{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:16.293152Z",
     "iopub.status.busy": "2024-05-28T14:52:16.292540Z",
     "iopub.status.idle": "2024-05-28T14:52:17.111429Z",
     "shell.execute_reply": "2024-05-28T14:52:17.110616Z",
     "shell.execute_reply.started": "2024-05-28T14:52:16.293118Z"
    }
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:17.113325Z",
     "iopub.status.busy": "2024-05-28T14:52:17.112978Z",
     "iopub.status.idle": "2024-05-28T14:52:18.294078Z",
     "shell.execute_reply": "2024-05-28T14:52:18.293195Z",
     "shell.execute_reply.started": "2024-05-28T14:52:17.113302Z"
    }
   },
   "outputs": [],
   "source": [
    "df=pd.read_csv(\"/kaggle/input/imdb-dataset-of-50k-movie-reviews/IMDB Dataset.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:25:43.527134Z",
     "iopub.status.busy": "2024-05-28T14:25:43.526863Z",
     "iopub.status.idle": "2024-05-28T14:25:43.531421Z",
     "shell.execute_reply": "2024-05-28T14:25:43.530388Z",
     "shell.execute_reply.started": "2024-05-28T14:25:43.527112Z"
    }
   },
   "source": [
    "df=df.head(10000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:18.295520Z",
     "iopub.status.busy": "2024-05-28T14:52:18.295184Z",
     "iopub.status.idle": "2024-05-28T14:52:18.320913Z",
     "shell.execute_reply": "2024-05-28T14:52:18.320001Z",
     "shell.execute_reply.started": "2024-05-28T14:52:18.295492Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "sentiment\n",
       "positive    25000\n",
       "negative    25000\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['sentiment'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:18.324117Z",
     "iopub.status.busy": "2024-05-28T14:52:18.323673Z",
     "iopub.status.idle": "2024-05-28T14:52:18.340689Z",
     "shell.execute_reply": "2024-05-28T14:52:18.339777Z",
     "shell.execute_reply.started": "2024-05-28T14:52:18.324090Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "review       0\n",
       "sentiment    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:18.342289Z",
     "iopub.status.busy": "2024-05-28T14:52:18.341941Z",
     "iopub.status.idle": "2024-05-28T14:52:18.511426Z",
     "shell.execute_reply": "2024-05-28T14:52:18.510510Z",
     "shell.execute_reply.started": "2024-05-28T14:52:18.342257Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "418"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.duplicated().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:18.513001Z",
     "iopub.status.busy": "2024-05-28T14:52:18.512633Z",
     "iopub.status.idle": "2024-05-28T14:52:18.662976Z",
     "shell.execute_reply": "2024-05-28T14:52:18.662258Z",
     "shell.execute_reply.started": "2024-05-28T14:52:18.512969Z"
    }
   },
   "outputs": [],
   "source": [
    "df=df.drop_duplicates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:18.664321Z",
     "iopub.status.busy": "2024-05-28T14:52:18.664037Z",
     "iopub.status.idle": "2024-05-28T14:52:18.811830Z",
     "shell.execute_reply": "2024-05-28T14:52:18.810966Z",
     "shell.execute_reply.started": "2024-05-28T14:52:18.664297Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.duplicated().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# **Removing HTML Tags**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:18.813219Z",
     "iopub.status.busy": "2024-05-28T14:52:18.812944Z",
     "iopub.status.idle": "2024-05-28T14:52:18.817734Z",
     "shell.execute_reply": "2024-05-28T14:52:18.816871Z",
     "shell.execute_reply.started": "2024-05-28T14:52:18.813195Z"
    }
   },
   "outputs": [],
   "source": [
    "import re\n",
    "def remove_tags(text):\n",
    "    return re.sub(re.compile('<.*?>'),'',text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:18.819205Z",
     "iopub.status.busy": "2024-05-28T14:52:18.818864Z",
     "iopub.status.idle": "2024-05-28T14:52:19.094654Z",
     "shell.execute_reply": "2024-05-28T14:52:19.093668Z",
     "shell.execute_reply.started": "2024-05-28T14:52:18.819173Z"
    }
   },
   "outputs": [],
   "source": [
    "df['review']=df['review'].apply(remove_tags)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:19.099305Z",
     "iopub.status.busy": "2024-05-28T14:52:19.099017Z",
     "iopub.status.idle": "2024-05-28T14:52:19.112472Z",
     "shell.execute_reply": "2024-05-28T14:52:19.111531Z",
     "shell.execute_reply.started": "2024-05-28T14:52:19.099280Z"
    }
   },
   "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>review</th>\n",
       "      <th>sentiment</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>One of the other reviewers has mentioned that ...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>A wonderful little production. The filming tec...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>I thought this was a wonderful way to spend ti...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Basically there's a family where a little boy ...</td>\n",
       "      <td>negative</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Petter Mattei's \"Love in the Time of Money\" is...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              review sentiment\n",
       "0  One of the other reviewers has mentioned that ...  positive\n",
       "1  A wonderful little production. The filming tec...  positive\n",
       "2  I thought this was a wonderful way to spend ti...  positive\n",
       "3  Basically there's a family where a little boy ...  negative\n",
       "4  Petter Mattei's \"Love in the Time of Money\" is...  positive"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# **Lowercase**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:19.113977Z",
     "iopub.status.busy": "2024-05-28T14:52:19.113619Z",
     "iopub.status.idle": "2024-05-28T14:52:19.299489Z",
     "shell.execute_reply": "2024-05-28T14:52:19.298706Z",
     "shell.execute_reply.started": "2024-05-28T14:52:19.113944Z"
    }
   },
   "outputs": [],
   "source": [
