Pima_Neural.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyPblsrW/QZKv/kdMH+4IZMZ",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/mohanrajmit/DL-Training/blob/master/Pima_Neural.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "rsJO3X_YHiOh"
      },
      "outputs": [],
      "source": [
        "import pandas as pd"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data = pd.read_csv(\"/content/pima-indians-diabetes.csv\")"
      ],
      "metadata": {
        "id": "4hz-nKBtIH0Z"
      },
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "data.info()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "u3qjo_IWIQ70",
        "outputId": "e07046e8-f729-404b-8cb1-00a1ac3aca0e"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 768 entries, 0 to 767\n",
            "Data columns (total 9 columns):\n",
            " #   Column  Non-Null Count  Dtype  \n",
            "---  ------  --------------  -----  \n",
            " 0   Preg    768 non-null    int64  \n",
            " 1   Plas    768 non-null    int64  \n",
            " 2   Pres    768 non-null    int64  \n",
            " 3   skin    768 non-null    int64  \n",
            " 4   test    768 non-null    int64  \n",
            " 5   mass    768 non-null    float64\n",
            " 6   pedi    768 non-null    float64\n",
            " 7   age     768 non-null    int64  \n",
            " 8   class   768 non-null    int64  \n",
            "dtypes: float64(2), int64(7)\n",
            "memory usage: 54.1 KB\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Zrmk1xcPITFf",
        "outputId": "8e6c665e-f4a4-42ba-aa25-8cb85667f20e"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(768, 9)"
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "X7XNORFnIsLk",
        "outputId": "5d635e4c-a42b-48c9-84c8-d5890a837d52"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   Preg  Plas  Pres  skin  test  mass   pedi  age  class\n",
              "0     6   148    72    35     0  33.6  0.627   50      1\n",
              "1     1    85    66    29     0  26.6  0.351   31      0\n",
              "2     8   183    64     0     0  23.3  0.672   32      1\n",
              "3     1    89    66    23    94  28.1  0.167   21      0\n",
              "4     0   137    40    35   168  43.1  2.288   33      1"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-7931c928-4ad9-437c-b6fb-427ad593504f\" 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>Preg</th>\n",
              "      <th>Plas</th>\n",
              "      <th>Pres</th>\n",
              "      <th>skin</th>\n",
              "      <th>test</th>\n",
              "      <th>mass</th>\n",
              "      <th>pedi</th>\n",
              "      <th>age</th>\n",
              "      <th>class</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>6</td>\n",
              "      <td>148</td>\n",
              "      <td>72</td>\n",
              "      <td>35</td>\n",
              "      <td>0</td>\n",
              "      <td>33.6</td>\n",
              "      <td>0.627</td>\n",
              "      <td>50</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>85</td>\n",
              "      <td>66</td>\n",
              "      <td>29</td>\n",
              "      <td>0</td>\n",
              "      <td>26.6</td>\n",
              "      <td>0.351</td>\n",
              "      <td>31</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>8</td>\n",
              "      <td>183</td>\n",
              "      <td>64</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>23.3</td>\n",
              "      <td>0.672</td>\n",
              "      <td>32</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1</td>\n",
              "      <td>89</td>\n",
              "      <td>66</td>\n",
              "      <td>23</td>\n",
              "      <td>94</td>\n",
              "      <td>28.1</td>\n",
              "      <td>0.167</td>\n",
              "      <td>21</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0</td>\n",
              "      <td>137</td>\n",
              "      <td>40</td>\n",
              "      <td>35</td>\n",
              "      <td>168</td>\n",
              "      <td>43.1</td>\n",
              "      <td>2.288</td>\n",
              "      <td>33</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-7931c928-4ad9-437c-b6fb-427ad593504f')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-7931c928-4ad9-437c-b6fb-427ad593504f 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-7931c928-4ad9-437c-b6fb-427ad593504f');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-563eeae5-4e1f-4be8-b85f-851e9c26c1e5\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-563eeae5-4e1f-4be8-b85f-851e9c26c1e5')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-563eeae5-4e1f-4be8-b85f-851e9c26c1e5 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "data",
