{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import nltk\n",
    "from nltk.sentiment.vader import SentimentIntensityAnalyzer\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package vader_lexicon to C:\\Users\\Rikhil\n",
      "[nltk_data]     Nellimarla\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package vader_lexicon is already up-to-date!\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Download VADER lexicon for sentiment analysis\n",
    "nltk.download('vader_lexicon')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "ename": "FileNotFoundError",
     "evalue": "[Errno 2] No such file or directory: '../Datasets/IMDB Dataset.csv'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[38], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m data \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mread_csv(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m../Datasets/IMDB Dataset.csv\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\io\\parsers\\readers.py:1026\u001b[0m, in \u001b[0;36mread_csv\u001b[1;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)\u001b[0m\n\u001b[0;32m   1013\u001b[0m kwds_defaults \u001b[38;5;241m=\u001b[39m _refine_defaults_read(\n\u001b[0;32m   1014\u001b[0m     dialect,\n\u001b[0;32m   1015\u001b[0m     delimiter,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   1022\u001b[0m     dtype_backend\u001b[38;5;241m=\u001b[39mdtype_backend,\n\u001b[0;32m   1023\u001b[0m )\n\u001b[0;32m   1024\u001b[0m kwds\u001b[38;5;241m.\u001b[39mupdate(kwds_defaults)\n\u001b[1;32m-> 1026\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m _read(filepath_or_buffer, kwds)\n",
      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\io\\parsers\\readers.py:620\u001b[0m, in \u001b[0;36m_read\u001b[1;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[0;32m    617\u001b[0m _validate_names(kwds\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnames\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m))\n\u001b[0;32m    619\u001b[0m \u001b[38;5;66;03m# Create the parser.\u001b[39;00m\n\u001b[1;32m--> 620\u001b[0m parser \u001b[38;5;241m=\u001b[39m TextFileReader(filepath_or_buffer, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwds)\n\u001b[0;32m    622\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m chunksize \u001b[38;5;129;01mor\u001b[39;00m iterator:\n\u001b[0;32m    623\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m parser\n",
      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\io\\parsers\\readers.py:1620\u001b[0m, in \u001b[0;36mTextFileReader.__init__\u001b[1;34m(self, f, engine, **kwds)\u001b[0m\n\u001b[0;32m   1617\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m kwds[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[0;32m   1619\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles: IOHandles \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m-> 1620\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_engine \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_make_engine(f, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mengine)\n",
      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\io\\parsers\\readers.py:1880\u001b[0m, in \u001b[0;36mTextFileReader._make_engine\u001b[1;34m(self, f, engine)\u001b[0m\n\u001b[0;32m   1878\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m mode:\n\u001b[0;32m   1879\u001b[0m         mode \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m-> 1880\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles \u001b[38;5;241m=\u001b[39m get_handle(\n\u001b[0;32m   1881\u001b[0m     f,\n\u001b[0;32m   1882\u001b[0m     mode,\n\u001b[0;32m   1883\u001b[0m     encoding\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mencoding\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m),\n\u001b[0;32m   1884\u001b[0m     compression\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcompression\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m),\n\u001b[0;32m   1885\u001b[0m     memory_map\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmemory_map\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mFalse\u001b[39;00m),\n\u001b[0;32m   1886\u001b[0m     is_text\u001b[38;5;241m=\u001b[39mis_text,\n\u001b[0;32m   1887\u001b[0m     errors\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mencoding_errors\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstrict\u001b[39m\u001b[38;5;124m\"\u001b[39m),\n\u001b[0;32m   1888\u001b[0m     storage_options\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstorage_options\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m),\n\u001b[0;32m   1889\u001b[0m )\n\u001b[0;32m   1890\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m   1891\u001b[0m f \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles\u001b[38;5;241m.\u001b[39mhandle\n",
