyAcc-arCoeff()-X,1                                            0.014036   \n",
      "...                                                                    ...   \n",
      "angle(tBodyAccMean,gravity)                                      -0.028879   \n",
      "angle(tBodyAccJerkMean),gravityMean)                              0.033313   \n",
      "angle(tBodyGyroMean,gravityMean)                                 -0.105026   \n",
      "angle(Y,gravityMean)                                             -0.010612   \n",
      "angle(Z,gravityMean)                                             -0.012794   \n",
      "\n",
      "                                      angle(X,gravityMean)  \\\n",
      "tBodyAcc-min()-X                                  0.365909   \n",
      "tBodyAcc-min()-Y                                  0.368332   \n",
      "tBodyAcc-min()-Z                                  0.320789   \n",
      "tBodyAcc-energy()-X                              -0.331298   \n",
      "tBodyAcc-arCoeff()-X,1                            0.135781   \n",
      "...                                                    ...   \n",
      "angle(tBodyAccMean,gravity)                       0.017381   \n",
      "angle(tBodyAccJerkMean),gravityMean)              0.021180   \n",
      "angle(tBodyGyroMean,gravityMean)                 -0.014708   \n",
      "angle(Y,gravityMean)                             -0.785761   \n",
      "angle(Z,gravityMean)                             -0.651242   \n",
      "\n",
      "                                      angle(Y,gravityMean)  \\\n",
      "tBodyAcc-min()-X                                 -0.473320   \n",
      "tBodyAcc-min()-Y                                 -0.496055   \n",
      "tBodyAcc-min()-Z                                 -0.432682   \n",
      "tBodyAcc-energy()-X                               0.391967   \n",
      "tBodyAcc-arCoeff()-X,1                           -0.296630   \n",
      "...                                                    ...   \n",
      "angle(tBodyAccMean,gravity)                      -0.008217   \n",
      "angle(tBodyAccJerkMean),gravityMean)             -0.007186   \n",
      "angle(tBodyGyroMean,gravityMean)                  0.003695   \n",
      "angle(Y,gravityMean)                              1.000000   \n",
      "angle(Z,gravityMean)                              0.592328   \n",
      "\n",
      "                                      angle(Z,gravityMean)  Activity  \n",
      "tBodyAcc-min()-X                                 -0.397002  0.004400  \n",
      "tBodyAcc-min()-Y                                 -0.413302  0.007141  \n",
      "tBodyAcc-min()-Z                                 -0.478486  0.005819  \n",
      "tBodyAcc-energy()-X                               0.327524  0.003506  \n",
      "tBodyAcc-arCoeff()-X,1                           -0.204150  0.023373  \n",
      "...                                                    ...       ...  \n",
      "angle(tBodyAccMean,gravity)                      -0.010504  0.017136  \n",
      "angle(tBodyAccJerkMean),gravityMean)             -0.018179  0.004869  \n",
      "angle(tBodyGyroMean,gravityMean)                 -0.007246  0.000474  \n",
      "angle(Y,gravityMean)                              0.592328  0.006971  \n",
      "angle(Z,gravityMean)                              1.000000  0.017044  \n",
      "\n",
      "[101 rows x 348 columns]\n"
     ]
    }
   ],
   "source": [
    "#Method-1 (Find Features, those are highly correlated to target feature and then train and test then predict model score)\n",
    "\n",
    "selected_features = correlation_matrix[\n",
    "    (correlation_matrix['Activity'] > threshold) &\n",
    "    (correlation_matrix.index != 'Activity')\n",
    "]\n",
    "\n",
    "print(\"Selected features:\")\n",
    "print(selected_features)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "b288165e",
   "metadata": {},
   "outputs": [],
   "source": [
    "selected_feature_names= selected_features.index.to_list()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "ab7ff8ee",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train_vt_ac= pd.DataFrame(X_train_high_variance, columns=selected_feature_names)\n",
    "X_test_vt_ac= pd.DataFrame(X_test_high_variance, columns=selected_feature_names)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "4972c184",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5146, 101)"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train_vt_ac.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "f47bf218",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-3 {color: black;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-3 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MLPClassifier()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MLPClassifier</label><div class=\"sk-toggleable__content\"><pre>MLPClassifier()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "MLPClassifier()"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model= MLPClassifier()\n",
    "model.fit(X_train_vt_ac,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "dc9de066",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.970081595648232"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Model_Score_After_one_to_many_corr=model.score(X_test_vt_ac,y_test)\n",
    "Model_Score_After_one_to_many_corr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "60f6e77e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Method-2 (Find those features, which are highly correlated to eachother)\n",
    "\n",
    "threshold= 0.95\n",
    "correlation_matrix= X_train_high_variance.corr()\n",
    "\n",
    "highly_correlated_features= set()\n",
    "\n",
    "for i in range (len(correlation_matrix.columns)):\n",
    "    for j in range (i):\n",
    "        if correlation_matrix.iloc[i,j]>threshold:\n",
    "            highly_correlated_features.add(correlation_matrix.columns[i])\n",
    "            highly_correlated_features.add(correlation_matrix.columns[j])\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "198e6751",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train_high_variance.drop(columns= highly_correlated_features , axis=1, inplace= True)\n",
    "X_test_high_variance.drop(columns= highly_correlated_features, axis=1, inplace= True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "d4d07dd3",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train_high_variance.drop('Activity', axis=1, inplace= True ) #Activity we add only just to find correlation between each and every column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "33014863",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train_ac2=pd.DataFrame(X_train_high_variance, columns=X_train_high_variance.columns)\n",
    "X_test_ac2=pd.DataFrame(X_test_high_variance, columns=X_test_high_variance.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "26cd47a3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5146, 114)"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train_ac2.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "c890d3b8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-4 {color: black;}#sk-container-id-4 pre{padding: 0;}#sk-container-id-4 div.sk-toggleable {background-color: white;}#sk-container-id-4 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-4 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-4 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-4 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-4 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-4 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-4 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-4 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-4 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-4 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-4 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-4 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-4 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-4 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-4 div.sk-item {position: relative;z-index: 1;}#sk-container-id-4 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-4 div.sk-item::before, #sk-container-id-4 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-4 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-4 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-4 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-4 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-4 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-4 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-4 div.sk-label-container {text-align: center;}#sk-container-id-4 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-4 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-4\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MLPClassifier()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" checked><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MLPClassifier</label><div class=\"sk-toggleable__content\"><pre>MLPClassifier()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "MLPClassifier()"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model= MLPClassifier()\n",
    "model.fit(X_train_ac2,y_train)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "5e8d295c",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9732547597461468"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Model_Score_After_one_to_one_corr=model.score(X_test_ac2, y_test)\n",
    "Model_Score_After_one_to_one_corr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "dd929865",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model_Score_Raw_data: 0.9814143245693563\n",
      "Model_Score_After_vt: 0.986400725294651\n",
      "Model_Score_After_one_to_many_corr: 0.970081595648232\n",
      "Model_Score_After_one_to_one_corr: 0.9732547597461468\n"
     ]
    }
   ],
   "source": [
    "print('Model_Score_Raw_data:',Model_Score_Raw_data)\n",
    "print('Model_Score_After_vt:',Model_Score_After_vt)\n",
    "print('Model_Score_After_one_to_many_corr:',Model_Score_After_one_to_many_corr)\n",
    "print('Model_Score_After_one_to_one_corr:',Model_Score_After_one_to_one_corr)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3602bcf6",
   "metadata": {},
   "source": [
    "**ANOVA Feature Selection:**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "3d5ccaac",
   "metadata": {},
   "outputs": [],
   "source": [
    "sel= SelectKBest(f_classif, k=100).fit(X_train_ac2,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "165e32d4",
   "metadata": {},
   "outputs": [],
