Python/ml/Amazon_Alexa_Reviews_Analysis.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Amazon Alexa Reviews Analysis"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### The aim is to analyse Alexa's reviews by performing NLP and using logistic regression. If the feedback is positive, the result is 1, else it is 0. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Link to the dataset: [Amazon Alexa Reviews](https://www.kaggle.com/sid321axn/amazon-alexa-reviews)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Importing Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package stopwords to\n",
      "[nltk_data]     C:\\Users\\DELL\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package stopwords is already up-to-date!\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import nltk \n",
    "nltk.download('stopwords')                 # download the stopwords from NLTK\n",
    "\n",
    "import re                                  # library for regular expression operations\n",
    "import string                              # for string operations\n",
    "\n",
    "from nltk.corpus import stopwords          # module for stop words that come with NLTK\n",
    "from nltk.stem import PorterStemmer        # module for stemming\n",
    "from nltk.tokenize import TweetTokenizer   # module for tokenizing strings\n",
    "\n",
    "from sklearn.linear_model import LogisticRegression  \n",
    "from sklearn.feature_extraction.text import CountVectorizer  \n",
    "from sklearn.model_selection import train_test_split  \n",
    "from sklearn.metrics import roc_auc_score\n",
    "from sklearn.metrics import confusion_matrix\n",
    "import matplotlib.pyplot as plt            # library for visualization\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Getting our Data"
   ]
  },
  {
   "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>rating</th>\n",
       "      <th>date</th>\n",
       "      <th>variation</th>\n",
       "      <th>verified_reviews</th>\n",
       "      <th>feedback</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5</td>\n",
       "      <td>31-Jul-18</td>\n",
       "      <td>Charcoal Fabric</td>\n",
       "      <td>Love my Echo!</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5</td>\n",
       "      <td>31-Jul-18</td>\n",
       "      <td>Charcoal Fabric</td>\n",
       "      <td>Loved it!</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4</td>\n",
       "      <td>31-Jul-18</td>\n",
       "      <td>Walnut Finish</td>\n",
       "      <td>Sometimes while playing a game, you can answer...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>5</td>\n",
       "      <td>31-Jul-18</td>\n",
       "      <td>Charcoal Fabric</td>\n",
       "      <td>I have had a lot of fun with this thing. My 4 ...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>31-Jul-18</td>\n",
       "      <td>Charcoal Fabric</td>\n",
       "      <td>Music</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3145</th>\n",
       "      <td>5</td>\n",
       "      <td>30-Jul-18</td>\n",
       "      <td>Black  Dot</td>\n",
       "      <td>Perfect for kids, adults and everyone in betwe...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3146</th>\n",
       "      <td>5</td>\n",
       "      <td>30-Jul-18</td>\n",
       "      <td>Black  Dot</td>\n",
       "      <td>Listening to music, searching locations, check...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3147</th>\n",
       "      <td>5</td>\n",
       "      <td>30-Jul-18</td>\n",
       "      <td>Black  Dot</td>\n",
       "      <td>I do love these things, i have them running my...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3148</th>\n",
       "      <td>5</td>\n",
       "      <td>30-Jul-18</td>\n",
       "      <td>White  Dot</td>\n",
       "      <td>Only complaint I have is that the sound qualit...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3149</th>\n",
       "      <td>4</td>\n",
       "      <td>29-Jul-18</td>\n",
       "      <td>Black  Dot</td>\n",
       "      <td>Good</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3150 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      rating       date         variation  \\\n",
       "0          5  31-Jul-18  Charcoal Fabric    \n",
       "1          5  31-Jul-18  Charcoal Fabric    \n",
       "2          4  31-Jul-18    Walnut Finish    \n",
       "3          5  31-Jul-18  Charcoal Fabric    \n",
       "4          5  31-Jul-18  Charcoal Fabric    \n",
       "...      ...        ...               ...   \n",
       "3145       5  30-Jul-18        Black  Dot   \n",
       "3146       5  30-Jul-18        Black  Dot   \n",
       "3147       5  30-Jul-18        Black  Dot   \n",
       "3148       5  30-Jul-18        White  Dot   \n",
       "3149       4  29-Jul-18        Black  Dot   \n",
       "\n",
       "                                       verified_reviews  feedback  \n",
       "0                                         Love my Echo!         1  \n",
       "1                                             Loved it!         1  \n",
       "2     Sometimes while playing a game, you can answer...         1  \n",
       "3     I have had a lot of fun with this thing. My 4 ...         1  \n",
       "4                                                 Music         1  \n",
       "...                                                 ...       ...  \n",
       "3145  Perfect for kids, adults and everyone in betwe...         1  \n",
       "3146  Listening to music, searching locations, check...         1  \n",
       "3147  I do love these things, i have them running my...         1  \n",
       "3148  Only complaint I have is that the sound qualit...         1  \n",
       "3149                                               Good         1  \n",
       "\n",
