diff --git "a/Movie Genre Prediction Code.ipynb" "b/Movie Genre Prediction Code.ipynb"
new file mode 100644--- /dev/null
+++ "b/Movie Genre Prediction Code.ipynb"
@@ -0,0 +1,2922 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Importing Libraries"
+      ],
+      "metadata": {
+        "id": "jiNlo56ax2Us"
+      },
+      "id": "jiNlo56ax2Us"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "id": "e0c77096",
+      "metadata": {
+        "id": "e0c77096"
+      },
+      "outputs": [],
+      "source": [
+        "# Importing required Libraries\n",
+        "\n",
+        "import pandas as pd\n",
+        "import numpy as np\n",
+        "from sklearn.preprocessing import LabelEncoder\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "from sklearn.naive_bayes import MultinomialNB\n",
+        "from sklearn.metrics import accuracy_score\n",
+        "from sklearn.feature_extraction.text import TfidfVectorizer"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "id": "b5fbe912",
+      "metadata": {
+        "scrolled": true,
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "b5fbe912",
+        "outputId": "a8b49040-2f4b-429b-d174-aead00979ed5"
+      },
+      "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"
+          ]
+        }
+      ],
+      "source": [
+        "# Downloading NLTK Packages\n",
+        "\n",
+        "import nltk\n",
+        "nltk.download('stopwords')\n",
+        "nltk.download('punkt')\n",
+        "from nltk.corpus import stopwords\n",
+        "from nltk.tokenize import word_tokenize\n",
+        "import re"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "id": "fcb105bd",
+      "metadata": {
+        "id": "fcb105bd"
+      },
+      "outputs": [],
+      "source": [
+        "# Creating set of stop words\n",
+        "\n",
+        "stop_words = set(stopwords.words('english'))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Importing and Pre-processing Training Dataset"
+      ],
+      "metadata": {
+        "id": "8mICKWhquvro"
+      },
+      "id": "8mICKWhquvro"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "id": "f5965adb",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 206
+        },
+        "id": "f5965adb",
+        "outputId": "42ca0d77-46cb-4032-9071-37bad3d4ce61"
+      },
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "      id                                         movie_name  \\\n",
+              "0  44978                                           Super Me   \n",
+              "1  50185                                     Entity Project   \n",
+              "2  34131  Behavioral Family Therapy for Serious Psychiat...   \n",
+              "3  78522                                      Blood Glacier   \n",
+              "4   2206                                      Apat na anino   \n",
+              "\n",
+              "                                            synopsis    genre  \n",
+              "0  A young scriptwriter starts bringing valuable ...  fantasy  \n",
+              "1  A director and her friends renting a haunted h...   horror  \n",
+              "2  This is an educational video for families and ...   family  \n",
+              "3  Scientists working in the Austrian Alps discov...    scifi  \n",
+              "4  Buy Day - Four Men Widely - Apart in Life - By...   action  "
+            ],
+            "text/html": [
+              "\n",
+              "\n",
+              "  <div id=\"df-84fda861-274d-4176-909f-c6a2c5dfc3e1\">\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>id</th>\n",
+              "      <th>movie_name</th>\n",
+              "      <th>synopsis</th>\n",
+              "      <th>genre</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>44978</td>\n",
+              "      <td>Super Me</td>\n",
+              "      <td>A young scriptwriter starts bringing valuable ...</td>\n",
+              "      <td>fantasy</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>50185</td>\n",
+              "      <td>Entity Project</td>\n",
+              "      <td>A director and her friends renting a haunted h...</td>\n",
+              "      <td>horror</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>34131</td>\n",
+              "      <td>Behavioral Family Therapy for Serious Psychiat...</td>\n",
+              "      <td>This is an educational video for families and ...</td>\n",
+              "      <td>family</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>78522</td>\n",
+              "      <td>Blood Glacier</td>\n",
+              "      <td>Scientists working in the Austrian Alps discov...</td>\n",
+              "      <td>scifi</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>2206</td>\n",
+              "      <td>Apat na anino</td>\n",
+              "      <td>Buy Day - Four Men Widely - Apart in Life - By...</td>\n",
+              "      <td>action</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>\n",
+              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-84fda861-274d-4176-909f-c6a2c5dfc3e1')\"\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",
+              "\n",
+              "\n",
+              "    <div id=\"df-0ec6d55e-8b69-4dd0-b0bc-2677bd1ad33f\">\n",
+              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-0ec6d55e-8b69-4dd0-b0bc-2677bd1ad33f')\"\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",
+              "    </div>\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 containerElement = document.querySelector('#' + key);\n",
+              "        const charts = await google.colab.kernel.invokeFunction(\n",
+              "            'suggestCharts', [key], {});\n",
+              "      }\n",
+              "    </script>\n",
+              "\n",
+              "      <script>\n",
+              "\n",
+              "function displayQuickchartButton(domScope) {\n",
+              "  let quickchartButtonEl =\n",
+              "    domScope.querySelector('#df-0ec6d55e-8b69-4dd0-b0bc-2677bd1ad33f button.colab-df-quickchart');\n",
+              "  quickchartButtonEl.style.display =\n",
+              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "}\n",
+              "\n",
+              "        displayQuickchartButton(document);\n",
+              "      </script>\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-84fda861-274d-4176-909f-c6a2c5dfc3e1 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-84fda861-274d-4176-909f-c6a2c5dfc3e1');\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
+        }
+      ],
+      "source": [
+        "# Importing Tranining Dataset\n",
+        "\n",
+        "train_data = pd.read_csv(\"train.csv\")\n",
+        "train_data.head()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "id": "20d4b346",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "20d4b346",
+        "outputId": "7e787488-2023-4854-e1f3-e5e1d5e237c2"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "<class 'pandas.core.frame.DataFrame'>\n",
+            "RangeIndex: 54000 entries, 0 to 53999\n",
+            "Data columns (total 4 columns):\n",
+            " #   Column      Non-Null Count  Dtype \n",
