ParkinsonDisease_detection.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "be3411e5",
   "metadata": {},
   "outputs": [],
   "source": [
    "## importing the required libraries\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import os\n",
    "import sys\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "from xgboost import XGBClassifier\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import accuracy_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "f2751bd5",
   "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>...</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>...</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>...</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>...</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>...</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>...</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",
       "    <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>190</th>\n",
       "      <td>phon_R01_S50_2</td>\n",
       "      <td>174.188</td>\n",
       "      <td>230.978</td>\n",
       "      <td>94.261</td>\n",
       "      <td>0.00459</td>\n",
       "      <td>0.00003</td>\n",
       "      <td>0.00263</td>\n",
       "      <td>0.00259</td>\n",
       "      <td>0.00790</td>\n",
       "      <td>0.04087</td>\n",
       "      <td>...</td>\n",
       "      <td>0.07008</td>\n",
       "      <td>0.02764</td>\n",
       "      <td>19.517</td>\n",
       "      <td>0</td>\n",
       "      <td>0.448439</td>\n",
       "      <td>0.657899</td>\n",
       "      <td>-6.538586</td>\n",
       "      <td>0.121952</td>\n",
       "      <td>2.657476</td>\n",
       "      <td>0.133050</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>191</th>\n",
       "      <td>phon_R01_S50_3</td>\n",
       "      <td>209.516</td>\n",
       "      <td>253.017</td>\n",
       "      <td>89.488</td>\n",
       "      <td>0.00564</td>\n",
       "      <td>0.00003</td>\n",
       "      <td>0.00331</td>\n",
       "      <td>0.00292</td>\n",
       "      <td>0.00994</td>\n",
       "      <td>0.02751</td>\n",
       "      <td>...</td>\n",
       "      <td>0.04812</td>\n",
       "      <td>0.01810</td>\n",
       "      <td>19.147</td>\n",
       "      <td>0</td>\n",
       "      <td>0.431674</td>\n",
       "      <td>0.683244</td>\n",
       "      <td>-6.195325</td>\n",
       "      <td>0.129303</td>\n",
       "      <td>2.784312</td>\n",
       "      <td>0.168895</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>192</th>\n",
       "      <td>phon_R01_S50_4</td>\n",
       "      <td>174.688</td>\n",
       "      <td>240.005</td>\n",
       "      <td>74.287</td>\n",
       "      <td>0.01360</td>\n",
       "      <td>0.00008</td>\n",
       "      <td>0.00624</td>\n",
       "      <td>0.00564</td>\n",
       "      <td>0.01873</td>\n",
       "      <td>0.02308</td>\n",
       "      <td>...</td>\n",
       "      <td>0.03804</td>\n",
       "      <td>0.10715</td>\n",
       "      <td>17.883</td>\n",
       "      <td>0</td>\n",
       "      <td>0.407567</td>\n",
       "      <td>0.655683</td>\n",
       "      <td>-6.787197</td>\n",
       "      <td>0.158453</td>\n",
       "      <td>2.679772</td>\n",
       "      <td>0.131728</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>193</th>\n",
       "      <td>phon_R01_S50_5</td>\n",
       "      <td>198.764</td>\n",
       "      <td>396.961</td>\n",
       "      <td>74.904</td>\n",
       "      <td>0.00740</td>\n",
       "      <td>0.00004</td>\n",
       "      <td>0.00370</td>\n",
       "      <td>0.00390</td>\n",
       "      <td>0.01109</td>\n",
       "      <td>0.02296</td>\n",
       "      <td>...</td>\n",
       "      <td>0.03794</td>\n",
       "      <td>0.07223</td>\n",
       "      <td>19.020</td>\n",
       "      <td>0</td>\n",
       "      <td>0.451221</td>\n",
       "      <td>0.643956</td>\n",
       "      <td>-6.744577</td>\n",
       "      <td>0.207454</td>\n",
       "      <td>2.138608</td>\n",
       "      <td>0.123306</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>194</th>\n",
       "      <td>phon_R01_S50_6</td>\n",
       "      <td>214.289</td>\n",
       "      <td>260.277</td>\n",
       "      <td>77.973</td>\n",
       "      <td>0.00567</td>\n",
       "      <td>0.00003</td>\n",
       "      <td>0.00295</td>\n",
       "      <td>0.00317</td>\n",
       "      <td>0.00885</td>\n",
       "      <td>0.01884</td>\n",
       "      <td>...</td>\n",
