Text_Classification_Using_Bert_with_Spam_and_Not_Spam_NLP.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Text Classification Using Bert with Spam and Not Spam NLP.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyPYDHSXsjcLtaiwo0PNgFN8",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "gpuClass": "standard",
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/rajni-arora/Deep-Learning-Projects/blob/main/Text_Classification_Using_Bert_with_Spam_and_Not_Spam_NLP.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pip install tensorflow-text"
      ],
      "metadata": {
        "id": "s-S_JHsth_YE"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install tensorflow "
      ],
      "metadata": {
        "id": "es93BdSVhzTe"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf\n",
        "import tensorflow_hub as hub\n",
        "import tensorflow_text as text"
      ],
      "metadata": {
        "id": "k2CsygA0g5nG"
      },
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!wget 'https://raw.githubusercontent.com/codebasics/deep-learning-keras-tf-tutorial/master/47_BERT_text_classification/spam.csv'"
      ],
      "metadata": {
        "id": "QoiKM0guC-NI"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "\n",
        "df = pd.read_csv('/content/spam.csv')\n",
        "df.head(5)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "czMjwXNmDCTo",
        "outputId": "44801f3c-39a2-4ae6-8b93-17e219b1c4b1"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  Category                                            Message\n",
              "0      ham  Go until jurong point, crazy.. Available only ...\n",
              "1      ham                      Ok lar... Joking wif u oni...\n",
              "2     spam  Free entry in 2 a wkly comp to win FA Cup fina...\n",
              "3      ham  U dun say so early hor... U c already then say...\n",
              "4      ham  Nah I don't think he goes to usf, he lives aro..."
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-3acff2a7-9ed1-4f56-a0e7-7d2d65c59497\">\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>Category</th>\n",
              "      <th>Message</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>ham</td>\n",
              "      <td>Go until jurong point, crazy.. Available only ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>ham</td>\n",
              "      <td>Ok lar... Joking wif u oni...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>spam</td>\n",
              "      <td>Free entry in 2 a wkly comp to win FA Cup fina...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>ham</td>\n",
              "      <td>U dun say so early hor... U c already then say...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>ham</td>\n",
              "      <td>Nah I don't think he goes to usf, he lives aro...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-3acff2a7-9ed1-4f56-a0e7-7d2d65c59497')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-3acff2a7-9ed1-4f56-a0e7-7d2d65c59497 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-3acff2a7-9ed1-4f56-a0e7-7d2d65c59497');\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": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.groupby('Category').describe()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 175
        },
        "id": "Cya_-dh1DLiD",
        "outputId": "8c463bf5-7f3e-4ae6-85ca-e432d33f6e9f"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "         Message                                                            \\\n",
              "           count unique                                                top   \n",
              "Category                                                                     \n",
              "ham         4825   4516                             Sorry, I'll call later   \n",
              "spam         747    641  Please call our customer service representativ...   \n",
              "\n",
              "               \n",
              "         freq  \n",
              "Category       \n",
              "ham        30  \n",
              "spam        4  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-d863d653-ce06-48de-8238-9b9d5070a004\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead tr th {\n",
              "        text-align: left;\n",
              "    }\n",
              "\n",
              "    .dataframe thead tr:last-of-type th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr>\n",
              "      <th></th>\n",
              "      <th colspan=\"4\" halign=\"left\">Message</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th></th>\n",
              "      <th>count</th>\n",
              "      <th>unique</th>\n",
              "      <th>top</th>\n",
              "      <th>freq</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Category</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>ham</th>\n",
              "      <td>4825</td>\n",
              "      <td>4516</td>\n",
              "      <td>Sorry, I'll call later</td>\n",
              "      <td>30</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>spam</th>\n",
              "      <td>747</td>\n",
              "      <td>641</td>\n",
              "      <td>Please call our customer service representativ...</td>\n",
              "      <td>4</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-d863d653-ce06-48de-8238-9b9d5070a004')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-d863d653-ce06-48de-8238-9b9d5070a004 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-d863d653-ce06-48de-8238-9b9d5070a004');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Here the dataset is imbalance, and we are using downsampling."