   "source": [
    "columns=X_train_ac2.columns[sel.get_support()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "ef5e4a65",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train_anova= sel.transform(X_train_ac2)\n",
    "X_test_anova= sel.transform(X_test_ac2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "bbf27eff",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train_anova= pd.DataFrame(X_train_ac2, columns=columns)\n",
    "X_test_anova= pd.DataFrame(X_test_ac2, columns=columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "c7073c55",
   "metadata": {},
   "outputs": [],
   "source": [
    "model= MLPClassifier()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "ea61f8e3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-5 {color: black;}#sk-container-id-5 pre{padding: 0;}#sk-container-id-5 div.sk-toggleable {background-color: white;}#sk-container-id-5 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-5 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-5 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-5 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-5 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-5 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-5 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-5 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-5 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-5 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-5 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-5 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-5 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-5 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-5 div.sk-item {position: relative;z-index: 1;}#sk-container-id-5 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-5 div.sk-item::before, #sk-container-id-5 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-5 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-5 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-5 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-5 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-5 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-5 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-5 div.sk-label-container {text-align: center;}#sk-container-id-5 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-5 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-5\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MLPClassifier()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" checked><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MLPClassifier</label><div class=\"sk-toggleable__content\"><pre>MLPClassifier()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "MLPClassifier()"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.fit(X_train_anova,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "6755c2ec",
   "metadata": {},
   "outputs": [],
   "source": [
    "Model_Score_after_ANOVA_feature_selection=model.score(X_test_anova,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "d741e631",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model_Score_Raw_data: 0.9814143245693563\n",
      "Model_Score_After_vt: 0.986400725294651\n",
      "Model_Score_After_one_to_many_corr: 0.970081595648232\n",
      "Model_Score_After_one_to_one_corr: 0.9732547597461468\n",
      "Model_Score_After_AVONA_Feature_selection: 0.970081595648232\n"
     ]
    }
   ],
   "source": [
    "print('Model_Score_Raw_data:',Model_Score_Raw_data)\n",
    "print('Model_Score_After_vt:',Model_Score_After_vt)\n",
    "print('Model_Score_After_one_to_many_corr:',Model_Score_After_one_to_many_corr)\n",
    "print('Model_Score_After_one_to_one_corr:',Model_Score_After_one_to_one_corr)\n",
    "print('Model_Score_After_AVONA_Feature_selection:',Model_Score_after_ANOVA_feature_selection)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "053f6a3b",
   "metadata": {},
   "source": [
    "**Chi Square Feature Selection Method:**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "b0e17e8e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the Titanic dataset\n",
    "\n",
    "titanic_data = pd.read_csv(r\"F:\\IT Learning\\My Projects\\Python Projects\\Data Cleaning Datasets\\titanic_data.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "5a04d132",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>survived</th>\n",
       "      <th>pclass</th>\n",
       "      <th>sex</th>\n",
       "      <th>age</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>fare</th>\n",
       "      <th>embarked</th>\n",
       "      <th>classe</th>\n",
       "      <th>who</th>\n",
       "      <th>adult_male</th>\n",
       "      <th>deck</th>\n",
       "      <th>embark_town</th>\n",
       "      <th>alive</th>\n",
       "      <th>alone</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>S</td>\n",
       "      <td>Third</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C</td>\n",
       "      <td>First</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>Cherbourg</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>S</td>\n",
       "      <td>Third</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>S</td>\n",
       "      <td>First</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>C</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>S</td>\n",
       "      <td>Third</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>True</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>884</th>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13.0000</td>\n",
       "      <td>S</td>\n",
       "      <td>Second</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>885</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>female</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>S</td>\n",
       "      <td>First</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>B</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>23.4500</td>\n",
       "      <td>S</td>\n",
       "      <td>Third</td>\n",
       "      <td>woman</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>male</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0000</td>\n",
       "      <td>C</td>\n",
       "      <td>First</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>C</td>\n",
       "      <td>Cherbourg</td>\n",
       "      <td>yes</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>male</td>\n",
       "      <td>32.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7.7500</td>\n",
       "      <td>Q</td>\n",
       "      <td>Third</td>\n",
       "      <td>man</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Queenstown</td>\n",
       "      <td>no</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>889 rows × 15 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     survived  pclass     sex   age  sibsp  parch     fare embarked  classe  \\\n",
       "0           0       3    male  22.0      1      0   7.2500        S   Third   \n",
       "1           1       1  female  38.0      1      0  71.2833        C   First   \n",
       "2           1       3  female  26.0      0      0   7.9250        S   Third   \n",
       "3           1       1  female  35.0      1      0  53.1000        S   First   \n",
       "4           0       3    male  35.0      0      0   8.0500        S   Third   \n",
       "..        ...     ...     ...   ...    ...    ...      ...      ...     ...   \n",
       "884         0       2    male  27.0      0      0  13.0000        S  Second   \n",
       "885         1       1  female  19.0      0      0  30.0000        S   First   \n",
       "886         0       3  female   NaN      1      2  23.4500        S   Third   \n",
       "887         1       1    male  26.0      0      0  30.0000        C   First   \n",
       "888         0       3    male  32.0      0      0   7.7500        Q   Third   \n",
       "\n",
       "       who  adult_male deck  embark_town alive  alone  \n",
       "0      man        True  NaN  Southampton    no  False  \n",
       "1    woman       False    C    Cherbourg   yes  False  \n",
       "2    woman       False  NaN  Southampton   yes   True  \n",
       "3    woman       False    C  Southampton   yes  False  \n",
       "4      man        True  NaN  Southampton    no   True  \n",
       "..     ...         ...  ...          ...   ...    ...  \n",
       "884    man        True  NaN  Southampton    no   True  \n",
       "885  woman       False    B  Southampton   yes   True  \n",
       "886  woman       False  NaN  Southampton    no  False  \n",
       "887    man        True    C    Cherbourg   yes   True  \n",
       "888    man        True  NaN   Queenstown    no   True  \n",
       "\n",
       "[889 rows x 15 columns]"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "titanic_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "7cadcc6f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "survived         0\n",
       "pclass           0\n",
       "sex              0\n",
       "age            176\n",
       "sibsp            0\n",
       "parch            0\n",
       "fare             0\n",
       "embarked         2\n",
       "classe           0\n",
       "who              0\n",
       "adult_male       0\n",
       "deck           686\n",
       "embark_town      2\n",
       "alive            0\n",
       "alone            0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "titanic_data.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "2625d6f2",
   "metadata": {},
   "outputs": [],
   "source": [
    "titanic_data['age'].fillna(titanic_data['age'].mean(),inplace= True)\n",
    "titanic_data['embarked'].fillna(titanic_data['embarked'].mode(),inplace= True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "9efb83cc",
   "metadata": {},
   "outputs": [],
   "source": [
    "titanic_data['age'].fillna(titanic_data['age'].median(), inplace=True)\n",
    "titanic_data['embarked'].fillna(titanic_data['embarked'].mode()[0], inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "a76c51d0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "survived         0\n",
       "pclass           0\n",
       "sex              0\n",
       "age              0\n",
       "sibsp            0\n",
       "parch            0\n",
       "fare             0\n",
       "embarked         0\n",
       "classe           0\n",
       "who              0\n",
       "adult_male       0\n",
       "deck           686\n",
       "embark_town      2\n",
       "alive            0\n",