       "      <td>0.03078</td>\n",
       "      <td>0.04398</td>\n",
       "      <td>21.209</td>\n",
       "      <td>0</td>\n",
       "      <td>0.462803</td>\n",
       "      <td>0.664357</td>\n",
       "      <td>-5.724056</td>\n",
       "      <td>0.190667</td>\n",
       "      <td>2.555477</td>\n",
       "      <td>0.148569</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>195 rows × 24 columns</p>\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",
       "190  phon_R01_S50_2      174.188       230.978        94.261         0.00459   \n",
       "191  phon_R01_S50_3      209.516       253.017        89.488         0.00564   \n",
       "192  phon_R01_S50_4      174.688       240.005        74.287         0.01360   \n",
       "193  phon_R01_S50_5      198.764       396.961        74.904         0.00740   \n",
       "194  phon_R01_S50_6      214.289       260.277        77.973         0.00567   \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",
       "190           0.00003   0.00263   0.00259     0.00790       0.04087  ...   \n",
       "191           0.00003   0.00331   0.00292     0.00994       0.02751  ...   \n",
       "192           0.00008   0.00624   0.00564     0.01873       0.02308  ...   \n",
       "193           0.00004   0.00370   0.00390     0.01109       0.02296  ...   \n",
       "194           0.00003   0.00295   0.00317     0.00885       0.01884  ...   \n",
       "\n",
       "     Shimmer:DDA      NHR     HNR  status      RPDE       DFA   spread1  \\\n",
       "0        0.06545  0.02211  21.033       1  0.414783  0.815285 -4.813031   \n",
       "1        0.09403  0.01929  19.085       1  0.458359  0.819521 -4.075192   \n",
       "2        0.08270  0.01309  20.651       1  0.429895  0.825288 -4.443179   \n",
       "3        0.08771  0.01353  20.644       1  0.434969  0.819235 -4.117501   \n",
       "4        0.10470  0.01767  19.649       1  0.417356  0.823484 -3.747787   \n",
       "..           ...      ...     ...     ...       ...       ...       ...   \n",
       "190      0.07008  0.02764  19.517       0  0.448439  0.657899 -6.538586   \n",
       "191      0.04812  0.01810  19.147       0  0.431674  0.683244 -6.195325   \n",
       "192      0.03804  0.10715  17.883       0  0.407567  0.655683 -6.787197   \n",
       "193      0.03794  0.07223  19.020       0  0.451221  0.643956 -6.744577   \n",
       "194      0.03078  0.04398  21.209       0  0.462803  0.664357 -5.724056   \n",
       "\n",
       "      spread2        D2       PPE  \n",
       "0    0.266482  2.301442  0.284654  \n",
       "1    0.335590  2.486855  0.368674  \n",
       "2    0.311173  2.342259  0.332634  \n",
       "3    0.334147  2.405554  0.368975  \n",
       "4    0.234513  2.332180  0.410335  \n",
       "..        ...       ...       ...  \n",
       "190  0.121952  2.657476  0.133050  \n",
       "191  0.129303  2.784312  0.168895  \n",
       "192  0.158453  2.679772  0.131728  \n",
       "193  0.207454  2.138608  0.123306  \n",
       "194  0.190667  2.555477  0.148569  \n",
       "\n",
       "[195 rows x 24 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "## Displaying the data\n",
    "path = \"/home/ashish/projects/PArkinson_Presence_XGBCLASSIFIER/parkinsons.park\"\n",
    "data = pd.read_csv(path)\n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "fc7695a2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[119.992, 157.302, 74.997, ..., 0.266482, 2.301442, 0.284654],\n",
       "       [122.4, 148.65, 113.819, ..., 0.33559, 2.486855, 0.368674],\n",
       "       [116.682, 131.111, 111.555, ..., 0.311173, 2.342259, 0.332634],\n",
       "       ...,\n",
       "       [174.688, 240.005, 74.287, ..., 0.158453, 2.679772, 0.131728],\n",
       "       [198.764, 396.961, 74.904, ..., 0.207454, 2.138608, 0.123306],\n",
       "       [214.289, 260.277, 77.973, ..., 0.190667, 2.555477, 0.148569]],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "## Geting all the features(columns) except the result featoure from our data\n",
    "features = data.loc[:,data.columns!=\"status\"].values[:,1:]\n",
    "features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "1be25d0a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [1],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0],\n",
       "       [0]])"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "## getting the labels for our status or result\n",
    "labels = data.loc[:,data.columns==\"status\"].values\n",