    "df['review']=df['review'].apply(lambda x:x.lower())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:19.300853Z",
     "iopub.status.busy": "2024-05-28T14:52:19.300570Z",
     "iopub.status.idle": "2024-05-28T14:52:19.311359Z",
     "shell.execute_reply": "2024-05-28T14:52:19.310381Z",
     "shell.execute_reply.started": "2024-05-28T14:52:19.300827Z"
    }
   },
   "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>review</th>\n",
       "      <th>sentiment</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>one of the other reviewers has mentioned that ...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a wonderful little production. the filming tec...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>i thought this was a wonderful way to spend ti...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>basically there's a family where a little boy ...</td>\n",
       "      <td>negative</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>petter mattei's \"love in the time of money\" is...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              review sentiment\n",
       "0  one of the other reviewers has mentioned that ...  positive\n",
       "1  a wonderful little production. the filming tec...  positive\n",
       "2  i thought this was a wonderful way to spend ti...  positive\n",
       "3  basically there's a family where a little boy ...  negative\n",
       "4  petter mattei's \"love in the time of money\" is...  positive"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# **Removing Stopwords**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:19.313147Z",
     "iopub.status.busy": "2024-05-28T14:52:19.312754Z",
     "iopub.status.idle": "2024-05-28T14:52:20.687218Z",
     "shell.execute_reply": "2024-05-28T14:52:20.686234Z",
     "shell.execute_reply.started": "2024-05-28T14:52:19.313113Z"
    }
   },
   "outputs": [],
   "source": [
    "from nltk.corpus import stopwords"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:20.688722Z",
     "iopub.status.busy": "2024-05-28T14:52:20.688422Z",
     "iopub.status.idle": "2024-05-28T14:52:20.695776Z",
     "shell.execute_reply": "2024-05-28T14:52:20.694869Z",
     "shell.execute_reply.started": "2024-05-28T14:52:20.688690Z"
    }
   },
   "outputs": [],
   "source": [
    "sw_list=stopwords.words('english')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:20.697662Z",
     "iopub.status.busy": "2024-05-28T14:52:20.696910Z",
     "iopub.status.idle": "2024-05-28T14:52:41.103845Z",
     "shell.execute_reply": "2024-05-28T14:52:41.103006Z",
     "shell.execute_reply.started": "2024-05-28T14:52:20.697626Z"
    }
   },
   "outputs": [],
   "source": [
    "df['review']=df['review'].apply(lambda x:[item for item in x.split() if item not in sw_list]).apply(lambda x:\" \".join(x))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:41.105206Z",
     "iopub.status.busy": "2024-05-28T14:52:41.104945Z",
     "iopub.status.idle": "2024-05-28T14:52:41.115077Z",
     "shell.execute_reply": "2024-05-28T14:52:41.114149Z",
     "shell.execute_reply.started": "2024-05-28T14:52:41.105183Z"
    }
   },
   "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>review</th>\n",
       "      <th>sentiment</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>one reviewers mentioned watching 1 oz episode ...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>wonderful little production. filming technique...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>thought wonderful way spend time hot summer we...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>basically there's family little boy (jake) thi...</td>\n",
       "      <td>negative</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>petter mattei's \"love time money\" visually stu...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              review sentiment\n",
       "0  one reviewers mentioned watching 1 oz episode ...  positive\n",
       "1  wonderful little production. filming technique...  positive\n",
       "2  thought wonderful way spend time hot summer we...  positive\n",
       "3  basically there's family little boy (jake) thi...  negative\n",
       "4  petter mattei's \"love time money\" visually stu...  positive"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# **Removing Numbers**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:41.116693Z",
     "iopub.status.busy": "2024-05-28T14:52:41.116370Z",
     "iopub.status.idle": "2024-05-28T14:52:42.350128Z",
     "shell.execute_reply": "2024-05-28T14:52:42.349082Z",
     "shell.execute_reply.started": "2024-05-28T14:52:41.116666Z"
    }
   },
   "outputs": [],
   "source": [
    "df['review']=df['review'].apply(lambda x:' '.join([i for i in x.split() if not i.isdigit()]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:42.352200Z",
     "iopub.status.busy": "2024-05-28T14:52:42.351476Z",
     "iopub.status.idle": "2024-05-28T14:52:42.361695Z",
     "shell.execute_reply": "2024-05-28T14:52:42.360686Z",
     "shell.execute_reply.started": "2024-05-28T14:52:42.352154Z"
    }
   },
   "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>review</th>\n",
       "      <th>sentiment</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>one reviewers mentioned watching oz episode ho...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>wonderful little production. filming technique...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>thought wonderful way spend time hot summer we...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>basically there's family little boy (jake) thi...</td>\n",
       "      <td>negative</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>petter mattei's \"love time money\" visually stu...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              review sentiment\n",
       "0  one reviewers mentioned watching oz episode ho...  positive\n",
       "1  wonderful little production. filming technique...  positive\n",