              "summary": "{\n  \"name\": \"data\",\n  \"rows\": 768,\n  \"fields\": [\n    {\n      \"column\": \"Preg\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 3,\n        \"min\": 0,\n        \"max\": 17,\n        \"num_unique_values\": 17,\n        \"samples\": [\n          6,\n          1,\n          3\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Plas\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 31,\n        \"min\": 0,\n        \"max\": 199,\n        \"num_unique_values\": 136,\n        \"samples\": [\n          151,\n          101,\n          112\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Pres\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 19,\n        \"min\": 0,\n        \"max\": 122,\n        \"num_unique_values\": 47,\n        \"samples\": [\n          86,\n          46,\n          85\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"skin\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 15,\n        \"min\": 0,\n        \"max\": 99,\n        \"num_unique_values\": 51,\n        \"samples\": [\n          7,\n          12,\n          48\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"test\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 115,\n        \"min\": 0,\n        \"max\": 846,\n        \"num_unique_values\": 186,\n        \"samples\": [\n          52,\n          41,\n          183\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"mass\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 7.884160320375446,\n        \"min\": 0.0,\n        \"max\": 67.1,\n        \"num_unique_values\": 248,\n        \"samples\": [\n          19.9,\n          31.0,\n          38.1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"pedi\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.3313285950127749,\n        \"min\": 0.078,\n        \"max\": 2.42,\n        \"num_unique_values\": 517,\n        \"samples\": [\n          1.731,\n          0.426,\n          0.138\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"age\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 11,\n        \"min\": 21,\n        \"max\": 81,\n        \"num_unique_values\": 52,\n        \"samples\": [\n          60,\n          47,\n          72\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"class\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0,\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "cor = data.corr()"
      ],
      "metadata": {
        "id": "svQbcnOTQhZv"
      },
      "execution_count": 47,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "cor"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 331
        },
        "id": "nc0dZ2jtQkBm",
        "outputId": "1ae8107f-0808-4616-d65e-4221154c857a"
      },
      "execution_count": 48,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "           Preg      Plas      Pres      skin      test      mass      pedi  \\\n",
              "Preg   1.000000  0.129459  0.141282 -0.081672 -0.073535  0.017683 -0.033523   \n",
              "Plas   0.129459  1.000000  0.152590  0.057328  0.331357  0.221071  0.137337   \n",
              "Pres   0.141282  0.152590  1.000000  0.207371  0.088933  0.281805  0.041265   \n",
              "skin  -0.081672  0.057328  0.207371  1.000000  0.436783  0.392573  0.183928   \n",
              "test  -0.073535  0.331357  0.088933  0.436783  1.000000  0.197859  0.185071   \n",
              "mass   0.017683  0.221071  0.281805  0.392573  0.197859  1.000000  0.140647   \n",
              "pedi  -0.033523  0.137337  0.041265  0.183928  0.185071  0.140647  1.000000   \n",
              "age    0.544341  0.263514  0.239528 -0.113970 -0.042163  0.036242  0.033561   \n",
              "class  0.221898  0.466581  0.065068  0.074752  0.130548  0.292695  0.173844   \n",
              "\n",
              "            age     class  \n",
              "Preg   0.544341  0.221898  \n",
              "Plas   0.263514  0.466581  \n",
              "Pres   0.239528  0.065068  \n",
              "skin  -0.113970  0.074752  \n",
              "test  -0.042163  0.130548  \n",
              "mass   0.036242  0.292695  \n",
              "pedi   0.033561  0.173844  \n",
              "age    1.000000  0.238356  \n",
              "class  0.238356  1.000000  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-1efeb5ad-03b5-4dc3-a04e-4d20ff080db4\" 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>Preg</th>\n",
              "      <th>Plas</th>\n",
              "      <th>Pres</th>\n",
              "      <th>skin</th>\n",
              "      <th>test</th>\n",
              "      <th>mass</th>\n",
              "      <th>pedi</th>\n",
              "      <th>age</th>\n",
              "      <th>class</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>Preg</th>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.129459</td>\n",
              "      <td>0.141282</td>\n",
              "      <td>-0.081672</td>\n",
