skilfoy/sentiment-analysis-of-tweets-on-indian-prime-ministerial-candidates.ipynb

## sentiment-analysis-of-tweets-on-indian-prime-ministerial-candidates.ipynb
{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/skilfoy/67d14c41e96d70c463dd0082e300c2f0/sentiment-analysis-of-tweets-on-indian-prime-ministerial-candidates.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "xUeLhRVJQG83"
      },
      "source": [
        "\n",
        "# Sentiment Analysis of Tweets on Indian Prime Ministerial Candidates\n",
        "\n",
        "**Sean Kilfoy**"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "0Sc3QlmEQXSs"
      },
      "source": [
        "## Scenario\n",
        "\n",
        "You are a data scientist working for a Political Consulting Firm. You are given a dataset containing in Twitter_Data.csv. This dataset has the following two columns:\n",
        "\n",
        "- **clean_text**: Tweets made by the people extracted from Twitter Mainly Focused on tweets Made by People on Modi(2019 Indian Prime Minister candidate) and Other Prime Ministerial Candidates.\n",
        "- **category**: It describes the actual sentiment of the respective tweet with three values of -1, 0, and 1."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "QTbQGvz7ehbJ"
      },
      "source": [
        "## Introduction\n",
        "\n",
        "In this analysis, we will explore the sentiments of tweets regarding Indian Prime Ministerial candidates, primarily focusing on Narendra Modi during the 2019 elections. The dataset contains tweets and their associated sentiment categories. We will perform various text preprocessing and feature extraction techniques to understand the sentiment better."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "EUhXK8Eeenb8"
      },
      "source": [
        "## Step 1: Load the Dataset\n",
        "\n",
        "First, we will load the dataset `Twitter_Data.csv` into memory. This dataset contains two columns: `clean_text` and `category`."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "OhF_fGBYRhnc",
        "outputId": "83eaa576-6d2d-45bf-c220-3ea393397fa0"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
          ]
        }
      ],
      "source": [
        "import pandas as pd\n",
        "from sklearn.feature_extraction.text import CountVectorizer\n",
        "from sklearn.feature_extraction.text import TfidfTransformer\n",
        "from sklearn.feature_extraction.text import TfidfVectorizer\n",
        "from sklearn.feature_extraction.text import HashingVectorizer\n",
        "\n",
        "from google.colab import drive\n",
        "drive.mount('/content/drive')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "7sFjJ0sNSFAI",
        "outputId": "b114c331-1457-4ec0-c45e-27695e8d8a67"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                          clean_text  category\n",
              "0  when modi promised “minimum government maximum...        -1\n",
              "1  talk all the nonsense and continue all the dra...         0\n",
              "2  what did just say vote for modi  welcome bjp t...         1\n",
              "3  asking his supporters prefix chowkidar their n...         1\n",
              "4  answer who among these the most powerful world...         1"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-c2954525-b984-4395-b86e-a0eac69fe4ca\" 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>clean_text</th>\n",
              "      <th>category</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>when modi promised “minimum government maximum...</td>\n",
              "      <td>-1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>talk all the nonsense and continue all the dra...</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>what did just say vote for modi  welcome bjp t...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>asking his supporters prefix chowkidar their n...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>answer who among these the most powerful world...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-c2954525-b984-4395-b86e-a0eac69fe4ca')\"\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-c2954525-b984-4395-b86e-a0eac69fe4ca 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-c2954525-b984-4395-b86e-a0eac69fe4ca');\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-91928bad-5cbd-44a1-829a-e238259ea465\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-91928bad-5cbd-44a1-829a-e238259ea465')\"\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",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-91928bad-5cbd-44a1-829a-e238259ea465 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "data"
            }
          },
          "metadata": {},
          "execution_count": 9
        }
      ],
      "source": [
        "data = pd.read_csv(\"/content/drive/MyDrive/Colab Notebooks/DSCI614_text_mining/Week 4/Twitter_Data.csv\")\n",
        "\n",
        "# Check for null values in the clean_text column and remove them\n",
        "data = data.dropna(subset=['clean_text', 'category'])\n",
        "\n",
        "# Ensure the category column is of type int\n",
        "data['category'] = data['category'].astype(int)\n",
        "\n",
        "data.head()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "IbA2Nq52dHs0"
      },
      "source": [
        "## Step 2: Convert Tweets to a Matrix of Token Counts Using CountVectorizer\n",
        "We will use the `CountVectorizer` to transform the `clean_text` column into a matrix of token counts, including both unigrams and bigrams.\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "12McK0R5cOSj",