+            "---  ------      --------------  ----- \n",
+            " 0   id          54000 non-null  int64 \n",
+            " 1   movie_name  54000 non-null  object\n",
+            " 2   synopsis    54000 non-null  object\n",
+            " 3   genre       54000 non-null  object\n",
+            "dtypes: int64(1), object(3)\n",
+            "memory usage: 1.6+ MB\n"
+          ]
+        }
+      ],
+      "source": [
+        "# Getting Info about Train Data\n",
+        "\n",
+        "train_data.info()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 6,
+      "id": "fc1a181f",
+      "metadata": {
+        "scrolled": false,
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "fc1a181f",
+        "outputId": "594fa4a9-9456-489c-eea1-4e5b160f850f"
+      },
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "id            0\n",
+              "movie_name    0\n",
+              "synopsis      0\n",
+              "genre         0\n",
+              "dtype: int64"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 6
+        }
+      ],
+      "source": [
+        "# Checking for Null Values\n",
+        "\n",
+        "train_data.isnull().sum()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 7,
+      "id": "ccbc40da",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "ccbc40da",
+        "outputId": "27766f2e-df95-49b1-c6bf-dbf281b3bf21"
+      },
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "fantasy      5400\n",
+              "horror       5400\n",
+              "family       5400\n",
+              "scifi        5400\n",
+              "action       5400\n",
+              "crime        5400\n",
+              "adventure    5400\n",
+              "mystery      5400\n",
+              "romance      5400\n",
+              "thriller     5400\n",
+              "Name: genre, dtype: int64"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 7
+        }
+      ],
+      "source": [
+        "# Getting Number of Classes and their Distribution in Train Data\n",
+        "\n",
+        "train_data['genre'].value_counts()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 8,
+      "id": "b630de43",
+      "metadata": {
+        "id": "b630de43"
+      },
+      "outputs": [],
+      "source": [
+        "# Method to pre-process text from column: movie_name\n",
+        "\n",
+        "def preprocessMovieName(movieNames):\n",
+        "  \"\"\"\n",
+        "  Converting text to lowercase and Removing extra spaces from movie_name column values\n",
+        "  \"\"\"\n",
+        "  cleanedMovieNames = []\n",
+        "\n",
+        "  for movie in movieNames:\n",
+        "      text = movie.lower()\n",
+        "      text = text.strip('  ')\n",
+        "      cleanedMovieNames.append(text)\n",
+        "\n",
+        "  return cleanedMovieNames"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 9,
+      "id": "6bc44949",
+      "metadata": {
+        "scrolled": true,
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 206
+        },
+        "id": "6bc44949",
+        "outputId": "8765cf23-b184-4c66-fe6b-23709fcaa5c8"
+      },
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "      id                                         movie_name  \\\n",
+              "0  44978                                           super me   \n",
+              "1  50185                                     entity project   \n",
+              "2  34131  behavioral family therapy for serious psychiat...   \n",
+              "3  78522                                      blood glacier   \n",
+              "4   2206                                      apat na anino   \n",
+              "\n",
+              "                                            synopsis    genre  \n",
+              "0  A young scriptwriter starts bringing valuable ...  fantasy  \n",
+              "1  A director and her friends renting a haunted h...   horror  \n",
+              "2  This is an educational video for families and ...   family  \n",
+              "3  Scientists working in the Austrian Alps discov...    scifi  \n",
+              "4  Buy Day - Four Men Widely - Apart in Life - By...   action  "
+            ],
+            "text/html": [
+              "\n",
+              "\n",
+              "  <div id=\"df-6a93c294-da8e-41fb-93bb-9088f1d309d9\">\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>id</th>\n",
+              "      <th>movie_name</th>\n",
+              "      <th>synopsis</th>\n",
+              "      <th>genre</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>44978</td>\n",
+              "      <td>super me</td>\n",
+              "      <td>A young scriptwriter starts bringing valuable ...</td>\n",
+              "      <td>fantasy</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>50185</td>\n",
+              "      <td>entity project</td>\n",
+              "      <td>A director and her friends renting a haunted h...</td>\n",
+              "      <td>horror</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>34131</td>\n",
+              "      <td>behavioral family therapy for serious psychiat...</td>\n",
+              "      <td>This is an educational video for families and ...</td>\n",
+              "      <td>family</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>78522</td>\n",
+              "      <td>blood glacier</td>\n",
+              "      <td>Scientists working in the Austrian Alps discov...</td>\n",
+              "      <td>scifi</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>2206</td>\n",
+              "      <td>apat na anino</td>\n",
+              "      <td>Buy Day - Four Men Widely - Apart in Life - By...</td>\n",
+              "      <td>action</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>\n",
+              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-6a93c294-da8e-41fb-93bb-9088f1d309d9')\"\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",
+              "\n",
+              "\n",
+              "    <div id=\"df-4074d92b-5b86-4387-a32b-ec6e2c0a677f\">\n",
+              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-4074d92b-5b86-4387-a32b-ec6e2c0a677f')\"\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",
+              "    </div>\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 containerElement = document.querySelector('#' + key);\n",
+              "        const charts = await google.colab.kernel.invokeFunction(\n",
+              "            'suggestCharts', [key], {});\n",
+              "      }\n",
+              "    </script>\n",
+              "\n",
+              "      <script>\n",
+              "\n",
+              "function displayQuickchartButton(domScope) {\n",
+              "  let quickchartButtonEl =\n",
+              "    domScope.querySelector('#df-4074d92b-5b86-4387-a32b-ec6e2c0a677f button.colab-df-quickchart');\n",
+              "  quickchartButtonEl.style.display =\n",
+              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "}\n",
+              "\n",
+              "        displayQuickchartButton(document);\n",
