Author ID prediction.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "no. of Chris training emails: 7936\n",
      "no. of Sara training emails: 7884\n",
      "Training time:  3.376 s\n"
     ]
    }
   ],
   "source": [
    "#!/usr/bin/python\n",
    "\n",
    "\"\"\" \n",
    "    This is the code to accompany the Lesson 1 (Naive Bayes) mini-project. \n",
    "\n",
    "    Use a Naive Bayes Classifier to identify emails by their authors\n",
    "    \n",
    "    authors and labels:\n",
    "    Sara has label 0\n",
    "    Chris has label 1\n",
    "\"\"\"\n",
    "import os\n",
    "os.chdir('C:/Users/abc/ud120-projects-master/naive_bayes')\n",
    "import sys\n",
    "from time import time\n",
    "sys.path.append(\"C:/Users/abc/ud120-projects-master/tools\")\n",
    "from email_preprocess import preprocess\n",
    "\n",
    "\n",
    "### features_train and features_test are the features for the training\n",
    "### and testing datasets, respectively\n",
    "### labels_train and labels_test are the corresponding item labels\n",
    "features_train, features_test, labels_train, labels_test = preprocess()\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "clf = GaussianNB()\n",
    "t0 = time()\n",
    "clf.fit(features_train,labels_train)\n",
    "print 'Training time: ',round(time()- t0, 3), 's'\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "#########################################################\n",
    "### your code goes here ###\n",
    "\n",
    "\n",
    "#########################################################\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Prediction time:  0.74 s\n"
     ]
    }
   ],
   "source": [
    "t1 = time()\n",
    "y_pred = clf.predict(features_test)\n",
    "print 'Prediction time: ',round(time()- t1, 3),'s'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.97326507394766781"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "accuracy_score(labels_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}