sentiment_analysis.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/darshbaxi/axios_week_project/blob/main/sentiment_analysis.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 123,
      "metadata": {
        "id": "Ha5Qhe2OeFtN"
      },
      "outputs": [],
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "import tensorflow as tf\n",
        "import keras"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Reading Dataset"
      ],
      "metadata": {
        "id": "ruMYCpRv4UvW"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 124,
      "metadata": {
        "id": "dgxDQo5iepr_"
      },
      "outputs": [],
      "source": [
        "df=pd.read_csv('IMDB Dataset.csv',engine='python')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 125,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 423
        },
        "id": "zB3TWItTe4g6",
        "outputId": "8ce0d09e-c7cc-4054-adf7-a7b0f6303dfc"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                                  review sentiment\n",
              "0      One of the other reviewers has mentioned that ...  positive\n",
              "1      A wonderful little production. <br /><br />The...  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\n",
              "...                                                  ...       ...\n",
              "49995  I thought this movie did a down right good job...  positive\n",
              "49996  Bad plot, bad dialogue, bad acting, idiotic di...  negative\n",
              "49997  I am a Catholic taught in parochial elementary...  negative\n",
              "49998  I'm going to have to disagree with the previou...  negative\n",
              "49999  No one expects the Star Trek movies to be high...  negative\n",
              "\n",
              "[50000 rows x 2 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-e1f765c9-39ef-443d-9254-b0ab05bab1d6\" class=\"colab-df-container\">\n",
              "    <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. &lt;br /&gt;&lt;br /&gt;The...</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",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>49995</th>\n",
              "      <td>I thought this movie did a down right good job...</td>\n",
              "      <td>positive</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>49996</th>\n",
              "      <td>Bad plot, bad dialogue, bad acting, idiotic di...</td>\n",
              "      <td>negative</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>49997</th>\n",
              "      <td>I am a Catholic taught in parochial elementary...</td>\n",
              "      <td>negative</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>49998</th>\n",
              "      <td>I'm going to have to disagree with the previou...</td>\n",
              "      <td>negative</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>49999</th>\n",
              "      <td>No one expects the Star Trek movies to be high...</td>\n",
              "      <td>negative</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>50000 rows × 2 columns</p>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e1f765c9-39ef-443d-9254-b0ab05bab1d6')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-e1f765c9-39ef-443d-9254-b0ab05bab1d6 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-e1f765c9-39ef-443d-9254-b0ab05bab1d6');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-8541d25d-023d-4ab1-a302-1097c44ad142\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-8541d25d-023d-4ab1-a302-1097c44ad142')\"\n",
              "            title=\"Suggest charts.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "    background-color: #E8F0FE;\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: #1967D2;\n",
              "    height: 32px;\n",
              "    padding: 0 0 0 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: #E2EBFA;\n",
              "    box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: #174EA6;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "    background-color: #3B4455;\n",
              "    fill: #D2E3FC;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart:hover {\n",
              "    background-color: #434B5C;\n",
              "    box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "    filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "    fill: #FFFFFF;\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const charts = await google.colab.kernel.invokeFunction(\n",
              "          'suggestCharts', [key], {});\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-8541d25d-023d-4ab1-a302-1097c44ad142 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 125
        }
      ],
      "source": [
        "df"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 126,
      "metadata": {
        "id": "D1XiXAMqhKXh"
      },
      "outputs": [],
      "source": [
        "x=df['review']"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 127,
      "metadata": {
        "id": "Q97ntKcIj3f5"
      },
      "outputs": [],
      "source": [
        "y=df['sentiment']"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 128,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "CqQMpI6sm-li",
        "outputId": "710b4b7d-3ab2-43b3-fdd7-686e25a25f0a"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(50000,)"