       "alone            0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "titanic_data.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "ca9de61a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "survived         0\n",
       "pclass           0\n",
       "sex              0\n",
       "age              0\n",
       "sibsp            0\n",
       "parch            0\n",
       "fare             0\n",
       "embarked         0\n",
       "classe           0\n",
       "who              0\n",
       "adult_male       0\n",
       "deck           686\n",
       "embark_town      2\n",
       "alive            0\n",
       "alone            0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "titanic_data.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "19ad5d63",
   "metadata": {},
   "outputs": [],
   "source": [
    "titanic_data.drop(columns= 'deck',inplace= True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "5cf77c4b",
   "metadata": {},
   "outputs": [],
   "source": [
    "titanic_data['embark_town'].fillna(titanic_data['embark_town'].mode()[0], inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "fce8b71a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "survived       0\n",
       "pclass         0\n",
       "sex            0\n",
       "age            0\n",
       "sibsp          0\n",
       "parch          0\n",
       "fare           0\n",
       "embarked       0\n",
       "classe         0\n",
       "who            0\n",
       "adult_male     0\n",
       "embark_town    0\n",
       "alive          0\n",
       "alone          0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "titanic_data.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "eb68ba9c",
   "metadata": {},
   "outputs": [],
   "source": [
    "categorical_columns= ['sex','sibsp','parch','embarked','classe','who','embark_town','alive','survived']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "ab00fc7e",
   "metadata": {},
   "outputs": [],
   "source": [
    "data= pd.DataFrame(titanic_data, columns= categorical_columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "f6e92ec1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>sex</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>embarked</th>\n",
       "      <th>classe</th>\n",
       "      <th>who</th>\n",
       "      <th>embark_town</th>\n",
       "      <th>alive</th>\n",
       "      <th>survived</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>male</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>S</td>\n",
       "      <td>Third</td>\n",
       "      <td>man</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>C</td>\n",
       "      <td>First</td>\n",
       "      <td>woman</td>\n",
       "      <td>Cherbourg</td>\n",
       "      <td>yes</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>S</td>\n",
       "      <td>Third</td>\n",
       "      <td>woman</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>S</td>\n",
       "      <td>First</td>\n",
       "      <td>woman</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>S</td>\n",
       "      <td>Third</td>\n",
       "      <td>man</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>884</th>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>S</td>\n",
       "      <td>Second</td>\n",
       "      <td>man</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>885</th>\n",
       "      <td>female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>S</td>\n",
       "      <td>First</td>\n",
       "      <td>woman</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>yes</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>female</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>S</td>\n",
       "      <td>Third</td>\n",
       "      <td>woman</td>\n",
       "      <td>Southampton</td>\n",
       "      <td>no</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>C</td>\n",
       "      <td>First</td>\n",
       "      <td>man</td>\n",
       "      <td>Cherbourg</td>\n",
       "      <td>yes</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Q</td>\n",
       "      <td>Third</td>\n",
       "      <td>man</td>\n",
       "      <td>Queenstown</td>\n",
       "      <td>no</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>889 rows × 9 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        sex  sibsp  parch embarked  classe    who  embark_town alive  survived\n",
       "0      male      1      0        S   Third    man  Southampton    no         0\n",
       "1    female      1      0        C   First  woman    Cherbourg   yes         1\n",
       "2    female      0      0        S   Third  woman  Southampton   yes         1\n",
       "3    female      1      0        S   First  woman  Southampton   yes         1\n",
       "4      male      0      0        S   Third    man  Southampton    no         0\n",
       "..      ...    ...    ...      ...     ...    ...          ...   ...       ...\n",
       "884    male      0      0        S  Second    man  Southampton    no         0\n",
       "885  female      0      0        S   First  woman  Southampton   yes         1\n",
       "886  female      1      2        S   Third  woman  Southampton    no         0\n",
       "887    male      0      0        C   First    man    Cherbourg   yes         1\n",
       "888    male      0      0        Q   Third    man   Queenstown    no         0\n",
       "\n",
       "[889 rows x 9 columns]"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a07a8b11",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "98f2b088",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Label encode categorical variables\n",
    "label_encoder = LabelEncoder()\n",
    "for column in categorical_columns:\n",
    "    data[column]= label_encoder.fit_transform(data[column])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "3ca2396c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>sex</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>embarked</th>\n",
       "      <th>classe</th>\n",
       "      <th>who</th>\n",
       "      <th>embark_town</th>\n",
       "      <th>alive</th>\n",
       "      <th>survived</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>884</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>885</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>886</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>889 rows × 9 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     sex  sibsp  parch  embarked  classe  who  embark_town  alive  survived\n",
       "0      1      1      0         2       2    1            2      0         0\n",
       "1      0      1      0         0       0    2            0      1         1\n",
       "2      0      0      0         2       2    2            2      1         1\n",
       "3      0      1      0         2       0    2            2      1         1\n",
       "4      1      0      0         2       2    1            2      0         0\n",
       "..   ...    ...    ...       ...     ...  ...          ...    ...       ...\n",
       "884    1      0      0         2       1    1            2      0         0\n",
       "885    0      0      0         2       0    2            2      1         1\n",
       "886    0      1      2         2       2    2            2      0         0\n",
       "887    1      0      0         0       0    1            0      1         1\n",
       "888    1      0      0         1       2    1            1      0         0\n",
       "\n",
       "[889 rows x 9 columns]"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "917574c4",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Separate features (X) and target (y)\n",
    "X= data.drop('survived',axis= 1)\n",
    "y= data['survived']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "c3be806b",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Perform feature selection using Chi-Square test\n",
    "selector= SelectKBest(chi2, k=5)\n",
    "X_new= selector.fit_transform(X,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "id": "5e93c7cd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1, 2, 1, 2, 0],\n",
       "       [0, 0, 2, 0, 1],\n",
       "       [0, 2, 2, 2, 1],\n",
       "       ...,\n",
       "       [0, 2, 2, 2, 0],\n",
       "       [1, 0, 1, 0, 1],\n",
       "       [1, 2, 1, 1, 0]], dtype=int64)"
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_new"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "0c77ecd6",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "# Get the selected features \n",
    "selected_features=X.columns[selector.get_support()] "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "8efdf493",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['sex', 'classe', 'who', 'embark_town', 'alive'], dtype='object')"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "selected_features\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "d7caa8aa",
   "metadata": {},
   "outputs": [],
   "source": [
    "p_values = selector.pvalues_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "3b64fdc8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Feature: sex, p-value: 6.7367605109736825e-22\n",
      "Feature: classe, p-value: 0.26567465104725535\n",
      "Feature: who, p-value: 0.0016689080576356504\n",
      "Feature: embark_town, p-value: 0.0013845383784896526\n",
      "Feature: alive, p-value: 1.8725279618960658e-13\n"
     ]
    }
   ],
   "source": [
    "# Print the selected features and their p-values\n",
    "for feature, p_value in zip(selected_features, p_values):\n",
    "    print(f\"Feature: {feature}, p-value: {p_value}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c7383306",
   "metadata": {},
   "source": [
    "# Wrapper Method:\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6e2cc242",
   "metadata": {},
   "source": [
    "**Forward Selection Method:**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "109dd80f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load Dataset\n",
    "from sklearn.datasets import load_breast_cancer\n",
    "\n",
    "data = load_breast_cancer()\n",
    "X = data.data\n",
    "y = data.target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "9bef3083",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "30"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Before Feature Seletion Columns\n",
    "raw_data_columns= X.shape[1]\n",
    "raw_data_columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "9ef93d84",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Train Test Split Data\n",
