Parkinson's Disease Detection.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Project Title: Detection of Parkinson's Disease "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "#pip install scikit-learn==1.2.2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Importing libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "import seaborn as sns\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.max_rows', None)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Loading dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Link to dataset: https://archive.ics.uci.edu/dataset/174/parkinsons\n",
    "df=pd.read_csv(\"parkinsons.data\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>name</th>\n",
       "      <th>MDVP:Fo(Hz)</th>\n",
       "      <th>MDVP:Fhi(Hz)</th>\n",
       "      <th>MDVP:Flo(Hz)</th>\n",
       "      <th>MDVP:Jitter(%)</th>\n",
       "      <th>MDVP:Jitter(Abs)</th>\n",
       "      <th>MDVP:RAP</th>\n",
       "      <th>MDVP:PPQ</th>\n",
       "      <th>Jitter:DDP</th>\n",
       "      <th>MDVP:Shimmer</th>\n",
       "      <th>MDVP:Shimmer(dB)</th>\n",
       "      <th>Shimmer:APQ3</th>\n",
       "      <th>Shimmer:APQ5</th>\n",
       "      <th>MDVP:APQ</th>\n",
       "      <th>Shimmer:DDA</th>\n",
       "      <th>NHR</th>\n",
       "      <th>HNR</th>\n",
       "      <th>status</th>\n",
       "      <th>RPDE</th>\n",
       "      <th>DFA</th>\n",
       "      <th>spread1</th>\n",
       "      <th>spread2</th>\n",
       "      <th>D2</th>\n",
       "      <th>PPE</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>phon_R01_S01_1</td>\n",
       "      <td>119.992</td>\n",
       "      <td>157.302</td>\n",
       "      <td>74.997</td>\n",
       "      <td>0.00784</td>\n",
       "      <td>0.00007</td>\n",
       "      <td>0.00370</td>\n",
       "      <td>0.00554</td>\n",
       "      <td>0.01109</td>\n",
       "      <td>0.04374</td>\n",
       "      <td>0.426</td>\n",
       "      <td>0.02182</td>\n",
       "      <td>0.03130</td>\n",
       "      <td>0.02971</td>\n",
       "      <td>0.06545</td>\n",
       "      <td>0.02211</td>\n",
       "      <td>21.033</td>\n",
       "      <td>1</td>\n",
       "      <td>0.414783</td>\n",
       "      <td>0.815285</td>\n",
       "      <td>-4.813031</td>\n",
       "      <td>0.266482</td>\n",
       "      <td>2.301442</td>\n",
       "      <td>0.284654</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>phon_R01_S01_2</td>\n",
       "      <td>122.400</td>\n",
       "      <td>148.650</td>\n",
       "      <td>113.819</td>\n",
       "      <td>0.00968</td>\n",
       "      <td>0.00008</td>\n",
       "      <td>0.00465</td>\n",
       "      <td>0.00696</td>\n",
       "      <td>0.01394</td>\n",
       "      <td>0.06134</td>\n",
       "      <td>0.626</td>\n",
       "      <td>0.03134</td>\n",
       "      <td>0.04518</td>\n",
       "      <td>0.04368</td>\n",
       "      <td>0.09403</td>\n",
       "      <td>0.01929</td>\n",
       "      <td>19.085</td>\n",
       "      <td>1</td>\n",
       "      <td>0.458359</td>\n",
       "      <td>0.819521</td>\n",
       "      <td>-4.075192</td>\n",
       "      <td>0.335590</td>\n",
       "      <td>2.486855</td>\n",
       "      <td>0.368674</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>phon_R01_S01_3</td>\n",
       "      <td>116.682</td>\n",
       "      <td>131.111</td>\n",
       "      <td>111.555</td>\n",
       "      <td>0.01050</td>\n",
       "      <td>0.00009</td>\n",
       "      <td>0.00544</td>\n",
       "      <td>0.00781</td>\n",
       "      <td>0.01633</td>\n",
       "      <td>0.05233</td>\n",
       "      <td>0.482</td>\n",
       "      <td>0.02757</td>\n",
       "      <td>0.03858</td>\n",
       "      <td>0.03590</td>\n",
       "      <td>0.08270</td>\n",
       "      <td>0.01309</td>\n",
       "      <td>20.651</td>\n",
       "      <td>1</td>\n",
       "      <td>0.429895</td>\n",
       "      <td>0.825288</td>\n",
       "      <td>-4.443179</td>\n",
       "      <td>0.311173</td>\n",
       "      <td>2.342259</td>\n",
       "      <td>0.332634</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>phon_R01_S01_4</td>\n",
       "      <td>116.676</td>\n",
       "      <td>137.871</td>\n",
       "      <td>111.366</td>\n",
       "      <td>0.00997</td>\n",
       "      <td>0.00009</td>\n",
       "      <td>0.00502</td>\n",
       "      <td>0.00698</td>\n",
       "      <td>0.01505</td>\n",
       "      <td>0.05492</td>\n",
       "      <td>0.517</td>\n",
       "      <td>0.02924</td>\n",
       "      <td>0.04005</td>\n",
       "      <td>0.03772</td>\n",
       "      <td>0.08771</td>\n",
       "      <td>0.01353</td>\n",
       "      <td>20.644</td>\n",
       "      <td>1</td>\n",
       "      <td>0.434969</td>\n",
       "      <td>0.819235</td>\n",
       "      <td>-4.117501</td>\n",
       "      <td>0.334147</td>\n",
       "      <td>2.405554</td>\n",
       "      <td>0.368975</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>phon_R01_S01_5</td>\n",
       "      <td>116.014</td>\n",
       "      <td>141.781</td>\n",
       "      <td>110.655</td>\n",
       "      <td>0.01284</td>\n",
       "      <td>0.00011</td>\n",
       "      <td>0.00655</td>\n",
       "      <td>0.00908</td>\n",
       "      <td>0.01966</td>\n",
       "      <td>0.06425</td>\n",
       "      <td>0.584</td>\n",
       "      <td>0.03490</td>\n",
       "      <td>0.04825</td>\n",
       "      <td>0.04465</td>\n",
       "      <td>0.10470</td>\n",
       "      <td>0.01767</td>\n",
       "      <td>19.649</td>\n",
       "      <td>1</td>\n",
       "      <td>0.417356</td>\n",
       "      <td>0.823484</td>\n",
       "      <td>-3.747787</td>\n",
       "      <td>0.234513</td>\n",
       "      <td>2.332180</td>\n",
       "      <td>0.410335</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             name  MDVP:Fo(Hz)  MDVP:Fhi(Hz)  MDVP:Flo(Hz)  MDVP:Jitter(%)  \\\n",
       "0  phon_R01_S01_1      119.992       157.302        74.997         0.00784   \n",
       "1  phon_R01_S01_2      122.400       148.650       113.819         0.00968   \n",
       "2  phon_R01_S01_3      116.682       131.111       111.555         0.01050   \n",