       "[3150 rows x 5 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('amazon_alexa.csv')\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Data Preprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>verified_reviews</th>\n",
       "      <th>feedback</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Love my Echo!</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Loved it!</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Sometimes while playing a game, you can answer...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>I have had a lot of fun with this thing. My 4 ...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Music</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3145</th>\n",
       "      <td>Perfect for kids, adults and everyone in betwe...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3146</th>\n",
       "      <td>Listening to music, searching locations, check...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3147</th>\n",
       "      <td>I do love these things, i have them running my...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3148</th>\n",
       "      <td>Only complaint I have is that the sound qualit...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3149</th>\n",
       "      <td>Good</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3150 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                       verified_reviews  feedback\n",
       "0                                         Love my Echo!         1\n",
       "1                                             Loved it!         1\n",
       "2     Sometimes while playing a game, you can answer...         1\n",
       "3     I have had a lot of fun with this thing. My 4 ...         1\n",
       "4                                                 Music         1\n",
       "...                                                 ...       ...\n",
       "3145  Perfect for kids, adults and everyone in betwe...         1\n",
       "3146  Listening to music, searching locations, check...         1\n",
       "3147  I do love these things, i have them running my...         1\n",
       "3148  Only complaint I have is that the sound qualit...         1\n",
       "3149                                               Good         1\n",
       "\n",
       "[3150 rows x 2 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = df.drop(['rating', 'date', 'variation'], axis = 1)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "verified_reviews    False\n",
       "feedback            False\n",
       "dtype: bool"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().any()  # checking for null values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 3150 entries, 0 to 3149\n",
      "Data columns (total 2 columns):\n",
      " #   Column            Non-Null Count  Dtype \n",
      "---  ------            --------------  ----- \n",
      " 0   verified_reviews  3150 non-null   object\n",
      " 1   feedback          3150 non-null   int64 \n",
      "dtypes: int64(1), object(1)\n",
      "memory usage: 49.3+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "def process_rev(rev):\n",
    "    \"\"\"Process review function.\n",
    "    Input:\n",
    "        rev: a string containing a review\n",
    "    Output:\n",
    "        rev_clean: a list of words containing the processed review\n",
    "\n",
    "    \"\"\"\n",
    "    stemmer = PorterStemmer()\n",
    "    stopwords_english = stopwords.words('english')\n",
    "    # tokenize reviews\n",
    "    tokenizer = TweetTokenizer(preserve_case=False, strip_handles=True,\n",
    "                               reduce_len=True)\n",
    "    rev_tokens = tokenizer.tokenize(rev)\n",
    "\n",
    "    rev_clean = []\n",
    "    for word in rev_tokens:\n",
    "        if (word not in stopwords_english and  # remove stopwords\n",
    "                word not in string.punctuation):  # remove punctuation\n",
    "            # rev_clean.append(word)\n",
    "            stem_word = stemmer.stem(word)  # stemming word\n",
    "            rev_clean.append(stem_word)\n",
    "\n",
    "    return rev_clean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>verified_reviews</th>\n",
       "      <th>feedback</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>[love, echo]</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>[love]</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>[sometim, play, game, answer, question, correc...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>[lot, fun, thing, 4, yr, old, learn, dinosaur,...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>[music]</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3145</th>\n",
       "      <td>[perfect, kid, adult, everyon]</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3146</th>\n",
       "      <td>[listen, music, search, locat, check, time, lo...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3147</th>\n",
       "      <td>[love, thing, run, entir, home, tv, light, the...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3148</th>\n",
       "      <td>[complaint, sound, qualiti, great, mostli, use...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3149</th>\n",
       "      <td>[good]</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3150 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                       verified_reviews  feedback\n",
       "0                                          [love, echo]         1\n",
       "1                                                [love]         1\n",
       "2     [sometim, play, game, answer, question, correc...         1\n",
       "3     [lot, fun, thing, 4, yr, old, learn, dinosaur,...         1\n",
       "4                                               [music]         1\n",
       "...                                                 ...       ...\n",
       "3145                     [perfect, kid, adult, everyon]         1\n",