      ],
      "metadata": {
        "id": "B6kmrpNfG5V5"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df['Category'].value_counts()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-gHewR_rDmli",
        "outputId": "03a4f2d9-239d-4f2d-bd6b-6e5f5eda27d1"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "ham     4825\n",
              "spam     747\n",
              "Name: Category, dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "747/4825 "
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cdRWrkKIHm-d",
        "outputId": "b2eeaead-9c3e-46b9-d380-ecb495d324a8"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.15481865284974095"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "15% are spam emails and 85% are ham emails"
      ],
      "metadata": {
        "id": "Z0T-lOjyIBhv"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df_spam = df[df['Category'] == 'spam']\n",
        "df_spam.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xU8WaZerIBEg",
        "outputId": "420326f2-5a2d-4697-a2b1-fa5ee6ca7f96"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(747, 2)"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df_ham = df[df['Category'] == 'ham']\n",
        "df_ham.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dZo7xHgZH-g2",
        "outputId": "6798d40b-c9dd-4a72-d0e4-c39754400d67"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(4825, 2)"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df_ham.sample(747)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 423
        },
        "id": "MQMyz936JKvJ",
        "outputId": "aa6e1ea5-477d-46b6-c588-78499bfd79e1"
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "     Category                                            Message\n",
              "1910      ham                     Then u going ikea str aft dat?\n",
              "1791      ham  Am not working but am up to eyes in philosophy...\n",
              "4320      ham                Are you still playing with gautham?\n",
              "4389      ham          see you then, we're all christmassy here!\n",
              "2449      ham                       Do u knw dis no. &lt;#&gt; ?\n",
              "...       ...                                                ...\n",
              "1214      ham  Yeah, probably but not sure. Ilol let u know, ...\n",
              "432       ham  Does she usually take fifteen fucking minutes ...\n",
              "4275      ham  Ball is moving a lot.will spin in last :)so ve...\n",
              "2727      ham     No i am not having not any movies in my laptop\n",
              "1170      ham  Msgs r not time pass.They silently say that I ...\n",
              "\n",
              "[747 rows x 2 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-3eb38963-c042-4722-bcda-663ff2a16c0d\">\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>Category</th>\n",
              "      <th>Message</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>1910</th>\n",
              "      <td>ham</td>\n",
              "      <td>Then u going ikea str aft dat?</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1791</th>\n",
              "      <td>ham</td>\n",
              "      <td>Am not working but am up to eyes in philosophy...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4320</th>\n",
              "      <td>ham</td>\n",
              "      <td>Are you still playing with gautham?</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4389</th>\n",
              "      <td>ham</td>\n",
              "      <td>see you then, we're all christmassy here!</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2449</th>\n",
              "      <td>ham</td>\n",
              "      <td>Do u knw dis no. &amp;lt;#&amp;gt; ?</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1214</th>\n",
              "      <td>ham</td>\n",
              "      <td>Yeah, probably but not sure. Ilol let u know, ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>432</th>\n",
              "      <td>ham</td>\n",
              "      <td>Does she usually take fifteen fucking minutes ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4275</th>\n",
              "      <td>ham</td>\n",
              "      <td>Ball is moving a lot.will spin in last :)so ve...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2727</th>\n",
              "      <td>ham</td>\n",
              "      <td>No i am not having not any movies in my laptop</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1170</th>\n",
              "      <td>ham</td>\n",
              "      <td>Msgs r not time pass.They silently say that I ...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>747 rows × 2 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-3eb38963-c042-4722-bcda-663ff2a16c0d')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-3eb38963-c042-4722-bcda-663ff2a16c0d 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-3eb38963-c042-4722-bcda-663ff2a16c0d');\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
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df_ham_downsampled = df_ham.sample(df_spam.shape[0])\n",
        "df_ham_downsampled.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DJ9FxsUhJYOc",
        "outputId": "1a0177ae-e6b0-432a-8b86-1911c938fadb"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(747, 2)"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Now concatenate both to make balanced dataframe "
      ],
      "metadata": {
        "id": "cLBkd8ExKQ3i"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df_balanced = pd.concat([df_spam, df_ham_downsampled])\n",
        "df_balanced.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "63Q4VYn8J-K6",
        "outputId": "163ad797-e7eb-429d-9ff8-27d8ae996225"
      },
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(1494, 2)"
            ]
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df_balanced['Category'].value_counts()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ebfZCGoAKjCf",
        "outputId": "092f09fe-afad-4ad9-86f7-6aac036a9925"
      },
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "spam    747\n",
              "ham     747\n",
              "Name: Category, dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df_balanced.sample(5)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "Igmh2y8YKu2a",
        "outputId": "9536bb59-ddcd-4712-ae7e-37ae2020485d"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "     Category                                            Message\n",
              "2250     spam  Thanks for your ringtone order, ref number R83...\n",
              "1745     spam  Someone has conacted our dating service and en...\n",
              "4800      ham    I dont know why she.s not getting your messages\n",
              "2642     spam  You are guaranteed the latest Nokia Phone, a 4...\n",
              "1752      ham  * Was thinking about chuckin ur red green n bl..."