+              "      </script>\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-6a93c294-da8e-41fb-93bb-9088f1d309d9 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-6a93c294-da8e-41fb-93bb-9088f1d309d9');\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": 9
+        }
+      ],
+      "source": [
+        "# Transforming movie_name column using preprocessMovieName method\n",
+        "\n",
+        "movieNames = train_data['movie_name']\n",
+        "train_data['movie_name'] = preprocessMovieName(movieNames)\n",
+        "train_data.head()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 10,
+      "id": "bebcffc9",
+      "metadata": {
+        "id": "bebcffc9"
+      },
+      "outputs": [],
+      "source": [
+        "# Method to pre-process text from column: synopsis\n",
+        "\n",
+        "def preprocessSynopsis(synopsis):\n",
+        "  \"\"\"\n",
+        "  Converting text to lowercase, Removing extra spaces, digits, symbols, stop words from synopsis column values\n",
+        "  \"\"\"\n",
+        "  cleanedSynopses = []\n",
+        "\n",
+        "  for synop in synopsis:\n",
+        "      text = re.sub(r'[^a-zA-Z]', ' ', synop.lower())\n",
+        "      text = text.strip('  ')\n",
+        "      word_tokens = word_tokenize(text)\n",
+        "      cleanedText = [w for w in word_tokens if w not in stop_words]\n",
+        "      cleanedSynop = ' '.join(cleanedText)\n",
+        "      cleanedSynopses.append(cleanedSynop)\n",
+        "\n",
+        "  return cleanedSynopses"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 11,
+      "id": "5994c4ee",
+      "metadata": {
+        "scrolled": true,
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 206
+        },
+        "id": "5994c4ee",
+        "outputId": "84e4f903-491b-4313-c7b0-287b0748e2bb"
+      },
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "      id                                         movie_name  \\\n",
+              "0  44978                                           super me   \n",
+              "1  50185                                     entity project   \n",
+              "2  34131  behavioral family therapy for serious psychiat...   \n",
+              "3  78522                                      blood glacier   \n",
+              "4   2206                                      apat na anino   \n",
+              "\n",
+              "                                            synopsis    genre  \n",
+              "0  young scriptwriter starts bringing valuable ob...  fantasy  \n",
+              "1  director friends renting haunted house capture...   horror  \n",
+              "2  educational video families family therapists d...   family  \n",
+              "3  scientists working austrian alps discover glac...    scifi  \n",
+              "4  buy day four men widely apart life night shado...   action  "
+            ],
+            "text/html": [
+              "\n",
+              "\n",
+              "  <div id=\"df-4a27cc30-9e9f-47ce-9b98-5754cc9caa31\">\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>id</th>\n",
+              "      <th>movie_name</th>\n",
+              "      <th>synopsis</th>\n",
+              "      <th>genre</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>44978</td>\n",
+              "      <td>super me</td>\n",
+              "      <td>young scriptwriter starts bringing valuable ob...</td>\n",
+              "      <td>fantasy</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>50185</td>\n",
+              "      <td>entity project</td>\n",
+              "      <td>director friends renting haunted house capture...</td>\n",
+              "      <td>horror</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>34131</td>\n",
+              "      <td>behavioral family therapy for serious psychiat...</td>\n",
+              "      <td>educational video families family therapists d...</td>\n",
+              "      <td>family</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>78522</td>\n",
+              "      <td>blood glacier</td>\n",
+              "      <td>scientists working austrian alps discover glac...</td>\n",
+              "      <td>scifi</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>2206</td>\n",
+              "      <td>apat na anino</td>\n",
+              "      <td>buy day four men widely apart life night shado...</td>\n",
+              "      <td>action</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>\n",
+              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-4a27cc30-9e9f-47ce-9b98-5754cc9caa31')\"\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",
+              "\n",
+              "\n",
+              "    <div id=\"df-ca021f19-6401-4cae-a40e-6d6f7fffef24\">\n",
+              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-ca021f19-6401-4cae-a40e-6d6f7fffef24')\"\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",
+              "    </div>\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 containerElement = document.querySelector('#' + key);\n",
+              "        const charts = await google.colab.kernel.invokeFunction(\n",
+              "            'suggestCharts', [key], {});\n",
+              "      }\n",
+              "    </script>\n",
+              "\n",
+              "      <script>\n",
+              "\n",
+              "function displayQuickchartButton(domScope) {\n",
+              "  let quickchartButtonEl =\n",
+              "    domScope.querySelector('#df-ca021f19-6401-4cae-a40e-6d6f7fffef24 button.colab-df-quickchart');\n",
+              "  quickchartButtonEl.style.display =\n",
+              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "}\n",
+              "\n",
+              "        displayQuickchartButton(document);\n",
+              "      </script>\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-4a27cc30-9e9f-47ce-9b98-5754cc9caa31 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-4a27cc30-9e9f-47ce-9b98-5754cc9caa31');\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": 11
+        }
+      ],
+      "source": [
+        "# Transforming synopsis column using preprocessSynopsis method\n",
+        "\n",
+        "synopsis = train_data['synopsis']\n",
+        "train_data['synopsis'] = preprocessSynopsis(synopsis)\n",
+        "train_data.head()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Method to combine text values from movie_name and synopsis columns\n",
+        "\n",
+        "def mergeText(df):\n",
+        "  \"\"\"\n",
+        "  Combining text from movie_name and synopsis i.e. resulting values will be of the form: movie_name+' '+synopsis\n",
+        "  \"\"\"\n",
+        "  movieSynposis=[]\n",
+        "\n",
+        "  for ind in df.index:\n",
+        "    ms_text = str(df['movie_name'][ind]) + ' ' + str(df['synopsis'][ind])\n",
+        "    movieSynposis.append(ms_text)\n",
+        "\n",
+        "  return movieSynposis"
+      ],
+      "metadata": {
+        "id": "SuSa8M9yvemY"
+      },
+      "id": "SuSa8M9yvemY",
+      "execution_count": 12,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Applying mergeText method and storing values in new column: movie_synopsis\n",