    "X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "id": "8702ed10",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Initail Base Model For initialization\n",
    "base_model= LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "id": "5401a4ef",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-6 {color: black;}#sk-container-id-6 pre{padding: 0;}#sk-container-id-6 div.sk-toggleable {background-color: white;}#sk-container-id-6 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-6 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-6 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-6 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-6 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-6 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-6 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-6 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-6 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-6 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-6 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-6 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-6 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-6 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-6 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-6 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-6 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-6 div.sk-item {position: relative;z-index: 1;}#sk-container-id-6 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-6 div.sk-item::before, #sk-container-id-6 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-6 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-6 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-6 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-6 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-6 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-6 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-6 div.sk-label-container {text-align: center;}#sk-container-id-6 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-6 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-6\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" checked><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LogisticRegression()"
      ]
     },
     "execution_count": 78,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "base_model.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "id": "626d7e75",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.956140350877193"
      ]
     },
     "execution_count": 79,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Base Model Score\n",
    "base_model_score= base_model.score(X_test,y_test)\n",
    "base_model_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "b97c4cd9",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Initialize the SequentialFeatureSelector\n",
    "selector= SequentialFeatureSelector(model,n_features_to_select=5,direction= 'forward',scoring= 'accuracy',n_jobs=-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "6671576a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Fit the SequentialFeatureSelector on the training data\n",
    "selector= selector.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "id": "c7ca19b9",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Selected features indices\n",
    "selected_features= selector.get_support(indices= True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "ce0a730e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 6,  9, 17, 20, 25], dtype=int64)"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "selected_features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "55a0ebf9",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Transform the training and testing data to include selected features only\n",
    "X_train_selected= selector.transform(X_train)\n",
    "X_test_selected= selector.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "45ea7a4f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Train a final model using the selected features\n",
    "final_model= LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "id": "19c51da3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-7 {color: black;}#sk-container-id-7 pre{padding: 0;}#sk-container-id-7 div.sk-toggleable {background-color: white;}#sk-container-id-7 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-7 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-7 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-7 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-7 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-7 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-7 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-7 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-7 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-7 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-7 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-7 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-7 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-7 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-7 div.sk-item {position: relative;z-index: 1;}#sk-container-id-7 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-7 div.sk-item::before, #sk-container-id-7 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-7 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-7 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-7 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-7 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-7 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-7 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-7 div.sk-label-container {text-align: center;}#sk-container-id-7 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-7 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-7\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" checked><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LogisticRegression()"
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_model.fit(X_train_selected,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "id": "bfc419d4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9649122807017544"
      ]
     },
     "execution_count": 87,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Final Model Score After Feature Selection \n",
    "final_model_score=final_model.score(X_test_selected,y_test)\n",
    "final_model_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "0e21cf9a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5"
      ]
     },
     "execution_count": 88,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# No. Of features After Forward Selection Method\n",
    "forward_selection_columns= X_train_selected.shape[1]\n",
    "forward_selection_columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "13b7689e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "raw_data_columns: 30 & base_model_score: 0.956140350877193\n",
      "forward_selection_columns: 5 & final_model_score: 0.9649122807017544\n"
     ]
    }
   ],
   "source": [
    "# Final Results\n",
    "print ('raw_data_columns:', raw_data_columns,'&', 'base_model_score:', base_model_score)\n",
    "print ('forward_selection_columns:', forward_selection_columns,'&', 'final_model_score:', final_model_score)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3bd23343",
   "metadata": {},
   "source": [
    "**Backward Elimination Feature Seletion:**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "78aad392",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the breast cancer dataset\n",
    "data = load_breast_cancer()\n",
    "X = data.data\n",
    "y = data.target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "60aee0c6",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Train Test Split Data\n",
    "X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "id": "ac429ee8",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Base Model Score\n",
    "base_model= LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "272488b4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-8 {color: black;}#sk-container-id-8 pre{padding: 0;}#sk-container-id-8 div.sk-toggleable {background-color: white;}#sk-container-id-8 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-8 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-8 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-8 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-8 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-8 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-8 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-8 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-8 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-8 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-8 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-8 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-8 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-8 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-8 div.sk-item {position: relative;z-index: 1;}#sk-container-id-8 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-8 div.sk-item::before, #sk-container-id-8 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-8 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-8 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-8 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-8 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-8 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-8 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-8 div.sk-label-container {text-align: center;}#sk-container-id-8 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-8 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-8\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" checked><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LogisticRegression()"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "base_model.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "0f52a8de",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.956140350877193"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "base_model_score= base_model.score(X_test,y_test)\n",
    "base_model_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "35395c49",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Initialize the SequentialFeatureSelector\n",
    "selector= SequentialFeatureSelector(base_model,n_features_to_select=5,direction= 'backward',scoring= 'accuracy',n_jobs=-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "afbe0ed6",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Fit the SequentialFeatureSelector on the training data\n",