    "labels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "6b78709a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Counts of 1's --  147\n",
      "Count of 0's --  48\n"
     ]
    }
   ],
   "source": [
    "## Count of 0's and 1's\n",
    "print(\"Counts of 1's -- \", labels[labels==1].shape[0])\n",
    "print(\"Count of 0's -- \",labels[labels==0].shape[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "2e6535ea",
   "metadata": {},
   "outputs": [],
   "source": [
    "## Normalize the features by scaling the features to between -1 and 1\n",
    "scaler = MinMaxScaler((-1,1))\n",
    "x = scaler.fit_transform(features)\n",
    "y = labels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "d1ea1074",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[-0.63138346, -0.77481654, -0.89037042, ...,  0.17153026,\n",
       "        -0.21867743, -0.0053808 ],\n",
       "       [-0.6033463 , -0.81013911, -0.4433544 , ...,  0.48267409,\n",
       "        -0.05370956,  0.34265204],\n",
       "       [-0.66992292, -0.88174367, -0.46942324, ...,  0.37274182,\n",
       "        -0.18236124,  0.19336492],\n",
       "       ...,\n",
       "       [ 0.00546073, -0.43717403, -0.89854572, ..., -0.31484696,\n",
       "         0.11793486, -0.63884033],\n",
       "       [ 0.28578581,  0.20361309, -0.89144127, ..., -0.09423055,\n",
       "        -0.36355605, -0.67372646],\n",
       "       [ 0.46654868, -0.35441175, -0.85610326, ..., -0.16981039,\n",
       "         0.00734563, -0.5690805 ]])"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "## This is how our updated/scaled features look like\n",
    "x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "1b712f4d",
   "metadata": {},
   "outputs": [],
   "source": [
    "## Splitting the dataset into training(80%) and testing(20%) set\n",
    "x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.2,random_state=7)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "8ecb73c4",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ashish/anaconda3/lib/python3.8/site-packages/xgboost/sklearn.py:1224: UserWarning: The use of label encoder in XGBClassifier is deprecated and will be removed in a future release. To remove this warning, do the following: 1) Pass option use_label_encoder=False when constructing XGBClassifier object; and 2) Encode your labels (y) as integers starting with 0, i.e. 0, 1, 2, ..., [num_class - 1].\n",
      "  warnings.warn(label_encoder_deprecation_msg, UserWarning)\n",
      "/home/ashish/anaconda3/lib/python3.8/site-packages/sklearn/utils/validation.py:63: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
      "  return f(*args, **kwargs)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[03:38:12] WARNING: ../src/learner.cc:1115: Starting in XGBoost 1.3.0, the default evaluation metric used with the objective 'binary:logistic' was changed from 'error' to 'logloss'. Explicitly set eval_metric if you'd like to restore the old behavior.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n",
       "              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,\n",
       "              gamma=0, gpu_id=-1, importance_type=None,\n",
       "              interaction_constraints='', learning_rate=0.300000012,\n",
       "              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,\n",
       "              monotone_constraints='()', n_estimators=100, n_jobs=4,\n",
       "              num_parallel_tree=1, predictor='auto', random_state=0,\n",
       "              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, subsample=1,\n",
       "              tree_method='exact', validate_parameters=1, verbosity=None)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "## Building our XGBClassifier model (Extreme Gradient Boosting)\n",
    "model = XGBClassifier()\n",
    "model.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "36935a6b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy ::  94.87179487179486\n"
     ]
    }
   ],
   "source": [
    "## Calculating the accuracy of our model\n",
    "y_pred = model.predict(x_test)\n",
    "print(\"Accuracy :: \",accuracy_score(y_test,y_pred)*100)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d1210ff6",
   "metadata": {},
   "source": [
    "## S0 our Accuracy is ::  94.87179487179486.\n",
    "    This means that 94.87 times out of 100, we are gonna corectly predict those ones who are suffering from Parkinsons and those who are not."
   ]
  }
 ],
 "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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}