       "2  thought wonderful way spend time hot summer we...  positive\n",
       "3  basically there's family little boy (jake) thi...  negative\n",
       "4  petter mattei's \"love time money\" visually stu...  positive"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# **Removing Punctuation**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:42.363205Z",
     "iopub.status.busy": "2024-05-28T14:52:42.362921Z",
     "iopub.status.idle": "2024-05-28T14:52:42.369773Z",
     "shell.execute_reply": "2024-05-28T14:52:42.368884Z",
     "shell.execute_reply.started": "2024-05-28T14:52:42.363181Z"
    }
   },
   "outputs": [],
   "source": [
    "import string\n",
    "PUNCT_TO_REMOVE = string.punctuation\n",
    "def remove_punctuation(text):\n",
    "    return text.translate(str.maketrans('', '', PUNCT_TO_REMOVE))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:42.371097Z",
     "iopub.status.busy": "2024-05-28T14:52:42.370761Z",
     "iopub.status.idle": "2024-05-28T14:52:43.206495Z",
     "shell.execute_reply": "2024-05-28T14:52:43.205666Z",
     "shell.execute_reply.started": "2024-05-28T14:52:42.371071Z"
    }
   },
   "outputs": [],
   "source": [
    "df['review']=df['review'].apply(remove_punctuation)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:43.207858Z",
     "iopub.status.busy": "2024-05-28T14:52:43.207590Z",
     "iopub.status.idle": "2024-05-28T14:52:43.217082Z",
     "shell.execute_reply": "2024-05-28T14:52:43.216131Z",
     "shell.execute_reply.started": "2024-05-28T14:52:43.207835Z"
    }
   },
   "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>review</th>\n",
       "      <th>sentiment</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>one reviewers mentioned watching oz episode ho...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>wonderful little production filming technique ...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>thought wonderful way spend time hot summer we...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>basically theres family little boy jake thinks...</td>\n",
       "      <td>negative</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>petter matteis love time money visually stunni...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              review sentiment\n",
       "0  one reviewers mentioned watching oz episode ho...  positive\n",
       "1  wonderful little production filming technique ...  positive\n",
       "2  thought wonderful way spend time hot summer we...  positive\n",
       "3  basically theres family little boy jake thinks...  negative\n",
       "4  petter matteis love time money visually stunni...  positive"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# **Removing Contractions**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:43.218467Z",
     "iopub.status.busy": "2024-05-28T14:52:43.218186Z",
     "iopub.status.idle": "2024-05-28T14:52:56.917289Z",
     "shell.execute_reply": "2024-05-28T14:52:56.916286Z",
     "shell.execute_reply.started": "2024-05-28T14:52:43.218441Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: contractions in /opt/conda/lib/python3.10/site-packages (0.1.73)\n",
      "Requirement already satisfied: textsearch>=0.0.21 in /opt/conda/lib/python3.10/site-packages (from contractions) (0.0.24)\n",
      "Requirement already satisfied: anyascii in /opt/conda/lib/python3.10/site-packages (from textsearch>=0.0.21->contractions) (0.3.2)\n",
      "Requirement already satisfied: pyahocorasick in /opt/conda/lib/python3.10/site-packages (from textsearch>=0.0.21->contractions) (2.1.0)\n"
     ]
    }
   ],
   "source": [
    "!pip install contractions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:56.919161Z",
     "iopub.status.busy": "2024-05-28T14:52:56.918839Z",
     "iopub.status.idle": "2024-05-28T14:52:56.944515Z",
     "shell.execute_reply": "2024-05-28T14:52:56.943830Z",
     "shell.execute_reply.started": "2024-05-28T14:52:56.919130Z"
    }
   },
   "outputs": [],
   "source": [
    "import contractions\n",
    "def remove_contractions(text):\n",
    "    return contractions.fix(text)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:52:56.945783Z",
     "iopub.status.busy": "2024-05-28T14:52:56.945518Z",
     "iopub.status.idle": "2024-05-28T14:53:00.977406Z",
     "shell.execute_reply": "2024-05-28T14:53:00.976592Z",
     "shell.execute_reply.started": "2024-05-28T14:52:56.945760Z"
    }
   },
   "outputs": [],
   "source": [
    "df['review']=df['review'].apply(remove_contractions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:00.978856Z",
     "iopub.status.busy": "2024-05-28T14:53:00.978551Z",
     "iopub.status.idle": "2024-05-28T14:53:00.991438Z",
     "shell.execute_reply": "2024-05-28T14:53:00.990549Z",
     "shell.execute_reply.started": "2024-05-28T14:53:00.978830Z"
    }
   },
   "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>review</th>\n",
       "      <th>sentiment</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>one reviewers mentioned watching oz episode ho...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>wonderful little production filming technique ...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>thought wonderful way spend time hot summer we...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>basically there is family little boy jake thin...</td>\n",
       "      <td>negative</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>petter matteis love time money visually stunni...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49995</th>\n",
       "      <td>thought movie right good job creative original...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49996</th>\n",
       "      <td>bad plot bad dialogue bad acting idiotic direc...</td>\n",
       "      <td>negative</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49997</th>\n",
       "      <td>catholic taught parochial elementary schools n...</td>\n",