       "3  phon_R01_S01_4      116.676       137.871       111.366         0.00997   \n",
       "4  phon_R01_S01_5      116.014       141.781       110.655         0.01284   \n",
       "\n",
       "   MDVP:Jitter(Abs)  MDVP:RAP  MDVP:PPQ  Jitter:DDP  MDVP:Shimmer  \\\n",
       "0           0.00007   0.00370   0.00554     0.01109       0.04374   \n",
       "1           0.00008   0.00465   0.00696     0.01394       0.06134   \n",
       "2           0.00009   0.00544   0.00781     0.01633       0.05233   \n",
       "3           0.00009   0.00502   0.00698     0.01505       0.05492   \n",
       "4           0.00011   0.00655   0.00908     0.01966       0.06425   \n",
       "\n",
       "   MDVP:Shimmer(dB)  Shimmer:APQ3  Shimmer:APQ5  MDVP:APQ  Shimmer:DDA  \\\n",
       "0             0.426       0.02182       0.03130   0.02971      0.06545   \n",
       "1             0.626       0.03134       0.04518   0.04368      0.09403   \n",
       "2             0.482       0.02757       0.03858   0.03590      0.08270   \n",
       "3             0.517       0.02924       0.04005   0.03772      0.08771   \n",
       "4             0.584       0.03490       0.04825   0.04465      0.10470   \n",
       "\n",
       "       NHR     HNR  status      RPDE       DFA   spread1   spread2        D2  \\\n",
       "0  0.02211  21.033       1  0.414783  0.815285 -4.813031  0.266482  2.301442   \n",
       "1  0.01929  19.085       1  0.458359  0.819521 -4.075192  0.335590  2.486855   \n",
       "2  0.01309  20.651       1  0.429895  0.825288 -4.443179  0.311173  2.342259   \n",
       "3  0.01353  20.644       1  0.434969  0.819235 -4.117501  0.334147  2.405554   \n",
       "4  0.01767  19.649       1  0.417356  0.823484 -3.747787  0.234513  2.332180   \n",
       "\n",
       "        PPE  \n",
       "0  0.284654  \n",
       "1  0.368674  \n",
       "2  0.332634  \n",
       "3  0.368975  \n",
       "4  0.410335  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(195, 24)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Removing column name"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "df=df.drop([\"name\"], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>MDVP:Fo(Hz)</th>\n",
       "      <th>MDVP:Fhi(Hz)</th>\n",
       "      <th>MDVP:Flo(Hz)</th>\n",
       "      <th>MDVP:Jitter(%)</th>\n",
       "      <th>MDVP:Jitter(Abs)</th>\n",
       "      <th>MDVP:RAP</th>\n",
       "      <th>MDVP:PPQ</th>\n",
       "      <th>Jitter:DDP</th>\n",
       "      <th>MDVP:Shimmer</th>\n",
       "      <th>MDVP:Shimmer(dB)</th>\n",
       "      <th>Shimmer:APQ3</th>\n",
       "      <th>Shimmer:APQ5</th>\n",
       "      <th>MDVP:APQ</th>\n",
       "      <th>Shimmer:DDA</th>\n",
       "      <th>NHR</th>\n",
       "      <th>HNR</th>\n",
       "      <th>status</th>\n",
       "      <th>RPDE</th>\n",
       "      <th>DFA</th>\n",
       "      <th>spread1</th>\n",
       "      <th>spread2</th>\n",
       "      <th>D2</th>\n",
       "      <th>PPE</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>131</th>\n",
       "      <td>120.256</td>\n",
       "      <td>125.306</td>\n",
       "      <td>104.773</td>\n",
       "      <td>0.00407</td>\n",
       "      <td>0.00003</td>\n",
       "      <td>0.00224</td>\n",
       "      <td>0.00205</td>\n",
       "      <td>0.00671</td>\n",
       "      <td>0.01516</td>\n",
       "      <td>0.138</td>\n",
       "      <td>0.00721</td>\n",
       "      <td>0.00815</td>\n",
       "      <td>0.01310</td>\n",
       "      <td>0.02164</td>\n",
       "      <td>0.01015</td>\n",
       "      <td>26.017</td>\n",
       "      <td>1</td>\n",
       "      <td>0.468621</td>\n",
       "      <td>0.735136</td>\n",
       "      <td>-6.112667</td>\n",
       "      <td>0.217013</td>\n",
       "      <td>2.527742</td>\n",
       "      <td>0.170633</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>116</th>\n",
       "      <td>158.219</td>\n",
       "      <td>442.557</td>\n",
       "      <td>71.948</td>\n",
       "      <td>0.00476</td>\n",
       "      <td>0.00003</td>\n",
       "      <td>0.00214</td>\n",
       "      <td>0.00207</td>\n",
       "      <td>0.00642</td>\n",
       "      <td>0.01458</td>\n",
       "      <td>0.148</td>\n",
       "      <td>0.00606</td>\n",
       "      <td>0.00747</td>\n",
       "      <td>0.01312</td>\n",
       "      <td>0.01818</td>\n",
       "      <td>0.01554</td>\n",
       "      <td>26.356</td>\n",
       "      <td>1</td>\n",
       "      <td>0.450798</td>\n",
       "      <td>0.653823</td>\n",
       "      <td>-6.051233</td>\n",
       "      <td>0.273280</td>\n",
       "      <td>2.640798</td>\n",
       "      <td>0.170106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>91</th>\n",
       "      <td>151.955</td>\n",
       "      <td>163.335</td>\n",
       "      <td>147.226</td>\n",
       "      <td>0.00419</td>\n",
       "      <td>0.00003</td>\n",
       "      <td>0.00224</td>\n",
       "      <td>0.00227</td>\n",
       "      <td>0.00672</td>\n",
       "      <td>0.07959</td>\n",
       "      <td>0.772</td>\n",
       "      <td>0.04421</td>\n",
       "      <td>0.04962</td>\n",
       "      <td>0.05690</td>\n",
       "      <td>0.13262</td>\n",
       "      <td>0.01658</td>\n",
       "      <td>19.664</td>\n",
       "      <td>1</td>\n",
       "      <td>0.501037</td>\n",
       "      <td>0.714360</td>\n",
       "      <td>-6.411497</td>\n",
       "      <td>0.207156</td>\n",
       "      <td>2.344876</td>\n",
       "      <td>0.134120</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>152</th>\n",
       "      <td>198.116</td>\n",
       "      <td>233.099</td>\n",
       "      <td>174.478</td>\n",
       "      <td>0.02714</td>\n",
       "      <td>0.00014</td>\n",
       "      <td>0.01568</td>\n",
       "      <td>0.01699</td>\n",
       "      <td>0.04705</td>\n",
       "      <td>0.08684</td>\n",
       "      <td>1.018</td>\n",
       "      <td>0.04284</td>\n",
       "      <td>0.05556</td>\n",
       "      <td>0.08318</td>\n",
       "      <td>0.12851</td>\n",
       "      <td>0.16265</td>\n",
       "      <td>9.449</td>\n",
       "      <td>1</td>\n",
       "      <td>0.584164</td>\n",
       "      <td>0.754449</td>\n",
