{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 98,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import time\n",
    "import datetime\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import sklearn\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sb\n",
    "from sklearn.linear_model import SGDClassifier\n",
    "from sklearn.model_selection import train_test_split as ttsplit\n",
    "from sklearn.model_selection import cross_val_predict as cvpredict\n",
    "from sklearn.metrics import confusion_matrix, precision_score, recall_score, f1_score\n",
    "from sklearn.utils import shuffle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "metadata": {},
   "outputs": [],
   "source": [
    "DataTrain = pd.read_csv(\"C:\\\\Users\\\\Admin\\\\Documents\\\\machine learning\\\\CleanData.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "metadata": {},
   "outputs": [],
   "source": [
    "DataTrain = pd.get_dummies(DataTrain)\n",
    "Data = DataTrain.drop(columns='left')\n",
    "Target = DataTrain['left']\n",
    "Classifier = SGDClassifier(random_state=30)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Confusion Matrix:  [[8453  169]\n",
      " [ 409 1389]]\n",
      "Precision:  0.8915275994865212\n",
      "Recall:  0.7725250278086763\n",
      "F1 Score:  0.8277711561382599\n"
     ]
    }
   ],
   "source": [
    "D_train, D_test, T_train, T_test = ttsplit(Data, Target, test_size=0.15, stratify= Target)\n",
    "D_train, T_train = shuffle(D_train, T_train)\n",
    "T_train_pred = cvpredict(Classifier, D_train, T_train, cv=5)\n",
    "confusion = confusion_matrix(T_train, T_train_pred)\n",
    "precision = precision_score(T_train, T_train_pred)\n",
    "recall = recall_score(T_train, T_train_pred)\n",
    "f1 = f1_score(T_train, T_train_pred)\n",
    "\n",
    "print(\"Confusion Matrix: \", confusion)\n",
    "print(\"Precision: \", precision)\n",
    "print(\"Recall: \", recall)\n",
    "print(\"F1 Score: \", f1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Confusion Matrix:  [[7482  126]\n",
      " [ 370 1216]]\n",
      "Precision:  0.9061102831594635\n",
      "Recall:  0.7667087011349306\n",
      "F1 Score:  0.8306010928961749\n"
     ]
    }
   ],
   "source": [
    "D_train, D_test, T_train, T_test = ttsplit(Data, Target, test_size=0.25, stratify= Target)\n",
    "D_train, T_train = shuffle(D_train, T_train)\n",
    "T_train_pred = cvpredict(Classifier, D_train, T_train, cv=5)\n",
    "confusion = confusion_matrix(T_train, T_train_pred)\n",
    "precision = precision_score(T_train, T_train_pred)\n",
    "recall = recall_score(T_train, T_train_pred)\n",
    "f1 = f1_score(T_train, T_train_pred)\n",
    "\n",
    "print(\"Confusion Matrix: \", confusion)\n",
    "print(\"Precision: \", precision)\n",
    "print(\"Recall: \", recall)\n",
    "print(\"F1 Score: \", f1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Confusion Matrix:  [[6457  136]\n",
      " [ 388  987]]\n",
      "Precision:  0.8788958147818343\n",
      "Recall:  0.7178181818181818\n",
      "F1 Score:  0.7902321857485988\n"
     ]
    }
   ],
   "source": [
    "D_train, D_test, T_train, T_test = ttsplit(Data, Target, test_size=0.35, stratify= Target)\n",
    "D_train, T_train = shuffle(D_train, T_train)\n",
    "T_train_pred = cvpredict(Classifier, D_train, T_train, cv=5)\n",
    "confusion = confusion_matrix(T_train, T_train_pred)\n",
    "precision = precision_score(T_train, T_train_pred)\n",
    "recall = recall_score(T_train, T_train_pred)\n",
    "f1 = f1_score(T_train, T_train_pred)\n",
    "\n",
    "print(\"Confusion Matrix: \", confusion)\n",
    "print(\"Precision: \", precision)\n",
    "print(\"Recall: \", recall)\n",
    "print(\"F1 Score: \", f1)"
   ]
  }
 ],
 "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": "3.7.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}