      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\io\\common.py:873\u001b[0m, in \u001b[0;36mget_handle\u001b[1;34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[0m\n\u001b[0;32m    868\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(handle, \u001b[38;5;28mstr\u001b[39m):\n\u001b[0;32m    869\u001b[0m     \u001b[38;5;66;03m# Check whether the filename is to be opened in binary mode.\u001b[39;00m\n\u001b[0;32m    870\u001b[0m     \u001b[38;5;66;03m# Binary mode does not support 'encoding' and 'newline'.\u001b[39;00m\n\u001b[0;32m    871\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m ioargs\u001b[38;5;241m.\u001b[39mencoding \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m ioargs\u001b[38;5;241m.\u001b[39mmode:\n\u001b[0;32m    872\u001b[0m         \u001b[38;5;66;03m# Encoding\u001b[39;00m\n\u001b[1;32m--> 873\u001b[0m         handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mopen\u001b[39m(\n\u001b[0;32m    874\u001b[0m             handle,\n\u001b[0;32m    875\u001b[0m             ioargs\u001b[38;5;241m.\u001b[39mmode,\n\u001b[0;32m    876\u001b[0m             encoding\u001b[38;5;241m=\u001b[39mioargs\u001b[38;5;241m.\u001b[39mencoding,\n\u001b[0;32m    877\u001b[0m             errors\u001b[38;5;241m=\u001b[39merrors,\n\u001b[0;32m    878\u001b[0m             newline\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m    879\u001b[0m         )\n\u001b[0;32m    880\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m    881\u001b[0m         \u001b[38;5;66;03m# Binary mode\u001b[39;00m\n\u001b[0;32m    882\u001b[0m         handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mopen\u001b[39m(handle, ioargs\u001b[38;5;241m.\u001b[39mmode)\n",
      "\u001b[1;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: '../Datasets/IMDB Dataset.csv'"
     ]
    }
   ],
   "source": [
    "data = pd.read_csv('../Datasets/IMDB Dataset.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data=data.head(500)\n",
    "sia = SentimentIntensityAnalyzer()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[23], line 2\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mreview\u001b[39m\u001b[38;5;124m'\u001b[39m \u001b[38;5;129;01min\u001b[39;00m data\u001b[38;5;241m.\u001b[39mcolumns:\n\u001b[1;32m----> 2\u001b[0m     data[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124msentiment_score\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m data[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mreview\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mapply(\u001b[38;5;28;01mlambda\u001b[39;00m x: sia\u001b[38;5;241m.\u001b[39mpolarity_scores(x)[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcompound\u001b[39m\u001b[38;5;124m'\u001b[39m])\n\u001b[0;32m      3\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m      4\u001b[0m     \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mColumn \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mreview\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m not found.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\core\\series.py:4924\u001b[0m, in \u001b[0;36mSeries.apply\u001b[1;34m(self, func, convert_dtype, args, by_row, **kwargs)\u001b[0m\n\u001b[0;32m   4789\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mapply\u001b[39m(\n\u001b[0;32m   4790\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m   4791\u001b[0m     func: AggFuncType,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   4796\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[0;32m   4797\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m DataFrame \u001b[38;5;241m|\u001b[39m Series:\n\u001b[0;32m   4798\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m   4799\u001b[0m \u001b[38;5;124;03m    Invoke function on values of Series.