    "selector=selector.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "id": "07061671",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Selected features indices\n",
    "selected_features= selector.get_support(indices=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "id": "b037d6bc",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Transform the training and testing data to include selected features only\n",
    "X_train_selected= selector.transform(X_train)\n",
    "X_test_selected= selector.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "id": "c32e6396",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Train a final model using the selected features\n",
    "final_model= LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "id": "ce997e88",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-9 {color: black;}#sk-container-id-9 pre{padding: 0;}#sk-container-id-9 div.sk-toggleable {background-color: white;}#sk-container-id-9 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-9 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-9 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-9 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-9 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-9 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-9 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-9 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-9 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-9 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-9 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-9 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-9 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-9 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-9 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-9 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-9 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-9 div.sk-item {position: relative;z-index: 1;}#sk-container-id-9 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-9 div.sk-item::before, #sk-container-id-9 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-9 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-9 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-9 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-9 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-9 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-9 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-9 div.sk-label-container {text-align: center;}#sk-container-id-9 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-9 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-9\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-9\" type=\"checkbox\" checked><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LogisticRegression()"
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_model.fit(X_train_selected,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "id": "56f22b7d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9649122807017544"
      ]
     },
     "execution_count": 101,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Final Model Score After Feature Selection\n",
    "final_model_score= final_model.score(X_test_selected,y_test)\n",
    "final_model_score"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "48e2f1f1",
   "metadata": {},
   "source": [
    "**Exhaustive Selection/ Best Feature Selection:**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "id": "f74f50de",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the iris data\n",
    "from sklearn.datasets import load_iris\n",
    "iris = load_iris()\n",
    "X = iris.data\n",
    "y = iris.target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "id": "d3f9cdeb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'data': array([[5.1, 3.5, 1.4, 0.2],\n",
       "        [4.9, 3. , 1.4, 0.2],\n",
       "        [4.7, 3.2, 1.3, 0.2],\n",
       "        [4.6, 3.1, 1.5, 0.2],\n",
       "        [5. , 3.6, 1.4, 0.2],\n",
       "        [5.4, 3.9, 1.7, 0.4],\n",
       "        [4.6, 3.4, 1.4, 0.3],\n",
       "        [5. , 3.4, 1.5, 0.2],\n",
       "        [4.4, 2.9, 1.4, 0.2],\n",
       "        [4.9, 3.1, 1.5, 0.1],\n",
       "        [5.4, 3.7, 1.5, 0.2],\n",
       "        [4.8, 3.4, 1.6, 0.2],\n",
       "        [4.8, 3. , 1.4, 0.1],\n",
       "        [4.3, 3. , 1.1, 0.1],\n",
       "        [5.8, 4. , 1.2, 0.2],\n",
       "        [5.7, 4.4, 1.5, 0.4],\n",
       "        [5.4, 3.9, 1.3, 0.4],\n",
       "        [5.1, 3.5, 1.4, 0.3],\n",
       "        [5.7, 3.8, 1.7, 0.3],\n",
       "        [5.1, 3.8, 1.5, 0.3],\n",
       "        [5.4, 3.4, 1.7, 0.2],\n",
       "        [5.1, 3.7, 1.5, 0.4],\n",
       "        [4.6, 3.6, 1. , 0.2],\n",
       "        [5.1, 3.3, 1.7, 0.5],\n",
       "        [4.8, 3.4, 1.9, 0.2],\n",
       "        [5. , 3. , 1.6, 0.2],\n",
       "        [5. , 3.4, 1.6, 0.4],\n",
       "        [5.2, 3.5, 1.5, 0.2],\n",
       "        [5.2, 3.4, 1.4, 0.2],\n",
       "        [4.7, 3.2, 1.6, 0.2],\n",
       "        [4.8, 3.1, 1.6, 0.2],\n",
       "        [5.4, 3.4, 1.5, 0.4],\n",
       "        [5.2, 4.1, 1.5, 0.1],\n",
       "        [5.5, 4.2, 1.4, 0.2],\n",
       "        [4.9, 3.1, 1.5, 0.2],\n",
       "        [5. , 3.2, 1.2, 0.2],\n",
       "        [5.5, 3.5, 1.3, 0.2],\n",
       "        [4.9, 3.6, 1.4, 0.1],\n",
       "        [4.4, 3. , 1.3, 0.2],\n",
       "        [5.1, 3.4, 1.5, 0.2],\n",
       "        [5. , 3.5, 1.3, 0.3],\n",
       "        [4.5, 2.3, 1.3, 0.3],\n",
       "        [4.4, 3.2, 1.3, 0.2],\n",
       "        [5. , 3.5, 1.6, 0.6],\n",
       "        [5.1, 3.8, 1.9, 0.4],\n",
       "        [4.8, 3. , 1.4, 0.3],\n",
       "        [5.1, 3.8, 1.6, 0.2],\n",
       "        [4.6, 3.2, 1.4, 0.2],\n",
       "        [5.3, 3.7, 1.5, 0.2],\n",
       "        [5. , 3.3, 1.4, 0.2],\n",
       "        [7. , 3.2, 4.7, 1.4],\n",
       "        [6.4, 3.2, 4.5, 1.5],\n",
       "        [6.9, 3.1, 4.9, 1.5],\n",
       "        [5.5, 2.3, 4. , 1.3],\n",
       "        [6.5, 2.8, 4.6, 1.5],\n",
       "        [5.7, 2.8, 4.5, 1.3],\n",
       "        [6.3, 3.3, 4.7, 1.6],\n",
       "        [4.9, 2.4, 3.3, 1. ],\n",
       "        [6.6, 2.9, 4.6, 1.3],\n",
       "        [5.2, 2.7, 3.9, 1.4],\n",
       "        [5. , 2. , 3.5, 1. ],\n",
       "        [5.9, 3. , 4.2, 1.5],\n",
       "        [6. , 2.2, 4. , 1. ],\n",
       "        [6.1, 2.9, 4.7, 1.4],\n",
       "        [5.6, 2.9, 3.6, 1.3],\n",
       "        [6.7, 3.1, 4.4, 1.4],\n",
       "        [5.6, 3. , 4.5, 1.5],\n",
       "        [5.8, 2.7, 4.1, 1. ],\n",
       "        [6.2, 2.2, 4.5, 1.5],\n",
       "        [5.6, 2.5, 3.9, 1.1],\n",
       "        [5.9, 3.2, 4.8, 1.8],\n",
       "        [6.1, 2.8, 4. , 1.3],\n",
       "        [6.3, 2.5, 4.9, 1.5],\n",
       "        [6.1, 2.8, 4.7, 1.2],\n",
       "        [6.4, 2.9, 4.3, 1.3],\n",
       "        [6.6, 3. , 4.4, 1.4],\n",
       "        [6.8, 2.8, 4.8, 1.4],\n",
       "        [6.7, 3. , 5. , 1.7],\n",
       "        [6. , 2.9, 4.5, 1.5],\n",
       "        [5.7, 2.6, 3.5, 1. ],\n",
       "        [5.5, 2.4, 3.8, 1.1],\n",
       "        [5.5, 2.4, 3.7, 1. ],\n",
       "        [5.8, 2.7, 3.9, 1.2],\n",
       "        [6. , 2.7, 5.1, 1.6],\n",
       "        [5.4, 3. , 4.5, 1.5],\n",
       "        [6. , 3.4, 4.5, 1.6],\n",
       "        [6.7, 3.1, 4.7, 1.5],\n",
       "        [6.3, 2.3, 4.4, 1.3],\n",
       "        [5.6, 3. , 4.1, 1.3],\n",
       "        [5.5, 2.5, 4. , 1.3],\n",
       "        [5.5, 2.6, 4.4, 1.2],\n",
       "        [6.1, 3. , 4.6, 1.4],\n",
       "        [5.8, 2.6, 4. , 1.2],\n",
       "        [5. , 2.3, 3.3, 1. ],\n",
       "        [5.6, 2.7, 4.2, 1.3],\n",
       "        [5.7, 3. , 4.2, 1.2],\n",
       "        [5.7, 2.9, 4.2, 1.3],\n",
       "        [6.2, 2.9, 4.3, 1.3],\n",
       "        [5.1, 2.5, 3. , 1.1],\n",
       "        [5.7, 2.8, 4.1, 1.3],\n",
       "        [6.3, 3.3, 6. , 2.5],\n",
       "        [5.8, 2.7, 5.1, 1.9],\n",
       "        [7.1, 3. , 5.9, 2.1],\n",
       "        [6.3, 2.9, 5.6, 1.8],\n",
       "        [6.5, 3. , 5.8, 2.2],\n",
       "        [7.6, 3. , 6.6, 2.1],\n",
       "        [4.9, 2.5, 4.5, 1.7],\n",
       "        [7.3, 2.9, 6.3, 1.8],\n",
       "        [6.7, 2.5, 5.8, 1.8],\n",
       "        [7.2, 3.6, 6.1, 2.5],\n",
       "        [6.5, 3.2, 5.1, 2. ],\n",
       "        [6.4, 2.7, 5.3, 1.9],\n",
       "        [6.8, 3. , 5.5, 2.1],\n",
       "        [5.7, 2.5, 5. , 2. ],\n",
       "        [5.8, 2.8, 5.1, 2.4],\n",
       "        [6.4, 3.2, 5.3, 2.3],\n",
       "        [6.5, 3. , 5.5, 1.8],\n",
       "        [7.7, 3.8, 6.7, 2.2],\n",
       "        [7.7, 2.6, 6.9, 2.3],\n",
       "        [6. , 2.2, 5. , 1.5],\n",
       "        [6.9, 3.2, 5.7, 2.3],\n",
       "        [5.6, 2.8, 4.9, 2. ],\n",
       "        [7.7, 2.8, 6.7, 2. ],\n",
       "        [6.3, 2.7, 4.9, 1.8],\n",
       "        [6.7, 3.3, 5.7, 2.1],\n",
       "        [7.2, 3.2, 6. , 1.8],\n",
       "        [6.2, 2.8, 4.8, 1.8],\n",
       "        [6.1, 3. , 4.9, 1.8],\n",
       "        [6.4, 2.8, 5.6, 2.1],\n",
       "        [7.2, 3. , 5.8, 1.6],\n",
       "        [7.4, 2.8, 6.1, 1.9],\n",
       "        [7.9, 3.8, 6.4, 2. ],\n",
       "        [6.4, 2.8, 5.6, 2.2],\n",
       "        [6.3, 2.8, 5.1, 1.5],\n",
       "        [6.1, 2.6, 5.6, 1.4],\n",
       "        [7.7, 3. , 6.1, 2.3],\n",
       "        [6.3, 3.4, 5.6, 2.4],\n",
       "        [6.4, 3.1, 5.5, 1.8],\n",
       "        [6. , 3. , 4.8, 1.8],\n",
       "        [6.9, 3.1, 5.4, 2.1],\n",
       "        [6.7, 3.1, 5.6, 2.4],\n",
       "        [6.9, 3.1, 5.1, 2.3],\n",
       "        [5.8, 2.7, 5.1, 1.9],\n",
       "        [6.8, 3.2, 5.9, 2.3],\n",
       "        [6.7, 3.3, 5.7, 2.5],\n",
       "        [6.7, 3. , 5.2, 2.3],\n",
       "        [6.3, 2.5, 5. , 1.9],\n",
       "        [6.5, 3. , 5.2, 2. ],\n",
       "        [6.2, 3.4, 5.4, 2.3],\n",
       "        [5.9, 3. , 5.1, 1.8]]),\n",
       " 'target': array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "        0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "        0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
       "        2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
       "        2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]),\n",
       " 'frame': None,\n",
       " 'target_names': array(['setosa', 'versicolor', 'virginica'], dtype='<U10'),\n",