       "      <td>negative</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49998</th>\n",
       "      <td>i am going disagree previous comment side malt...</td>\n",
       "      <td>negative</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49999</th>\n",
       "      <td>one expects star trek movies high art fans exp...</td>\n",
       "      <td>negative</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>49582 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                  review sentiment\n",
       "0      one reviewers mentioned watching oz episode ho...  positive\n",
       "1      wonderful little production filming technique ...  positive\n",
       "2      thought wonderful way spend time hot summer we...  positive\n",
       "3      basically there is family little boy jake thin...  negative\n",
       "4      petter matteis love time money visually stunni...  positive\n",
       "...                                                  ...       ...\n",
       "49995  thought movie right good job creative original...  positive\n",
       "49996  bad plot bad dialogue bad acting idiotic direc...  negative\n",
       "49997  catholic taught parochial elementary schools n...  negative\n",
       "49998  i am going disagree previous comment side malt...  negative\n",
       "49999  one expects star trek movies high art fans exp...  negative\n",
       "\n",
       "[49582 rows x 2 columns]"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:00.993229Z",
     "iopub.status.busy": "2024-05-28T14:53:00.992777Z",
     "iopub.status.idle": "2024-05-28T14:53:01.001576Z",
     "shell.execute_reply": "2024-05-28T14:53:01.000876Z",
     "shell.execute_reply.started": "2024-05-28T14:53:00.993151Z"
    }
   },
   "outputs": [],
   "source": [
    "x=df.drop(columns='sentiment')\n",
    "y=df['sentiment']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:01.003284Z",
     "iopub.status.busy": "2024-05-28T14:53:01.002910Z",
     "iopub.status.idle": "2024-05-28T14:53:01.014799Z",
     "shell.execute_reply": "2024-05-28T14:53:01.013876Z",
     "shell.execute_reply.started": "2024-05-28T14:53:01.003260Z"
    }
   },
   "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>review</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>one reviewers mentioned watching oz episode ho...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>wonderful little production filming technique ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>thought wonderful way spend time hot summer we...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>basically there is family little boy jake thin...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>petter matteis love time money visually stunni...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49995</th>\n",
       "      <td>thought movie right good job creative original...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49996</th>\n",
       "      <td>bad plot bad dialogue bad acting idiotic direc...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49997</th>\n",
       "      <td>catholic taught parochial elementary schools n...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49998</th>\n",
       "      <td>i am going disagree previous comment side malt...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49999</th>\n",
       "      <td>one expects star trek movies high art fans exp...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>49582 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                  review\n",
       "0      one reviewers mentioned watching oz episode ho...\n",
       "1      wonderful little production filming technique ...\n",
       "2      thought wonderful way spend time hot summer we...\n",
       "3      basically there is family little boy jake thin...\n",
       "4      petter matteis love time money visually stunni...\n",
       "...                                                  ...\n",
       "49995  thought movie right good job creative original...\n",
       "49996  bad plot bad dialogue bad acting idiotic direc...\n",
       "49997  catholic taught parochial elementary schools n...\n",
       "49998  i am going disagree previous comment side malt...\n",
       "49999  one expects star trek movies high art fans exp...\n",
       "\n",
       "[49582 rows x 1 columns]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:01.022597Z",
     "iopub.status.busy": "2024-05-28T14:53:01.022330Z",
     "iopub.status.idle": "2024-05-28T14:53:01.030503Z",
     "shell.execute_reply": "2024-05-28T14:53:01.029518Z",
     "shell.execute_reply.started": "2024-05-28T14:53:01.022574Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0        positive\n",
       "1        positive\n",
       "2        positive\n",
       "3        negative\n",
       "4        positive\n",
       "           ...   \n",
       "49995    positive\n",
       "49996    negative\n",
       "49997    negative\n",
       "49998    negative\n",
       "49999    negative\n",
       "Name: sentiment, Length: 49582, dtype: object"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:01.032109Z",
     "iopub.status.busy": "2024-05-28T14:53:01.031731Z",
     "iopub.status.idle": "2024-05-28T14:53:01.037243Z",
     "shell.execute_reply": "2024-05-28T14:53:01.036374Z",
     "shell.execute_reply.started": "2024-05-28T14:53:01.032084Z"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import LabelEncoder"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:01.038703Z",
     "iopub.status.busy": "2024-05-28T14:53:01.038403Z",
     "iopub.status.idle": "2024-05-28T14:53:01.057333Z",
     "shell.execute_reply": "2024-05-28T14:53:01.056511Z",
     "shell.execute_reply.started": "2024-05-28T14:53:01.038679Z"
    }
   },
   "outputs": [],
   "source": [
    "y=LabelEncoder().fit_transform(y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:01.058600Z",
     "iopub.status.busy": "2024-05-28T14:53:01.058345Z",