            ]
          },
          "metadata": {},
          "execution_count": 128
        }
      ],
      "source": [
        "x.shape"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 129,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yU427h9enE2B",
        "outputId": "65394fca-722a-425b-e4f9-cdee639a68bd"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(50000,)"
            ]
          },
          "metadata": {},
          "execution_count": 129
        }
      ],
      "source": [
        "y.shape"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 130,
      "metadata": {
        "id": "i1-BLU28lmQh"
      },
      "outputs": [],
      "source": [
        "y=list(map(lambda i:0 if i=='negative' else 1,y ))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 131,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "u1uutZCAlsIf",
        "outputId": "9864dfcb-0b60-466b-bfcf-1b2d0c56ce7f"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[1, 1, 1, 0, 1, 1, 1, 0, 0, 1]"
            ]
          },
          "metadata": {},
          "execution_count": 131
        }
      ],
      "source": [
        "y[:10]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 132,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ONhnu3fPm7KT",
        "outputId": "57d45e0b-4ac3-4ac5-fccd-24fb105288d0"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0    One of the other reviewers has mentioned that ...\n",
              "1    A wonderful little production. <br /><br />The...\n",
              "Name: review, dtype: object"
            ]
          },
          "metadata": {},
          "execution_count": 132
        }
      ],
      "source": [
        "x[:2]"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Data Cleaning"
      ],
      "metadata": {
        "id": "r-O1ZuYD4atp"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 133,
      "metadata": {
        "id": "EySvc2eFnlR1"
      },
      "outputs": [],
      "source": [
        "import re\n",
        "removal_tag=re.compile(\"<[a-zA-Z]+\\s\\/>\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 134,
      "metadata": {
        "id": "-UWU9fMHwv0y"
      },
      "outputs": [],
      "source": [
        "def tagremove(text):\n",
        "  return removal_tag.sub(' ',text)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 135,
      "metadata": {
        "id": "go27HhF-wNd5"
      },
      "outputs": [],
      "source": [
        "x_tag_removal=[]\n",
        "for i in range(len(x)):\n",
        "  sent=x[i]\n",
        "  x_tag_removal.append(tagremove(sent))\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "TIWEhJBTwhVt"
      },
      "outputs": [],
      "source": [
        "x_tag_removal[:2]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 137,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "sBY7adbvzWSI",
        "outputId": "9f9919cb-575c-4aac-b9cd-f890ec3e6078"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "50000"
            ]
          },
          "metadata": {},
          "execution_count": 137
        }
      ],
      "source": [
        "len(x_tag_removal)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 138,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jbQvs-JWyS3C",
        "outputId": "6cc360cb-3fdb-4086-b0ad-48ef88c2909e"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "[nltk_data] Downloading package punkt to /root/nltk_data...\n",
            "[nltk_data]   Package punkt is already up-to-date!\n",
            "[nltk_data] Downloading package stopwords to /root/nltk_data...\n",
            "[nltk_data]   Package stopwords is already up-to-date!\n",
            "[nltk_data] Downloading package wordnet to /root/nltk_data...\n",
            "[nltk_data]   Package wordnet is already up-to-date!\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "True"
            ]
          },
          "metadata": {},
          "execution_count": 138
        }
      ],
      "source": [
        "import nltk\n",
        "from nltk.stem import PorterStemmer as ps\n",
        "from nltk.stem import WordNetLemmatizer as wl\n",
        "from nltk.corpus import stopwords\n",
        "nltk.download('punkt')\n",
        "nltk.download('stopwords')\n",
        "lammtizer=wl()\n",
        "stemmer=ps()\n",
        "nltk.download('wordnet')\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "corpus=[]\n",
        "for i in range(len(x_tag_removal)):\n",
        "  sentence=re.sub('[^a-zA-Z]',' ',x_tag_removal[i])\n",
        "  sentence=re.sub('\\s+',' ',sentence)\n",
        "  sentence=sentence.lower()\n",
        "  word=nltk.word_tokenize(sentence)\n",
        "  arr=[]\n",
        "  for j in word:\n",
        "    if j not in set(stopwords.words('english')):\n",
        "      arr.append(stemmer.stem(j))\n",
        "  sentence=' '.join(arr)\n",
        "  corpus.append(sentence)"
      ],
      "metadata": {
        "id": "9xtkOd-bNm_n"
      },
      "execution_count": 139,
      "outputs": []
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "YY9h54nKnf5F"
      },
      "outputs": [],
      "source": [
        "corpus\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 141,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8IrHJKRKx7MY",