+        "\n",
+        "train_data['movie_synopsis'] = mergeText(train_data)\n",
+        "train_data.head()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 206
+        },
+        "id": "6Ag-7TllvLm4",
+        "outputId": "2d851bd2-c64a-4a4a-f97b-a98f24df8ac9"
+      },
+      "id": "6Ag-7TllvLm4",
+      "execution_count": 13,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "      id                                         movie_name  \\\n",
+              "0  44978                                           super me   \n",
+              "1  50185                                     entity project   \n",
+              "2  34131  behavioral family therapy for serious psychiat...   \n",
+              "3  78522                                      blood glacier   \n",
+              "4   2206                                      apat na anino   \n",
+              "\n",
+              "                                            synopsis    genre  \\\n",
+              "0  young scriptwriter starts bringing valuable ob...  fantasy   \n",
+              "1  director friends renting haunted house capture...   horror   \n",
+              "2  educational video families family therapists d...   family   \n",
+              "3  scientists working austrian alps discover glac...    scifi   \n",
+              "4  buy day four men widely apart life night shado...   action   \n",
+              "\n",
+              "                                      movie_synopsis  \n",
+              "0  super me young scriptwriter starts bringing va...  \n",
+              "1  entity project director friends renting haunte...  \n",
+              "2  behavioral family therapy for serious psychiat...  \n",
+              "3  blood glacier scientists working austrian alps...  \n",
+              "4  apat na anino buy day four men widely apart li...  "
+            ],
+            "text/html": [
+              "\n",
+              "\n",
+              "  <div id=\"df-c36f113d-8954-4322-9b2e-2c41f4fb1784\">\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>id</th>\n",
+              "      <th>movie_name</th>\n",
+              "      <th>synopsis</th>\n",
+              "      <th>genre</th>\n",
+              "      <th>movie_synopsis</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>44978</td>\n",
+              "      <td>super me</td>\n",
+              "      <td>young scriptwriter starts bringing valuable ob...</td>\n",
+              "      <td>fantasy</td>\n",
+              "      <td>super me young scriptwriter starts bringing va...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>50185</td>\n",
+              "      <td>entity project</td>\n",
+              "      <td>director friends renting haunted house capture...</td>\n",
+              "      <td>horror</td>\n",
+              "      <td>entity project director friends renting haunte...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>34131</td>\n",
+              "      <td>behavioral family therapy for serious psychiat...</td>\n",
+              "      <td>educational video families family therapists d...</td>\n",
+              "      <td>family</td>\n",
+              "      <td>behavioral family therapy for serious psychiat...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>78522</td>\n",
+              "      <td>blood glacier</td>\n",
+              "      <td>scientists working austrian alps discover glac...</td>\n",
+              "      <td>scifi</td>\n",
+              "      <td>blood glacier scientists working austrian alps...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>2206</td>\n",
+              "      <td>apat na anino</td>\n",
+              "      <td>buy day four men widely apart life night shado...</td>\n",
+              "      <td>action</td>\n",
+              "      <td>apat na anino buy day four men widely apart li...</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>\n",
+              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-c36f113d-8954-4322-9b2e-2c41f4fb1784')\"\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",
+              "\n",
+              "\n",
+              "    <div id=\"df-af3243b3-42f2-4d8c-a3d9-3d5bbd6300fd\">\n",
+              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-af3243b3-42f2-4d8c-a3d9-3d5bbd6300fd')\"\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",
+              "    </div>\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 containerElement = document.querySelector('#' + key);\n",
+              "        const charts = await google.colab.kernel.invokeFunction(\n",
+              "            'suggestCharts', [key], {});\n",
+              "      }\n",
+              "    </script>\n",
+              "\n",
+              "      <script>\n",
+              "\n",
+              "function displayQuickchartButton(domScope) {\n",
+              "  let quickchartButtonEl =\n",
+              "    domScope.querySelector('#df-af3243b3-42f2-4d8c-a3d9-3d5bbd6300fd button.colab-df-quickchart');\n",
+              "  quickchartButtonEl.style.display =\n",
+              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "}\n",
+              "\n",
+              "        displayQuickchartButton(document);\n",
+              "      </script>\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-c36f113d-8954-4322-9b2e-2c41f4fb1784 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-c36f113d-8954-4322-9b2e-2c41f4fb1784');\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": 13
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Label Encoding Target Classes"
+      ],
+      "metadata": {
+        "id": "YpVgEjifxrCB"
+      },
+      "id": "YpVgEjifxrCB"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Using Label Encoder to encode classes from genre\n",
+        "\n",
+        "le_genre = LabelEncoder()\n",
+        "train_data['genre'] = le_genre.fit_transform(train_data['genre'])\n",
+        "train_data.head()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 206
+        },
+        "id": "iNAZim2poDBz",
+        "outputId": "65e6a4fb-8570-42c1-83cd-ac713e003657"
+      },
+      "id": "iNAZim2poDBz",
+      "execution_count": 14,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "      id                                         movie_name  \\\n",
+              "0  44978                                           super me   \n",
+              "1  50185                                     entity project   \n",
+              "2  34131  behavioral family therapy for serious psychiat...   \n",
+              "3  78522                                      blood glacier   \n",
+              "4   2206                                      apat na anino   \n",
+              "\n",
+              "                                            synopsis  genre  \\\n",
+              "0  young scriptwriter starts bringing valuable ob...      4   \n",
+              "1  director friends renting haunted house capture...      5   \n",
+              "2  educational video families family therapists d...      3   \n",