       "      <td>-2.839756</td>\n",
       "      <td>0.356224</td>\n",
       "      <td>3.184027</td>\n",
       "      <td>0.454721</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>122.400</td>\n",
       "      <td>148.650</td>\n",
       "      <td>113.819</td>\n",
       "      <td>0.00968</td>\n",
       "      <td>0.00008</td>\n",
       "      <td>0.00465</td>\n",
       "      <td>0.00696</td>\n",
       "      <td>0.01394</td>\n",
       "      <td>0.06134</td>\n",
       "      <td>0.626</td>\n",
       "      <td>0.03134</td>\n",
       "      <td>0.04518</td>\n",
       "      <td>0.04368</td>\n",
       "      <td>0.09403</td>\n",
       "      <td>0.01929</td>\n",
       "      <td>19.085</td>\n",
       "      <td>1</td>\n",
       "      <td>0.458359</td>\n",
       "      <td>0.819521</td>\n",
       "      <td>-4.075192</td>\n",
       "      <td>0.335590</td>\n",
       "      <td>2.486855</td>\n",
       "      <td>0.368674</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>164</th>\n",
       "      <td>102.273</td>\n",
       "      <td>142.830</td>\n",
       "      <td>85.902</td>\n",
       "      <td>0.00907</td>\n",
       "      <td>0.00009</td>\n",
       "      <td>0.00493</td>\n",
       "      <td>0.00461</td>\n",
       "      <td>0.01480</td>\n",
       "      <td>0.02814</td>\n",
       "      <td>0.272</td>\n",
       "      <td>0.01579</td>\n",
       "      <td>0.01553</td>\n",
       "      <td>0.02073</td>\n",
       "      <td>0.04736</td>\n",
       "      <td>0.03882</td>\n",
       "      <td>18.447</td>\n",
       "      <td>1</td>\n",
       "      <td>0.671378</td>\n",
       "      <td>0.674562</td>\n",
       "      <td>-2.929379</td>\n",
       "      <td>0.396746</td>\n",
       "      <td>2.560422</td>\n",
       "      <td>0.367233</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>77</th>\n",
       "      <td>110.568</td>\n",
       "      <td>125.394</td>\n",
       "      <td>106.821</td>\n",
       "      <td>0.00462</td>\n",
       "      <td>0.00004</td>\n",
       "      <td>0.00226</td>\n",
       "      <td>0.00280</td>\n",
       "      <td>0.00677</td>\n",
       "      <td>0.02199</td>\n",
       "      <td>0.197</td>\n",
       "      <td>0.01284</td>\n",
       "      <td>0.01199</td>\n",
       "      <td>0.01636</td>\n",
       "      <td>0.03852</td>\n",
       "      <td>0.00420</td>\n",
       "      <td>25.820</td>\n",
       "      <td>1</td>\n",
       "      <td>0.429484</td>\n",
       "      <td>0.816340</td>\n",
       "      <td>-5.391029</td>\n",
       "      <td>0.250572</td>\n",
       "      <td>1.777901</td>\n",
       "      <td>0.232744</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>128</th>\n",
       "      <td>119.031</td>\n",
       "      <td>127.533</td>\n",
       "      <td>109.216</td>\n",
       "      <td>0.00440</td>\n",
       "      <td>0.00004</td>\n",
       "      <td>0.00214</td>\n",
       "      <td>0.00192</td>\n",
       "      <td>0.00641</td>\n",
       "      <td>0.01033</td>\n",
       "      <td>0.098</td>\n",
       "      <td>0.00538</td>\n",
       "      <td>0.00570</td>\n",
       "      <td>0.00811</td>\n",
       "      <td>0.01614</td>\n",
       "      <td>0.01724</td>\n",
       "      <td>26.842</td>\n",
       "      <td>1</td>\n",
       "      <td>0.457541</td>\n",
       "      <td>0.699787</td>\n",
       "      <td>-6.890021</td>\n",
       "      <td>0.152941</td>\n",
       "      <td>2.328513</td>\n",
       "      <td>0.112856</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>173</th>\n",
       "      <td>113.715</td>\n",
       "      <td>116.443</td>\n",
       "      <td>96.913</td>\n",
       "      <td>0.00349</td>\n",
       "      <td>0.00003</td>\n",
       "      <td>0.00171</td>\n",
       "      <td>0.00203</td>\n",
       "      <td>0.00514</td>\n",
       "      <td>0.01472</td>\n",
       "      <td>0.133</td>\n",
       "      <td>0.00748</td>\n",
       "      <td>0.00905</td>\n",
       "      <td>0.01148</td>\n",
       "      <td>0.02245</td>\n",
       "      <td>0.00478</td>\n",
       "      <td>26.547</td>\n",
       "      <td>0</td>\n",
       "      <td>0.380253</td>\n",
       "      <td>0.766700</td>\n",
       "      <td>-5.943501</td>\n",
       "      <td>0.192150</td>\n",
       "      <td>1.852542</td>\n",
       "      <td>0.179677</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>87</th>\n",
       "      <td>176.281</td>\n",
       "      <td>227.381</td>\n",
       "      <td>125.610</td>\n",
       "      <td>0.00520</td>\n",
       "      <td>0.00003</td>\n",
       "      <td>0.00287</td>\n",
       "      <td>0.00312</td>\n",
       "      <td>0.00862</td>\n",
       "      <td>0.06511</td>\n",
       "      <td>0.580</td>\n",
       "      <td>0.03671</td>\n",
       "      <td>0.04159</td>\n",
       "      <td>0.04683</td>\n",
       "      <td>0.11012</td>\n",
       "      <td>0.04824</td>\n",
       "      <td>13.922</td>\n",
       "      <td>1</td>\n",
       "      <td>0.602874</td>\n",
       "      <td>0.740837</td>\n",
       "      <td>-5.515071</td>\n",
       "      <td>0.299549</td>\n",
       "      <td>3.136550</td>\n",
       "      <td>0.220968</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     MDVP:Fo(Hz)  MDVP:Fhi(Hz)  MDVP:Flo(Hz)  MDVP:Jitter(%)  \\\n",
       "131      120.256       125.306       104.773         0.00407   \n",
       "116      158.219       442.557        71.948         0.00476   \n",
       "91       151.955       163.335       147.226         0.00419   \n",
       "152      198.116       233.099       174.478         0.02714   \n",
       "1        122.400       148.650       113.819         0.00968   \n",
       "164      102.273       142.830        85.902         0.00907   \n",
       "77       110.568       125.394       106.821         0.00462   \n",
       "128      119.031       127.533       109.216         0.00440   \n",
       "173      113.715       116.443        96.913         0.00349   \n",
       "87       176.281       227.381       125.610         0.00520   \n",
       "\n",
       "     MDVP:Jitter(Abs)  MDVP:RAP  MDVP:PPQ  Jitter:DDP  MDVP:Shimmer  \\\n",
       "131           0.00003   0.00224   0.00205     0.00671       0.01516   \n",