       "3146  [listen, music, search, locat, check, time, lo...         1\n",
       "3147  [love, thing, run, entir, home, tv, light, the...         1\n",
       "3148  [complaint, sound, qualiti, great, mostli, use...         1\n",
       "3149                                             [good]         1\n",
       "\n",
       "[3150 rows x 2 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# using the process_rev function for:\n",
    "# 1. Removing stop words\n",
    "# 2. Tokenization\n",
    "# 3. Stemming\n",
    "A = []\n",
    "a = df['verified_reviews']\n",
    "for i in a:\n",
    "  i = process_rev(i)\n",
    "  A.append(i)\n",
    "df['verified_reviews'] = A\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Vectorizing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "cv = CountVectorizer(max_features=1500, analyzer='word', lowercase=False) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "df['verified_reviews'] = df['verified_reviews'].apply(lambda x: \" \".join(x) )  # to join all words in the lists\n",
    "X = cv.fit_transform(df['verified_reviews'])  # predictor variable 'X'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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>verified_reviews</th>\n",
       "      <th>feedback</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>love echo</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>love</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>sometim play game answer question correctli al...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>lot fun thing 4 yr old learn dinosaur control ...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>music</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3145</th>\n",
       "      <td>perfect kid adult everyon</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3146</th>\n",
       "      <td>listen music search locat check time look weat...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3147</th>\n",
       "      <td>love thing run entir home tv light thermostat ...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3148</th>\n",
       "      <td>complaint sound qualiti great mostli use comma...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3149</th>\n",
       "      <td>good</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3150 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                       verified_reviews  feedback\n",
       "0                                             love echo         1\n",
       "1                                                  love         1\n",
       "2     sometim play game answer question correctli al...         1\n",
       "3     lot fun thing 4 yr old learn dinosaur control ...         1\n",
       "4                                                 music         1\n",
       "...                                                 ...       ...\n",
       "3145                          perfect kid adult everyon         1\n",
       "3146  listen music search locat check time look weat...         1\n",
       "3147  love thing run entir home tv light thermostat ...         1\n",
       "3148  complaint sound qualiti great mostli use comma...         1\n",
       "3149                                               good         1\n",
       "\n",
       "[3150 rows x 2 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>feedback</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   feedback\n",
       "0         1\n",
       "1         1\n",
       "2         1\n",
       "3         1\n",
       "4         1"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y = pd.DataFrame(df['feedback'])  # respose variable 'y'\n",
    "y.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Splitting for Training and Testing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state = 0)  # splitting in the ratio 80:20"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\DELL\\anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py:72: 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",
      "  return f(**kwargs)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "LogisticRegression(random_state=0)"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "classifier = LogisticRegression(random_state = 0)\n",
    "classifier.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Making Predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1,\n",
       "       1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1,\n",
       "       1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1,\n",
       "       1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], dtype=int64)"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred = classifier.predict(X_test)\n",
    "y_pred"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Checking Accuracy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.6825810185185184"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "roc_auc_score(y_test, y_pred)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Predictions are 68.25% accurate."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Results' Visualization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 20,  34],\n",
       "       [  3, 573]], dtype=int64)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cm = confusion_matrix(y_test, y_pred)\n",
    "cm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Accuracy Score: 0.6825810185185184')"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x432 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(6,6))\n",
    "sns.heatmap(cm, annot=True, fmt=\".0f\", linewidths=0.5, square = True, cmap = 'Pastel1')\n",
    "plt.ylabel('Actual label')\n",
    "plt.xlabel('Predicted label')\n",
    "all_sample_title = 'Accuracy Score: {0}'.format(roc_auc_score(y_test, y_pred))\n",
    "plt.title(all_sample_title, size = 15)"
   ]
  }
 ],
 "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}