     "iopub.status.idle": "2024-05-28T14:53:01.067016Z",
     "shell.execute_reply": "2024-05-28T14:53:01.066135Z",
     "shell.execute_reply.started": "2024-05-28T14:53:01.058579Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 1, 1, ..., 0, 0, 0])"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:01.068374Z",
     "iopub.status.busy": "2024-05-28T14:53:01.068086Z",
     "iopub.status.idle": "2024-05-28T14:53:01.099626Z",
     "shell.execute_reply": "2024-05-28T14:53:01.098771Z",
     "shell.execute_reply.started": "2024-05-28T14:53:01.068341Z"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=3,stratify=y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:01.101218Z",
     "iopub.status.busy": "2024-05-28T14:53:01.100870Z",
     "iopub.status.idle": "2024-05-28T14:53:01.106109Z",
     "shell.execute_reply": "2024-05-28T14:53:01.105161Z",
     "shell.execute_reply.started": "2024-05-28T14:53:01.101184Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(39665, 1) (9917, 1)\n"
     ]
    }
   ],
   "source": [
    "print(x_train.shape,x_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Bag of Word"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:01.107866Z",
     "iopub.status.busy": "2024-05-28T14:53:01.107441Z",
     "iopub.status.idle": "2024-05-28T14:53:01.113900Z",
     "shell.execute_reply": "2024-05-28T14:53:01.112939Z",
     "shell.execute_reply.started": "2024-05-28T14:53:01.107829Z"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import CountVectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:01.115218Z",
     "iopub.status.busy": "2024-05-28T14:53:01.114952Z",
     "iopub.status.idle": "2024-05-28T14:53:01.121742Z",
     "shell.execute_reply": "2024-05-28T14:53:01.120751Z",
     "shell.execute_reply.started": "2024-05-28T14:53:01.115195Z"
    }
   },
   "outputs": [],
   "source": [
    "cv=CountVectorizer(max_features=10000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:01.123124Z",
     "iopub.status.busy": "2024-05-28T14:53:01.122830Z",
     "iopub.status.idle": "2024-05-28T14:53:01.134108Z",
     "shell.execute_reply": "2024-05-28T14:53:01.133166Z",
     "shell.execute_reply.started": "2024-05-28T14:53:01.123101Z"
    }
   },
   "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>review</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>17185</th>\n",
       "      <td>watching avalon which decent nice digital fx s...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12989</th>\n",
       "      <td>rarely denzil washington make bad movie come t...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31628</th>\n",
       "      <td>think movie reasonbaly good kind of weird olse...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12399</th>\n",
       "      <td>movie is horrible wonderful time first saw yea...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33230</th>\n",
       "      <td>watching the bodyguard last night felt compell...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31515</th>\n",
       "      <td>good cast with one major exception pushes way ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19133</th>\n",
       "      <td>seldom see short comments written imdb filmgoe...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>47930</th>\n",
       "      <td>say without shadow doubt going overboard singl...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35145</th>\n",
       "      <td>wife watched dvring encore action past week wo...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32654</th>\n",
       "      <td>pokemon little three four episodes tv series s...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>39665 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                  review\n",
       "17185  watching avalon which decent nice digital fx s...\n",
       "12989  rarely denzil washington make bad movie come t...\n",
       "31628  think movie reasonbaly good kind of weird olse...\n",
       "12399  movie is horrible wonderful time first saw yea...\n",
       "33230  watching the bodyguard last night felt compell...\n",
       "...                                                  ...\n",
       "31515  good cast with one major exception pushes way ...\n",
       "19133  seldom see short comments written imdb filmgoe...\n",
       "47930  say without shadow doubt going overboard singl...\n",
       "35145  wife watched dvring encore action past week wo...\n",
       "32654  pokemon little three four episodes tv series s...\n",
       "\n",
       "[39665 rows x 1 columns]"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:01.135399Z",
     "iopub.status.busy": "2024-05-28T14:53:01.135133Z",
     "iopub.status.idle": "2024-05-28T14:53:10.557535Z",
     "shell.execute_reply": "2024-05-28T14:53:10.556708Z",
     "shell.execute_reply.started": "2024-05-28T14:53:01.135377Z"
    }
   },
   "outputs": [],
   "source": [
    "x_train=cv.fit_transform(x_train['review']).toarray()\n",
    "x_test=cv.transform(x_test['review']).toarray()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:10.559169Z",
     "iopub.status.busy": "2024-05-28T14:53:10.558796Z",
     "iopub.status.idle": "2024-05-28T14:53:10.565563Z",
     "shell.execute_reply": "2024-05-28T14:53:10.564604Z",
     "shell.execute_reply.started": "2024-05-28T14:53:10.559135Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(39665, 10000)"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_train.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Applying NaiveBayes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:10.567583Z",
     "iopub.status.busy": "2024-05-28T14:53:10.566619Z",
     "iopub.status.idle": "2024-05-28T14:53:16.857125Z",
     "shell.execute_reply": "2024-05-28T14:53:16.856146Z",