       "116           0.00003   0.00214   0.00207     0.00642       0.01458   \n",
       "91            0.00003   0.00224   0.00227     0.00672       0.07959   \n",
       "152           0.00014   0.01568   0.01699     0.04705       0.08684   \n",
       "1             0.00008   0.00465   0.00696     0.01394       0.06134   \n",
       "164           0.00009   0.00493   0.00461     0.01480       0.02814   \n",
       "77            0.00004   0.00226   0.00280     0.00677       0.02199   \n",
       "128           0.00004   0.00214   0.00192     0.00641       0.01033   \n",
       "173           0.00003   0.00171   0.00203     0.00514       0.01472   \n",
       "87            0.00003   0.00287   0.00312     0.00862       0.06511   \n",
       "\n",
       "     MDVP:Shimmer(dB)  Shimmer:APQ3  Shimmer:APQ5  MDVP:APQ  Shimmer:DDA  \\\n",
       "131             0.138       0.00721       0.00815   0.01310      0.02164   \n",
       "116             0.148       0.00606       0.00747   0.01312      0.01818   \n",
       "91              0.772       0.04421       0.04962   0.05690      0.13262   \n",
       "152             1.018       0.04284       0.05556   0.08318      0.12851   \n",
       "1               0.626       0.03134       0.04518   0.04368      0.09403   \n",
       "164             0.272       0.01579       0.01553   0.02073      0.04736   \n",
       "77              0.197       0.01284       0.01199   0.01636      0.03852   \n",
       "128             0.098       0.00538       0.00570   0.00811      0.01614   \n",
       "173             0.133       0.00748       0.00905   0.01148      0.02245   \n",
       "87              0.580       0.03671       0.04159   0.04683      0.11012   \n",
       "\n",
       "         NHR     HNR  status      RPDE       DFA   spread1   spread2  \\\n",
       "131  0.01015  26.017       1  0.468621  0.735136 -6.112667  0.217013   \n",
       "116  0.01554  26.356       1  0.450798  0.653823 -6.051233  0.273280   \n",
       "91   0.01658  19.664       1  0.501037  0.714360 -6.411497  0.207156   \n",
       "152  0.16265   9.449       1  0.584164  0.754449 -2.839756  0.356224   \n",
       "1    0.01929  19.085       1  0.458359  0.819521 -4.075192  0.335590   \n",
       "164  0.03882  18.447       1  0.671378  0.674562 -2.929379  0.396746   \n",
       "77   0.00420  25.820       1  0.429484  0.816340 -5.391029  0.250572   \n",
       "128  0.01724  26.842       1  0.457541  0.699787 -6.890021  0.152941   \n",
       "173  0.00478  26.547       0  0.380253  0.766700 -5.943501  0.192150   \n",
       "87   0.04824  13.922       1  0.602874  0.740837 -5.515071  0.299549   \n",
       "\n",
       "           D2       PPE  \n",
       "131  2.527742  0.170633  \n",
       "116  2.640798  0.170106  \n",
       "91   2.344876  0.134120  \n",
       "152  3.184027  0.454721  \n",
       "1    2.486855  0.368674  \n",
       "164  2.560422  0.367233  \n",
       "77   1.777901  0.232744  \n",
       "128  2.328513  0.112856  \n",
       "173  1.852542  0.179677  \n",
       "87   3.136550  0.220968  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.sample(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "More information"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 195 entries, 0 to 194\n",
      "Data columns (total 23 columns):\n",
      " #   Column            Non-Null Count  Dtype  \n",
      "---  ------            --------------  -----  \n",
      " 0   MDVP:Fo(Hz)       195 non-null    float64\n",
      " 1   MDVP:Fhi(Hz)      195 non-null    float64\n",
      " 2   MDVP:Flo(Hz)      195 non-null    float64\n",
      " 3   MDVP:Jitter(%)    195 non-null    float64\n",
      " 4   MDVP:Jitter(Abs)  195 non-null    float64\n",
      " 5   MDVP:RAP          195 non-null    float64\n",
      " 6   MDVP:PPQ          195 non-null    float64\n",
      " 7   Jitter:DDP        195 non-null    float64\n",
      " 8   MDVP:Shimmer      195 non-null    float64\n",
      " 9   MDVP:Shimmer(dB)  195 non-null    float64\n",
      " 10  Shimmer:APQ3      195 non-null    float64\n",
      " 11  Shimmer:APQ5      195 non-null    float64\n",
      " 12  MDVP:APQ          195 non-null    float64\n",
      " 13  Shimmer:DDA       195 non-null    float64\n",
      " 14  NHR               195 non-null    float64\n",
      " 15  HNR               195 non-null    float64\n",
      " 16  status            195 non-null    int64  \n",
      " 17  RPDE              195 non-null    float64\n",
      " 18  DFA               195 non-null    float64\n",
      " 19  spread1           195 non-null    float64\n",
      " 20  spread2           195 non-null    float64\n",
      " 21  D2                195 non-null    float64\n",
      " 22  PPE               195 non-null    float64\n",
      "dtypes: float64(22), int64(1)\n",
      "memory usage: 35.2 KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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>MDVP:Fo(Hz)</th>\n",
       "      <th>MDVP:Fhi(Hz)</th>\n",
       "      <th>MDVP:Flo(Hz)</th>\n",
       "      <th>MDVP:Jitter(%)</th>\n",
       "      <th>MDVP:Jitter(Abs)</th>\n",
       "      <th>MDVP:RAP</th>\n",
       "      <th>MDVP:PPQ</th>\n",
       "      <th>Jitter:DDP</th>\n",
       "      <th>MDVP:Shimmer</th>\n",
       "      <th>MDVP:Shimmer(dB)</th>\n",
       "      <th>Shimmer:APQ3</th>\n",
       "      <th>Shimmer:APQ5</th>\n",
       "      <th>MDVP:APQ</th>\n",
       "      <th>Shimmer:DDA</th>\n",
       "      <th>NHR</th>\n",
       "      <th>HNR</th>\n",
       "      <th>status</th>\n",
       "      <th>RPDE</th>\n",
       "      <th>DFA</th>\n",
       "      <th>spread1</th>\n",
       "      <th>spread2</th>\n",
       "      <th>D2</th>\n",
       "      <th>PPE</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "      <td>195.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>154.228641</td>\n",
       "      <td>197.104918</td>\n",
       "      <td>116.324631</td>\n",
       "      <td>0.006220</td>\n",
       "      <td>0.000044</td>\n",
       "      <td>0.003306</td>\n",
       "      <td>0.003446</td>\n",
       "      <td>0.009920</td>\n",
       "      <td>0.029709</td>\n",
       "      <td>0.282251</td>\n",
       "      <td>0.015664</td>\n",