       " 'DESCR': '.. _iris_dataset:\\n\\nIris plants dataset\\n--------------------\\n\\n**Data Set Characteristics:**\\n\\n    :Number of Instances: 150 (50 in each of three classes)\\n    :Number of Attributes: 4 numeric, predictive attributes and the class\\n    :Attribute Information:\\n        - sepal length in cm\\n        - sepal width in cm\\n        - petal length in cm\\n        - petal width in cm\\n        - class:\\n                - Iris-Setosa\\n                - Iris-Versicolour\\n                - Iris-Virginica\\n                \\n    :Summary Statistics:\\n\\n    ============== ==== ==== ======= ===== ====================\\n                    Min  Max   Mean    SD   Class Correlation\\n    ============== ==== ==== ======= ===== ====================\\n    sepal length:   4.3  7.9   5.84   0.83    0.7826\\n    sepal width:    2.0  4.4   3.05   0.43   -0.4194\\n    petal length:   1.0  6.9   3.76   1.76    0.9490  (high!)\\n    petal width:    0.1  2.5   1.20   0.76    0.9565  (high!)\\n    ============== ==== ==== ======= ===== ====================\\n\\n    :Missing Attribute Values: None\\n    :Class Distribution: 33.3% for each of 3 classes.\\n    :Creator: R.A. Fisher\\n    :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)\\n    :Date: July, 1988\\n\\nThe famous Iris database, first used by Sir R.A. Fisher. The dataset is taken\\nfrom Fisher\\'s paper. Note that it\\'s the same as in R, but not as in the UCI\\nMachine Learning Repository, which has two wrong data points.\\n\\nThis is perhaps the best known database to be found in the\\npattern recognition literature.  Fisher\\'s paper is a classic in the field and\\nis referenced frequently to this day.  (See Duda & Hart, for example.)  The\\ndata set contains 3 classes of 50 instances each, where each class refers to a\\ntype of iris plant.  One class is linearly separable from the other 2; the\\nlatter are NOT linearly separable from each other.\\n\\n.. topic:: References\\n\\n   - Fisher, R.A. \"The use of multiple measurements in taxonomic problems\"\\n     Annual Eugenics, 7, Part II, 179-188 (1936); also in \"Contributions to\\n     Mathematical Statistics\" (John Wiley, NY, 1950).\\n   - Duda, R.O., & Hart, P.E. (1973) Pattern Classification and Scene Analysis.\\n     (Q327.D83) John Wiley & Sons.  ISBN 0-471-22361-1.  See page 218.\\n   - Dasarathy, B.V. (1980) \"Nosing Around the Neighborhood: A New System\\n     Structure and Classification Rule for Recognition in Partially Exposed\\n     Environments\".  IEEE Transactions on Pattern Analysis and Machine\\n     Intelligence, Vol. PAMI-2, No. 1, 67-71.\\n   - Gates, G.W. (1972) \"The Reduced Nearest Neighbor Rule\".  IEEE Transactions\\n     on Information Theory, May 1972, 431-433.\\n   - See also: 1988 MLC Proceedings, 54-64.  Cheeseman et al\"s AUTOCLASS II\\n     conceptual clustering system finds 3 classes in the data.\\n   - Many, many more ...',\n",
       " 'feature_names': ['sepal length (cm)',\n",
       "  'sepal width (cm)',\n",
       "  'petal length (cm)',\n",
       "  'petal width (cm)'],\n",
       " 'filename': 'iris.csv',\n",
       " 'data_module': 'sklearn.datasets.data'}"
      ]
     },
     "execution_count": 103,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iris"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "id": "4d5f7028",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create Data as DataFrame\n",
    "X= pd.DataFrame(X,columns=['sepal length', 'sepal width',\n",
    "                 'petal length', 'petal width'])\n",
    "y= pd.DataFrame(y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "id": "617980ac",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Train Test Split:\n",
    "X_train,X_test,y_train,y_test,=train_test_split(X,y,test_size=0.2,random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "id": "33f632f0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.0"
      ]
     },
     "execution_count": 106,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Create and train base model\n",
    "base_model= LogisticRegression()\n",
    "base_model.fit(X_train,y_train)\n",
    "base_model.score(X_test,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "id": "0f6e0f72",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Apply EFS method:\n",
    "sel=EFS(model,max_features=4,scoring= 'accuracy',cv=5,n_jobs=-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "id": "48d2d6f2",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Features: 15/15"
     ]
    }
   ],
   "source": [
    "# Fit the EFS on the training data\n",
    "sel= sel.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "id": "0087b242",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('sepal length', 'sepal width', 'petal length', 'petal width')"
      ]
     },
     "execution_count": 109,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Best Feature Name\n",
    "selected_features= sel.best_feature_names_\n",
    "selected_features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "id": "39f353bc",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Get Metric Data like score, cv score, accuracy,features and all.\n",
    "Metric_data=sel.get_metric_dict()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "id": "c7fb762c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.975"
      ]
     },
     "execution_count": 111,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Best Score of feature subset\n",
    "sel.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "id": "16b7074b",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Transform X_train, x_test Data according to selected features\n",
    "X_train_selected= sel.transform(X_train)\n",
    "X_test_selected= sel.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "id": "c974568d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.0"
      ]
     },
     "execution_count": 113,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Now Train Final Model\n",
    "final_model= LogisticRegression()\n",
    "final_model.fit(X_train_selected,y_train)\n",
    "final_model.score(X_test_selected,y_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a1ed3702",
   "metadata": {},
   "source": [
    "**Recursive Feature Elimination:**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "id": "c0d567c6",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Url of dataset\n",
    "url = \"https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "id": "2dc21821",
   "metadata": {},
   "outputs": [],
   "source": [
    "#column names \n",
    "column_names = [\"sepal_length\", \"sepal_width\", \"petal_length\", \"petal_width\", \"target\"]\n",
    "\n",
    "# Load the dataset from the URL into a Pandas DataFrame\n",
    "data = pd.read_csv(url, header=None, names=column_names)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "id": "e5701840",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>sepal_length</th>\n",
       "      <th>sepal_width</th>\n",
       "      <th>petal_length</th>\n",
       "      <th>petal_width</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.1</td>\n",
       "      <td>3.5</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4.7</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.6</td>\n",
       "      <td>3.1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.0</td>\n",
       "      <td>3.6</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>Iris-setosa</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   sepal_length  sepal_width  petal_length  petal_width       target\n",
       "0           5.1          3.5           1.4          0.2  Iris-setosa\n",
       "1           4.9          3.0           1.4          0.2  Iris-setosa\n",
       "2           4.7          3.2           1.3          0.2  Iris-setosa\n",
       "3           4.6          3.1           1.5          0.2  Iris-setosa\n",
       "4           5.0          3.6           1.4          0.2  Iris-setosa"
      ]
     },
     "execution_count": 116,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "id": "a8ec901e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Split Data in X and y\n",
    "X= data.drop('target',axis=1)\n",
    "y= data['target']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "id": "3f9e0a74",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Model Train and Test Process\n",
    "X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "id": "9e4728b2",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Base Model selection\n",
    "base_model= LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "id": "54e43122",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-10 {color: black;}#sk-container-id-10 pre{padding: 0;}#sk-container-id-10 div.sk-toggleable {background-color: white;}#sk-container-id-10 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-10 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-10 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-10 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-10 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-10 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-10 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-10 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-10 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-10 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-10 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-10 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-10 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-10 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-10 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-10 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-10 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-10 div.sk-item {position: relative;z-index: 1;}#sk-container-id-10 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-10 div.sk-item::before, #sk-container-id-10 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-10 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-10 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-10 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-10 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-10 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-10 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-10 div.sk-label-container {text-align: center;}#sk-container-id-10 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-10 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-10\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-10\" type=\"checkbox\" checked><label for=\"sk-estimator-id-10\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LogisticRegression()"
      ]
     },