     "shell.execute_reply.started": "2024-05-28T14:53:10.567557Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GaussianNB()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GaussianNB</label><div class=\"sk-toggleable__content\"><pre>GaussianNB()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "GaussianNB()"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.naive_bayes import GaussianNB\n",
    "gnb=GaussianNB()\n",
    "gnb.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:16.860063Z",
     "iopub.status.busy": "2024-05-28T14:53:16.858411Z",
     "iopub.status.idle": "2024-05-28T14:53:18.286607Z",
     "shell.execute_reply": "2024-05-28T14:53:18.285709Z",
     "shell.execute_reply.started": "2024-05-28T14:53:16.860034Z"
    }
   },
   "outputs": [],
   "source": [
    "y_pred=gnb.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:18.288847Z",
     "iopub.status.busy": "2024-05-28T14:53:18.288416Z",
     "iopub.status.idle": "2024-05-28T14:53:18.293343Z",
     "shell.execute_reply": "2024-05-28T14:53:18.292339Z",
     "shell.execute_reply.started": "2024-05-28T14:53:18.288789Z"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.metrics import accuracy_score,confusion_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:18.295253Z",
     "iopub.status.busy": "2024-05-28T14:53:18.294781Z",
     "iopub.status.idle": "2024-05-28T14:53:18.305801Z",
     "shell.execute_reply": "2024-05-28T14:53:18.304884Z",
     "shell.execute_reply.started": "2024-05-28T14:53:18.295215Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7354038519713623"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:18.307732Z",
     "iopub.status.busy": "2024-05-28T14:53:18.307121Z",
     "iopub.status.idle": "2024-05-28T14:53:18.316221Z",
     "shell.execute_reply": "2024-05-28T14:53:18.315238Z",
     "shell.execute_reply.started": "2024-05-28T14:53:18.307697Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[4276,  664],\n",
       "       [1960, 3017]])"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "confusion_matrix(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:53:18.317650Z",
     "iopub.status.busy": "2024-05-28T14:53:18.317380Z",
     "iopub.status.idle": "2024-05-28T14:55:29.097680Z",
     "shell.execute_reply": "2024-05-28T14:55:29.096708Z",
     "shell.execute_reply.started": "2024-05-28T14:53:18.317628Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8426943632146818"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier\n",
    "rf=RandomForestClassifier()\n",
    "rf.fit(x_train,y_train)\n",
    "y_pred=rf.predict(x_test)\n",
    "accuracy_score(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:55:29.099391Z",
     "iopub.status.busy": "2024-05-28T14:55:29.099103Z",
     "iopub.status.idle": "2024-05-28T14:55:29.108811Z",
     "shell.execute_reply": "2024-05-28T14:55:29.107863Z",
     "shell.execute_reply.started": "2024-05-28T14:55:29.099364Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[4152,  788],\n",
       "       [ 772, 4205]])"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "confusion_matrix(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# N_Grams"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:55:29.110803Z",
     "iopub.status.busy": "2024-05-28T14:55:29.110043Z",
     "iopub.status.idle": "2024-05-28T14:55:29.372362Z",
     "shell.execute_reply": "2024-05-28T14:55:29.371484Z",
     "shell.execute_reply.started": "2024-05-28T14:55:29.110765Z"
    }
   },
   "outputs": [],
   "source": [
    "x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=3,stratify=y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:55:29.373855Z",
     "iopub.status.busy": "2024-05-28T14:55:29.373553Z",
     "iopub.status.idle": "2024-05-28T14:55:29.393260Z",
     "shell.execute_reply": "2024-05-28T14:55:29.392224Z",
     "shell.execute_reply.started": "2024-05-28T14:55:29.373828Z"
    }
   },
   "outputs": [],
   "source": [
    "cv=CountVectorizer(ngram_range=(1,2),max_features=10000)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:55:29.394786Z",
     "iopub.status.busy": "2024-05-28T14:55:29.394486Z",
     "iopub.status.idle": "2024-05-28T14:56:00.578967Z",
     "shell.execute_reply": "2024-05-28T14:56:00.577883Z",
     "shell.execute_reply.started": "2024-05-28T14:55:29.394758Z"
    }
   },
   "outputs": [],
   "source": [
    "x_train=cv.fit_transform(x_train['review']).toarray()\n",
    "x_test=cv.transform(x_test['review']).toarray()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:56:00.580808Z",
     "iopub.status.busy": "2024-05-28T14:56:00.580266Z",
     "iopub.status.idle": "2024-05-28T14:58:18.070996Z",
     "shell.execute_reply": "2024-05-28T14:58:18.069821Z",
     "shell.execute_reply.started": "2024-05-28T14:56:00.580771Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.846324493294343"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier\n",
    "rf=RandomForestClassifier()\n",
    "rf.fit(x_train,y_train)\n",
    "y_pred=rf.predict(x_test)\n",
    "accuracy_score(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:58:18.072639Z",
     "iopub.status.busy": "2024-05-28T14:58:18.072319Z",
     "iopub.status.idle": "2024-05-28T14:58:18.081205Z",
     "shell.execute_reply": "2024-05-28T14:58:18.080365Z",
     "shell.execute_reply.started": "2024-05-28T14:58:18.072613Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[4178,  762],\n",
       "       [ 762, 4215]])"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "confusion_matrix(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Saving and Loading"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:01:45.937561Z",
     "iopub.status.busy": "2024-05-28T15:01:45.937238Z",
     "iopub.status.idle": "2024-05-28T15:01:46.088033Z",
     "shell.execute_reply": "2024-05-28T15:01:46.087204Z",
     "shell.execute_reply.started": "2024-05-28T15:01:45.937533Z"
    }
   },
   "outputs": [],
   "source": [
    "import pickle\n",
    "\n",
    "# save the iris classification model as a pickle file\n",
    "model_pkl_file = \"Sentimental_Analysis1.pkl\"  \n",
    "\n",
    "with open(model_pkl_file, 'wb') as file:  \n",