       "      <td>0.017878</td>\n",
       "      <td>0.024081</td>\n",
       "      <td>0.046993</td>\n",
       "      <td>0.024847</td>\n",
       "      <td>21.885974</td>\n",
       "      <td>0.753846</td>\n",
       "      <td>0.498536</td>\n",
       "      <td>0.718099</td>\n",
       "      <td>-5.684397</td>\n",
       "      <td>0.226510</td>\n",
       "      <td>2.381826</td>\n",
       "      <td>0.206552</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>41.390065</td>\n",
       "      <td>91.491548</td>\n",
       "      <td>43.521413</td>\n",
       "      <td>0.004848</td>\n",
       "      <td>0.000035</td>\n",
       "      <td>0.002968</td>\n",
       "      <td>0.002759</td>\n",
       "      <td>0.008903</td>\n",
       "      <td>0.018857</td>\n",
       "      <td>0.194877</td>\n",
       "      <td>0.010153</td>\n",
       "      <td>0.012024</td>\n",
       "      <td>0.016947</td>\n",
       "      <td>0.030459</td>\n",
       "      <td>0.040418</td>\n",
       "      <td>4.425764</td>\n",
       "      <td>0.431878</td>\n",
       "      <td>0.103942</td>\n",
       "      <td>0.055336</td>\n",
       "      <td>1.090208</td>\n",
       "      <td>0.083406</td>\n",
       "      <td>0.382799</td>\n",
       "      <td>0.090119</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>88.333000</td>\n",
       "      <td>102.145000</td>\n",
       "      <td>65.476000</td>\n",
       "      <td>0.001680</td>\n",
       "      <td>0.000007</td>\n",
       "      <td>0.000680</td>\n",
       "      <td>0.000920</td>\n",
       "      <td>0.002040</td>\n",
       "      <td>0.009540</td>\n",
       "      <td>0.085000</td>\n",
       "      <td>0.004550</td>\n",
       "      <td>0.005700</td>\n",
       "      <td>0.007190</td>\n",
       "      <td>0.013640</td>\n",
       "      <td>0.000650</td>\n",
       "      <td>8.441000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.256570</td>\n",
       "      <td>0.574282</td>\n",
       "      <td>-7.964984</td>\n",
       "      <td>0.006274</td>\n",
       "      <td>1.423287</td>\n",
       "      <td>0.044539</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>117.572000</td>\n",
       "      <td>134.862500</td>\n",
       "      <td>84.291000</td>\n",
       "      <td>0.003460</td>\n",
       "      <td>0.000020</td>\n",
       "      <td>0.001660</td>\n",
       "      <td>0.001860</td>\n",
       "      <td>0.004985</td>\n",
       "      <td>0.016505</td>\n",
       "      <td>0.148500</td>\n",
       "      <td>0.008245</td>\n",
       "      <td>0.009580</td>\n",
       "      <td>0.013080</td>\n",
       "      <td>0.024735</td>\n",
       "      <td>0.005925</td>\n",
       "      <td>19.198000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.421306</td>\n",
       "      <td>0.674758</td>\n",
       "      <td>-6.450096</td>\n",
       "      <td>0.174351</td>\n",
       "      <td>2.099125</td>\n",
       "      <td>0.137451</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>148.790000</td>\n",
       "      <td>175.829000</td>\n",
       "      <td>104.315000</td>\n",
       "      <td>0.004940</td>\n",
       "      <td>0.000030</td>\n",
       "      <td>0.002500</td>\n",
       "      <td>0.002690</td>\n",
       "      <td>0.007490</td>\n",
       "      <td>0.022970</td>\n",
       "      <td>0.221000</td>\n",
       "      <td>0.012790</td>\n",
       "      <td>0.013470</td>\n",
       "      <td>0.018260</td>\n",
       "      <td>0.038360</td>\n",
       "      <td>0.011660</td>\n",
       "      <td>22.085000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.495954</td>\n",
       "      <td>0.722254</td>\n",
       "      <td>-5.720868</td>\n",
       "      <td>0.218885</td>\n",
       "      <td>2.361532</td>\n",
       "      <td>0.194052</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>182.769000</td>\n",
       "      <td>224.205500</td>\n",
       "      <td>140.018500</td>\n",
       "      <td>0.007365</td>\n",
       "      <td>0.000060</td>\n",
       "      <td>0.003835</td>\n",
       "      <td>0.003955</td>\n",
       "      <td>0.011505</td>\n",
       "      <td>0.037885</td>\n",
       "      <td>0.350000</td>\n",
       "      <td>0.020265</td>\n",
       "      <td>0.022380</td>\n",
       "      <td>0.029400</td>\n",
       "      <td>0.060795</td>\n",
       "      <td>0.025640</td>\n",
       "      <td>25.075500</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.587562</td>\n",
       "      <td>0.761881</td>\n",
       "      <td>-5.046192</td>\n",
       "      <td>0.279234</td>\n",
       "      <td>2.636456</td>\n",
       "      <td>0.252980</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>260.105000</td>\n",
       "      <td>592.030000</td>\n",
       "      <td>239.170000</td>\n",
       "      <td>0.033160</td>\n",
       "      <td>0.000260</td>\n",
       "      <td>0.021440</td>\n",
       "      <td>0.019580</td>\n",
       "      <td>0.064330</td>\n",
       "      <td>0.119080</td>\n",
       "      <td>1.302000</td>\n",
       "      <td>0.056470</td>\n",
       "      <td>0.079400</td>\n",
       "      <td>0.137780</td>\n",
       "      <td>0.169420</td>\n",
       "      <td>0.314820</td>\n",
       "      <td>33.047000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.685151</td>\n",
       "      <td>0.825288</td>\n",
       "      <td>-2.434031</td>\n",
       "      <td>0.450493</td>\n",
       "      <td>3.671155</td>\n",
       "      <td>0.527367</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       MDVP:Fo(Hz)  MDVP:Fhi(Hz)  MDVP:Flo(Hz)  MDVP:Jitter(%)  \\\n",
       "count   195.000000    195.000000    195.000000      195.000000   \n",
       "mean    154.228641    197.104918    116.324631        0.006220   \n",
       "std      41.390065     91.491548     43.521413        0.004848   \n",
       "min      88.333000    102.145000     65.476000        0.001680   \n",
       "25%     117.572000    134.862500     84.291000        0.003460   \n",
       "50%     148.790000    175.829000    104.315000        0.004940   \n",
       "75%     182.769000    224.205500    140.018500        0.007365   \n",
       "max     260.105000    592.030000    239.170000        0.033160   \n",
       "\n",