        "outputId": "7b184270-a0e6-4ac9-bbd4-0b6f5ae80a8c"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "50000"
            ]
          },
          "metadata": {},
          "execution_count": 141
        }
      ],
      "source": [
        "len(corpus)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 142,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tL-gIL9ho_mU",
        "outputId": "9565d21f-e787-4734-8b6e-35793408fc1f"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "8290"
            ]
          },
          "metadata": {},
          "execution_count": 142
        }
      ],
      "source": [
        "maxlength=0\n",
        "for i in range(len(corpus)):\n",
        "  if(maxlength<len(corpus[i])):\n",
        "    maxlength=len(corpus[i])\n",
        "\n",
        "maxlength"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Reading Glove File"
      ],
      "metadata": {
        "id": "NZmEFanL4lJ0"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 143,
      "metadata": {
        "id": "kjduOztA_A1t"
      },
      "outputs": [],
      "source": [
        "\n",
        "\n",
        "file=open('/content/glove.6B.100d.txt','r',encoding='utf8')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 144,
      "metadata": {
        "id": "FkInbr6y65JW"
      },
      "outputs": [],
      "source": [
        "file_content=file.readlines()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "d9zyks9kg5jm"
      },
      "outputs": [],
      "source": [
        "file_content"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 146,
      "metadata": {
        "id": "-DV8gd5gnsIm"
      },
      "outputs": [],
      "source": [
        "embedding={}\n",
        "for i in file_content:\n",
        "  senc=i.split()\n",
        "  embedding[senc[0]]=np.array(senc[1:],dtype='float')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 147,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Z6sivZ7WoVSV",
        "outputId": "d938b1d9-f58e-4417-e1dd-bb9b585247ff"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "100"
            ]
          },
          "metadata": {},
          "execution_count": 147
        }
      ],
      "source": [
        "len(embedding['the'])"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Converting Text into Vector using Tokenizer"
      ],
      "metadata": {
        "id": "dpylm3334xvo"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 148,
      "metadata": {
        "id": "R91SnLcsA4kI"
      },
      "outputs": [],
      "source": [
        "from keras.preprocessing.text import Tokenizer\n",
        "word_total = Tokenizer()\n",
        "word_total.fit_on_texts(corpus)\n",
        "wordindex=word_total.word_index\n",
        "vocab_length = len(wordindex)+1"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 149,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "uBSPSnOOJMZK",
        "outputId": "d537ed4a-8e95-4cb3-c595-5d53e7c8f7e7"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "69014"
            ]
          },
          "metadata": {},
          "execution_count": 149
        }
      ],
      "source": [
        "vocab_length"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "71NFc7hEEqbE"
      },
      "outputs": [],
      "source": [
        "wordindex"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "_oqyUaiUCkwL"
      },
      "outputs": [],
      "source": [
        "Xtokens = word_total.texts_to_sequences(corpus)\n",
        "Xtokens\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 155,
      "metadata": {
        "id": "a5hZub2SGR3r"
      },
      "outputs": [],
      "source": [
        "x_train=tf.keras.utils.pad_sequences(Xtokens,maxlen=25,padding='post')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 156,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DTzSuSAXDGzm",
        "outputId": "78cf1e67-aae2-4996-c7fd-2a2e1a06c6a7"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[  970,   570,   558, ...,   438,  3374,   360],\n",
              "       [ 1146,   497,  1581, ...,   270,    16,   138],\n",
              "       [  367,   968,  1126, ...,    25,     9,   119],\n",
              "       ...,\n",
              "       [  704,    76,  3865, ...,  3223, 15604,  1044],\n",
              "       [ 1657,     3,     3, ...,  1795,  1417,   325],\n",
              "       [ 5021, 22111,    14, ...,   907,   564,     1]], dtype=int32)"
            ]
          },
          "metadata": {},
          "execution_count": 156
        }
      ],
      "source": [
        "x_train"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 157,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ZJEDdGaOGj5w",
        "outputId": "a3dd67b7-41b4-444e-ed31-d07ba4915b82"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(50000, 25)"
            ]
          },
          "metadata": {},
          "execution_count": 157
        }
      ],
      "source": [
        "x_train.shape"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "3_yujsFvHFvm"
      },
      "outputs": [],
      "source": [
        "wordindex.items()"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Building Embedding Matrix"
      ],
      "metadata": {
        "id": "e3QKReNj6gjO"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 158,
      "metadata": {
        "id": "tO1GHUjPqMJL"
      },