    "    pickle.dump(rf, file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:01:46.090237Z",
     "iopub.status.busy": "2024-05-28T15:01:46.089930Z",
     "iopub.status.idle": "2024-05-28T15:01:46.801994Z",
     "shell.execute_reply": "2024-05-28T15:01:46.800807Z",
     "shell.execute_reply.started": "2024-05-28T15:01:46.090212Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.844711102147827"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "with open(model_pkl_file, 'rb') as file:  \n",
    "    rf = pickle.load(file)\n",
    "y_pred=rf.predict(x_test)\n",
    "accuracy_score(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:58:19.511224Z",
     "iopub.status.busy": "2024-05-28T14:58:19.510906Z",
     "iopub.status.idle": "2024-05-28T14:58:19.785147Z",
     "shell.execute_reply": "2024-05-28T14:58:19.784066Z",
     "shell.execute_reply.started": "2024-05-28T14:58:19.511197Z"
    }
   },
   "outputs": [],
   "source": [
    "x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=3,stratify=y)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# TF_IDF"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:58:19.787439Z",
     "iopub.status.busy": "2024-05-28T14:58:19.786737Z",
     "iopub.status.idle": "2024-05-28T14:58:19.792198Z",
     "shell.execute_reply": "2024-05-28T14:58:19.791132Z",
     "shell.execute_reply.started": "2024-05-28T14:58:19.787387Z"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import TfidfVectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:58:53.029215Z",
     "iopub.status.busy": "2024-05-28T14:58:53.028431Z",
     "iopub.status.idle": "2024-05-28T14:58:53.033696Z",
     "shell.execute_reply": "2024-05-28T14:58:53.032603Z",
     "shell.execute_reply.started": "2024-05-28T14:58:53.029178Z"
    }
   },
   "outputs": [],
   "source": [
    "tfidf=TfidfVectorizer(max_features=10000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:58:58.538248Z",
     "iopub.status.busy": "2024-05-28T14:58:58.537480Z",
     "iopub.status.idle": "2024-05-28T14:59:09.408751Z",
     "shell.execute_reply": "2024-05-28T14:59:09.407944Z",
     "shell.execute_reply.started": "2024-05-28T14:58:58.538211Z"
    }
   },
   "outputs": [],
   "source": [
    "x_train=tfidf.fit_transform(x_train['review']).toarray()\n",
    "x_test=tfidf.transform(x_test['review'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T14:59:18.888515Z",
     "iopub.status.busy": "2024-05-28T14:59:18.888049Z",
     "iopub.status.idle": "2024-05-28T15:01:45.924455Z",
     "shell.execute_reply": "2024-05-28T15:01:45.923366Z",
     "shell.execute_reply.started": "2024-05-28T14:59:18.888481Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.844711102147827"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rf=RandomForestClassifier()\n",
    "rf.fit(x_train,y_train)\n",
    "y_pred=rf.predict(x_test)\n",
    "accuracy_score(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:01:45.926453Z",
     "iopub.status.busy": "2024-05-28T15:01:45.926143Z",
     "iopub.status.idle": "2024-05-28T15:01:45.935972Z",
     "shell.execute_reply": "2024-05-28T15:01:45.934872Z",
     "shell.execute_reply.started": "2024-05-28T15:01:45.926419Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[4182,  758],\n",
       "       [ 782, 4195]])"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "confusion_matrix(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:01:46.804239Z",
     "iopub.status.busy": "2024-05-28T15:01:46.803156Z",
     "iopub.status.idle": "2024-05-28T15:01:47.032951Z",
     "shell.execute_reply": "2024-05-28T15:01:47.031995Z",
     "shell.execute_reply.started": "2024-05-28T15:01:46.804189Z"
    }
   },
   "outputs": [],
   "source": [
    "x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=3,stratify=y)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Word2Vec"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:04:53.247003Z",
     "iopub.status.busy": "2024-05-28T15:04:53.246571Z",
     "iopub.status.idle": "2024-05-28T15:05:04.199287Z",
     "shell.execute_reply": "2024-05-28T15:05:04.198486Z",
     "shell.execute_reply.started": "2024-05-28T15:04:53.246970Z"
    }
   },
   "outputs": [],
   "source": [
    "import gensim"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:05:48.076456Z",
     "iopub.status.busy": "2024-05-28T15:05:48.076082Z",
     "iopub.status.idle": "2024-05-28T15:05:48.080852Z",
     "shell.execute_reply": "2024-05-28T15:05:48.079878Z",
     "shell.execute_reply.started": "2024-05-28T15:05:48.076427Z"
    }
   },
   "outputs": [],
   "source": [
    "from nltk import sent_tokenize\n",
    "from gensim.utils import simple_preprocess"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:07:37.532271Z",
     "iopub.status.busy": "2024-05-28T15:07:37.531546Z",
     "iopub.status.idle": "2024-05-28T15:08:02.872926Z",
     "shell.execute_reply": "2024-05-28T15:08:02.871888Z",
     "shell.execute_reply.started": "2024-05-28T15:07:37.532232Z"
    }
   },
   "outputs": [],
   "source": [
    "story=[]\n",
    "for doc in df['review']:\n",
    "    raw_sent=sent_tokenize(doc)\n",
    "    for sent in raw_sent:\n",
    "        story.append(simple_preprocess(sent))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:08:40.812263Z",
     "iopub.status.busy": "2024-05-28T15:08:40.811483Z",
     "iopub.status.idle": "2024-05-28T15:08:40.817557Z",
     "shell.execute_reply": "2024-05-28T15:08:40.816616Z",
     "shell.execute_reply.started": "2024-05-28T15:08:40.812227Z"
    }
   },
   "outputs": [],
   "source": [
    "model=gensim.models.Word2Vec(\n",
    "window=10,min_count=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:09:01.856845Z",
     "iopub.status.busy": "2024-05-28T15:09:01.855976Z",
     "iopub.status.idle": "2024-05-28T15:09:05.537674Z",
     "shell.execute_reply": "2024-05-28T15:09:05.536873Z",
     "shell.execute_reply.started": "2024-05-28T15:09:01.856798Z"
    }
   },
   "outputs": [],
   "source": [