+              "3  scientists working austrian alps discover glac...      8   \n",
+              "4  buy day four men widely apart life night shado...      0   \n",
+              "\n",
+              "                                      movie_synopsis  \n",
+              "0  super me young scriptwriter starts bringing va...  \n",
+              "1  entity project director friends renting haunte...  \n",
+              "2  behavioral family therapy for serious psychiat...  \n",
+              "3  blood glacier scientists working austrian alps...  \n",
+              "4  apat na anino buy day four men widely apart li...  "
+            ],
+            "text/html": [
+              "\n",
+              "\n",
+              "  <div id=\"df-ddc7ac91-05a2-43df-86b1-3c560f6e2919\">\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>id</th>\n",
+              "      <th>movie_name</th>\n",
+              "      <th>synopsis</th>\n",
+              "      <th>genre</th>\n",
+              "      <th>movie_synopsis</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>44978</td>\n",
+              "      <td>super me</td>\n",
+              "      <td>young scriptwriter starts bringing valuable ob...</td>\n",
+              "      <td>4</td>\n",
+              "      <td>super me young scriptwriter starts bringing va...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>50185</td>\n",
+              "      <td>entity project</td>\n",
+              "      <td>director friends renting haunted house capture...</td>\n",
+              "      <td>5</td>\n",
+              "      <td>entity project director friends renting haunte...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>34131</td>\n",
+              "      <td>behavioral family therapy for serious psychiat...</td>\n",
+              "      <td>educational video families family therapists d...</td>\n",
+              "      <td>3</td>\n",
+              "      <td>behavioral family therapy for serious psychiat...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>78522</td>\n",
+              "      <td>blood glacier</td>\n",
+              "      <td>scientists working austrian alps discover glac...</td>\n",
+              "      <td>8</td>\n",
+              "      <td>blood glacier scientists working austrian alps...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>2206</td>\n",
+              "      <td>apat na anino</td>\n",
+              "      <td>buy day four men widely apart life night shado...</td>\n",
+              "      <td>0</td>\n",
+              "      <td>apat na anino buy day four men widely apart li...</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>\n",
+              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-ddc7ac91-05a2-43df-86b1-3c560f6e2919')\"\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",
+              "\n",
+              "\n",
+              "    <div id=\"df-87fdb0b9-097a-4b4a-b479-b818b2bfac63\">\n",
+              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-87fdb0b9-097a-4b4a-b479-b818b2bfac63')\"\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",
+              "    </div>\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 containerElement = document.querySelector('#' + key);\n",
+              "        const charts = await google.colab.kernel.invokeFunction(\n",
+              "            'suggestCharts', [key], {});\n",
+              "      }\n",
+              "    </script>\n",
+              "\n",
+              "      <script>\n",
+              "\n",
+              "function displayQuickchartButton(domScope) {\n",
+              "  let quickchartButtonEl =\n",
+              "    domScope.querySelector('#df-87fdb0b9-097a-4b4a-b479-b818b2bfac63 button.colab-df-quickchart');\n",
+              "  quickchartButtonEl.style.display =\n",
+              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "}\n",
+              "\n",
+              "        displayQuickchartButton(document);\n",
+              "      </script>\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-ddc7ac91-05a2-43df-86b1-3c560f6e2919 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-ddc7ac91-05a2-43df-86b1-3c560f6e2919');\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": 14
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Retrieving list of classes from Label Encoder\n",
+        "\n",
+        "le_genre.classes_"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "jU8Xu7PmoFc1",
+        "outputId": "3e739ff8-6733-4985-c15e-bfb081c32802"
+      },
+      "id": "jU8Xu7PmoFc1",
+      "execution_count": 15,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "array(['action', 'adventure', 'crime', 'family', 'fantasy', 'horror',\n",
+              "       'mystery', 'romance', 'scifi', 'thriller'], dtype=object)"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 15
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Vectorizing Textual Data"
+      ],
+      "metadata": {
+        "id": "9ha441zmxtih"
+      },
+      "id": "9ha441zmxtih"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Vectorizing textual data i.e. converting each text token into integers using TF-IDF Vectorizer\n",
+        "\n",
+        "cv = TfidfVectorizer()\n",
+        "vectorized_synopsis = cv.fit_transform(train_data['movie_synopsis'])\n",
+        "vectorized_synopsis[0]"
+      ],
+      "metadata": {
+        "id": "pcC4sDFUbuDv",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "d37267d4-441d-4bed-8aa3-1973e200b5d2"
+      },
+      "id": "pcC4sDFUbuDv",
+      "execution_count": 16,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "<1x60085 sparse matrix of type '<class 'numpy.float64'>'\n",
+              "\twith 16 stored elements in Compressed Sparse Row format>"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 16
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Separating X: Features and Y: Target columns\n",
+        "\n",
+        "X = vectorized_synopsis\n",
+        "Y = train_data['genre'].values\n",
+        "\n",
+        "print(\"Features Shape: \",X.shape)\n",
+        "print(\"Target Shape: \",Y.shape)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "5n0JM8UHmq5s",
+        "outputId": "77361117-be79-4e7a-928d-ed78c4cda003"
+      },
+      "id": "5n0JM8UHmq5s",
+      "execution_count": 17,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Features Shape:  (54000, 60085)\n",
+            "Target Shape:  (54000,)\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Splitting data into Train and Validation Sets"
+      ],
+      "metadata": {
+        "id": "gs1QN3aUx-Jj"
+      },
+      "id": "gs1QN3aUx-Jj"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 18,
+      "id": "7d5005b3",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "7d5005b3",
+        "outputId": "ede369e4-af55-467f-8525-20a1ed145615"
+      },
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "<1x60085 sparse matrix of type '<class 'numpy.float64'>'\n",
+              "\twith 25 stored elements in Compressed Sparse Row format>"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 18
+        }
+      ],
+      "source": [