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-3387b47d-190f-4697-a9cf-245db64ce193\">\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>Category</th>\n",
              "      <th>Message</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2250</th>\n",
              "      <td>spam</td>\n",
              "      <td>Thanks for your ringtone order, ref number R83...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1745</th>\n",
              "      <td>spam</td>\n",
              "      <td>Someone has conacted our dating service and en...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4800</th>\n",
              "      <td>ham</td>\n",
              "      <td>I dont know why she.s not getting your messages</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2642</th>\n",
              "      <td>spam</td>\n",
              "      <td>You are guaranteed the latest Nokia Phone, a 4...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1752</th>\n",
              "      <td>ham</td>\n",
              "      <td>* Was thinking about chuckin ur red green n bl...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-3387b47d-190f-4697-a9cf-245db64ce193')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-3387b47d-190f-4697-a9cf-245db64ce193 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-3387b47d-190f-4697-a9cf-245db64ce193');\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": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df_balanced.head(10)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 363
        },
        "id": "wblrCcT5K9r2",
        "outputId": "f1815b20-96e0-4421-be7c-a2eca7f284b0"
      },
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   Category                                            Message\n",
              "2      spam  Free entry in 2 a wkly comp to win FA Cup fina...\n",
              "5      spam  FreeMsg Hey there darling it's been 3 week's n...\n",
              "8      spam  WINNER!! As a valued network customer you have...\n",
              "9      spam  Had your mobile 11 months or more? U R entitle...\n",
              "11     spam  SIX chances to win CASH! From 100 to 20,000 po...\n",
              "12     spam  URGENT! You have won a 1 week FREE membership ...\n",
              "15     spam  XXXMobileMovieClub: To use your credit, click ...\n",
              "19     spam  England v Macedonia - dont miss the goals/team...\n",
              "34     spam  Thanks for your subscription to Ringtone UK yo...\n",
              "42     spam  07732584351 - Rodger Burns - MSG = We tried to..."
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-88454ac6-b695-44bc-9224-b6d6d5eec152\">\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>Category</th>\n",
              "      <th>Message</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>spam</td>\n",
              "      <td>Free entry in 2 a wkly comp to win FA Cup fina...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>spam</td>\n",
              "      <td>FreeMsg Hey there darling it's been 3 week's n...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>8</th>\n",
              "      <td>spam</td>\n",
              "      <td>WINNER!! As a valued network customer you have...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9</th>\n",
              "      <td>spam</td>\n",
              "      <td>Had your mobile 11 months or more? U R entitle...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>11</th>\n",
              "      <td>spam</td>\n",
              "      <td>SIX chances to win CASH! From 100 to 20,000 po...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>12</th>\n",
              "      <td>spam</td>\n",
              "      <td>URGENT! You have won a 1 week FREE membership ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>15</th>\n",
              "      <td>spam</td>\n",
              "      <td>XXXMobileMovieClub: To use your credit, click ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>19</th>\n",
              "      <td>spam</td>\n",
              "      <td>England v Macedonia - dont miss the goals/team...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>34</th>\n",
              "      <td>spam</td>\n",
              "      <td>Thanks for your subscription to Ringtone UK yo...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>42</th>\n",
              "      <td>spam</td>\n",
              "      <td>07732584351 - Rodger Burns - MSG = We tried to...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-88454ac6-b695-44bc-9224-b6d6d5eec152')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-88454ac6-b695-44bc-9224-b6d6d5eec152 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-88454ac6-b695-44bc-9224-b6d6d5eec152');\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": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df_balanced['spam'] = df_balanced['Category'].apply(lambda x: 1 if x =='spam' else 0)"
      ],
      "metadata": {
        "id": "KUaC7ML1LAjN"
      },
      "execution_count": 17,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df_balanced.sample(10)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 363
        },
        "id": "B_g-NMs5PoX_",
        "outputId": "80062fcd-de3b-48e6-c0bf-7ac9e045d0d6"
      },
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "     Category                                            Message  spam\n",
              "401      spam  FREE RINGTONE text FIRST to 87131 for a poly o...     1\n",