\u001b[39;00m\n\u001b[0;32m   4800\u001b[0m \n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   4915\u001b[0m \u001b[38;5;124;03m    dtype: float64\u001b[39;00m\n\u001b[0;32m   4916\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[0;32m   4917\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m SeriesApply(\n\u001b[0;32m   4918\u001b[0m         \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m   4919\u001b[0m         func,\n\u001b[0;32m   4920\u001b[0m         convert_dtype\u001b[38;5;241m=\u001b[39mconvert_dtype,\n\u001b[0;32m   4921\u001b[0m         by_row\u001b[38;5;241m=\u001b[39mby_row,\n\u001b[0;32m   4922\u001b[0m         args\u001b[38;5;241m=\u001b[39margs,\n\u001b[0;32m   4923\u001b[0m         kwargs\u001b[38;5;241m=\u001b[39mkwargs,\n\u001b[1;32m-> 4924\u001b[0m     )\u001b[38;5;241m.\u001b[39mapply()\n",
      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\core\\apply.py:1427\u001b[0m, in \u001b[0;36mSeriesApply.apply\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m   1424\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mapply_compat()\n\u001b[0;32m   1426\u001b[0m \u001b[38;5;66;03m# self.func is Callable\u001b[39;00m\n\u001b[1;32m-> 1427\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mapply_standard()\n",
      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\core\\apply.py:1507\u001b[0m, in \u001b[0;36mSeriesApply.apply_standard\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m   1501\u001b[0m \u001b[38;5;66;03m# row-wise access\u001b[39;00m\n\u001b[0;32m   1502\u001b[0m \u001b[38;5;66;03m# apply doesn't have a `na_action` keyword and for backward compat reasons\u001b[39;00m\n\u001b[0;32m   1503\u001b[0m \u001b[38;5;66;03m# we need to give `na_action=\"ignore\"` for categorical data.\u001b[39;00m\n\u001b[0;32m   1504\u001b[0m \u001b[38;5;66;03m# TODO: remove the `na_action=\"ignore\"` when that default has been changed in\u001b[39;00m\n\u001b[0;32m   1505\u001b[0m \u001b[38;5;66;03m#  Categorical (GH51645).\u001b[39;00m\n\u001b[0;32m   1506\u001b[0m action \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mignore\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(obj\u001b[38;5;241m.\u001b[39mdtype, CategoricalDtype) \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m-> 1507\u001b[0m mapped \u001b[38;5;241m=\u001b[39m obj\u001b[38;5;241m.\u001b[39m_map_values(\n\u001b[0;32m   1508\u001b[0m     mapper\u001b[38;5;241m=\u001b[39mcurried, na_action\u001b[38;5;241m=\u001b[39maction, convert\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconvert_dtype\n\u001b[0;32m   1509\u001b[0m )\n\u001b[0;32m   1511\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(mapped) \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(mapped[\u001b[38;5;241m0\u001b[39m], ABCSeries):\n\u001b[0;32m   1512\u001b[0m     \u001b[38;5;66;03m# GH#43986 Need to do list(mapped) in order to get treated as nested\u001b[39;00m\n\u001b[0;32m   1513\u001b[0m     \u001b[38;5;66;03m#  See also GH#25959 regarding EA support\u001b[39;00m\n\u001b[0;32m   1514\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m obj\u001b[38;5;241m.\u001b[39m_constructor_expanddim(\u001b[38;5;28mlist\u001b[39m(mapped), index\u001b[38;5;241m=\u001b[39mobj\u001b[38;5;241m.\u001b[39mindex)\n",
      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\core\\base.py:921\u001b[0m, in \u001b[0;36mIndexOpsMixin._map_values\u001b[1;34m(self, mapper, na_action, convert)\u001b[0m\n\u001b[0;32m    918\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(arr, ExtensionArray):\n\u001b[0;32m    919\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m arr\u001b[38;5;241m.\u001b[39mmap(mapper, na_action\u001b[38;5;241m=\u001b[39mna_action)\n\u001b[1;32m--> 921\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m algorithms\u001b[38;5;241m.\u001b[39mmap_array(arr, mapper, na_action\u001b[38;5;241m=\u001b[39mna_action, convert\u001b[38;5;241m=\u001b[39mconvert)\n",
      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\pandas\\core\\algorithms.py:1743\u001b[0m, in \u001b[0;36mmap_array\u001b[1;34m(arr, mapper, na_action, convert)\u001b[0m\n\u001b[0;32m   1741\u001b[0m values \u001b[38;5;241m=\u001b[39m arr\u001b[38;5;241m.\u001b[39mastype(\u001b[38;5;28mobject\u001b[39m, copy\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[0;32m   1742\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m na_action \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m-> 1743\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m lib\u001b[38;5;241m.\u001b[39mmap_infer(values, mapper, convert\u001b[38;5;241m=\u001b[39mconvert)\n\u001b[0;32m   1744\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m   1745\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m lib\u001b[38;5;241m.\u001b[39mmap_infer_mask(\n\u001b[0;32m   1746\u001b[0m         values, mapper, mask\u001b[38;5;241m=\u001b[39misna(values)\u001b[38;5;241m.\u001b[39mview(np\u001b[38;5;241m.\u001b[39muint8), convert\u001b[38;5;241m=\u001b[39mconvert\n\u001b[0;32m   1747\u001b[0m     )\n",
