merged_datasets_random_forests_with_pca.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 130,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn import decomposition\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.svm import SVC\n",
    "\n",
    "from sklearn.ensemble import RandomForestClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "df1 = pd.read_csv('Transformed Data/Transformed_Co', index_col = 0)\n",
    "df2 = pd.read_csv('Transformed Data/Transformed_Pt' , index_col = 0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 132,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "pca1 = decomposition.PCA(n_components=4)\n",
    "df1 = pca1.fit_transform(df1)\n",
    "df2 = pca1.fit_transform(df2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(214, 4, 92, 4)"
      ]
     },
     "execution_count": 133,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1_len = df1.shape[0]\n",
    "df2_len = df2.shape[0]\n",
    "df2.shape + df1.shape\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 134,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "df1 = pd.DataFrame(df1)\n",
    "df2 = pd.DataFrame(df2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "metadata": {
    "collapsed": true,
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "X = pd.concat([df1, df2])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 136,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(92,)"
      ]
     },
     "execution_count": 136,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y1 = pd.Series([0]*df1_len)\n",
    "y1.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 137,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(214,)"
      ]
     },
     "execution_count": 137,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y2 = pd.Series([1]*df2_len, index = range(df1_len-1,(df1_len + df2_len)-1))\n",
    "y2.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 138,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(306,)"
      ]
     },
     "execution_count": 138,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y = pd.concat([y1,y2]) \n",
    "y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 139,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "300    1\n",
       "301    1\n",
       "302    1\n",
       "303    1\n",
       "304    1\n",
       "dtype: int64"
      ]
     },
     "execution_count": 139,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 140,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(229, 4)\n",
      "(77, 4)\n",
      "(229, 1)\n",
      "(77, 1)\n"
     ]
    }
   ],
   "source": [
    "X_train, X_test, y_train1, y_test1 = train_test_split(X, y)\n",
    "y_train = pd.DataFrame(y_train1)\n",
    "y_test = pd.DataFrame(y_test1)\n",
    "\n",
    "\n",
    "print(X_train.shape)\n",
    "print(X_test.shape)\n",
    "print(y_train.shape)\n",
    "print(y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 141,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Anaconda\\lib\\site-packages\\ipykernel_launcher.py:2: 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",
      "  \n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of RF classifier on training set: 1.00\n",
      "Accuracy of RF classifier on test set: 0.74\n"
     ]
    }
   ],
   "source": [
    "clf = RandomForestClassifier(n_estimators = 312, random_state = 0,n_jobs=-1)\n",
    "clf.fit(X_train, y_train)\n",
    "\n",
    "print('Accuracy of RF classifier on training set: {:.2f}'\n",
    "     .format(clf.score(X_train, y_train)))\n",
    "print('Accuracy of RF classifier on test set: {:.2f}'\n",
    "     .format(clf.score(X_test, y_test)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}