      "outputs": [],
      "source": [
        "embed_size = 100\n",
        "embeddingmatrix = np.zeros((vocab_length, embed_size))\n",
        "for word, i in wordindex.items():\n",
        "    embed_vector = embedding.get(word)\n",
        "    if embed_vector is not None:\n",
        "       embeddingmatrix[i] = embed_vector\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 159,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Lwg2UdVLr-GT",
        "outputId": "6f5d8ffd-21dc-4241-e5a1-e00d1c967c12"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(69014, 100)"
            ]
          },
          "metadata": {},
          "execution_count": 159
        }
      ],
      "source": [
        "embeddingmatrix.shape"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 160,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4H_cFMiu9hpr",
        "outputId": "89ece3f1-2357-4b4f-86f8-0cb278d0231b"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[ 0.      ,  0.      ,  0.      , ...,  0.      ,  0.      ,\n",
              "         0.      ],\n",
              "       [ 0.      ,  0.      ,  0.      , ...,  0.      ,  0.      ,\n",
              "         0.      ],\n",
              "       [ 0.19916 , -0.049702,  0.24579 , ..., -0.068109,  0.017651,\n",
              "         0.06455 ],\n",
              "       ...,\n",
              "       [ 0.      ,  0.      ,  0.      , ...,  0.      ,  0.      ,\n",
              "         0.      ],\n",
              "       [ 0.      ,  0.      ,  0.      , ...,  0.      ,  0.      ,\n",
              "         0.      ],\n",
              "       [ 0.027842,  0.59833 ,  0.53633 , ...,  0.12272 ,  0.48018 ,\n",
              "         0.54391 ]])"
            ]
          },
          "metadata": {},
          "execution_count": 160
        }
      ],
      "source": [
        "embeddingmatrix"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Building  Model"
      ],
      "metadata": {
        "id": "5c1Zch126mB0"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 161,
      "metadata": {
        "id": "6IcBXls76E35"
      },
      "outputs": [],
      "source": [
        "from keras.layers import LSTM,Dense,Embedding,Bidirectional\n",
        "from keras.models import Sequential"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 162,
      "metadata": {
        "id": "NdkxMtrH6wwL"
      },
      "outputs": [],
      "source": [
        "model = Sequential([\n",
        "    Embedding(input_dim = len(wordindex) + 1,\n",
        "              output_dim = embed_size,\n",
        "              input_length = 25,\n",
        "              weights = [embeddingmatrix],\n",
        "              trainable=False\n",
        "             ),\n",
        "    LSTM(64,return_sequences=True),\n",
        "    LSTM(16),\n",
        "    Dense(1, activation = 'sigmoid')\n",
        "])\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 163,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DOd3ihoz_qqz",
        "outputId": "8d5982d2-d2f9-42ea-a788-87d3a961b227"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model: \"sequential_5\"\n",
            "_________________________________________________________________\n",
            " Layer (type)                Output Shape              Param #   \n",
            "=================================================================\n",
            " embedding_5 (Embedding)     (None, 25, 100)           6901400   \n",
            "                                                                 \n",
            " lstm_10 (LSTM)              (None, 25, 64)            42240     \n",
            "                                                                 \n",
            " lstm_11 (LSTM)              (None, 16)                5184      \n",
            "                                                                 \n",
            " dense_5 (Dense)             (None, 1)                 17        \n",
            "                                                                 \n",
            "=================================================================\n",
            "Total params: 6,948,841\n",
            "Trainable params: 47,441\n",
            "Non-trainable params: 6,901,400\n",
            "_________________________________________________________________\n",
            "None\n"
          ]
        }
      ],
      "source": [
        "model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\n",
        "print(model.summary())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 164,
      "metadata": {
        "id": "qKoorcJYIt4z"
      },
      "outputs": [],
      "source": [
        "x=np.array(x_train)\n",
        "y_tra=np.array(y)"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_tra[:10]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "r2TY49I7_Kim",
        "outputId": "e0f42392-77a7-416f-a17e-f44305db570b"
      },
      "execution_count": 165,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([1, 1, 1, 0, 1, 1, 1, 0, 0, 1])"
            ]
          },
          "metadata": {},
          "execution_count": 165
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 166,
      "metadata": {
        "id": "ULlds4SGJC9V"
      },
      "outputs": [],
