Logistic Regression for Predicting Diabetes.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.externals import joblib"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data Description"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   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  \n"
     ]
    }
   ],
   "source": [
    "diabetes=pd.read_csv('diabetes.csv')\n",
    "print(diabetes.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 768 entries, 0 to 767\n",
      "Data columns (total 9 columns):\n",
      "Pregnancies                 768 non-null int64\n",
      "Glucose                     768 non-null int64\n",
      "BloodPressure               768 non-null int64\n",
      "SkinThickness               768 non-null int64\n",
      "Insulin                     768 non-null int64\n",
      "BMI                         768 non-null float64\n",
      "DiabetesPedigreeFunction    768 non-null float64\n",
      "Age                         768 non-null int64\n",
      "Outcome                     768 non-null int64\n",
      "dtypes: float64(2), int64(7)\n",
      "memory usage: 54.1 KB\n"
     ]
    }
   ],
   "source": [
    "diabetes.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data Exploration"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                          Pregnancies   Glucose  BloodPressure  SkinThickness  \\\n",
      "Pregnancies                  1.000000  0.129459       0.141282      -0.081672   \n",
      "Glucose                      0.129459  1.000000       0.152590       0.057328   \n",
      "BloodPressure                0.141282  0.152590       1.000000       0.207371   \n",
      "SkinThickness               -0.081672  0.057328       0.207371       1.000000   \n",
      "Insulin                     -0.073535  0.331357       0.088933       0.436783   \n",
      "BMI                          0.017683  0.221071       0.281805       0.392573   \n",
      "DiabetesPedigreeFunction    -0.033523  0.137337       0.041265       0.183928   \n",
      "Age                          0.544341  0.263514       0.239528      -0.113970   \n",
      "Outcome                      0.221898  0.466581       0.065068       0.074752   \n",
      "\n",
      "                           Insulin       BMI  DiabetesPedigreeFunction  \\\n",
      "Pregnancies              -0.073535  0.017683                 -0.033523   \n",
      "Glucose                   0.331357  0.221071                  0.137337   \n",
      "BloodPressure             0.088933  0.281805                  0.041265   \n",
      "SkinThickness             0.436783  0.392573                  0.183928   \n",
      "Insulin                   1.000000  0.197859                  0.185071   \n",
      "BMI                       0.197859  1.000000                  0.140647   \n",
      "DiabetesPedigreeFunction  0.185071  0.140647                  1.000000   \n",
      "Age                      -0.042163  0.036242                  0.033561   \n",
      "Outcome                   0.130548  0.292695                  0.173844   \n",
      "\n",
      "                               Age   Outcome  \n",
      "Pregnancies               0.544341  0.221898  \n",
      "Glucose                   0.263514  0.466581  \n",
      "BloodPressure             0.239528  0.065068  \n",
      "SkinThickness            -0.113970  0.074752  \n",
      "Insulin                  -0.042163  0.130548  \n",
      "BMI                       0.036242  0.292695  \n",
      "DiabetesPedigreeFunction  0.033561  0.173844  \n",
      "Age                       1.000000  0.238356  \n",
      "Outcome                   0.238356  1.000000  \n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x20e103b0710>"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "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": [
    "corr= diabetes.corr()\n",
    "print (corr)\n",
    "\n",
    "sns.heatmap(corr,\n",
    "           xticklabels=corr.columns,\n",
    "           yticklabels=corr.columns)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Dataset Preparation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "dftrain=diabetes[:650]\n",
    "dftest=diabetes[650:750]\n",
    "dfcheck=diabetes[750:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "trainLabel= np.asarray(dftrain['Outcome'])\n",
    "trainData= np.asarray(dftrain.drop('Outcome',1))\n",
    "testLabel= np.asarray(dftest['Outcome'])\n",
    "testData= np.asarray(dftest.drop('Outcome',1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "#normalizing\n",
    "means=np.mean(trainData,axis=0)\n",
    "stds=np.std(trainData,axis=0)\n",
    "trainData=(trainData-means)/stds\n",
    "testData=(testData-means)/stds\n",
    "\n",
    "#np.mean(trainData,axis=0)=> checks that new mean=0\n",
    "#np.std(trainData,axis=0)=> checks that new std=1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Training and Evaluating Machine Learning Models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\partheban\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\logistic.py:433: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.\n",
      "  FutureWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
       "          intercept_scaling=1, max_iter=100, multi_class='warn',\n",
       "          n_jobs=None, penalty='l2', random_state=None, solver='warn',\n",
       "          tol=0.0001, verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "diabetescheck=LogisticRegression()\n",
    "diabetescheck.fit(trainData, trainLabel)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "accuracy =  78.0 %\n"
     ]
    }
   ],
   "source": [
    "accuracy=diabetescheck.score(testData, testLabel)\n",
    "print(\"accuracy = \", accuracy*100, \"%\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Interpreting the model using Machine learning algorithms"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5,0,'importance')"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 792x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "coeff=list(diabetescheck.coef_[0])\n",
    "labels=list(dftrain.drop('Outcome',1).columns)\n",
    "\n",
    "features=pd.DataFrame()\n",
    "features['Features']=labels\n",
    "features['importance']=coeff\n",
    "features.sort_values(by=['importance'],ascending=True,inplace=True)\n",
    "features['positive']=features['importance']>0\n",
    "features.set_index('Features',inplace=True)\n",
    "features.importance.plot(kind='barh',figsize=(11,6),color=features.positive.map({True:'blue',False:'red'}))\n",
    "plt.xlabel('importance')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# making the predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "probablity: [[0.4385153 0.5614847]]\n",
      "prediction: [1]\n"
     ]
    }
   ],
   "source": [
    "sampleData=dfcheck[:1]\n",
    "\n",
    "#prepare sample\n",
    "sampleDataFeatures=np.asarray(sampleData.drop('Outcome',1))\n",
    "sampleDataFeatures=(sampleDataFeatures-means)/stds\n",
    "\n",
    "#predict\n",
    "predictionProbability=diabetescheck.predict_proba(sampleDataFeatures)\n",
    "prediction=diabetescheck.predict(sampleDataFeatures)\n",
    "print('Probablity:',predictionProbability)\n",
    "print('Prediction:',prediction)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# This model shows that 56.14% chance that the person is Diabetic"
   ]
  },
  {
   "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}