     "execution_count": 120,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Trained Data fit on model\n",
    "base_model.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "id": "3231263d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.0"
      ]
     },
     "execution_count": 121,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Base Model Score\n",
    "base_model.score(X_test,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "id": "a4b4c2a0",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Initialize RFE \n",
    "rfe= RFE(estimator= base_model,n_features_to_select=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "id": "83b2b6a3",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Fit the RFE on the training data\n",
    "rfe= rfe.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "id": "5be80636",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Best Feature Indices\n",
    "selected_features_indices= rfe.get_support(indices=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "id": "5cae72ce",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2, 3], dtype=int64)"
      ]
     },
     "execution_count": 125,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "selected_features_indices"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "id": "11684f99",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Best Feature Name\n",
    "selected_feature_names=X_train.columns[selected_features_indices]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "id": "e50d47d7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['petal_length', 'petal_width'], dtype='object')"
      ]
     },
     "execution_count": 127,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "selected_feature_names"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "id": "6edb2dbf",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Transform X_train, x_test Data according to selected features\n",
    "X_train_selected= rfe.transform(X_train)\n",
    "X_test_selected= rfe.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 129,
   "id": "2c2978e3",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Now Train Final Model\n",
    "final_model= LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "id": "b6215fae",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-11 {color: black;}#sk-container-id-11 pre{padding: 0;}#sk-container-id-11 div.sk-toggleable {background-color: white;}#sk-container-id-11 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-11 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-11 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-11 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-11 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-11 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-11 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-11 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-11 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-11 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-11 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-11 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-11 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-11 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-11 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-11 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-11 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-11 div.sk-item {position: relative;z-index: 1;}#sk-container-id-11 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-11 div.sk-item::before, #sk-container-id-11 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-11 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-11 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-11 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-11 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-11 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-11 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-11 div.sk-label-container {text-align: center;}#sk-container-id-11 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-11 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-11\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-11\" type=\"checkbox\" checked><label for=\"sk-estimator-id-11\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LogisticRegression()"
      ]
     },
     "execution_count": 130,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_model.fit(X_train_selected,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "id": "5ed100e0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.0"
      ]
     },
     "execution_count": 131,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_model.score(X_test_selected,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 132,
   "id": "a5c0c5ac",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([3, 2, 1, 1])"
      ]
     },
     "execution_count": 132,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Features Ranking\n",
    "features_ranking=rfe.ranking_\n",
    "features_ranking\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f25eefb4",
   "metadata": {},
   "source": [
    "# Embedded Feature Selection  method:"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0dbdad96",
   "metadata": {},
   "source": [
    "**Regularization Method (Lasso):**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "id": "aa59e3cd",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.datasets import load_iris\n",
    "\n",
    "# Load the Iris dataset\n",
    "iris = load_iris()\n",
    "\n",
    "# Access the data and target attributes\n",
    "X = iris.data  # Features\n",
    "y = iris.target  # Target variable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 134,
   "id": "c1fff4f6",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create Dataframe for both X and y\n",
    "X= pd.DataFrame(X, columns= iris.feature_names)\n",
    "y= pd.DataFrame(y, columns= ['target'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "id": "8659a247",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Split the data into training and testing sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 136,
   "id": "72058c27",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create a Lasso model\n",
    "lasso = Lasso(alpha=0.02, random_state=42)\n",
    "# 'alpha' controls the strength of the L1 regularization, higher values result in more feature sparsity"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 137,
   "id": "de084eca",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create a feature selection transformer using SelectFromModel\n",
    "# This transformer will select features based on the model's coefficients\n",
    "feature_selector = SelectFromModel(lasso)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 138,
   "id": "8a551ad9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-12 {color: black;}#sk-container-id-12 pre{padding: 0;}#sk-container-id-12 div.sk-toggleable {background-color: white;}#sk-container-id-12 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-12 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-12 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-12 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-12 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-12 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-12 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-12 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-12 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-12 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-12 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-12 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-12 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-12 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-12 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-12 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-12 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-12 div.sk-item {position: relative;z-index: 1;}#sk-container-id-12 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-12 div.sk-item::before, #sk-container-id-12 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-12 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-12 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-12 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-12 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-12 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-12 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-12 div.sk-label-container {text-align: center;}#sk-container-id-12 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-12 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-12\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>SelectFromModel(estimator=Lasso(alpha=0.02, random_state=42))</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-12\" type=\"checkbox\" ><label for=\"sk-estimator-id-12\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SelectFromModel</label><div class=\"sk-toggleable__content\"><pre>SelectFromModel(estimator=Lasso(alpha=0.02, random_state=42))</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-13\" type=\"checkbox\" ><label for=\"sk-estimator-id-13\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: Lasso</label><div class=\"sk-toggleable__content\"><pre>Lasso(alpha=0.02, random_state=42)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-14\" type=\"checkbox\" ><label for=\"sk-estimator-id-14\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Lasso</label><div class=\"sk-toggleable__content\"><pre>Lasso(alpha=0.02, random_state=42)</pre></div></div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "SelectFromModel(estimator=Lasso(alpha=0.02, random_state=42))"
      ]
     },
     "execution_count": 138,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Fit the transformer to the training data\n",
    "feature_selector.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 139,
   "id": "cd291297",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Get the selected features using get_support\n",
    "selected_features = feature_selector.get_support(indices=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 140,
   "id": "e940f603",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['sepal length (cm)', 'petal length (cm)', 'petal width (cm)'], dtype='object')"
      ]
     },
     "execution_count": 140,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Get Selected Features Name (if data is in dataframe)\n",
    "selected_features_name= X_train.columns[selected_features]\n",