    "model.build_vocab(story)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:10:20.091520Z",
     "iopub.status.busy": "2024-05-28T15:10:20.091143Z",
     "iopub.status.idle": "2024-05-28T15:10:51.764165Z",
     "shell.execute_reply": "2024-05-28T15:10:51.763105Z",
     "shell.execute_reply.started": "2024-05-28T15:10:20.091491Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(28382867, 30062525)"
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.train(story,total_examples=model.corpus_count,epochs=model.epochs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:11:03.211080Z",
     "iopub.status.busy": "2024-05-28T15:11:03.210673Z",
     "iopub.status.idle": "2024-05-28T15:11:03.218564Z",
     "shell.execute_reply": "2024-05-28T15:11:03.217552Z",
     "shell.execute_reply.started": "2024-05-28T15:11:03.211047Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "79870"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(model.wv.index_to_key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:13:11.657877Z",
     "iopub.status.busy": "2024-05-28T15:13:11.657479Z",
     "iopub.status.idle": "2024-05-28T15:13:11.663513Z",
     "shell.execute_reply": "2024-05-28T15:13:11.662556Z",
     "shell.execute_reply.started": "2024-05-28T15:13:11.657844Z"
    }
   },
   "outputs": [],
   "source": [
    "def dec_vector(doc):\n",
    "    doc=[word for word in doc.split() if word in model.wv.index_to_key]\n",
    "    return np.mean(model.wv[doc],axis=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:14:29.737526Z",
     "iopub.status.busy": "2024-05-28T15:14:29.736457Z",
     "iopub.status.idle": "2024-05-28T15:14:29.742036Z",
     "shell.execute_reply": "2024-05-28T15:14:29.740881Z",
     "shell.execute_reply.started": "2024-05-28T15:14:29.737484Z"
    }
   },
   "outputs": [],
   "source": [
    "from tqdm import tqdm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:16:04.216141Z",
     "iopub.status.busy": "2024-05-28T15:16:04.215772Z",
     "iopub.status.idle": "2024-05-28T15:35:52.614033Z",
     "shell.execute_reply": "2024-05-28T15:35:52.613102Z",
     "shell.execute_reply.started": "2024-05-28T15:16:04.216114Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 49582/49582 [19:48<00:00, 41.72it/s]\n"
     ]
    }
   ],
   "source": [
    "X=[]\n",
    "for doc in tqdm(df['review'].values):\n",
    "    X.append(dec_vector(doc))\n",
    "                "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:35:52.757355Z",
     "iopub.status.busy": "2024-05-28T15:35:52.756711Z",
     "iopub.status.idle": "2024-05-28T15:35:52.801878Z",
     "shell.execute_reply": "2024-05-28T15:35:52.800886Z",
     "shell.execute_reply.started": "2024-05-28T15:35:52.757317Z"
    }
   },
   "outputs": [],
   "source": [
    "X=np.array(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:35:52.992514Z",
     "iopub.status.busy": "2024-05-28T15:35:52.992157Z",
     "iopub.status.idle": "2024-05-28T15:35:52.999577Z",
     "shell.execute_reply": "2024-05-28T15:35:52.998462Z",
     "shell.execute_reply.started": "2024-05-28T15:35:52.992480Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(49582, 100)"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:35:53.001378Z",
     "iopub.status.busy": "2024-05-28T15:35:53.000874Z",
     "iopub.status.idle": "2024-05-28T15:35:53.008752Z",
     "shell.execute_reply": "2024-05-28T15:35:53.007881Z",
     "shell.execute_reply.started": "2024-05-28T15:35:53.001350Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 1, 1, ..., 0, 0, 0])"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:35:53.010300Z",
     "iopub.status.busy": "2024-05-28T15:35:53.009962Z",
     "iopub.status.idle": "2024-05-28T15:35:53.046198Z",
     "shell.execute_reply": "2024-05-28T15:35:53.045411Z",
     "shell.execute_reply.started": "2024-05-28T15:35:53.010269Z"
    }
   },
   "outputs": [],
   "source": [
    "x_train,x_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=3,stratify=y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:35:53.047433Z",
     "iopub.status.busy": "2024-05-28T15:35:53.047187Z",
     "iopub.status.idle": "2024-05-28T15:36:36.307334Z",
     "shell.execute_reply": "2024-05-28T15:36:36.306297Z",
     "shell.execute_reply.started": "2024-05-28T15:35:53.047411Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8395684178683069"
      ]
     },
     "execution_count": 79,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rf=RandomForestClassifier()\n",
    "rf.fit(x_train,y_train)\n",
    "y_pred=rf.predict(x_test)\n",
    "accuracy_score(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:36:36.308713Z",
     "iopub.status.busy": "2024-05-28T15:36:36.308416Z",
     "iopub.status.idle": "2024-05-28T15:36:36.317103Z",
     "shell.execute_reply": "2024-05-28T15:36:36.316187Z",
     "shell.execute_reply.started": "2024-05-28T15:36:36.308682Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[4011,  929],\n",
       "       [ 662, 4315]])"
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "confusion_matrix(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-05-28T15:36:36.319780Z",
     "iopub.status.busy": "2024-05-28T15:36:36.319506Z",
     "iopub.status.idle": "2024-05-28T15:36:37.272618Z",
     "shell.execute_reply": "2024-05-28T15:36:37.271741Z",
     "shell.execute_reply.started": "2024-05-28T15:36:36.319756Z"
    }
   },
   "outputs": [],
   "source": [
    "model_pkl_file = \"Sentimental_Analysis_Word2Vec.pkl\"  \n",
    "\n",
    "with open(model_pkl_file, 'wb') as file:  \n",
    "    pickle.dump(rf, file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kaggle": {
   "accelerator": "nvidiaTeslaT4",
   "dataSources": [
    {
     "datasetId": 134715,
     "sourceId": 320111,
     "sourceType": "datasetVersion"
    }
   ],
   "dockerImageVersionId": 30699,
   "isGpuEnabled": true,
   "isInternetEnabled": true,
   "language": "python",
   "sourceType": "notebook"
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}