Sentiment_Analysis_using_NLP.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyPD60ebEGSa7WsXww2MWtjF",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/Sayuru99/Sentiment-Analysis-using-NLP/blob/main/Sentiment_Analysis_using_NLP.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 25,
      "metadata": {
        "id": "2A42ugVNNwgx"
      },
      "outputs": [],
      "source": [
        "import pandas as pd\n",
        "import numpy"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Read the dataset using pandas library."
      ],
      "metadata": {
        "id": "Jq8OdT5EOQQg"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df = pd.read_csv('/content/Tweets.csv')"
      ],
      "metadata": {
        "id": "MRN3moZmONlV"
      },
      "execution_count": 26,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# df.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "p8zBKxQdTvkp",
        "outputId": "86603fac-aa1a-4ab7-cce3-d83a7dae6ace"
      },
      "execution_count": 29,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(14640, 15)"
            ]
          },
          "metadata": {},
          "execution_count": 29
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.head(5)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 496
        },
        "id": "P6RUdV5xOt8f",
        "outputId": "b2971770-e4a0-4ad8-f96f-e1edb001becf"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "             tweet_id airline_sentiment  airline_sentiment_confidence  \\\n",
              "0  570306133677760513           neutral                        1.0000   \n",
              "1  570301130888122368          positive                        0.3486   \n",
              "2  570301083672813571           neutral                        0.6837   \n",
              "3  570301031407624196          negative                        1.0000   \n",
              "4  570300817074462722          negative                        1.0000   \n",
              "\n",
              "  negativereason  negativereason_confidence         airline  \\\n",
              "0            NaN                        NaN  Virgin America   \n",
              "1            NaN                     0.0000  Virgin America   \n",
              "2            NaN                        NaN  Virgin America   \n",
              "3     Bad Flight                     0.7033  Virgin America   \n",
              "4     Can't Tell                     1.0000  Virgin America   \n",
              "\n",
              "  airline_sentiment_gold        name negativereason_gold  retweet_count  \\\n",
              "0                    NaN     cairdin                 NaN              0   \n",
              "1                    NaN    jnardino                 NaN              0   \n",
              "2                    NaN  yvonnalynn                 NaN              0   \n",
              "3                    NaN    jnardino                 NaN              0   \n",
              "4                    NaN    jnardino                 NaN              0   \n",
              "\n",
              "                                                text tweet_coord  \\\n",
              "0                @VirginAmerica What @dhepburn said.         NaN   \n",
              "1  @VirginAmerica plus you've added commercials t...         NaN   \n",
              "2  @VirginAmerica I didn't today... Must mean I n...         NaN   \n",
              "3  @VirginAmerica it's really aggressive to blast...         NaN   \n",
              "4  @VirginAmerica and it's a really big bad thing...         NaN   \n",
              "\n",
              "               tweet_created tweet_location               user_timezone  \n",
              "0  2015-02-24 11:35:52 -0800            NaN  Eastern Time (US & Canada)  \n",
              "1  2015-02-24 11:15:59 -0800            NaN  Pacific Time (US & Canada)  \n",
              "2  2015-02-24 11:15:48 -0800      Lets Play  Central Time (US & Canada)  \n",
              "3  2015-02-24 11:15:36 -0800            NaN  Pacific Time (US & Canada)  \n",
              "4  2015-02-24 11:14:45 -0800            NaN  Pacific Time (US & Canada)  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-54fc8e19-0c83-44d9-b4d0-78827f20bef0\">\n",
              "    <div 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>tweet_id</th>\n",
              "      <th>airline_sentiment</th>\n",
              "      <th>airline_sentiment_confidence</th>\n",
              "      <th>negativereason</th>\n",
              "      <th>negativereason_confidence</th>\n",
              "      <th>airline</th>\n",
              "      <th>airline_sentiment_gold</th>\n",
              "      <th>name</th>\n",
              "      <th>negativereason_gold</th>\n",
              "      <th>retweet_count</th>\n",
