nlp_yelp_reviews_sentiment_analysis.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "import nltk\n",
    "from nltk.corpus import stopwords"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>Unnamed: 0</th>\n",
       "      <th>id</th>\n",
       "      <th>review</th>\n",
       "      <th>rating</th>\n",
       "      <th>text length</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>g6AFW-zY0wDvBl9U82g4zg</td>\n",
       "      <td>This place definitely lives up to its 5-star r...</td>\n",
       "      <td>5</td>\n",
       "      <td>151</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>g6AFW-zY0wDvBl9U82g4zg</td>\n",
       "      <td>I love love love this cafe! From the delicious...</td>\n",
       "      <td>5</td>\n",
       "      <td>158</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>g6AFW-zY0wDvBl9U82g4zg</td>\n",
       "      <td>Love love love love this place! Service is PHE...</td>\n",
       "      <td>5</td>\n",
       "      <td>161</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>e41TP5cXZqSrz50xCBJqZw</td>\n",
       "      <td>I have been here over 10 times in the past yea...</td>\n",
       "      <td>5</td>\n",
       "      <td>158</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>e41TP5cXZqSrz50xCBJqZw</td>\n",
       "      <td>Insomnia a really nice place for a brunch with...</td>\n",
       "      <td>5</td>\n",
       "      <td>159</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0                      id  \\\n",
       "0           0  g6AFW-zY0wDvBl9U82g4zg   \n",
       "1           1  g6AFW-zY0wDvBl9U82g4zg   \n",
       "2           2  g6AFW-zY0wDvBl9U82g4zg   \n",
       "3           3  e41TP5cXZqSrz50xCBJqZw   \n",
       "4           4  e41TP5cXZqSrz50xCBJqZw   \n",
       "\n",
       "                                              review  rating  text length  \n",
       "0  This place definitely lives up to its 5-star r...       5          151  \n",
       "1  I love love love this cafe! From the delicious...       5          158  \n",
       "2  Love love love love this place! Service is PHE...       5          161  \n",
       "3  I have been here over 10 times in the past yea...       5          158  \n",
       "4  Insomnia a really nice place for a brunch with...       5          159  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#import yelp reviews from root dir\n",
    "yelp = pd.read_csv(r'reviews_and_ids.csv')\n",
    "\n",
    "#add text length column\n",
    "yelp['text length'] = yelp['review'].apply(len)\n",
    "\n",
    "#print top few rows\n",
    "yelp.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x1969bb7f898>"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x196a35e5be0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#visualize to explore correlation between length of review and rating\n",
    "g = sns.FacetGrid(data=yelp, col='rating')\n",
    "g.map(plt.hist, 'text length', bins=50)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Distribution appears similar, but number of reviews greater for 4/5 stars"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x196a3bd21d0>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x196a3566d30>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.boxplot(x='rating', y='text length', data=yelp)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Evidences length of reviews comparitively"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Text preprocessing"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Convert text corpus to vector via bag of words"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "yelp_class= yelp[(yelp['rating'] == 1) | (yelp['rating'] == 5)]\n",
    "\n",
    "X = yelp_class['review']\n",
    "y = yelp_class['rating']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "import string\n",
    "\n",
    "def text_process(text):\n",
    "    '''\n",
    "    Takes in a string of text, performs:\n",
    "    1. Remove all punctuation\n",
    "    2. Remove all stopwords\n",
    "    3. Return the cleaned text as a list of words\n",
    "    '''\n",
    "    nopunc = [char for char in text if char not in string.punctuation]\n",
    "    nopunc = ''.join(nopunc)\n",
    "    \n",
    "    return [word for word in nopunc.split() if word.lower() not in stopwords.words('english')]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import CountVectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "bow_transformer = CountVectorizer(analyzer=text_process).fit(X)\n",
    "X = bow_transformer.transform(X)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Train Test Split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=101)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Build and train"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Multinomial Naive Bayes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "MultinomialNB(alpha=1.0, class_prior=None, fit_prior=True)"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.naive_bayes import MultinomialNB\n",
    "nb = MultinomialNB()\n",
    "nb.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Predict and evaluate"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "preds = nb.predict(X_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Confusion Matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import confusion_matrix, classification_report"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[0 0]\n",
      " [6 4]]\n",
      "\n",
      "\n",
      "             precision    recall  f1-score   support\n",
      "\n",
      "          1       0.00      0.00      0.00         0\n",
      "          5       1.00      0.40      0.57        10\n",
      "\n",
      "avg / total       1.00      0.40      0.57        10\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\janei\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\classification.py:1137: UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in labels with no true samples.\n",
      "  'recall', 'true', average, warn_for)\n"
     ]
    }
   ],
   "source": [
    "print(confusion_matrix(y_test, preds))\n",
    "print('\\n')\n",
    "print(classification_report(y_test, preds))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Predict random positive review"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"This is a great brunch spot but if you're not going to be there from door opening you've got to expect to wait 30-45min to get in as the place is pretty...\""
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "positive_review = yelp_class['review'][59]\n",
    "positive_review"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<1x348 sparse matrix of type '<class 'numpy.int64'>'\n",
       "\twith 15 stored elements in Compressed Sparse Row format>"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "positive_review_transformed = bow_transformer.transform([positive_review])\n",
    "positive_review_transformed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nb.predict(positive_review_transformed)[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Predicting random negative"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'look no further if you need another reason to make your own sandwich at home.\\r\\npls. get the smoking staff away from the view of the customers. wash your...'"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "negative_review = yelp_class['review'][22]\n",
    "negative_review"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<1x348 sparse matrix of type '<class 'numpy.int64'>'\n",
       "\twith 15 stored elements in Compressed Sparse Row format>"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "negative_review_transformed = bow_transformer.transform([negative_review])\n",
    "negative_review_transformed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nb.predict(negative_review_transformed)[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Predicting another random negative"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"We came here on a weekend for lunch. The space is small, casual and cute. There weren't any other customers there, but they were quite busy with online...\""
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "another_negative_review = yelp_class['review'][48]\n",
    "another_negative_review"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<1x348 sparse matrix of type '<class 'numpy.int64'>'\n",
       "\twith 12 stored elements in Compressed Sparse Row format>"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "another_negative_review_transformed = bow_transformer.transform([another_negative_review])\n",
    "another_negative_review_transformed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nb.predict(another_negative_review_transformed)[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [],
   "source": [
    "positive_review_ = 'Wow fantastic restaurant; i like the fact that it was cheap'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "positive_review_transformed = bow_transformer.transform([positive_review_])\n",
    "nb.predict(positive_review_transformed)[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "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": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}