        "outputId": "30f0a14c-7fd8-41e3-ae45-4a5b15d1d335"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(162969, 1199719)\n"
          ]
        }
      ],
      "source": [
        "# Initialize the CountVectorizer\n",
        "count_vect = CountVectorizer(ngram_range=(1, 2))\n",
        "\n",
        "# Transform the clean_text to a matrix of token counts\"\n",
        "X_counts = count_vect.fit_transform(data['clean_text'])\n",
        "\n",
        "# Display the shape of the resulting matrix\n",
        "print(X_counts.shape)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "RJFj5u2jhTEP"
      },
      "source": [
        "## Step 3: Perform TF-IDF Analysis Using CountVectorizer and TfidfTransformer\n",
        "\n",
        "Next, we will perform TF-IDF analysis by first converting the `clean_text` to token counts using `CountVectorizer` and then applying `TfidfTransformer`."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "HDr3NC4-hctW",
        "outputId": "68239f0d-f6a1-48dd-e2ef-f570f8a7db6f"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(162969, 1199719)\n"
          ]
        }
      ],
      "source": [
        "# Initialize the TfidfTransformer\n",
        "tfidf_transformer = TfidfTransformer()\n",
        "\n",
        "# Transform the token counts to TF-IDF representation\n",
        "X_tfidf = tfidf_transformer.fit_transform(X_counts)\n",
        "\n",
        "# Display the shape of the resulting TF-IDF matrix\n",
        "print(X_tfidf.shape)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "NiNCpdZ8hfiu"
      },
      "source": [
        "## Step 4: Perform TF-IDF Analysis Using TfidfVectorizer\n",
        "\n",
        "We will use the `TfidfVectorizer` to directly convert the `clean_text` column into a TF-IDF matrix."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "L8tkbshDheUP",
        "outputId": "b6c33f8f-ff1a-40bd-e251-3f5c4f6c2fff"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(162969, 1199719)\n"
          ]
        }
      ],
      "source": [
        "# Initialize the TfidfVectorizer\n",
        "tfidf_vect = TfidfVectorizer(ngram_range=(1, 2))\n",
        "\n",
        "# Transform the clean_text to a TF-IDF representation\n",
        "X_tfidf_vect = tfidf_vect.fit_transform(data['clean_text'])\n",
        "\n",
        "# Display the shape of the resulting TF-IDF matrix\n",
        "print(X_tfidf_vect.shape)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "fJ_cirlphpqL"
      },
      "source": [
        "## Step 5: Perform TF-IDF Analysis Using HashingVectorizer and TfidfTransformer\n",
        "\n",
        "Finally, we will use `HashingVectorizer` to convert the `clean_text` column into a hashed term-frequency matrix, and then apply `TfidfTransformer` to transform it into a TF-IDF representation."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5GrR1rcLhnKH",
        "outputId": "fb3e1129-ca8e-45a3-b729-dc50b5ae5fa2"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(162969, 1048576)\n"
          ]
        }
      ],
      "source": [
        "# Initialize the HashingVectorizer\n",
        "hash_vect = HashingVectorizer(ngram_range=(1, 2), alternate_sign=False)\n",
        "\n",
        "# Transform the clean_text to a hashed term-frequency matrix\n",
        "X_hash = hash_vect.transform(data['clean_text'])\n",
        "\n",
        "# Apply TfidfTransformer to the hashed term-frequency matrix\n",
        "X_hash_tfidf = tfidf_transformer.fit_transform(X_hash)\n",
        "\n",
        "# Display the shape of the resulting TF-IDF matrix\n",
        "print(X_hash_tfidf.shape)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "EzbFPTMd28fZ"
      },
      "source": [
        "## Advanced Analytics\n",
        "\n",
        "Next, I will explore a few additional topics and techniques that TF-IDF allows us to leverage."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "slmSGWgEi9UN"
      },
      "source": [
        "### 1. Sentiment Classification\n",
        "\n",
        "With TF-IDF vectors, we can train machine learning models to classify the sentiment of tweets. For instance, we can use algorithms like Logistic Regression, Support Vector Machines, or Random Forests to predict whether a tweet has a positive, neutral, or negative sentiment based on its TF-IDF features."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7G9mrN-Qi8Gv",
        "outputId": "2b975e40-441c-48d2-c433-c1c0a6d26180"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "              precision    recall  f1-score   support\n",
            "\n",
            "          -1       0.91      0.66      0.76      7152\n",
            "           0       0.82      0.95      0.88     11067\n",
            "           1       0.89      0.90      0.90     14375\n",
            "\n",
            "    accuracy                           0.87     32594\n",
            "   macro avg       0.87      0.84      0.85     32594\n",
            "weighted avg       0.87      0.87      0.86     32594\n",
            "\n",
            "Accuracy: 0.867030741854329\n"
          ]
        }
      ],
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.linear_model import LogisticRegression\n",
        "from sklearn.metrics import classification_report, accuracy_score\n",
        "\n",
        "# Split the data into training and testing sets\n",
        "X_train, X_test, y_train, y_test = train_test_split(X_tfidf, data['category'], test_size=0.2, random_state=42)\n",
        "\n",
        "# Train a Logistic Regression model with appropriate solver\n",
        "model = LogisticRegression(solver='liblinear')\n",
        "model.fit(X_train, y_train)\n",
        "\n",