              "34       spam  Thanks for your subscription to Ringtone UK yo...     1\n",
              "4918     spam  This is the 2nd time we have tried 2 contact u...     1\n",
              "5014      ham  Uncle G, just checking up on you. Do have a re...     0\n",
              "3981     spam                                 ringtoneking 84484     1\n",
              "3891     spam  Double Mins & 1000 txts on Orange tariffs. Lat...     1\n",
              "576      spam  You have won ?1,000 cash or a ?2,000 prize! To...     1\n",
              "1598     spam  URGENT! Your Mobile number has been awarded wi...     1\n",
              "2041      ham        You always make things bigger than they are     0\n",
              "803      spam  FREE for 1st week! No1 Nokia tone 4 ur mobile ...     1"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-9fc6b0a9-2844-474d-871a-335588f1a624\">\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>Category</th>\n",
              "      <th>Message</th>\n",
              "      <th>spam</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>401</th>\n",
              "      <td>spam</td>\n",
              "      <td>FREE RINGTONE text FIRST to 87131 for a poly o...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>34</th>\n",
              "      <td>spam</td>\n",
              "      <td>Thanks for your subscription to Ringtone UK yo...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4918</th>\n",
              "      <td>spam</td>\n",
              "      <td>This is the 2nd time we have tried 2 contact u...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5014</th>\n",
              "      <td>ham</td>\n",
              "      <td>Uncle G, just checking up on you. Do have a re...</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3981</th>\n",
              "      <td>spam</td>\n",
              "      <td>ringtoneking 84484</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3891</th>\n",
              "      <td>spam</td>\n",
              "      <td>Double Mins &amp; 1000 txts on Orange tariffs. Lat...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>576</th>\n",
              "      <td>spam</td>\n",
              "      <td>You have won ?1,000 cash or a ?2,000 prize! To...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1598</th>\n",
              "      <td>spam</td>\n",
              "      <td>URGENT! Your Mobile number has been awarded wi...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2041</th>\n",
              "      <td>ham</td>\n",
              "      <td>You always make things bigger than they are</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>803</th>\n",
              "      <td>spam</td>\n",
              "      <td>FREE for 1st week! No1 Nokia tone 4 ur mobile ...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-9fc6b0a9-2844-474d-871a-335588f1a624')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-9fc6b0a9-2844-474d-871a-335588f1a624 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-9fc6b0a9-2844-474d-871a-335588f1a624');\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": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "X_train, X_test, y_train, y_test = train_test_split(df_balanced['Message'], df_balanced['spam'], stratify = df_balanced['spam'])"
      ],
      "metadata": {
        "id": "1CnKBcuHRNa9"
      },
      "execution_count": 19,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X_train.head(4)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "W605tbbuRryh",
        "outputId": "d83209e6-fc10-4197-a9dd-330fbfc7c7d8"
      },
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "2581    U are subscribed to the best Mobile Content Se...\n",
              "2579    Erm. I thought the contract ran out the4th of ...\n",
              "8       WINNER!! As a valued network customer you have...\n",
              "1218    Damn, can you make it tonight or do you want t...\n",
              "Name: Message, dtype: object"
            ]
          },
          "metadata": {},
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "bert_preprocess = hub.KerasLayer(\"https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3\")\n",
        "bert_encoder = hub.KerasLayer(\"https://tfhub.dev/tensorflow/bert_en_uncased_L-12_H-768_A-12/4\")"
      ],
      "metadata": {
        "id": "Y_bznrTlTl9j"
      },
      "execution_count": 21,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def get_sentence_embeding(sentences):\n",
        "    preprocessed_text = bert_preprocess(sentences)\n",
        "    return bert_encoder(preprocessed_text)['pooled_output']\n",
        "\n",
        "get_sentence_embeding([\n",
        "    \"500$ discount. hurry up\", \n",
        "    \"Bhavin, are you up for a volleybal game tomorrow?\"]\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fF7odWI9XVal",
        "outputId": "96ac03e2-2038-429f-bdff-aca23a77e247"
      },
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<tf.Tensor: shape=(2, 768), dtype=float32, numpy=\n",
              "array([[-0.84351724, -0.51327276, -0.88845724, ..., -0.74748844,\n",
              "        -0.7531474 ,  0.91964495],\n",
              "       [-0.87208337, -0.5054394 , -0.94446665, ..., -0.85847497,\n",
              "        -0.71745324,  0.8808295 ]], dtype=float32)>"
            ]
          },
          "metadata": {},
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "e = get_sentence_embeding([\n",
        "                            \"banana\",\n",
        "                            \"grapes\",\n",
