review-sentiment-model.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import nltk\n",
    "from nltk.corpus import stopwords\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn import naive_bayes\n",
    "from sklearn.metrics import roc_auc_score,accuracy_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package stopwords to\n",
      "[nltk_data]     C:\\Users\\Lucif\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package stopwords is already up-to-date!\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nltk.download(\"stopwords\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset = pd.read_csv('datasets/reviews.txt',sep = '\\t', names =['Reviews','Comments'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Reviews</th>\n",
       "      <th>Comments</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>The Da Vinci Code book is just awesome.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>this was the first clive cussler i've ever rea...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>i liked the Da Vinci Code a lot.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>i liked the Da Vinci Code a lot.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>I liked the Da Vinci Code but it ultimatly did...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6913</th>\n",
       "      <td>0</td>\n",
       "      <td>Brokeback Mountain was boring.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6914</th>\n",
       "      <td>0</td>\n",
       "      <td>So Brokeback Mountain was really depressing.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6915</th>\n",
       "      <td>0</td>\n",
       "      <td>As I sit here, watching the MTV Movie Awards, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6916</th>\n",
       "      <td>0</td>\n",
       "      <td>Ok brokeback mountain is such a horrible movie.</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6917</th>\n",
       "      <td>0</td>\n",
       "      <td>Oh, and Brokeback Mountain was a terrible movie.</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6918 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Reviews                                           Comments\n",
       "0           1            The Da Vinci Code book is just awesome.\n",
       "1           1  this was the first clive cussler i've ever rea...\n",
       "2           1                   i liked the Da Vinci Code a lot.\n",
       "3           1                   i liked the Da Vinci Code a lot.\n",
       "4           1  I liked the Da Vinci Code but it ultimatly did...\n",
       "...       ...                                                ...\n",
       "6913        0                     Brokeback Mountain was boring.\n",
       "6914        0       So Brokeback Mountain was really depressing.\n",
       "6915        0  As I sit here, watching the MTV Movie Awards, ...\n",
       "6916        0    Ok brokeback mountain is such a horrible movie.\n",
       "6917        0   Oh, and Brokeback Mountain was a terrible movie.\n",
       "\n",
       "[6918 rows x 2 columns]"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "stopword_set = set(stopwords.words('english'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "vectorizer = TfidfVectorizer(use_idf = True,lowercase = True, strip_accents='ascii',stop_words=stopword_set)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = vectorizer.fit_transform(dataset.Comments)\n",
    "y = dataset.Reviews"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Saving the vectorizer/transformer model to use later when classifying other movie reviews."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "pickle.dump(vectorizer, open('vectorizer.pkl', 'wb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state=42)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We're using a Multinomial Naive Bayes clasifier because it generally works better on text data when compared to other classification techniques."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "MultinomialNB()"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clasifier = naive_bayes.MultinomialNB()\n",
    "clasifier.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9747109826589595"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(y_test,clasifier.predict(X_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Training the model on rest of the data available to us"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "MultinomialNB()"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clasifier = naive_bayes.MultinomialNB()\n",
    "clasifier.fit(X,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9877167630057804"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(y_test,clasifier.predict(X_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "filename = 'review-sentiment-model.pkl'\n",
    "pickle.dump(clasifier, open(filename, 'wb'))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "movie",
   "language": "python",
   "name": "movie"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}