              "      <th>text</th>\n",
              "      <th>tweet_coord</th>\n",
              "      <th>tweet_created</th>\n",
              "      <th>tweet_location</th>\n",
              "      <th>user_timezone</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>570306133677760513</td>\n",
              "      <td>neutral</td>\n",
              "      <td>1.0000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>Virgin America</td>\n",
              "      <td>NaN</td>\n",
              "      <td>cairdin</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0</td>\n",
              "      <td>@VirginAmerica What @dhepburn said.</td>\n",
              "      <td>NaN</td>\n",
              "      <td>2015-02-24 11:35:52 -0800</td>\n",
              "      <td>NaN</td>\n",
              "      <td>Eastern Time (US &amp; Canada)</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>570301130888122368</td>\n",
              "      <td>positive</td>\n",
              "      <td>0.3486</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0.0000</td>\n",
              "      <td>Virgin America</td>\n",
              "      <td>NaN</td>\n",
              "      <td>jnardino</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0</td>\n",
              "      <td>@VirginAmerica plus you've added commercials t...</td>\n",
              "      <td>NaN</td>\n",
              "      <td>2015-02-24 11:15:59 -0800</td>\n",
              "      <td>NaN</td>\n",
              "      <td>Pacific Time (US &amp; Canada)</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>570301083672813571</td>\n",
              "      <td>neutral</td>\n",
              "      <td>0.6837</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>Virgin America</td>\n",
              "      <td>NaN</td>\n",
              "      <td>yvonnalynn</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0</td>\n",
              "      <td>@VirginAmerica I didn't today... Must mean I n...</td>\n",
              "      <td>NaN</td>\n",
              "      <td>2015-02-24 11:15:48 -0800</td>\n",
              "      <td>Lets Play</td>\n",
              "      <td>Central Time (US &amp; Canada)</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>570301031407624196</td>\n",
              "      <td>negative</td>\n",
              "      <td>1.0000</td>\n",
              "      <td>Bad Flight</td>\n",
              "      <td>0.7033</td>\n",
              "      <td>Virgin America</td>\n",
              "      <td>NaN</td>\n",
              "      <td>jnardino</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0</td>\n",
              "      <td>@VirginAmerica it's really aggressive to blast...</td>\n",
              "      <td>NaN</td>\n",
              "      <td>2015-02-24 11:15:36 -0800</td>\n",
              "      <td>NaN</td>\n",
              "      <td>Pacific Time (US &amp; Canada)</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>570300817074462722</td>\n",
              "      <td>negative</td>\n",
              "      <td>1.0000</td>\n",
              "      <td>Can't Tell</td>\n",
              "      <td>1.0000</td>\n",
              "      <td>Virgin America</td>\n",
              "      <td>NaN</td>\n",
              "      <td>jnardino</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0</td>\n",
              "      <td>@VirginAmerica and it's a really big bad thing...</td>\n",
              "      <td>NaN</td>\n",
              "      <td>2015-02-24 11:14:45 -0800</td>\n",
              "      <td>NaN</td>\n",
              "      <td>Pacific Time (US &amp; Canada)</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-54fc8e19-0c83-44d9-b4d0-78827f20bef0')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-54fc8e19-0c83-44d9-b4d0-78827f20bef0 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-54fc8e19-0c83-44d9-b4d0-78827f20bef0');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df = df[[\"airline_sentiment\", \"text\"]]"
      ],
      "metadata": {
        "id": "9_TjuxLJO2l6"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# df.head(5)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "K7uLl5vHO4F9",
        "outputId": "afa01d4c-c709-4ff5-c582-f9b1188f194f"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  airline_sentiment                                               text\n",
              "0           neutral                @VirginAmerica What @dhepburn said.\n",
              "1          positive  @VirginAmerica plus you've added commercials t...\n",
              "2           neutral  @VirginAmerica I didn't today... Must mean I n...\n",
              "3          negative  @VirginAmerica it's really aggressive to blast...\n",
              "4          negative  @VirginAmerica and it's a really big bad thing..."