        "                            \"mango\",\n",
        "                            \"jeff bezos\",\n",
        "                            \"elon musk\",\n",
        "                            \"bill gates\"\n",
        "])"
      ],
      "metadata": {
        "id": "qoBiTRfVYZDi"
      },
      "execution_count": 23,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "e"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "07kcZwmovRbk",
        "outputId": "555be5a1-e17a-44ce-b555-42958939fdf6"
      },
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<tf.Tensor: shape=(6, 768), dtype=float32, numpy=\n",
              "array([[-0.7606916 , -0.14219397,  0.49604574, ...,  0.42165306,\n",
              "        -0.5322139 ,  0.80312157],\n",
              "       [-0.86023194, -0.21242912,  0.4915695 , ...,  0.39798063,\n",
              "        -0.60506254,  0.8447163 ],\n",
              "       [-0.7128858 , -0.15463883,  0.38401723, ...,  0.35278767,\n",
              "        -0.50991315,  0.73474056],\n",
              "       [-0.82533485, -0.35550627, -0.5906983 , ..., -0.01613823,\n",
              "        -0.614176  ,  0.872303  ],\n",
              "       [-0.75041324, -0.2681263 , -0.26689714, ...,  0.02839372,\n",
              "        -0.59380966,  0.7974984 ],\n",
              "       [-0.785443  , -0.29949623,  0.4102765 , ...,  0.52225506,\n",
              "        -0.4957351 ,  0.81507415]], dtype=float32)>"
            ]
          },
          "metadata": {},
          "execution_count": 24
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.metrics.pairwise import cosine_similarity\n",
        "\n",
        "cosine_similarity([e[0]], [e[1]])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "g1957jw5ujO_",
        "outputId": "418cb35f-6bf8-440a-8b86-69dfcc99aa03"
      },
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.9911088]], dtype=float32)"
            ]
          },
          "metadata": {},
          "execution_count": 25
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#Bert Layers\n",
        "\n",
        "text_input = tf.keras.layers.Input(shape = (), dtype = tf.string, name=\"text\")\n",
        "\n",
        "preprocessed_text = bert_preprocess(text_input)\n",
        "outputs = bert_encoder(preprocessed_text)\n",
        "\n",
        "# Neural network layers\n",
        "l = tf.keras.layers.Dropout(0.1, name='dropout')(outputs['pooled_output'])\n",
        "l = tf.keras.layers.Dense(1, activation = 'sigmoid', name = 'output')(l)\n",
        "\n",
        "# construct final model\n",
        "model = tf.keras.Model(inputs=[text_input], outputs=[l])"
      ],
      "metadata": {
        "id": "sH_YoaQFu6Y6"
      },
      "execution_count": 26,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model.summary()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_KS2MUFzA0kS",
        "outputId": "23e36bfd-238d-4010-bb55-7b452f49ae6a"
      },
      "execution_count": 27,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model: \"model\"\n",
            "__________________________________________________________________________________________________\n",
            " Layer (type)                   Output Shape         Param #     Connected to                     \n",
            "==================================================================================================\n",
            " text (InputLayer)              [(None,)]            0           []                               \n",
            "                                                                                                  \n",
            " keras_layer (KerasLayer)       {'input_word_ids':   0           ['text[0][0]']                   \n",
            "                                (None, 128),                                                      \n",
            "                                 'input_type_ids':                                                \n",
            "                                (None, 128),                                                      \n",
            "                                 'input_mask': (Non                                               \n",
            "                                e, 128)}                                                          \n",
            "                                                                                                  \n",
            " keras_layer_1 (KerasLayer)     {'default': (None,   109482241   ['keras_layer[0][0]',            \n",
            "                                768),                             'keras_layer[0][1]',            \n",
            "                                 'sequence_output':               'keras_layer[0][2]']            \n",
            "                                 (None, 128, 768),                                                \n",
            "                                 'pooled_output': (                                               \n",
            "                                None, 768),                                                       \n",
            "                                 'encoder_outputs':                                               \n",
            "                                 [(None, 128, 768),                                               \n",
            "                                 (None, 128, 768),                                                \n",
            "                                 (None, 128, 768),                                                \n",