       "       MDVP:Jitter(Abs)    MDVP:RAP    MDVP:PPQ  Jitter:DDP  MDVP:Shimmer  \\\n",
       "count        195.000000  195.000000  195.000000  195.000000    195.000000   \n",
       "mean           0.000044    0.003306    0.003446    0.009920      0.029709   \n",
       "std            0.000035    0.002968    0.002759    0.008903      0.018857   \n",
       "min            0.000007    0.000680    0.000920    0.002040      0.009540   \n",
       "25%            0.000020    0.001660    0.001860    0.004985      0.016505   \n",
       "50%            0.000030    0.002500    0.002690    0.007490      0.022970   \n",
       "75%            0.000060    0.003835    0.003955    0.011505      0.037885   \n",
       "max            0.000260    0.021440    0.019580    0.064330      0.119080   \n",
       "\n",
       "       MDVP:Shimmer(dB)  Shimmer:APQ3  Shimmer:APQ5    MDVP:APQ  Shimmer:DDA  \\\n",
       "count        195.000000    195.000000    195.000000  195.000000   195.000000   \n",
       "mean           0.282251      0.015664      0.017878    0.024081     0.046993   \n",
       "std            0.194877      0.010153      0.012024    0.016947     0.030459   \n",
       "min            0.085000      0.004550      0.005700    0.007190     0.013640   \n",
       "25%            0.148500      0.008245      0.009580    0.013080     0.024735   \n",
       "50%            0.221000      0.012790      0.013470    0.018260     0.038360   \n",
       "75%            0.350000      0.020265      0.022380    0.029400     0.060795   \n",
       "max            1.302000      0.056470      0.079400    0.137780     0.169420   \n",
       "\n",
       "              NHR         HNR      status        RPDE         DFA     spread1  \\\n",
       "count  195.000000  195.000000  195.000000  195.000000  195.000000  195.000000   \n",
       "mean     0.024847   21.885974    0.753846    0.498536    0.718099   -5.684397   \n",
       "std      0.040418    4.425764    0.431878    0.103942    0.055336    1.090208   \n",
       "min      0.000650    8.441000    0.000000    0.256570    0.574282   -7.964984   \n",
       "25%      0.005925   19.198000    1.000000    0.421306    0.674758   -6.450096   \n",
       "50%      0.011660   22.085000    1.000000    0.495954    0.722254   -5.720868   \n",
       "75%      0.025640   25.075500    1.000000    0.587562    0.761881   -5.046192   \n",
       "max      0.314820   33.047000    1.000000    0.685151    0.825288   -2.434031   \n",
       "\n",
       "          spread2          D2         PPE  \n",
       "count  195.000000  195.000000  195.000000  \n",
       "mean     0.226510    2.381826    0.206552  \n",
       "std      0.083406    0.382799    0.090119  \n",
       "min      0.006274    1.423287    0.044539  \n",
       "25%      0.174351    2.099125    0.137451  \n",
       "50%      0.218885    2.361532    0.194052  \n",
       "75%      0.279234    2.636456    0.252980  \n",
       "max      0.450493    3.671155    0.527367  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Check for missing values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "MDVP:Fo(Hz)         0\n",
       "MDVP:Fhi(Hz)        0\n",
       "MDVP:Flo(Hz)        0\n",
       "MDVP:Jitter(%)      0\n",
       "MDVP:Jitter(Abs)    0\n",
       "MDVP:RAP            0\n",
       "MDVP:PPQ            0\n",
       "Jitter:DDP          0\n",
       "MDVP:Shimmer        0\n",
       "MDVP:Shimmer(dB)    0\n",
       "Shimmer:APQ3        0\n",
       "Shimmer:APQ5        0\n",
       "MDVP:APQ            0\n",
       "Shimmer:DDA         0\n",
       "NHR                 0\n",
       "HNR                 0\n",
       "status              0\n",
       "RPDE                0\n",
       "DFA                 0\n",
       "spread1             0\n",
       "spread2             0\n",
       "D2                  0\n",
       "PPE                 0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Labels for Status\n",
    "1. {1: Person has disease}\n",
    "2. {0: Person is absolutely healthy}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1    147\n",
       "0     48\n",
       "Name: status, dtype: int64"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"status\"].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Data visualisation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Countplot for status\n",
    "plt.figure(figsize=(6,6))\n",
    "sns.countplot(data=df, x=\"status\")\n",
    "plt.title(\"Frequency of Status\")\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Training and testing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "X=df.drop([\"status\"], axis=1)\n",
    "y=df[\"status\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "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>MDVP:Fo(Hz)</th>\n",
       "      <th>MDVP:Fhi(Hz)</th>\n",
       "      <th>MDVP:Flo(Hz)</th>\n",
       "      <th>MDVP:Jitter(%)</th>\n",
       "      <th>MDVP:Jitter(Abs)</th>\n",
       "      <th>MDVP:RAP</th>\n",
       "      <th>MDVP:PPQ</th>\n",
       "      <th>Jitter:DDP</th>\n",
       "      <th>MDVP:Shimmer</th>\n",
       "      <th>MDVP:Shimmer(dB)</th>\n",
       "      <th>Shimmer:APQ3</th>\n",
       "      <th>Shimmer:APQ5</th>\n",
       "      <th>MDVP:APQ</th>\n",
       "      <th>Shimmer:DDA</th>\n",
       "      <th>NHR</th>\n",
       "      <th>HNR</th>\n",
       "      <th>RPDE</th>\n",
       "      <th>DFA</th>\n",
       "      <th>spread1</th>\n",
       "      <th>spread2</th>\n",
       "      <th>D2</th>\n",
       "      <th>PPE</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>119.992</td>\n",
       "      <td>157.302</td>\n",
       "      <td>74.997</td>\n",
       "      <td>0.00784</td>\n",
       "      <td>0.00007</td>\n",
       "      <td>0.00370</td>\n",
       "      <td>0.00554</td>\n",
       "      <td>0.01109</td>\n",
       "      <td>0.04374</td>\n",
       "      <td>0.426</td>\n",
       "      <td>0.02182</td>\n",
       "      <td>0.03130</td>\n",
       "      <td>0.02971</td>\n",
       "      <td>0.06545</td>\n",
       "      <td>0.02211</td>\n",
       "      <td>21.033</td>\n",
       "      <td>0.414783</td>\n",
       "      <td>0.815285</td>\n",
       "      <td>-4.813031</td>\n",
       "      <td>0.266482</td>\n",
       "      <td>2.301442</td>\n",