        "# Predict on the test set\n",
        "y_pred = model.predict(X_test)\n",
        "\n",
        "# Evaluate the model\n",
        "print(classification_report(y_test, y_pred))\n",
        "print('Accuracy:', accuracy_score(y_test, y_pred))\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ww2jqchsjIjc"
      },
      "source": [
        "### 2. Topic Modeling\n",
        "\n",
        "TF-IDF can be used in topic modeling to discover abstract topics within a collection of tweets. Latent Dirichlet Allocation (LDA) or Non-negative Matrix Factorization (NMF) can be applied to TF-IDF matrices to uncover hidden themes and topics in the data.\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "kYjapWbEi8DI",
        "outputId": "c7aeefff-e372-4c80-fee3-f039bf1c1bff"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Topic #0\n",
            "['for', 'was', 'has', 'not', 'will', 'that', 'this', 'modi', 'and', 'the']\n",
            "Topic #1\n",
            "['the', 'nation', 'address', 'modi', 'minister narendra', 'prime minister', 'prime', 'minister', 'narendra modi', 'narendra']\n",
            "Topic #2\n",
            "['only', 'bjp', 'modi for', 'will vote', 'will', 'modi', 'for modi', 'vote for', 'vote', 'for']\n",
            "Topic #3\n",
            "['and', 'have', 'not', 'modi you', 'with', 'modi', 'your', 'you are', 'are', 'you']\n",
            "Topic #4\n",
            "['shot', 'shot down', 'down satellite', 'says', 'space power', 'power', 'down', 'satellite', 'space', 'india']\n"
          ]
        }
      ],
      "source": [
        "from sklearn.decomposition import NMF\n",
        "\n",
        "# Initialize the NMF model\n",
        "nmf_model = NMF(n_components=5, random_state=42)\n",
        "\n",
        "# Fit the model to the TF-IDF matrix\n",
        "nmf_model.fit(X_tfidf)\n",
        "\n",
        "# Extract topics\n",
        "for index, topic in enumerate(nmf_model.components_):\n",
        "    print(f'Topic #{index}')\n",
        "    print([tfidf_vect.get_feature_names_out()[i] for i in topic.argsort()[-10:]])\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "0_-MDtnfjRic"
      },
      "source": [
        "### 3. Similarity Search\n",
        "TF-IDF vectors can be used to find similar tweets or documents. By calculating the cosine similarity between vectors, you can identify tweets that are most similar to a given query tweet."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "soSdkFD2hxE3",
        "outputId": "25cc8180-c552-482e-f915-9c9baf777c31"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Top 10 important features for sentiment classification:\n",
            "more\n",
            "corrupt\n",
            "stupid\n",
            "other\n",
            "bad\n",
            "failed\n",
            "wrong\n",
            "fake\n",
            "poor\n",
            "hate\n"
          ]
        }
      ],
      "source": [
        "import numpy as np\n",
        "\n",
        "# Get feature importance from the trained model\n",
        "feature_importance = np.abs(model.coef_[0])\n",
        "\n",
        "# Get the indices of the top 10 important features\n",
        "top_features = feature_importance.argsort()[-10:]\n",
        "\n",
        "print('Top 10 important features for sentiment classification:')\n",
        "for index in top_features:\n",
        "    print(tfidf_vect.get_feature_names_out()[index])"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "it-ngJlzjNYi"
      },
      "source": [
        "### 4. Clustering\n",
        "You can use clustering algorithms like K-Means to group similar tweets together based on their TF-IDF vectors. This can help identify natural groupings or segments within the data, such as clusters of tweets discussing similar issues or expressing similar sentiments."
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.decomposition import TruncatedSVD\n",
        "from sklearn.cluster import KMeans\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "# Initialize the TruncatedSVD model\n",
        "svd = TruncatedSVD(n_components=2, random_state=42)\n",
        "\n",
        "# Fit and transform the TF-IDF matrix\n",
        "X_svd = svd.fit_transform(X_tfidf)\n",
        "\n",
        "# Initialize the KMeans model\n",
        "kmeans = KMeans(n_clusters=3, random_state=11)\n",
        "\n",
        "# Fit the model to the SVD-transformed TF-IDF matrix\n",
        "kmeans.fit(X_svd)\n",
        "\n",
        "# Predict the clusters\n",
        "clusters = kmeans.predict(X_svd)\n",
        "\n",
        "# Visualize the clusters\n",
        "plt.figure(figsize=(10, 6))\n",
        "plt.scatter(X_svd[:, 0], X_svd[:, 1], c=clusters, cmap='viridis')\n",
        "plt.title('Tweet Clusters after Truncated SVD')\n",
        "plt.xlabel('Component 1')\n",
        "plt.ylabel('Component 2')\n",
        "plt.colorbar(label='Cluster Label')\n",
        "plt.show()"
      ],
      "metadata": {
        "id": "kzdUuW_LJlDd",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 560
        },
        "outputId": "a20a78b0-ded7-4356-addd-268c276b9327"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/sklearn/cluster/_kmeans.py:870: FutureWarning: The default value of `n_init` will change from 10 to 'auto' in 1.4. Set the value of `n_init` explicitly to suppress the warning\n",
            "  warnings.warn(\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x600 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    }
  ],
  "metadata": {
    "accelerator": "TPU",
    "colab": {
      "gpuType": "V28",
      "machine_shape": "hm",
      "provenance": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}