            "                                 (None, 128, 768),                                                \n",
            "                                 (None, 128, 768),                                                \n",
            "                                 (None, 128, 768),                                                \n",
            "                                 (None, 128, 768),                                                \n",
            "                                 (None, 128, 768),                                                \n",
            "                                 (None, 128, 768),                                                \n",
            "                                 (None, 128, 768),                                                \n",
            "                                 (None, 128, 768),                                                \n",
            "                                 (None, 128, 768)]}                                               \n",
            "                                                                                                  \n",
            " dropout (Dropout)              (None, 768)          0           ['keras_layer_1[0][13]']         \n",
            "                                                                                                  \n",
            " output (Dense)                 (None, 1)            769         ['dropout[0][0]']                \n",
            "                                                                                                  \n",
            "==================================================================================================\n",
            "Total params: 109,483,010\n",
            "Trainable params: 769\n",
            "Non-trainable params: 109,482,241\n",
            "__________________________________________________________________________________________________\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "METRICS = [\n",
        "           tf.keras.metrics.BinaryAccuracy(name='BinaryAccuracy'),\n",
        "           tf.keras.metrics.Precision(name='precision'),\n",
        "           tf.keras.metrics.Recall(name='recall')\n",
        "]\n",
        "\n",
        "model.compile(optimizer='adam',\n",
        "              loss = 'binary_crossentropy',\n",
        "              metrics = METRICS)"
      ],
      "metadata": {
        "id": "vkdvJJZrBF2J"
      },
      "execution_count": 28,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model.fit(X_train, y_train, epochs=10)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "M9y6ExKHB4Pj",
        "outputId": "6a5afc88-fdbe-4f23-8679-88b0bd84c7ac"
      },
      "execution_count": 29,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/10\n",
            "35/35 [==============================] - 19s 304ms/step - loss: 0.6327 - BinaryAccuracy: 0.6705 - precision: 0.6819 - recall: 0.6393\n",
            "Epoch 2/10\n",
            "35/35 [==============================] - 11s 307ms/step - loss: 0.5153 - BinaryAccuracy: 0.8232 - precision: 0.8007 - recall: 0.8607\n",
            "Epoch 3/10\n",
            "35/35 [==============================] - 11s 311ms/step - loss: 0.4526 - BinaryAccuracy: 0.8455 - precision: 0.8342 - recall: 0.8625\n",
            "Epoch 4/10\n",
            "35/35 [==============================] - 11s 314ms/step - loss: 0.4075 - BinaryAccuracy: 0.8652 - precision: 0.8508 - recall: 0.8857\n",
            "Epoch 5/10\n",
            "35/35 [==============================] - 11s 319ms/step - loss: 0.3761 - BinaryAccuracy: 0.8759 - precision: 0.8713 - recall: 0.8821\n",
            "Epoch 6/10\n",
            "35/35 [==============================] - 11s 325ms/step - loss: 0.3466 - BinaryAccuracy: 0.8938 - precision: 0.8731 - recall: 0.9214\n",
            "Epoch 7/10\n",
            "35/35 [==============================] - 12s 332ms/step - loss: 0.3267 - BinaryAccuracy: 0.9000 - precision: 0.8889 - recall: 0.9143\n",
            "Epoch 8/10\n",
            "35/35 [==============================] - 12s 341ms/step - loss: 0.3172 - BinaryAccuracy: 0.8929 - precision: 0.8846 - recall: 0.9036\n",
            "Epoch 9/10\n",
            "35/35 [==============================] - 12s 343ms/step - loss: 0.3036 - BinaryAccuracy: 0.9036 - precision: 0.8910 - recall: 0.9196\n",
            "Epoch 10/10\n",
            "35/35 [==============================] - 12s 335ms/step - loss: 0.3048 - BinaryAccuracy: 0.8955 - precision: 0.8879 - recall: 0.9054\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.History at 0x7f2e7f5d82d0>"
            ]
          },
          "metadata": {},
          "execution_count": 29
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model.evaluate(X_test, y_test)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "UUhozYZ7CCiR",
        "outputId": "b70caca2-ec09-493c-b912-913ac9adf98c"
      },
      "execution_count": 30,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "12/12 [==============================] - 5s 320ms/step - loss: 0.2852 - BinaryAccuracy: 0.9144 - precision: 0.9379 - recall: 0.8877\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[0.2852499783039093,\n",
              " 0.9144384860992432,\n",
              " 0.9378530979156494,\n",
              " 0.8877005577087402]"
            ]
          },
          "metadata": {},
          "execution_count": 30
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_predicted = model.predict(X_test)\n",