       "      <td>0.284654</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>122.400</td>\n",
       "      <td>148.650</td>\n",
       "      <td>113.819</td>\n",
       "      <td>0.00968</td>\n",
       "      <td>0.00008</td>\n",
       "      <td>0.00465</td>\n",
       "      <td>0.00696</td>\n",
       "      <td>0.01394</td>\n",
       "      <td>0.06134</td>\n",
       "      <td>0.626</td>\n",
       "      <td>0.03134</td>\n",
       "      <td>0.04518</td>\n",
       "      <td>0.04368</td>\n",
       "      <td>0.09403</td>\n",
       "      <td>0.01929</td>\n",
       "      <td>19.085</td>\n",
       "      <td>0.458359</td>\n",
       "      <td>0.819521</td>\n",
       "      <td>-4.075192</td>\n",
       "      <td>0.335590</td>\n",
       "      <td>2.486855</td>\n",
       "      <td>0.368674</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>116.682</td>\n",
       "      <td>131.111</td>\n",
       "      <td>111.555</td>\n",
       "      <td>0.01050</td>\n",
       "      <td>0.00009</td>\n",
       "      <td>0.00544</td>\n",
       "      <td>0.00781</td>\n",
       "      <td>0.01633</td>\n",
       "      <td>0.05233</td>\n",
       "      <td>0.482</td>\n",
       "      <td>0.02757</td>\n",
       "      <td>0.03858</td>\n",
       "      <td>0.03590</td>\n",
       "      <td>0.08270</td>\n",
       "      <td>0.01309</td>\n",
       "      <td>20.651</td>\n",
       "      <td>0.429895</td>\n",
       "      <td>0.825288</td>\n",
       "      <td>-4.443179</td>\n",
       "      <td>0.311173</td>\n",
       "      <td>2.342259</td>\n",
       "      <td>0.332634</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>116.676</td>\n",
       "      <td>137.871</td>\n",
       "      <td>111.366</td>\n",
       "      <td>0.00997</td>\n",
       "      <td>0.00009</td>\n",
       "      <td>0.00502</td>\n",
       "      <td>0.00698</td>\n",
       "      <td>0.01505</td>\n",
       "      <td>0.05492</td>\n",
       "      <td>0.517</td>\n",
       "      <td>0.02924</td>\n",
       "      <td>0.04005</td>\n",
       "      <td>0.03772</td>\n",
       "      <td>0.08771</td>\n",
       "      <td>0.01353</td>\n",
       "      <td>20.644</td>\n",
       "      <td>0.434969</td>\n",
       "      <td>0.819235</td>\n",
       "      <td>-4.117501</td>\n",
       "      <td>0.334147</td>\n",
       "      <td>2.405554</td>\n",
       "      <td>0.368975</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>116.014</td>\n",
       "      <td>141.781</td>\n",
       "      <td>110.655</td>\n",
       "      <td>0.01284</td>\n",
       "      <td>0.00011</td>\n",
       "      <td>0.00655</td>\n",
       "      <td>0.00908</td>\n",
       "      <td>0.01966</td>\n",
       "      <td>0.06425</td>\n",
       "      <td>0.584</td>\n",
       "      <td>0.03490</td>\n",
       "      <td>0.04825</td>\n",
       "      <td>0.04465</td>\n",
       "      <td>0.10470</td>\n",
       "      <td>0.01767</td>\n",
       "      <td>19.649</td>\n",
       "      <td>0.417356</td>\n",
       "      <td>0.823484</td>\n",
       "      <td>-3.747787</td>\n",
       "      <td>0.234513</td>\n",
       "      <td>2.332180</td>\n",
       "      <td>0.410335</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   MDVP:Fo(Hz)  MDVP:Fhi(Hz)  MDVP:Flo(Hz)  MDVP:Jitter(%)  MDVP:Jitter(Abs)  \\\n",
       "0      119.992       157.302        74.997         0.00784           0.00007   \n",
       "1      122.400       148.650       113.819         0.00968           0.00008   \n",
       "2      116.682       131.111       111.555         0.01050           0.00009   \n",
       "3      116.676       137.871       111.366         0.00997           0.00009   \n",
       "4      116.014       141.781       110.655         0.01284           0.00011   \n",
       "\n",
       "   MDVP:RAP  MDVP:PPQ  Jitter:DDP  MDVP:Shimmer  MDVP:Shimmer(dB)  \\\n",
       "0   0.00370   0.00554     0.01109       0.04374             0.426   \n",
       "1   0.00465   0.00696     0.01394       0.06134             0.626   \n",
       "2   0.00544   0.00781     0.01633       0.05233             0.482   \n",
       "3   0.00502   0.00698     0.01505       0.05492             0.517   \n",
       "4   0.00655   0.00908     0.01966       0.06425             0.584   \n",
       "\n",
       "   Shimmer:APQ3  Shimmer:APQ5  MDVP:APQ  Shimmer:DDA      NHR     HNR  \\\n",
       "0       0.02182       0.03130   0.02971      0.06545  0.02211  21.033   \n",
       "1       0.03134       0.04518   0.04368      0.09403  0.01929  19.085   \n",
       "2       0.02757       0.03858   0.03590      0.08270  0.01309  20.651   \n",
       "3       0.02924       0.04005   0.03772      0.08771  0.01353  20.644   \n",
       "4       0.03490       0.04825   0.04465      0.10470  0.01767  19.649   \n",
       "\n",
       "       RPDE       DFA   spread1   spread2        D2       PPE  \n",
       "0  0.414783  0.815285 -4.813031  0.266482  2.301442  0.284654  \n",
       "1  0.458359  0.819521 -4.075192  0.335590  2.486855  0.368674  \n",
       "2  0.429895  0.825288 -4.443179  0.311173  2.342259  0.332634  \n",
       "3  0.434969  0.819235 -4.117501  0.334147  2.405554  0.368975  \n",
       "4  0.417356  0.823484 -3.747787  0.234513  2.332180  0.410335  "
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    1\n",
       "1    1\n",
       "2    1\n",
       "3    1\n",
       "4    1\n",
       "Name: status, dtype: int64"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test=train_test_split(X, y, test_size=0.20, random_state=42)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Data standardization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import MinMaxScaler"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "#mmc\n",
    "mmc=MinMaxScaler(feature_range = (0,1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train_trans=mmc.fit_transform(X_train)\n",
    "X_test_trans=mmc.transform(X_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "XGB Classifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: xgboost in /opt/anaconda3/lib/python3.8/site-packages (1.7.6)\n",
      "Requirement already satisfied: numpy in /opt/anaconda3/lib/python3.8/site-packages (from xgboost) (1.23.5)\n",