              "      <td>-0.073535</td>\n",
              "      <td>0.017683</td>\n",
              "      <td>-0.033523</td>\n",
              "      <td>0.544341</td>\n",
              "      <td>0.221898</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Plas</th>\n",
              "      <td>0.129459</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.152590</td>\n",
              "      <td>0.057328</td>\n",
              "      <td>0.331357</td>\n",
              "      <td>0.221071</td>\n",
              "      <td>0.137337</td>\n",
              "      <td>0.263514</td>\n",
              "      <td>0.466581</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Pres</th>\n",
              "      <td>0.141282</td>\n",
              "      <td>0.152590</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.207371</td>\n",
              "      <td>0.088933</td>\n",
              "      <td>0.281805</td>\n",
              "      <td>0.041265</td>\n",
              "      <td>0.239528</td>\n",
              "      <td>0.065068</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>skin</th>\n",
              "      <td>-0.081672</td>\n",
              "      <td>0.057328</td>\n",
              "      <td>0.207371</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.436783</td>\n",
              "      <td>0.392573</td>\n",
              "      <td>0.183928</td>\n",
              "      <td>-0.113970</td>\n",
              "      <td>0.074752</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>test</th>\n",
              "      <td>-0.073535</td>\n",
              "      <td>0.331357</td>\n",
              "      <td>0.088933</td>\n",
              "      <td>0.436783</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.197859</td>\n",
              "      <td>0.185071</td>\n",
              "      <td>-0.042163</td>\n",
              "      <td>0.130548</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mass</th>\n",
              "      <td>0.017683</td>\n",
              "      <td>0.221071</td>\n",
              "      <td>0.281805</td>\n",
              "      <td>0.392573</td>\n",
              "      <td>0.197859</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.140647</td>\n",
              "      <td>0.036242</td>\n",
              "      <td>0.292695</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>pedi</th>\n",
              "      <td>-0.033523</td>\n",
              "      <td>0.137337</td>\n",
              "      <td>0.041265</td>\n",
              "      <td>0.183928</td>\n",
              "      <td>0.185071</td>\n",
              "      <td>0.140647</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.033561</td>\n",
              "      <td>0.173844</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>age</th>\n",
              "      <td>0.544341</td>\n",
              "      <td>0.263514</td>\n",
              "      <td>0.239528</td>\n",
              "      <td>-0.113970</td>\n",
              "      <td>-0.042163</td>\n",
              "      <td>0.036242</td>\n",
              "      <td>0.033561</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.238356</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>class</th>\n",
              "      <td>0.221898</td>\n",
              "      <td>0.466581</td>\n",
              "      <td>0.065068</td>\n",
              "      <td>0.074752</td>\n",
              "      <td>0.130548</td>\n",
              "      <td>0.292695</td>\n",
              "      <td>0.173844</td>\n",
              "      <td>0.238356</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-1efeb5ad-03b5-4dc3-a04e-4d20ff080db4')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-1efeb5ad-03b5-4dc3-a04e-4d20ff080db4 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-1efeb5ad-03b5-4dc3-a04e-4d20ff080db4');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-05c8cabd-d9ce-407a-a5ea-618b7439172d\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-05c8cabd-d9ce-407a-a5ea-618b7439172d')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-05c8cabd-d9ce-407a-a5ea-618b7439172d button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "  <div id=\"id_cf07c6a3-5d9f-4413-b70f-7729d9e4d2b5\">\n",
              "    <style>\n",
              "      .colab-df-generate {\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-generate: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-generate {\n",
              "        background-color: #3B4455;\n",
              "        fill: #D2E3FC;\n",
              "      }\n",
              "\n",
              "      [theme=dark] .colab-df-generate: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",
              "    <button class=\"colab-df-generate\" onclick=\"generateWithVariable('cor')\"\n",
              "            title=\"Generate code using this dataframe.\"\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=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "    <script>\n",