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-3563e248-ecc2-4c41-9ea5-1fd13bea1b09\">\n",
              "    <div 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>airline_sentiment</th>\n",
              "      <th>text</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>neutral</td>\n",
              "      <td>@VirginAmerica What @dhepburn said.</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>positive</td>\n",
              "      <td>@VirginAmerica plus you've added commercials t...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>neutral</td>\n",
              "      <td>@VirginAmerica I didn't today... Must mean I n...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>negative</td>\n",
              "      <td>@VirginAmerica it's really aggressive to blast...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>negative</td>\n",
              "      <td>@VirginAmerica and it's a really big bad thing...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-3563e248-ecc2-4c41-9ea5-1fd13bea1b09')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-3563e248-ecc2-4c41-9ea5-1fd13bea1b09 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-3563e248-ecc2-4c41-9ea5-1fd13bea1b09');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# df.groupby('airline_sentiment').describe()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 300
        },
        "id": "7hQcLT3NVWWn",
        "outputId": "72a36e7c-8069-4de8-9ebb-fac20c54c8f0"
      },
      "execution_count": 35,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                  tweet_id                                            \\\n",
              "                     count          mean           std           min   \n",
              "airline_sentiment                                                      \n",
              "negative            9178.0  5.692602e+17  7.572474e+14  5.675900e+17   \n",
              "neutral             3099.0  5.691841e+17  8.068405e+14  5.675883e+17   \n",
              "positive            2363.0  5.691006e+17  8.112476e+14  5.676555e+17   \n",
              "\n",
              "                                                                           \\\n",
              "                            25%           50%           75%           max   \n",
              "airline_sentiment                                                           \n",
              "negative           5.686511e+17  5.695355e+17  5.698798e+17  5.703106e+17   \n",
              "neutral            5.684852e+17  5.693080e+17  5.699305e+17  5.703093e+17   \n",
              "positive           5.684331e+17  5.691980e+17  5.698788e+17  5.703093e+17   \n",
              "\n",
              "                  airline_sentiment_confidence            ...  \\\n",
              "                                         count      mean  ...   \n",
              "airline_sentiment                                         ...   \n",
              "negative                                9178.0  0.933365  ...   \n",
              "neutral                                 3099.0  0.823303  ...   \n",
              "positive                                2363.0  0.872039  ...   \n",
              "\n",
              "                  negativereason_confidence      retweet_count            \\\n",
              "                                        75%  max         count      mean   \n",
              "airline_sentiment                                                          \n",
              "negative                                1.0  1.0        9178.0  0.093375   \n",
              "neutral                                 0.0  0.0        3099.0  0.060987   \n",
              "positive                                0.0  0.0        2363.0  0.069403   \n",
              "\n",
              "                                                       \n",
              "                        std  min  25%  50%  75%   max  \n",
              "airline_sentiment                                      \n",
              "negative           0.792865  0.0  0.0  0.0  0.0  44.0  \n",
              "neutral            0.658037  0.0  0.0  0.0  0.0  28.0  \n",
              "positive           0.659914  0.0  0.0  0.0  0.0  22.0  \n",
              "\n",
              "[3 rows x 32 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-1a1601c4-4131-43a4-ada8-145ebc3836b2\">\n",
              "    <div 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 tr th {\n",
              "        text-align: left;\n",
              "    }\n",
              "\n",
              "    .dataframe thead tr:last-of-type th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr>\n",
              "      <th></th>\n",
              "      <th colspan=\"8\" halign=\"left\">tweet_id</th>\n",
              "      <th colspan=\"2\" halign=\"left\">airline_sentiment_confidence</th>\n",
              "      <th>...</th>\n",
              "      <th colspan=\"2\" halign=\"left\">negativereason_confidence</th>\n",
              "      <th colspan=\"8\" halign=\"left\">retweet_count</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th></th>\n",
              "      <th>count</th>\n",
              "      <th>mean</th>\n",
              "      <th>std</th>\n",
              "      <th>min</th>\n",
              "      <th>25%</th>\n",
              "      <th>50%</th>\n",
              "      <th>75%</th>\n",
              "      <th>max</th>\n",
              "      <th>count</th>\n",