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "X_train, X_test, y_train, y_test = train_test_split(x, y_tra, test_size=0.33, random_state=42)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 167,
      "metadata": {
        "id": "3_corRouFHHr",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "8e3bcf60-2633-44e5-cd08-b8cbeea25096"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/5\n",
            "1047/1047 [==============================] - 40s 34ms/step - loss: 0.5680 - accuracy: 0.7025\n",
            "Epoch 2/5\n",
            "1047/1047 [==============================] - 35s 33ms/step - loss: 0.4999 - accuracy: 0.7531\n",
            "Epoch 3/5\n",
            "1047/1047 [==============================] - 36s 34ms/step - loss: 0.4624 - accuracy: 0.7791\n",
            "Epoch 4/5\n",
            "1047/1047 [==============================] - 34s 33ms/step - loss: 0.4354 - accuracy: 0.7952\n",
            "Epoch 5/5\n",
            "1047/1047 [==============================] - 36s 34ms/step - loss: 0.4073 - accuracy: 0.8133\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.History at 0x7f6eef5f3160>"
            ]
          },
          "metadata": {},
          "execution_count": 167
        }
      ],
      "source": [
        "model.fit(X_train,y_train,epochs=5,batch_size=32)"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_glove_pred=model.predict(X_test)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "zh9qOQN8aP4L",
        "outputId": "6acef816-fff9-426b-ddbb-0b62d5decfb5"
      },
      "execution_count": 223,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "516/516 [==============================] - 7s 12ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "for i in range(len(y_glove_pred)):\n",
        "  if(y_glove_pred[i]>0.5):\n",
        "    y_glove_pred[i]=1;\n",
        "  else:\n",
        "    y_glove_pred[i]=0;"
      ],
      "metadata": {
        "id": "GuylNkcLduBD"
      },
      "execution_count": 227,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.metrics import accuracy_score\n",
        "accuracy_score(y_test,y_glove_pred)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9AeCA38caWT0",
        "outputId": "cfb25171-54f4-4189-9aa3-75eec7d706b2"
      },
      "execution_count": 228,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.7698787878787878"
            ]
          },
          "metadata": {},
          "execution_count": 228
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "VBzoxfgkGIZf"
      },
      "source": [
        "## one hot encoding"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from keras.preprocessing.text import one_hot\n",
        "onehotxtrain=[one_hot(senct,vocab_length) for senct in corpus]"
      ],
      "metadata": {
        "id": "BbyA6nc0ZSKk"
      },
      "execution_count": 202,
      "outputs": []
    },
    {
      "cell_type": "code",
      "execution_count": 203,
      "metadata": {
        "id": "vDvSe-TjHDdc"
      },
      "outputs": [],
      "source": [
        "onehot_xtrain=tf.keras.utils.pad_sequences(onehotxtrain,maxlen=25,padding='post')"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
        "# onehot=pad_sequences(onehot_xtrain,padding='post',maxlen=20)"
      ],
      "metadata": {
        "id": "NrdbeNLaJczz"
      },
      "execution_count": 204,
      "outputs": []
    },
    {
      "cell_type": "code",
      "execution_count": 205,
      "metadata": {
        "id": "iZvh8r3sHjCy",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "0bc0828a-12cf-4a54-f835-d6d5c5c4e0c7"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([61623, 24372, 33917, 38200, 52697, 28340, 65865,  6462, 55447,\n",
              "       23686, 22086,  8295, 50793,  8295, 44420,   774, 21933, 19189,\n",
              "       35038, 10353, 36261, 53194, 32169, 47552, 68338], dtype=int32)"
            ]
          },
          "metadata": {},
          "execution_count": 205
        }
      ],
      "source": [
        "onehot_xtrain[101]"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "x_trainone=np.array(onehot_xtrain)\n",
        "x_trainone"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "d4lDUWcx_hqO",
        "outputId": "6cfea16a-e205-4f1b-d17f-d7dfd3aaf4ea"
      },
      "execution_count": 206,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[36766, 50488, 33857, ..., 15655, 25675, 46149],\n",
              "       [57830, 41884, 29563, ..., 59176, 60010, 39941],\n",
              "       [ 5001, 11722, 39740, ..., 24372, 49856, 35468],\n",
              "       ...,\n",
              "       [ 5623,  4166, 24345, ..., 66967, 33148, 59171],\n",
              "       [55351, 60682, 60682, ..., 50936, 14642, 60689],\n",
              "       [30795,  8155, 24112, ...,  3033, 14526, 32198]], dtype=int32)"
            ]
          },
          "metadata": {},
          "execution_count": 206
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_tra"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BpUfPCzjH28L",
        "outputId": "0f23ac27-3dcc-4be6-fd76-2215972172fc"
      },
      "execution_count": 207,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([1, 1, 1, ..., 0, 0, 0])"
            ]
          },
          "metadata": {},
          "execution_count": 207
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "x_train2, x_test2, y_train2, y_test2 = train_test_split(x_trainone, y_tra, test_size=0.20, random_state=42)"