+        "# Splitting into Training and Validation Sets with 25% validation split\n",
+        "\n",
+        "X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.25)\n",
+        "X_train[0]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Model Building: Training, Prediction and Metric Evaluation"
+      ],
+      "metadata": {
+        "id": "XXWXGR_iyH-G"
+      },
+      "id": "XXWXGR_iyH-G"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Training model using Multinomial Naive Bayes, Getting predictions on Validation set, Calculating Metric: Accuracy\n",
+        "\n",
+        "from sklearn.naive_bayes import MultinomialNB\n",
+        "\n",
+        "mnb = MultinomialNB()\n",
+        "\n",
+        "mnb.fit(X_train, y_train)\n",
+        "\n",
+        "y_pred = mnb.predict(X_test)\n",
+        "\n",
+        "print(\"Val Acc using MultinomialNB: \", accuracy_score(y_test, y_pred))"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "bJXTw8qxOEIV",
+        "outputId": "0ee8688b-60a0-42a8-d657-0327475f439c"
+      },
+      "id": "bJXTw8qxOEIV",
+      "execution_count": 19,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Val Acc using MultinomialNB:  0.3622222222222222\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Training model using Decision Tree Classifier, Getting predictions on Validation set, Calculating Metric: Accuracy\n",
+        "\n",
+        "from sklearn.tree import DecisionTreeClassifier\n",
+        "\n",
+        "dt_clf = DecisionTreeClassifier()\n",
+        "\n",
+        "dt_clf.fit(X_train, y_train)\n",
+        "\n",
+        "y_pred = dt_clf.predict(X_test)\n",
+        "\n",
+        "print(\"Val Acc using Decision Tree: \", accuracy_score(y_test, y_pred))"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "1ytk2S35RooF",
+        "outputId": "6b9f3f83-c832-4f10-edc5-a56ee6f62d7c"
+      },
+      "id": "1ytk2S35RooF",
+      "execution_count": 20,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Val Acc using Decision Tree:  0.18748148148148147\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Training model using KNN (K-Nearest Neighbours Classifier), Getting predictions on Validation set, Calculating Metric: Accuracy\n",
+        "\n",
+        "from sklearn.neighbors import KNeighborsClassifier\n",
+        "\n",
+        "knn = KNeighborsClassifier(n_neighbors=7)\n",
+        "\n",
+        "knn.fit(X_train, y_train)\n",
+        "\n",
+        "y_pred = knn.predict(X_test)\n",
+        "\n",
+        "print(\"Val Acc using KNN: \", accuracy_score(y_test, y_pred))"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "6MOxLHJVe9um",
+        "outputId": "c3b8154c-2923-4a34-d474-0d8796d3c957"
+      },
+      "id": "6MOxLHJVe9um",
+      "execution_count": 21,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Val Acc using KNN:  0.23837037037037037\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "As our principle metric to consider is Accuracy, we finalize Multinomial Naive Bayes as our Final Model. <br>\n",
+        "Multinomial Naives Bayes outperforms among all the considered models, hence using it for Test Data Prediction."
+      ],
+      "metadata": {
+        "id": "-5VNI6OVyVXW"
+      },
+      "id": "-5VNI6OVyVXW"
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### Test Data Prediction"
+      ],
+      "metadata": {
+        "id": "6hZGPKFgT5X_"
+      },
+      "id": "6hZGPKFgT5X_"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "test_data = pd.read_csv(\"test.csv\")\n",
+        "test_data.head()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 206
+        },
+        "id": "kKZySdPbT04P",
+        "outputId": "b525b13a-4f69-4eba-faaf-f1390788bfc8"
+      },
+      "id": "kKZySdPbT04P",
+      "execution_count": 22,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "      id          movie_name  \\\n",
+              "0  16863    A Death Sentence   \n",
+              "1  48456          Intermedio   \n",
+              "2  41383    30 Chua Phai Tet   \n",
+              "3  84007           Paranoiac   \n",
+              "4  40269  Ordinary Happiness   \n",
+              "\n",
+              "                                            synopsis   genre  \n",
+              "0  12 y.o. Ida's dad'll die without a DKK1,500,00...  action  \n",
+              "1  A group of four teenage friends become trapped...  action  \n",
+              "2  A guy left his home for 12 years till he came ...  action  \n",
+              "3  A man long believed dead returns to the family...  action  \n",
+              "4  After a deadly accident, Paolo comes back on E...  action  "
+            ],
+            "text/html": [
+              "\n",
+              "\n",
+              "  <div id=\"df-4a7a3fc1-4c6d-40b9-ba82-9c4f8fb48f55\">\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>id</th>\n",
+              "      <th>movie_name</th>\n",
+              "      <th>synopsis</th>\n",
+              "      <th>genre</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>16863</td>\n",
+              "      <td>A Death Sentence</td>\n",
+              "      <td>12 y.o. Ida's dad'll die without a DKK1,500,00...</td>\n",
+              "      <td>action</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>48456</td>\n",
+              "      <td>Intermedio</td>\n",
+              "      <td>A group of four teenage friends become trapped...</td>\n",
+              "      <td>action</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>41383</td>\n",
+              "      <td>30 Chua Phai Tet</td>\n",
+              "      <td>A guy left his home for 12 years till he came ...</td>\n",
+              "      <td>action</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>84007</td>\n",
+              "      <td>Paranoiac</td>\n",
+              "      <td>A man long believed dead returns to the family...</td>\n",
+              "      <td>action</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>40269</td>\n",
+              "      <td>Ordinary Happiness</td>\n",
+              "      <td>After a deadly accident, Paolo comes back on E...</td>\n",
+              "      <td>action</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>\n",
+              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-4a7a3fc1-4c6d-40b9-ba82-9c4f8fb48f55')\"\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",
+              "\n",
+              "\n",
+              "    <div id=\"df-2e493891-31ee-4b72-bc0a-de54c06b62d3\">\n",
+              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-2e493891-31ee-4b72-bc0a-de54c06b62d3')\"\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",
+              "    </div>\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 containerElement = document.querySelector('#' + key);\n",
+              "        const charts = await google.colab.kernel.invokeFunction(\n",
+              "            'suggestCharts', [key], {});\n",
+              "      }\n",
+              "    </script>\n",
+              "\n",
+              "      <script>\n",
+              "\n",
+              "function displayQuickchartButton(domScope) {\n",
+              "  let quickchartButtonEl =\n",