              "      <th>mean</th>\n",
              "      <th>...</th>\n",
              "      <th>75%</th>\n",
              "      <th>max</th>\n",
              "      <th>count</th>\n",
              "      <th>mean</th>\n",
              "      <th>std</th>\n",
              "      <th>min</th>\n",
              "      <th>25%</th>\n",
              "      <th>50%</th>\n",
              "      <th>75%</th>\n",
              "      <th>max</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>airline_sentiment</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>negative</th>\n",
              "      <td>9178.0</td>\n",
              "      <td>5.692602e+17</td>\n",
              "      <td>7.572474e+14</td>\n",
              "      <td>5.675900e+17</td>\n",
              "      <td>5.686511e+17</td>\n",
              "      <td>5.695355e+17</td>\n",
              "      <td>5.698798e+17</td>\n",
              "      <td>5.703106e+17</td>\n",
              "      <td>9178.0</td>\n",
              "      <td>0.933365</td>\n",
              "      <td>...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>9178.0</td>\n",
              "      <td>0.093375</td>\n",
              "      <td>0.792865</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>44.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>neutral</th>\n",
              "      <td>3099.0</td>\n",
              "      <td>5.691841e+17</td>\n",
              "      <td>8.068405e+14</td>\n",
              "      <td>5.675883e+17</td>\n",
              "      <td>5.684852e+17</td>\n",
              "      <td>5.693080e+17</td>\n",
              "      <td>5.699305e+17</td>\n",
              "      <td>5.703093e+17</td>\n",
              "      <td>3099.0</td>\n",
              "      <td>0.823303</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>3099.0</td>\n",
              "      <td>0.060987</td>\n",
              "      <td>0.658037</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>28.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>positive</th>\n",
              "      <td>2363.0</td>\n",
              "      <td>5.691006e+17</td>\n",
              "      <td>8.112476e+14</td>\n",
              "      <td>5.676555e+17</td>\n",
              "      <td>5.684331e+17</td>\n",
              "      <td>5.691980e+17</td>\n",
              "      <td>5.698788e+17</td>\n",
              "      <td>5.703093e+17</td>\n",
              "      <td>2363.0</td>\n",
              "      <td>0.872039</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2363.0</td>\n",
              "      <td>0.069403</td>\n",
              "      <td>0.659914</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>22.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>3 rows × 32 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-1a1601c4-4131-43a4-ada8-145ebc3836b2')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-1a1601c4-4131-43a4-ada8-145ebc3836b2 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-1a1601c4-4131-43a4-ada8-145ebc3836b2');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 35
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "neutral_tweets = df[df['airline_sentiment'] == 'neutral']\n",
        "unique_neutral_tweets = neutral_tweets['text'].nunique()\n",
        "print(\"Number of unique neutral tweets:\", unique_neutral_tweets)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "bAV3IpHXWw7Y",
        "outputId": "d0582487-e1ef-408e-f3a6-6c75411d1a82"
      },
      "execution_count": 38,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Number of unique neutral tweets: 3067\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import nltk\n",
        "\n",
        "import string\n",
        "\n",
        "import re\n",
        "\n",
        "\n",
        "\n",
        "from nltk.stem.porter import PorterStemmer\n",
        "\n",
        "\n",
        "\n",
        "nltk.download('stopwords')\n",
        "\n",
        "from nltk.corpus import stopwords\n",
        "\n",
        "\n",
        "\n",
        "nltk.download('punkt')\n",
        "\n",
        "ps = PorterStemmer()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-rvqd7pWPr_P",
        "outputId": "d5b6d9e0-9f4d-4a67-9b66-bc2a88561758"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "[nltk_data] Downloading package stopwords to /root/nltk_data...\n",
            "[nltk_data]   Package stopwords is already up-to-date!\n",
            "[nltk_data] Downloading package punkt to /root/nltk_data...\n",
            "[nltk_data]   Package punkt is already up-to-date!\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def clean_text(text):\n",
        "\n",
        "    text = text.lower()\n",
        "\n",
        "    text = re.sub(r'http.?://[^\\s]+[\\s]?', '', text)\n",
        "\n",
        "    text = nltk.word_tokenize(text)\n",
        "\n",
        "    y = []\n",
        "\n",
        "    for i in text:\n",
        "          if i not in stopwords.words('english'):\n",
        "            y.append(i)\n",
        "\n",
        "    text = y[:]\n",
        "\n",
        "    y.clear()\n",
        "\n",
        "    for i in text:\n",
        "\n",
        "        y.append(ps.stem(i))\n",
        "\n",
        "    return\" \".join(y)"
      ],
      "metadata": {
        "id": "s8iTq0EmO8Zw"
      },
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Apply “clean_text” function to “text” column and assign the resulting text to new column named “text_cleaned”."
