Diabetes_KNN_Classifier.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "import seaborn as sns\n",
    "sns.set_style('white')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>148</td>\n",
       "      <td>72</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>33.6</td>\n",
       "      <td>0.627</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "      <td>66</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>26.6</td>\n",
       "      <td>0.351</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8</td>\n",
       "      <td>183</td>\n",
       "      <td>64</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>23.3</td>\n",
       "      <td>0.672</td>\n",
       "      <td>32</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>89</td>\n",
       "      <td>66</td>\n",
       "      <td>23</td>\n",
       "      <td>94</td>\n",
       "      <td>28.1</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>137</td>\n",
       "      <td>40</td>\n",
       "      <td>35</td>\n",
       "      <td>168</td>\n",
       "      <td>43.1</td>\n",
       "      <td>2.288</td>\n",
       "      <td>33</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin   BMI  \\\n",
       "0            6      148             72             35        0  33.6   \n",
       "1            1       85             66             29        0  26.6   \n",
       "2            8      183             64              0        0  23.3   \n",
       "3            1       89             66             23       94  28.1   \n",
       "4            0      137             40             35      168  43.1   \n",
       "\n",
       "   DiabetesPedigreeFunction  Age  Outcome  \n",
       "0                     0.627   50        1  \n",
       "1                     0.351   31        0  \n",
       "2                     0.672   32        1  \n",
       "3                     0.167   21        0  \n",
       "4                     2.288   33        1  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = pd.read_csv('diabetes.csv')\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import MinMaxScaler\n",
    "Mm= MinMaxScaler()"
   ]
  },
  {
   "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>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.352941</td>\n",
       "      <td>0.743719</td>\n",
       "      <td>0.590164</td>\n",
       "      <td>0.353535</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.500745</td>\n",
       "      <td>0.234415</td>\n",
       "      <td>0.483333</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.058824</td>\n",
       "      <td>0.427136</td>\n",
       "      <td>0.540984</td>\n",
       "      <td>0.292929</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.396423</td>\n",
       "      <td>0.116567</td>\n",
       "      <td>0.166667</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.470588</td>\n",
       "      <td>0.919598</td>\n",
       "      <td>0.524590</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.347243</td>\n",
       "      <td>0.253629</td>\n",
       "      <td>0.183333</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.058824</td>\n",
       "      <td>0.447236</td>\n",
       "      <td>0.540984</td>\n",
       "      <td>0.232323</td>\n",
       "      <td>0.111111</td>\n",
       "      <td>0.418778</td>\n",
       "      <td>0.038002</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.688442</td>\n",
       "      <td>0.327869</td>\n",
       "      <td>0.353535</td>\n",
       "      <td>0.198582</td>\n",
       "      <td>0.642325</td>\n",
       "      <td>0.943638</td>\n",
       "      <td>0.200000</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Pregnancies   Glucose  BloodPressure  SkinThickness   Insulin       BMI  \\\n",
       "0     0.352941  0.743719       0.590164       0.353535  0.000000  0.500745   \n",
       "1     0.058824  0.427136       0.540984       0.292929  0.000000  0.396423   \n",
       "2     0.470588  0.919598       0.524590       0.000000  0.000000  0.347243   \n",
       "3     0.058824  0.447236       0.540984       0.232323  0.111111  0.418778   \n",
       "4     0.000000  0.688442       0.327869       0.353535  0.198582  0.642325   \n",
       "\n",
       "   DiabetesPedigreeFunction       Age  Outcome  \n",
       "0                  0.234415  0.483333      1.0  \n",
       "1                  0.116567  0.166667      0.0  \n",
       "2                  0.253629  0.183333      1.0  \n",
       "3                  0.038002  0.000000      0.0  \n",
       "4                  0.943638  0.200000      1.0  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "temp = Mm.fit_transform(data)\n",
    "tmp = pd.DataFrame(temp, columns = data.columns)\n",
    "tmp.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "x = data.drop('Outcome', axis = 1)\n",
    "y = data['Outcome']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split as tts\n",
    "train_x, test_x, train_y, test_y = tts(x, y, random_state=96, stratify = y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.neighbors import KNeighborsClassifier as KNN  \n",
    "from sklearn.metrics import f1_score\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The Score is  0.6666666666666667\n"
     ]
    }
   ],
   "source": [
    "clf = KNN(n_neighbors =10)\n",
    "clf.fit(train_x, train_y)\n",
    "\n",
    "temp = clf.predict(train_x)\n",
    "score=f1_score(temp, train_y)\n",
    "print(\"The Score is \", score)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The Score is  0.5272727272727272\n"
     ]
    }
   ],
   "source": [
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import accuracy_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "metadata": {},
   "outputs": [],
   "source": [
    "def F1score(k):\n",
    "    \n",
    "    train_ls = []\n",
    "    test_ls = []\n",
    "    \n",
    "    for i in k:\n",
    "        \n",
    "        clf = KNN(n_neighbors = i)\n",
    "        clf.fit(train_x, train_y)\n",
    "        temp=clf.predict(train_x)\n",
    "        score=f1_score(temp, train_y.round())\n",
    "        train_ls.append(score)\n",
    "    \n",
    "    \n",
    "        tmp=clf.predict(test_x)\n",
    "        score1=f1_score(tmp, test_y.round())\n",
    "        test_ls.append(score1)\n",
    "    \n",
    "    return train_ls , test_ls\n",
    "    \n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "metadata": {},
   "outputs": [],
   "source": [
    "k = range(1,150)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "metadata": {},
   "outputs": [],
   "source": [
    "train, test = F1score(k)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "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>train score</th>\n",
       "      <th>test score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.511278</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.681967</td>\n",
       "      <td>0.400000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.781003</td>\n",
       "      <td>0.539683</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.654321</td>\n",
       "      <td>0.428571</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.720627</td>\n",
       "      <td>0.555556</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   train score  test score\n",
       "0     1.000000    0.511278\n",
       "1     0.681967    0.400000\n",
       "2     0.781003    0.539683\n",
       "3     0.654321    0.428571\n",
       "4     0.720627    0.555556"
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "score = pd.DataFrame({'train score': train , 'test score' : test})\n",
    "score.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x22d6b0bc188>"
      ]
     },
     "execution_count": 107,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(k[0:60], test[0:60], color = 'red' , label = 'test')\n",
    "plt.plot(k[0:60], train[0:60], color = 'green', label = 'train')\n",
    "plt.xlabel('K Neighbors')\n",
    "plt.ylabel('F1 Score')\n",
    "plt.title('F1 Curve')\n",
    "plt.ylim(0.4,1)\n",
    "plt.legend()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The Train Score is  0.6536312849162011\n",
      "The Test Score is  0.5663716814159292\n"
     ]
    }
   ],
   "source": [
    "clf = KNN(n_neighbors =18)\n",
    "clf.fit(train_x, train_y)\n",
    "\n",
    "temp = clf.predict(train_x)\n",
    "score=f1_score(temp, train_y)\n",
    "print(\"The Train Score is \", score)\n",
    "\n",
    "temp = clf.predict(test_x)\n",
    "score=f1_score(temp, test_y)\n",
    "print(\"The Test Score is \", score)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}