      "File \u001b[1;32mlib.pyx:2972\u001b[0m, in \u001b[0;36mpandas._libs.lib.map_infer\u001b[1;34m()\u001b[0m\n",
      "Cell \u001b[1;32mIn[23], line 2\u001b[0m, in \u001b[0;36m<lambda>\u001b[1;34m(x)\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mreview\u001b[39m\u001b[38;5;124m'\u001b[39m \u001b[38;5;129;01min\u001b[39;00m data\u001b[38;5;241m.\u001b[39mcolumns:\n\u001b[1;32m----> 2\u001b[0m     data[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124msentiment_score\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m data[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mreview\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mapply(\u001b[38;5;28;01mlambda\u001b[39;00m x: sia\u001b[38;5;241m.\u001b[39mpolarity_scores(x)[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcompound\u001b[39m\u001b[38;5;124m'\u001b[39m])\n\u001b[0;32m      3\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m      4\u001b[0m     \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mColumn \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mreview\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m not found.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\nltk\\sentiment\\vader.py:366\u001b[0m, in \u001b[0;36mSentimentIntensityAnalyzer.polarity_scores\u001b[1;34m(self, text)\u001b[0m\n\u001b[0;32m    355\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    356\u001b[0m \u001b[38;5;124;03mReturn a float for sentiment strength based on the input text.\u001b[39;00m\n\u001b[0;32m    357\u001b[0m \u001b[38;5;124;03mPositive values are positive valence, negative value are negative\u001b[39;00m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    363\u001b[0m \u001b[38;5;124;03m    matched as if it was a normal word in the sentence.\u001b[39;00m\n\u001b[0;32m    364\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    365\u001b[0m \u001b[38;5;66;03m# text, words_and_emoticons, is_cap_diff = self.preprocess(text)\u001b[39;00m\n\u001b[1;32m--> 366\u001b[0m sentitext \u001b[38;5;241m=\u001b[39m SentiText(\n\u001b[0;32m    367\u001b[0m     text, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconstants\u001b[38;5;241m.\u001b[39mPUNC_LIST, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconstants\u001b[38;5;241m.\u001b[39mREGEX_REMOVE_PUNCTUATION\n\u001b[0;32m    368\u001b[0m )\n\u001b[0;32m    369\u001b[0m sentiments \u001b[38;5;241m=\u001b[39m []\n\u001b[0;32m    370\u001b[0m words_and_emoticons \u001b[38;5;241m=\u001b[39m sentitext\u001b[38;5;241m.\u001b[39mwords_and_emoticons\n",
      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\nltk\\sentiment\\vader.py:274\u001b[0m, in \u001b[0;36mSentiText.__init__\u001b[1;34m(self, text, punc_list, regex_remove_punctuation)\u001b[0m\n\u001b[0;32m    272\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mPUNC_LIST \u001b[38;5;241m=\u001b[39m punc_list\n\u001b[0;32m    273\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mREGEX_REMOVE_PUNCTUATION \u001b[38;5;241m=\u001b[39m regex_remove_punctuation\n\u001b[1;32m--> 274\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mwords_and_emoticons \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_words_and_emoticons()\n\u001b[0;32m    275\u001b[0m \u001b[38;5;66;03m# doesn't separate words from\u001b[39;00m\n\u001b[0;32m    276\u001b[0m \u001b[38;5;66;03m# adjacent punctuation (keeps emoticons & contractions)\u001b[39;00m\n\u001b[0;32m    277\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mis_cap_diff \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mallcap_differential(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mwords_and_emoticons)\n",