      ],
      "metadata": {
        "id": "OYEu9wiGRWMY"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df['text_cleaned'] = df['text'].apply(clean_text)"
      ],
      "metadata": {
        "id": "JdvpC8nZQ_cp"
      },
      "execution_count": 15,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "#Step 3"
      ],
      "metadata": {
        "id": "vzdEm6GRR161"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "Create a “TfidfVectorizer” using the “sklearn” library by specifying “max_features” as 3000"
      ],
      "metadata": {
        "id": "64FSLWdPR0fm"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.feature_extraction.text import TfidfVectorizer\n",
        "\n",
        "tfidf = TfidfVectorizer(max_features=3000)"
      ],
      "metadata": {
        "id": "vWCfST2IRZVV"
      },
      "execution_count": 16,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Use “TfidfVectorizer”  created to generate TF-IDF vector representation of cleaned text in the column “text_cleaned”, convert the vector representation to an array, and assigned it to a new variable named “X”."
      ],
      "metadata": {
        "id": "ls4i8fY4R4T-"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "X = tfidf.fit_transform(df['text_cleaned']).toarray()"
      ],
      "metadata": {
        "id": "27dW3W_-R7vg"
      },
      "execution_count": 17,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Convert the column “airline_sentiment” to an array and assigned it to a new variable named “Y”."
      ],
      "metadata": {
        "id": "6cmiO11HR954"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "Y = df['airline_sentiment'].values"
      ],
      "metadata": {
        "id": "nl_-zL3JSASh"
      },
      "execution_count": 19,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "#Train Model"
      ],
      "metadata": {
        "id": "iYrO4VeISP69"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "Split the dataset into training and testing sets using the function “train_test_split” available in the “sklearn” library. Set the parameters of the functions “test_size” to 0.2 and “random_state” to 2."
      ],
      "metadata": {
        "id": "uzwm63KSSRci"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=2)"
      ],
      "metadata": {
        "id": "fraV71boSTx7"
      },
      "execution_count": 20,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Train a multinomial Naïve Bayes classifier using the training dataset and predict the sentiment of tweets in the test dataset. Find the accuracy of the model in predicting sentiment labels for the test dataset."
      ],
      "metadata": {
        "id": "wIFjDtanSdeg"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.naive_bayes import MultinomialNB\n",
        "from sklearn.metrics import accuracy_score\n",
        "\n",
        "# Train a multinomial Naive Bayes classifier\n",
        "nb_classifier = MultinomialNB()\n",
        "nb_classifier.fit(X_train, Y_train)\n",
        "\n",
        "# Predict the sentiment of tweets in the test dataset\n",
        "Y_pred = nb_classifier.predict(X_test)\n",
        "\n",
        "# Calculate the accuracy of the model\n",
        "accuracy = accuracy_score(Y_test, Y_pred)\n",
        "print(\"Accuracy:\", accuracy)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "S-72ZpQXSgRu",
        "outputId": "4fcca8e7-777c-4dfe-9ccb-a403d5895432"
      },
      "execution_count": 21,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Accuracy: 0.7219945355191257\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# a = float(\"{0:.2f}\".format(accuracy))\n",
        "# print(a)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-7QtjyvLUW4W",
        "outputId": "1559357e-faf9-4cb4-c4c9-c25dbc55bccd"
      },
      "execution_count": 32,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0.72\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [],
      "metadata": {
        "id": "aX8j-e8DSrN0"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.ensemble import RandomForestClassifier\n",
        "\n",
        "model = RandomForestClassifier()\n",
        "\n",
        "model.fit(X_train,Y_train)\n",
        "\n",
        "y_pred = model.predict(X_test)\n",
        "\n",
        "print(accuracy_score(Y_test,y_pred))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "AyfVFYDkSvo_",
        "outputId": "c9aa9a0e-0315-4949-e3ea-90c3cc50b464"
      },
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0.7564890710382514\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# z = (accuracy_score(Y_test,y_pred))\n",
        "# a = float(\"{0:.2f}\".format(z))\n",
        "# print(a)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "RSbrHRddWAKk",
        "outputId": "51fb1216-752c-4e6d-d791-93f0dbfb6a7a"
      },
      "execution_count": 36,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0.76\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# print(\"Shape of X:\", X.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nSznZk4NUsXA",
        "outputId": "5de74de6-5c42-4e27-c73e-b79848c607da"
      },
      "execution_count": 33,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Shape of X: (14640, 3000)\n"
          ]
        }
      ]
    }
  ]
}