              "      (() => {\n",
              "      const buttonEl =\n",
              "        document.querySelector('#id_cf07c6a3-5d9f-4413-b70f-7729d9e4d2b5 button.colab-df-generate');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      buttonEl.onclick = () => {\n",
              "        google.colab.notebook.generateWithVariable('cor');\n",
              "      }\n",
              "      })();\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "cor",
              "summary": "{\n  \"name\": \"cor\",\n  \"rows\": 9,\n  \"fields\": [\n    {\n      \"column\": \"Preg\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.3551273944830802,\n        \"min\": -0.08167177444900726,\n        \"max\": 1.0,\n        \"num_unique_values\": 9,\n        \"samples\": [\n          0.5443412284023392,\n          0.12945867149927248,\n          0.017683090727830565\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Plas\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.28767750976254863,\n        \"min\": 0.05732789073817692,\n        \"max\": 1.0,\n        \"num_unique_values\": 9,\n        \"samples\": [\n          0.26351431982433343,\n          1.0,\n          0.2210710694589828\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Pres\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.2937568072929426,\n        \"min\": 0.04126494793009856,\n        \"max\": 1.0,\n        \"num_unique_values\": 9,\n        \"samples\": [\n          0.23952794642136344,\n          0.1525895865686646,\n          0.2818052888499109\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"skin\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.3415504031654345,\n        \"min\": -0.11397026236774152,\n        \"max\": 1.0,\n        \"num_unique_values\": 9,\n        \"samples\": [\n          -0.11397026236774152,\n          0.05732789073817692,\n          0.39257320415903835\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"test\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.3242652539286031,\n        \"min\": -0.07353461435162822,\n        \"max\": 1.0,\n        \"num_unique_values\": 9,\n        \"samples\": [\n          -0.04216295473537695,\n          0.3313571099202092,\n          0.19785905649310145\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"mass\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.29340599982594495,\n        \"min\": 0.017683090727830565,\n        \"max\": 1.0,\n        \"num_unique_values\": 9,\n        \"samples\": [\n          0.03624187009229395,\n          0.2210710694589828,\n          1.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"pedi\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.3073307082237146,\n        \"min\": -0.03352267296261304,\n        \"max\": 1.0,\n        \"num_unique_values\": 9,\n        \"samples\": [\n          0.03356131243480539,\n          0.13733729982837092,\n          0.14064695254510523\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"age\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.3463473783514741,\n        \"min\": -0.11397026236774152,\n        \"max\": 1.0,\n        \"num_unique_values\": 9,\n        \"samples\": [\n          1.0,\n          0.26351431982433343,\n          0.03624187009229395\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"class\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.2911432844711856,\n        \"min\": 0.06506835955033277,\n        \"max\": 1.0,\n        \"num_unique_values\": 9,\n        \"samples\": [\n          0.23835598302719757,\n          0.46658139830687373,\n          0.2926946626444454\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 48
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data.describe()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 300
        },
        "id": "SFxPTp7VIaZn",
        "outputId": "c267fb48-c03e-4397-8f73-516e0b236160"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "             Preg        Plas        Pres        skin        test        mass  \\\n",
              "count  768.000000  768.000000  768.000000  768.000000  768.000000  768.000000   \n",
              "mean     3.845052  120.894531   69.105469   20.536458   79.799479   31.992578   \n",
              "std      3.369578   31.972618   19.355807   15.952218  115.244002    7.884160   \n",
              "min      0.000000    0.000000    0.000000    0.000000    0.000000    0.000000   \n",
              "25%      1.000000   99.000000   62.000000    0.000000    0.000000   27.300000   \n",
              "50%      3.000000  117.000000   72.000000   23.000000   30.500000   32.000000   \n",
              "75%      6.000000  140.250000   80.000000   32.000000  127.250000   36.600000   \n",
              "max     17.000000  199.000000  122.000000   99.000000  846.000000   67.100000   \n",
              "\n",