+              "    domScope.querySelector('#df-2e493891-31ee-4b72-bc0a-de54c06b62d3 button.colab-df-quickchart');\n",
+              "  quickchartButtonEl.style.display =\n",
+              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "}\n",
+              "\n",
+              "        displayQuickchartButton(document);\n",
+              "      </script>\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-4a7a3fc1-4c6d-40b9-ba82-9c4f8fb48f55 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-4a7a3fc1-4c6d-40b9-ba82-9c4f8fb48f55');\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": 22
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "movieNames = test_data['movie_name']\n",
+        "test_data['movie_name'] = preprocessMovieName(movieNames)\n",
+        "\n",
+        "synopsis = test_data['synopsis']\n",
+        "test_data['synopsis'] = preprocessSynopsis(synopsis)\n",
+        "\n",
+        "test_data.head()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 206
+        },
+        "id": "0_bFugnGUsux",
+        "outputId": "3014bb16-d73b-4bc8-9216-e7b812966f50"
+      },
+      "id": "0_bFugnGUsux",
+      "execution_count": 23,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "      id          movie_name  \\\n",
+              "0  16863    a death sentence   \n",
+              "1  48456          intermedio   \n",
+              "2  41383    30 chua phai tet   \n",
+              "3  84007           paranoiac   \n",
+              "4  40269  ordinary happiness   \n",
+              "\n",
+              "                                            synopsis   genre  \n",
+              "0  ida dad die without dkk operation ida plans st...  action  \n",
+              "1  group four teenage friends become trapped mexi...  action  \n",
+              "2  guy left home years till came back claim fathe...  action  \n",
+              "3  man long believed dead returns family estate c...  action  \n",
+              "4  deadly accident paolo comes back earth minutes...  action  "
+            ],
+            "text/html": [
+              "\n",
+              "\n",
+              "  <div id=\"df-cca298de-e4c7-4361-93ae-45371e6fbb27\">\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>id</th>\n",
+              "      <th>movie_name</th>\n",
+              "      <th>synopsis</th>\n",
+              "      <th>genre</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>16863</td>\n",
+              "      <td>a death sentence</td>\n",
+              "      <td>ida dad die without dkk operation ida plans st...</td>\n",
+              "      <td>action</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>48456</td>\n",
+              "      <td>intermedio</td>\n",
+              "      <td>group four teenage friends become trapped mexi...</td>\n",
+              "      <td>action</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>41383</td>\n",
+              "      <td>30 chua phai tet</td>\n",
+              "      <td>guy left home years till came back claim fathe...</td>\n",
+              "      <td>action</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>84007</td>\n",
+              "      <td>paranoiac</td>\n",
+              "      <td>man long believed dead returns family estate c...</td>\n",
+              "      <td>action</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>40269</td>\n",
+              "      <td>ordinary happiness</td>\n",
+              "      <td>deadly accident paolo comes back earth minutes...</td>\n",
+              "      <td>action</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>\n",
+              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-cca298de-e4c7-4361-93ae-45371e6fbb27')\"\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",
+              "\n",
+              "\n",
+              "    <div id=\"df-18937a13-a371-4bc9-a2bf-fcaf90292637\">\n",
+              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-18937a13-a371-4bc9-a2bf-fcaf90292637')\"\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",
+              "    </div>\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 containerElement = document.querySelector('#' + key);\n",
+              "        const charts = await google.colab.kernel.invokeFunction(\n",
+              "            'suggestCharts', [key], {});\n",
+              "      }\n",
+              "    </script>\n",
+              "\n",
+              "      <script>\n",
+              "\n",
+              "function displayQuickchartButton(domScope) {\n",
+              "  let quickchartButtonEl =\n",
+              "    domScope.querySelector('#df-18937a13-a371-4bc9-a2bf-fcaf90292637 button.colab-df-quickchart');\n",
+              "  quickchartButtonEl.style.display =\n",
+              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "}\n",
+              "\n",
+              "        displayQuickchartButton(document);\n",
+              "      </script>\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-cca298de-e4c7-4361-93ae-45371e6fbb27 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-cca298de-e4c7-4361-93ae-45371e6fbb27');\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": 23
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "test_data['movie_synopsis'] = mergeText(test_data)\n",
+        "test_data.drop(['genre'], axis=1, inplace=True)\n",
+        "\n",
+        "test_data.head()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 206
+        },
+        "id": "Jq_alTF3USTX",
+        "outputId": "30568322-7d54-4a0e-9934-289f892f0b4f"
+      },
+      "id": "Jq_alTF3USTX",
+      "execution_count": 24,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "      id          movie_name  \\\n",
+              "0  16863    a death sentence   \n",
+              "1  48456          intermedio   \n",
+              "2  41383    30 chua phai tet   \n",
+              "3  84007           paranoiac   \n",
+              "4  40269  ordinary happiness   \n",
+              "\n",
+              "                                            synopsis  \\\n",
+              "0  ida dad die without dkk operation ida plans st...   \n",
+              "1  group four teenage friends become trapped mexi...   \n",
+              "2  guy left home years till came back claim fathe...   \n",
+              "3  man long believed dead returns family estate c...   \n",
+              "4  deadly accident paolo comes back earth minutes...   \n",
+              "\n",
+              "                                      movie_synopsis  \n",
+              "0  a death sentence ida dad die without dkk opera...  \n",
+              "1  intermedio group four teenage friends become t...  \n",
+              "2  30 chua phai tet guy left home years till came...  \n",
+              "3  paranoiac man long believed dead returns famil...  \n",
+              "4  ordinary happiness deadly accident paolo comes...  "
+            ],
+            "text/html": [
+              "\n",
+              "\n",
+              "  <div id=\"df-c05b5c7e-c108-48d6-9b8d-a7e4c4194027\">\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>id</th>\n",