      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\nltk\\sentiment\\vader.py:306\u001b[0m, in \u001b[0;36mSentiText._words_and_emoticons\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    300\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    301\u001b[0m \u001b[38;5;124;03mRemoves leading and trailing puncutation\u001b[39;00m\n\u001b[0;32m    302\u001b[0m \u001b[38;5;124;03mLeaves contractions and most emoticons\u001b[39;00m\n\u001b[0;32m    303\u001b[0m \u001b[38;5;124;03m    Does not preserve punc-plus-letter emoticons (e.g. :D)\u001b[39;00m\n\u001b[0;32m    304\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    305\u001b[0m wes \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtext\u001b[38;5;241m.\u001b[39msplit()\n\u001b[1;32m--> 306\u001b[0m words_punc_dict \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_words_plus_punc()\n\u001b[0;32m    307\u001b[0m wes \u001b[38;5;241m=\u001b[39m [we \u001b[38;5;28;01mfor\u001b[39;00m we \u001b[38;5;129;01min\u001b[39;00m wes \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(we) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m]\n\u001b[0;32m    308\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i, we \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(wes):\n",
      "File \u001b[1;32mc:\\Users\\Rikhil Nellimarla\\.conda\\envs\\NLP_env\\Lib\\site-packages\\nltk\\sentiment\\vader.py:293\u001b[0m, in \u001b[0;36mSentiText._words_plus_punc\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    291\u001b[0m words_only \u001b[38;5;241m=\u001b[39m {w \u001b[38;5;28;01mfor\u001b[39;00m w \u001b[38;5;129;01min\u001b[39;00m words_only \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(w) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m}\n\u001b[0;32m    292\u001b[0m \u001b[38;5;66;03m# the product gives ('cat', ',') and (',', 'cat')\u001b[39;00m\n\u001b[1;32m--> 293\u001b[0m punc_before \u001b[38;5;241m=\u001b[39m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(p): p[\u001b[38;5;241m1\u001b[39m] \u001b[38;5;28;01mfor\u001b[39;00m p \u001b[38;5;129;01min\u001b[39;00m product(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mPUNC_LIST, words_only)}\n\u001b[0;32m    294\u001b[0m punc_after \u001b[38;5;241m=\u001b[39m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(p): p[\u001b[38;5;241m0\u001b[39m] \u001b[38;5;28;01mfor\u001b[39;00m p \u001b[38;5;129;01min\u001b[39;00m product(words_only, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mPUNC_LIST)}\n\u001b[0;32m    295\u001b[0m words_punc_dict \u001b[38;5;241m=\u001b[39m punc_before\n",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "if 'review' in data.columns:\n",
    "    data['sentiment_score'] = data['review'].apply(lambda x: sia.polarity_scores(x)['compound'])\n",
    "else:\n",
    "    print(\"Column 'review' not found.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "This oatmeal is not good. Its mushy, soft, I don't like it. Quaker Oats is the way to go.\n"
     ]
    }
   ],
   "source": [
    "print(data['sentiment'].value_counts())\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['This', 'oatmeal', 'is', 'not', 'good', '.', 'Its', 'mushy', ',', 'soft']"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "plt.figure(figsize=(8, 6))\n",
    "sns.countplot(x='sentiment', data=data, palette='Set1')\n",
    "plt.title('Sentiment Distribution')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('This', 'DT'),\n",
       " ('oatmeal', 'NN'),\n",
       " ('is', 'VBZ'),\n",
       " ('not', 'RB'),\n",
       " ('good', 'JJ'),\n",
       " ('.', '.'),\n",
       " ('Its', 'PRP$'),\n",
       " ('mushy', 'NN'),\n",
       " (',', ','),\n",
       " ('soft', 'JJ')]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.to_csv('sentiment_analysis_results.csv', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(S\n",
      "  This/DT\n",
      "  oatmeal/NN\n",
      "  is/VBZ\n",
      "  not/RB\n",
      "  good/JJ\n",
      "  ./.\n",
      "  Its/PRP$\n",
      "  mushy/NN\n",
      "  ,/,\n",
      "  soft/JJ\n",
      "  ,/,\n",
      "  I/PRP\n",
      "  do/VBP\n",
      "  n't/RB\n",
      "  like/VB\n",
      "  it/PRP\n",
      "  ./.\n",
      "  (ORGANIZATION Quaker/NNP Oats/NNPS)\n",
      "  is/VBZ\n",
      "  the/DT\n",
      "  way/NN\n",
      "  to/TO\n",
      "  go/VB\n",
      "  ./.)\n"
     ]
    }
   ],
   "source": [
    "print(data[['review', 'sentiment_score', 'sentiment']].head())"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "NLP_env",
   "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": "3.12.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}