ml_raw_data.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "7cz67itTa-JM"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.model_selection import KFold\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.metrics import accuracy_score,roc_auc_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "NG3_PkJ3a-JZ"
   },
   "outputs": [],
   "source": [
    "dataset = pd.read_csv('Joint_Dataset.csv')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "Ph4R0LRma-Jh"
   },
   "outputs": [],
   "source": [
    "X = dataset.drop('label',axis=1)\n",
    "y = dataset['label']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 187
    },
    "colab_type": "code",
    "id": "yrx1_8g_a-Jo",
    "outputId": "72fd7dbe-c32e-4faa-f4d6-9d0b96005de9"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "95.26315789473684\n",
      "94.56140350877193\n",
      "94.34210526315789\n",
      "95.13157894736842\n",
      "95.6140350877193\n",
      "94.82456140350877\n",
      "94.16666666666667\n",
      "94.33962264150944\n",
      "95.17332163229487\n",
      "95.08556384379114\n"
     ]
    }
   ],
   "source": [
    "import pdb\n",
    "Kfold = KFold(10,True,1)\n",
    "for train_idx,test_idx in Kfold.split(dataset):\n",
    "    X_train,X_test,y_train,y_test = X.iloc[train_idx],X.iloc[test_idx],y.iloc[train_idx],y.iloc[test_idx]\n",
    "    clf = RandomForestClassifier(n_estimators=100, random_state=0, n_jobs=-1)\n",
    "    clf.fit(X_train,y_train)\n",
    "    output = clf.predict(X_test)\n",
    "    accuracy = accuracy_score(y_test,output)*100\n",
    "    print(accuracy)\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "XhQO7VCxa-Jz"
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "name": "Machine_learning_raw_data.ipynb",
   "provenance": [],
   "toc_visible": true
  },
  "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": 1
}