+              "      <th>movie_name</th>\n",
+              "      <th>synopsis</th>\n",
+              "      <th>movie_synopsis</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>16863</td>\n",
+              "      <td>a death sentence</td>\n",
+              "      <td>ida dad die without dkk operation ida plans st...</td>\n",
+              "      <td>a death sentence ida dad die without dkk opera...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>48456</td>\n",
+              "      <td>intermedio</td>\n",
+              "      <td>group four teenage friends become trapped mexi...</td>\n",
+              "      <td>intermedio group four teenage friends become t...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>41383</td>\n",
+              "      <td>30 chua phai tet</td>\n",
+              "      <td>guy left home years till came back claim fathe...</td>\n",
+              "      <td>30 chua phai tet guy left home years till came...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>84007</td>\n",
+              "      <td>paranoiac</td>\n",
+              "      <td>man long believed dead returns family estate c...</td>\n",
+              "      <td>paranoiac man long believed dead returns famil...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>40269</td>\n",
+              "      <td>ordinary happiness</td>\n",
+              "      <td>deadly accident paolo comes back earth minutes...</td>\n",
+              "      <td>ordinary happiness deadly accident paolo comes...</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>\n",
+              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-c05b5c7e-c108-48d6-9b8d-a7e4c4194027')\"\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",
+              "\n",
+              "\n",
+              "    <div id=\"df-93fd4fe7-b930-45d5-96d2-f2e9727e1c34\">\n",
+              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-93fd4fe7-b930-45d5-96d2-f2e9727e1c34')\"\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",
+              "    </div>\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 containerElement = document.querySelector('#' + key);\n",
+              "        const charts = await google.colab.kernel.invokeFunction(\n",
+              "            'suggestCharts', [key], {});\n",
+              "      }\n",
+              "    </script>\n",
+              "\n",
+              "      <script>\n",
+              "\n",
+              "function displayQuickchartButton(domScope) {\n",
+              "  let quickchartButtonEl =\n",
+              "    domScope.querySelector('#df-93fd4fe7-b930-45d5-96d2-f2e9727e1c34 button.colab-df-quickchart');\n",
+              "  quickchartButtonEl.style.display =\n",
+              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "}\n",
+              "\n",
+              "        displayQuickchartButton(document);\n",
+              "      </script>\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-c05b5c7e-c108-48d6-9b8d-a7e4c4194027 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-c05b5c7e-c108-48d6-9b8d-a7e4c4194027');\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": 24
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "vectorized_synopsis = cv.transform(test_data['movie_synopsis'])\n",
+        "\n",
+        "predictions = mnb.predict(vectorized_synopsis)\n",
+        "\n",
+        "genre_predictions = le_genre.inverse_transform(predictions)"
+      ],
+      "metadata": {
+        "id": "8yeCDG6kUifi"
+      },
+      "id": "8yeCDG6kUifi",
+      "execution_count": 25,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "submission = pd.DataFrame(pd.DataFrame({'id': test_data['id'], 'genre': genre_predictions}))\n",
+        "submission.head()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 206
+        },
+        "id": "Azmt1BZsVVgC",
+        "outputId": "a731ee69-6365-4537-e7ea-541a4962ab3e"
+      },
+      "id": "Azmt1BZsVVgC",
+      "execution_count": 26,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "      id    genre\n",
+              "0  16863    crime\n",
+              "1  48456   horror\n",
+              "2  41383    scifi\n",
+              "3  84007  mystery\n",
+              "4  40269  fantasy"
+            ],
+            "text/html": [
+              "\n",
+              "\n",
+              "  <div id=\"df-5f805ab6-9544-4a65-90bc-1ad1e04a373e\">\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>id</th>\n",
+              "      <th>genre</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>16863</td>\n",
+              "      <td>crime</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>48456</td>\n",
+              "      <td>horror</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>41383</td>\n",
+              "      <td>scifi</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>84007</td>\n",
+              "      <td>mystery</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>40269</td>\n",
+              "      <td>fantasy</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>\n",
+              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-5f805ab6-9544-4a65-90bc-1ad1e04a373e')\"\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",
+              "\n",
+              "\n",
+              "    <div id=\"df-a167ea63-c533-427b-8775-dff0e31d48bb\">\n",
+              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-a167ea63-c533-427b-8775-dff0e31d48bb')\"\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",
+              "    </div>\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 containerElement = document.querySelector('#' + key);\n",
+              "        const charts = await google.colab.kernel.invokeFunction(\n",
+              "            'suggestCharts', [key], {});\n",
+              "      }\n",
+              "    </script>\n",
+              "\n",
+              "      <script>\n",
+              "\n",
+              "function displayQuickchartButton(domScope) {\n",
+              "  let quickchartButtonEl =\n",
+              "    domScope.querySelector('#df-a167ea63-c533-427b-8775-dff0e31d48bb button.colab-df-quickchart');\n",
+              "  quickchartButtonEl.style.display =\n",
+              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "}\n",
+              "\n",
+              "        displayQuickchartButton(document);\n",
+              "      </script>\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-5f805ab6-9544-4a65-90bc-1ad1e04a373e 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-5f805ab6-9544-4a65-90bc-1ad1e04a373e');\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": 26
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "submission.to_csv('submission_ShalakaThorat.csv', index=False)"
+      ],
+      "metadata": {
+        "id": "u1kZLHbBWO0d"
+      },
+      "id": "u1kZLHbBWO0d",
+      "execution_count": 27,
+      "outputs": []
+    }
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.10.9"
+    },
+    "colab": {
+      "provenance": [],
+      "gpuType": "T4"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}
\ No newline at end of file