{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# HW4\n",
    "Attempt 1 using [this as a guide](https://www.geeksforgeeks.org/applying-multinomial-naive-bayes-to-nlp-problems/)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## STEP 1: Import ALL the things!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package stopwords to\n",
      "[nltk_data]     /Users/danielcaraway/nltk_data...\n",
      "[nltk_data]   Package stopwords is already up-to-date!\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# cleaning texts \n",
    "import pandas as pd \n",
    "import re \n",
    "import nltk \n",
    "from nltk.corpus import stopwords \n",
    "from nltk.stem.porter import PorterStemmer \n",
    "from sklearn.feature_extraction.text import CountVectorizer \n",
    "nltk.download('stopwords')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset = [[\"I liked the movie\", \"positive\"], \n",
    "           [\"It’s a good movie. Nice story\", \"positive\"], \n",
    "           [\"Hero’s acting is bad but heroine looks good. Overall nice movie\", \"positive\"], \n",
    "            [\"Nice songs. But sadly boring ending.\", \"negative\"], \n",
    "            [\"sad movie, boring movie\", \"negative\"]]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## STEP 2: Clean the data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "## 2a: Put data into a data frame\n",
    "\n",
    "dataset = pd.DataFrame(dataset)\n",
    "dataset.columns = [\"Text\", \"Reviews\"]\n",
    "corpus = []"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "I liked the movie\n",
      "It s a good movie  Nice story\n",
      "Hero s acting is bad but heroine looks good  Overall nice movie\n",
      "Nice songs  But sadly boring ending \n",
      "sad movie  boring movie\n"
     ]
    }
   ],
   "source": [
    "## 2b: Clean and process the data\n",
    "## Processing includes: lowering, splitting, stemming \n",
    "## and removing non alpha characters with regex\n",
    "\n",
    "for i in range(0,5):\n",
    "    text = re.sub('[^a-zA-Z]', ' ', dataset['Text'][i])\n",
    "    print(text)\n",
    "    text = text.lower()\n",
    "    text = text.split()\n",
    "    ps = PorterStemmer()\n",
    "    text = ' '.join(text)\n",
    "    corpus.append(text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['i liked the movie',\n",
       " 'it s a good movie nice story',\n",
       " 'hero s acting is bad but heroine looks good overall nice movie',\n",
       " 'nice songs but sadly boring ending',\n",
       " 'sad movie boring movie']"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "## 2c: Check our handiwork \n",
    "\n",
    "corpus"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## STEP 3: Create Bag of Words \n",
    "Using CountVectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "cv = CountVectorizer(max_features = 1500)\n",
    "x = cv.fit_transform(corpus).toarray()\n",
    "y = dataset.iloc[:,1].values"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## STEP 4: Split the data into train and test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "# from sklearn.cross_validation import train_test_split\n",
    "from sklearn.model_selection import train_test_split\n",
    "x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.25, random_state = 0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## STEP 5: Fit Naive Bayes to Training Set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GaussianNB(priors=None, var_smoothing=1e-09)"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.metrics import confusion_matrix\n",
    "\n",
    "classifier = GaussianNB()\n",
    "classifier.fit(x_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0, 0],\n",
       "       [2, 0]])"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred = classifier.predict(x_test)\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "cm"
   ]
  }
 ],
 "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}