      ],
      "metadata": {
        "id": "xJIpkQiw_1ZR"
      },
      "execution_count": 208,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "x_train2"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5yrZAQpq_7Uz",
        "outputId": "9b34388c-88e3-451f-af1c-8f2964c1e58b"
      },
      "execution_count": 209,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[66844, 15252, 61462, ..., 12110, 19494, 30370],\n",
              "       [40495,  3124,  7485, ..., 39033, 46259,  3694],\n",
              "       [44917, 46408, 31765, ..., 28680, 38450,  8182],\n",
              "       ...,\n",
              "       [35620, 15926,  8182, ..., 20042, 20486, 22938],\n",
              "       [42801,  1036,  4808, ...,  3694, 31568,  5074],\n",
              "       [69006, 24112, 25898, ..., 52704, 46408, 39365]], dtype=int32)"
            ]
          },
          "metadata": {},
          "execution_count": 209
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 210,
      "metadata": {
        "id": "MfbI8jLBHlfZ",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 74
        },
        "outputId": "65482d55-4cb5-4689-864c-4ce2107b89a7"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "MultinomialNB()"
            ],
            "text/html": [
              "<style>#sk-container-id-9 {color: black;background-color: white;}#sk-container-id-9 pre{padding: 0;}#sk-container-id-9 div.sk-toggleable {background-color: white;}#sk-container-id-9 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-9 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-9 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-9 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-9 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-9 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-9 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-9 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-9 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-9 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-9 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-9 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-9 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-9 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-9 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-9 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-9 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-9 div.sk-item {position: relative;z-index: 1;}#sk-container-id-9 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-9 div.sk-item::before, #sk-container-id-9 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-9 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-9 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-9 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-9 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-9 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-9 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-9 div.sk-label-container {text-align: center;}#sk-container-id-9 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-9 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-9\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MultinomialNB()</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-9\" type=\"checkbox\" checked><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MultinomialNB</label><div class=\"sk-toggleable__content\"><pre>MultinomialNB()</pre></div></div></div></div></div>"
            ]
          },
          "metadata": {},
          "execution_count": 210
        }
      ],
      "source": [
        "from sklearn.naive_bayes import MultinomialNB\n",
        "histroy = MultinomialNB()\n",
        "histroy.fit(x_train2, y_train2)"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_pred=histroy.predict(x_test2)"
      ],
      "metadata": {
        "id": "AfDfOGBN7oSS"
      },
      "execution_count": 211,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.metrics import accuracy_score\n",
        "accuracy_score(y_test2,y_pred)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "AXxyzEKyIJf5",
        "outputId": "db54ec93-cbd5-4fb8-bcae-476830c2a9d6"
      },
      "execution_count": 212,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.4978"
            ]
          },
          "metadata": {},
          "execution_count": 212
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model_hot = Sequential([\n",
        "    Embedding(input_dim = vocab_length,\n",
        "              output_dim = embed_size,\n",
        "              input_length = 25,\n",
        "             ),\n",
        "    LSTM(64,return_sequences=True),\n",
        "    LSTM(16),\n",
        "    Dense(1, activation = 'sigmoid')\n",
        "])"
      ],
      "metadata": {
        "id": "SgHq7VmVI5B_"
      },
      "execution_count": 217,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model_hot.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\n",
        "print(model_hot.summary())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ksNUx4CnI5xY",
        "outputId": "49d2aa38-24b1-43d1-c40d-0947396d1897"
      },
      "execution_count": 218,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model: \"sequential_10\"\n",