      "Requirement already satisfied: scipy in /opt/anaconda3/lib/python3.8/site-packages (from xgboost) (1.10.1)\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    }
   ],
   "source": [
    "pip install xgboost"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "from xgboost import XGBClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "xgb=XGBClassifier()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Model \n",
    "model=xgb.fit(X_train_trans, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;background-color: white;}#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>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "              colsample_bylevel=None, colsample_bynode=None,\n",
       "              colsample_bytree=None, early_stopping_rounds=None,\n",
       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "              gamma=None, gpu_id=None, grow_policy=None, importance_type=None,\n",
       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "              n_estimators=100, n_jobs=None, num_parallel_tree=None,\n",
       "              predictor=None, random_state=None, ...)</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\">XGBClassifier</label><div class=\"sk-toggleable__content\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "              colsample_bylevel=None, colsample_bynode=None,\n",
       "              colsample_bytree=None, early_stopping_rounds=None,\n",
       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "              gamma=None, gpu_id=None, grow_policy=None, importance_type=None,\n",
       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "              n_estimators=100, n_jobs=None, num_parallel_tree=None,\n",
       "              predictor=None, random_state=None, ...)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "              colsample_bylevel=None, colsample_bynode=None,\n",
       "              colsample_bytree=None, early_stopping_rounds=None,\n",
       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "              gamma=None, gpu_id=None, grow_policy=None, importance_type=None,\n",
       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "              n_estimators=100, n_jobs=None, num_parallel_tree=None,\n",
       "              predictor=None, random_state=None, ...)"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred=xgb.predict(X_test_trans)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1,\n",
       "       1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1])"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Accuracy score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import accuracy_score, confusion_matrix, classification_report"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy %= 94.87179487179486\n"
     ]
    }
   ],
   "source": [
    "score=accuracy_score(y_test, y_pred)\n",
    "print(\"Accuracy %=\",(score*100))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Classification report"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       1.00      0.71      0.83         7\n",
      "           1       0.94      1.00      0.97        32\n",
      "\n",
      "    accuracy                           0.95        39\n",
      "   macro avg       0.97      0.86      0.90        39\n",
      "weighted avg       0.95      0.95      0.95        39\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(classification_report(y_test,y_pred))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Confusion matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "matrix=confusion_matrix(y_test, y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 5,  2],\n",
       "       [ 0, 32]])"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "matrix"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Heatmap"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.heatmap(data=matrix, annot=True, fmt='g')\n",
    "plt.title(\"XGB Classifier\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Model testing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_input_1=pd.DataFrame([[119.992, 157.302, 74.997, 0.00784, 0.00007, 0.00370, 0.00554, \n",
    "                          0.01109, 0.04374, 0.426, 0.02182, 0.03130, 0.02971, 0.06545, \n",
    "                          0.02211, 21.033, 0.414783, 0.815285, -4.813031, 0.266482, 2.301442, 0.284654]], \n",
    "                        columns=[\"MDVP:Fo(Hz)\", \"MDVP:Fhi(Hz)\", \"MDVP:Flo(Hz)\", \"MDVP:Jitter(%)\", \"MDVP:Jitter(Abs)\",\n",
    "                                 \"MDVP:RAP\", \"MDVP:PPQ\", \"Jitter:DDP\", \"MDVP:Shimmer\", \"MDVP:Shimmer(dB)\", \"Shimmer:APQ3\",\n",
    "                                 \"Shimmer:APQ5\", \"MDVP:APQ\", \"Shimmer:DDA\", \"NHR\", \"HNR\", \"RPDE\", \"DFA\", \"spread1\", \"spread2\",\n",
    "                                 \"D2\", \"PPE\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0])"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "xgb.predict(test_input_1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_input_2=pd.DataFrame([[129.992, 167.302, 75.997, 0.00984, 0.00007, 0.00370, 0.00554, \n",
    "                          0.01209, 0.05, 0.4, 0.02182, 0.03130, 0.02971, 0.06545, \n",
    "                          0.02211, 21.033, 0.414783, 0.815285, -4.813031, 0.266482, 3.301442, 0.284]], \n",
    "                        columns=[\"MDVP:Fo(Hz)\", \"MDVP:Fhi(Hz)\", \"MDVP:Flo(Hz)\", \"MDVP:Jitter(%)\", \"MDVP:Jitter(Abs)\",\n",
    "                                 \"MDVP:RAP\", \"MDVP:PPQ\", \"Jitter:DDP\", \"MDVP:Shimmer\", \"MDVP:Shimmer(dB)\", \"Shimmer:APQ3\",\n",
    "                                 \"Shimmer:APQ5\", \"MDVP:APQ\", \"Shimmer:DDA\", \"NHR\", \"HNR\", \"RPDE\", \"DFA\", \"spread1\", \"spread2\",\n",
    "                                 \"D2\", \"PPE\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0])"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "xgb.predict(test_input_2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Import pickle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "with open(\"Model_Prediction.sav\", \"wb\") as f:\n",
    "    pickle.dump(model,f)\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"MinMaxScaler.sav\", \"wb\") as f:\n",
    "    pickle.dump(mmc,f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}