    "selected_features_name\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 141,
   "id": "9d516ffa",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Now Transform Fitted Data in X_train and X_test\n",
    "X_train= feature_selector.transform(X_train)\n",
    "X_test= feature_selector.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 142,
   "id": "77f30dbd",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create New Dataframe with new selected features\n",
    "X_train_selected= pd.DataFrame(X_train, columns= selected_features)\n",
    "X_test_selected= pd.DataFrame(X_test, columns= selected_features)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 143,
   "id": "dfb2fd02",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-13 {color: black;}#sk-container-id-13 pre{padding: 0;}#sk-container-id-13 div.sk-toggleable {background-color: white;}#sk-container-id-13 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-13 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-13 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-13 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-13 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-13 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-13 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-13 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-13 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-13 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-13 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-13 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-13 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-13 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-13 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-13 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-13 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-13 div.sk-item {position: relative;z-index: 1;}#sk-container-id-13 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-13 div.sk-item::before, #sk-container-id-13 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-13 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-13 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-13 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-13 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-13 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-13 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-13 div.sk-label-container {text-align: center;}#sk-container-id-13 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-13 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-13\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-15\" type=\"checkbox\" checked><label for=\"sk-estimator-id-15\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LogisticRegression()"
      ]
     },
     "execution_count": 143,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Final Score After Feature Selection\n",
    "model= LogisticRegression()\n",
    "model.fit(X_train_selected,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 144,
   "id": "fbacaeb6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9349898290500125"
      ]
     },
     "execution_count": 144,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Final Score After Feature Selection\n",
    "lasso.fit(X_train_selected,y_train)\n",
    "score= lasso.score(X_test_selected,y_test)\n",
    "score"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eaf56a8a",
   "metadata": {},
   "source": [
    "**Tree Based Embedded Method:**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 145,
   "id": "1c9e65cb",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.datasets import load_iris\n",
    "\n",
    "# Load the Iris dataset\n",
    "iris = load_iris()\n",
    "\n",
    "# Access the data and target attributes\n",
    "X = iris.data  # Features\n",
    "y = iris.target  # Target variable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 146,
   "id": "0de08eb7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Split the dataset into training and testing sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 147,
   "id": "08b18a21",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create a Random Forest classifier\n",
    "clf = RandomForestClassifier(n_estimators=100, random_state=42)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 148,
   "id": "320e4d87",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-14 {color: black;}#sk-container-id-14 pre{padding: 0;}#sk-container-id-14 div.sk-toggleable {background-color: white;}#sk-container-id-14 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-14 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-14 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-14 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-14 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-14 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-14 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-14 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-14 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-14 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-14 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-14 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-14 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-14 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-14 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-14 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-14 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-14 div.sk-item {position: relative;z-index: 1;}#sk-container-id-14 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-14 div.sk-item::before, #sk-container-id-14 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-14 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-14 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-14 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-14 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-14 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-14 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-14 div.sk-label-container {text-align: center;}#sk-container-id-14 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-14 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-14\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-16\" type=\"checkbox\" checked><label for=\"sk-estimator-id-16\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier(random_state=42)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomForestClassifier(random_state=42)"
      ]
     },
     "execution_count": 148,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Fit the model to your training data\n",
    "clf.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 149,
   "id": "916b9247",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create a SelectFromModel instance\n",
    "sfm = SelectFromModel(clf)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 150,
   "id": "1497f8bc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2, 3], dtype=int64)"
      ]
     },
     "execution_count": 150,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Selected Features Indices\n",
    "selected_features= sfm.get_support(indices=True)\n",
    "selected_features\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 151,
   "id": "6dce0858",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Fit the SelectFromModel instance and transform your data\n",
    "X_train_selected = sfm.transform(X_train)\n",
    "X_test_selected = sfm.transform(X_test)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 152,
   "id": "1d1ab1f2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-15 {color: black;}#sk-container-id-15 pre{padding: 0;}#sk-container-id-15 div.sk-toggleable {background-color: white;}#sk-container-id-15 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-15 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-15 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-15 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-15 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-15 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-15 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-15 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-15 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-15 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-15 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-15 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-15 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-15 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-15 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-15 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-15 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-15 div.sk-item {position: relative;z-index: 1;}#sk-container-id-15 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-15 div.sk-item::before, #sk-container-id-15 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-15 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-15 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-15 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-15 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-15 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-15 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-15 div.sk-label-container {text-align: center;}#sk-container-id-15 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-15 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-15\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-17\" type=\"checkbox\" checked><label for=\"sk-estimator-id-17\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier(random_state=42)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomForestClassifier(random_state=42)"
      ]
     },
     "execution_count": 152,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Train a classifier on the selected features\n",
    "clf_selected = RandomForestClassifier(n_estimators=100, random_state=42)\n",
    "clf_selected.fit(X_train_selected, y_train)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 153,
   "id": "b7648fd1",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Make predictions on the test set\n",
    "y_pred = clf_selected.predict(X_test_selected)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 154,
   "id": "24c08a50",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 1.0\n"
     ]
    }
   ],
   "source": [
    "# Check the accuracy of the model\n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print(\"Accuracy:\", accuracy)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}