            "_________________________________________________________________\n",
            " Layer (type)                Output Shape              Param #   \n",
            "=================================================================\n",
            " embedding_10 (Embedding)    (None, 25, 100)           6901400   \n",
            "                                                                 \n",
            " lstm_20 (LSTM)              (None, 25, 64)            42240     \n",
            "                                                                 \n",
            " lstm_21 (LSTM)              (None, 16)                5184      \n",
            "                                                                 \n",
            " dense_10 (Dense)            (None, 1)                 17        \n",
            "                                                                 \n",
            "=================================================================\n",
            "Total params: 6,948,841\n",
            "Trainable params: 6,948,841\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n",
            "None\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "X_train3, X_test3, y_train3, y_test3 = train_test_split(x_trainone, y_tra, test_size=0.20, random_state=42)"
      ],
      "metadata": {
        "id": "5ocguvtuKJEs"
      },
      "execution_count": 219,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model_hot.fit(X_train3,y_train3,epochs=5,batch_size=64)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "caK76QTYadrl",
        "outputId": "f8467e52-1af5-4073-eca8-5d15fbd3f88a"
      },
      "execution_count": 220,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/5\n",
            "625/625 [==============================] - 86s 132ms/step - loss: 0.4551 - accuracy: 0.7832\n",
            "Epoch 2/5\n",
            "625/625 [==============================] - 88s 141ms/step - loss: 0.3165 - accuracy: 0.8647\n",
            "Epoch 3/5\n",
            "625/625 [==============================] - 83s 133ms/step - loss: 0.2208 - accuracy: 0.9081\n",
            "Epoch 4/5\n",
            "625/625 [==============================] - 83s 133ms/step - loss: 0.1481 - accuracy: 0.9423\n",
            "Epoch 5/5\n",
            "625/625 [==============================] - 83s 134ms/step - loss: 0.0963 - accuracy: 0.9640\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.History at 0x7f6eab741fc0>"
            ]
          },
          "metadata": {},
          "execution_count": 220
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_onehot_pred=model_hot.predict(X_test3)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "KhHwHJNPebTC",
        "outputId": "e31758f9-4a99-4791-a763-970920f8544b"
      },
      "execution_count": 234,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "313/313 [==============================] - 4s 10ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "for i in range(len(y_onehot_pred)):\n",
        "  if(y_onehot_pred[i]>0.5):\n",
        "    y_onehot_pred[i]=1;\n",
        "  else:\n",
        "    y_onehot_pred[i]=0;"
      ],
      "metadata": {
        "id": "q8m5roineodW"
      },
      "execution_count": 235,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.metrics import accuracy_score\n",
        "accuracy_score(y_test3,y_onehot_pred)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "0cGNKaRle4ng",
        "outputId": "345f5f15-f955-445d-b1f9-9294b2febf3d"
      },
      "execution_count": 236,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.7773"
            ]
          },
          "metadata": {},
          "execution_count": 236
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "tspbH_B-0ZkE"
      },
      "source": [
        "## Bag OF Words"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "zVCM873x0dNH"
      },
      "outputs": [],
      "source": [
        "from sklearn.feature_extraction.text import CountVectorizer\n",
        "cv=CountVectorizer(binary=True)\n",
        "x_cv=cv.fit_transform(corpus).toarray()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "background_save": true
        },
        "id": "bvhWhXBE18ll"
      },
      "outputs": [],
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "x_train_bow, x_test_bow, y_train_bow, y_test_bow = train_test_split(x, y, test_size=0.33, random_state=42,stratify=True)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "7oaTn__56SOy"
      },
      "outputs": [],
      "source": [
        "model_bow = Sequential([\n",
        "    Embedding(input_dim = vocab_length,\n",
        "              output_dim = embed_size,\n",
        "              input_length = 100,\n",
        "             ),\n",
        "    LSTM(64,return_sequences=True),\n",
        "    LSTM(16),\n",
        "    Dense(1, activation = 'softmax')\n",
        "])"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "x1ixLbzf75Bz"
      },
      "outputs": [],
      "source": [
        "model_bow.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\n",
        "print(model_bow.summary())"
      ]
    }
  ],
  "metadata": {
    "accelerator": "TPU",
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyMDZjSFFlgyIA3qx59wqMPQ",
      "include_colab_link": true
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}