        "y_predicted = y_predicted.flatten() #Converting 2d to 1d array"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nNPFBmwKEV-I",
        "outputId": "94850fad-e175-4d3a-92ff-6438177bd2e9"
      },
      "execution_count": 35,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "12/12 [==============================] - 4s 318ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_predicted"
      ],
      "metadata": {
        "id": "SwC51pqLO3pn"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "\n",
        "y_predicted = np.where(y_predicted > 0.5, 1, 0) #If value > 0.5 that is equal to 1\n",
        "y_predicted"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "N5WYHfeBErdu",
        "outputId": "54685c0d-d1ed-4056-af54-fe948184e881"
      },
      "execution_count": 36,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([1, 1, 0, 1, 1, 0, 1, 1, 1, 0, 0, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1,\n",
              "       1, 0, 0, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0,\n",
              "       1, 0, 1, 1, 0, 1, 1, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 1, 0, 0, 0, 1,\n",
              "       1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0,\n",
              "       0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 0,\n",
              "       0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0, 1,\n",
              "       1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 0, 1, 0, 1, 0, 1, 0, 0, 1,\n",
              "       1, 0, 1, 1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0,\n",
              "       0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 0,\n",
              "       1, 0, 0, 0, 1, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0,\n",
              "       0, 0, 1, 0, 1, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 0, 0, 0, 1, 1,\n",
              "       1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0,\n",
              "       1, 0, 0, 1, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 0, 1, 1, 0, 1,\n",
              "       1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1,\n",
              "       0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1,\n",
              "       1, 0, 1, 1, 1, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0,\n",
              "       1, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 1, 0])"
            ]
          },
          "metadata": {},
          "execution_count": 36
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.metrics import confusion_matrix, classification_report\n",
        "cm = confusion_matrix(y_test, y_predicted)\n",
        "cm"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5NSezXKYSNri",
        "outputId": "59fb7070-1f51-43b7-f67e-42ac65e43789"
      },
      "execution_count": 39,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[176,  11],\n",
              "       [ 21, 166]])"
            ]
          },
          "metadata": {},
          "execution_count": 39
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from matplotlib import pyplot as plt\n",
        "import seaborn as sn\n",
        "sn.heatmap(cm, annot = True, fmt = 'd')\n",
        "plt.xlabel('Predicted')\n",
        "plt.ylabel('Truth')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 297
        },
        "id": "eNufYdARSfqi",
        "outputId": "77238c29-a9cd-4c38-fbca-067384cb1d1f"
      },
      "execution_count": 44,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Text(33.0, 0.5, 'Truth')"
            ]
          },
          "metadata": {},
          "execution_count": 44
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(classification_report(y_test, y_predicted))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "0qfTJxI7TW8e",
        "outputId": "dcfbfc72-fae7-4616-d8f6-05cfae8e2f84"
      },
      "execution_count": 45,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.89      0.94      0.92       187\n",
            "           1       0.94      0.89      0.91       187\n",
            "\n",
            "    accuracy                           0.91       374\n",
            "   macro avg       0.92      0.91      0.91       374\n",
            "weighted avg       0.92      0.91      0.91       374\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "reviews = [\n",
        "            'Enter a chance to win $5000, hurry up, offer valid until march 31, 2021',\n",
        "            'You are awarded a SiPix Digital Cameral! call 0t73218723616 from landline, Dilivery with in 28 days',\n",
        "            'Hey Richa are you coming for interview today',\n",
        "            'Can you plese solve my isuue i am getting in my project '\n",
        "]\n",
        "\n",
        "model.predict(reviews)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "n9dOeJBhUrtn",
        "outputId": "e168a95c-3dc2-4dba-8ad4-ec4e102bde2d"
      },
      "execution_count": 46,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1/1 [==============================] - 1s 1s/step\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.5399154 ],\n",
              "       [0.68494713],\n",
              "       [0.04099401],\n",
              "       [0.03547767]], dtype=float32)"
            ]
          },
          "metadata": {},
          "execution_count": 46
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "if value > 0.5 means Spam otherwise not spam"
      ],
      "metadata": {
        "id": "CX3DRd6lWmFv"
      }
    }
  ]
}