              "             pedi         age       class  \n",
              "count  768.000000  768.000000  768.000000  \n",
              "mean     0.471876   33.240885    0.348958  \n",
              "std      0.331329   11.760232    0.476951  \n",
              "min      0.078000   21.000000    0.000000  \n",
              "25%      0.243750   24.000000    0.000000  \n",
              "50%      0.372500   29.000000    0.000000  \n",
              "75%      0.626250   41.000000    1.000000  \n",
              "max      2.420000   81.000000    1.000000  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-d3be9534-4430-46a0-9af0-feb89fd8055f\" 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>Preg</th>\n",
              "      <th>Plas</th>\n",
              "      <th>Pres</th>\n",
              "      <th>skin</th>\n",
              "      <th>test</th>\n",
              "      <th>mass</th>\n",
              "      <th>pedi</th>\n",
              "      <th>age</th>\n",
              "      <th>class</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>768.000000</td>\n",
              "      <td>768.000000</td>\n",
              "      <td>768.000000</td>\n",
              "      <td>768.000000</td>\n",
              "      <td>768.000000</td>\n",
              "      <td>768.000000</td>\n",
              "      <td>768.000000</td>\n",
              "      <td>768.000000</td>\n",
              "      <td>768.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>3.845052</td>\n",
              "      <td>120.894531</td>\n",
              "      <td>69.105469</td>\n",
              "      <td>20.536458</td>\n",
              "      <td>79.799479</td>\n",
              "      <td>31.992578</td>\n",
              "      <td>0.471876</td>\n",
              "      <td>33.240885</td>\n",
              "      <td>0.348958</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>3.369578</td>\n",
              "      <td>31.972618</td>\n",
              "      <td>19.355807</td>\n",
              "      <td>15.952218</td>\n",
              "      <td>115.244002</td>\n",
              "      <td>7.884160</td>\n",
              "      <td>0.331329</td>\n",
              "      <td>11.760232</td>\n",
              "      <td>0.476951</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.078000</td>\n",
              "      <td>21.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>1.000000</td>\n",
              "      <td>99.000000</td>\n",
              "      <td>62.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>27.300000</td>\n",
              "      <td>0.243750</td>\n",
              "      <td>24.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>3.000000</td>\n",
              "      <td>117.000000</td>\n",
              "      <td>72.000000</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>30.500000</td>\n",
              "      <td>32.000000</td>\n",
              "      <td>0.372500</td>\n",
              "      <td>29.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>6.000000</td>\n",
              "      <td>140.250000</td>\n",
              "      <td>80.000000</td>\n",
              "      <td>32.000000</td>\n",
              "      <td>127.250000</td>\n",
              "      <td>36.600000</td>\n",
              "      <td>0.626250</td>\n",
              "      <td>41.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>17.000000</td>\n",
              "      <td>199.000000</td>\n",
              "      <td>122.000000</td>\n",
              "      <td>99.000000</td>\n",
              "      <td>846.000000</td>\n",
              "      <td>67.100000</td>\n",
              "      <td>2.420000</td>\n",
              "      <td>81.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-d3be9534-4430-46a0-9af0-feb89fd8055f')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-d3be9534-4430-46a0-9af0-feb89fd8055f 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-d3be9534-4430-46a0-9af0-feb89fd8055f');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-bb34da2c-2a83-403e-a0c2-e941fc777956\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-bb34da2c-2a83-403e-a0c2-e941fc777956')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-bb34da2c-2a83-403e-a0c2-e941fc777956 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "summary": "{\n  \"name\": \"data\",\n  \"rows\": 8,\n  \"fields\": [\n    {\n      \"column\": \"Preg\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 269.85223453356366,\n        \"min\": 0.0,\n        \"max\": 768.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          3.8450520833333335,\n          3.0,\n          768.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Plas\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 243.73802348295857,\n        \"min\": 0.0,\n        \"max\": 768.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          120.89453125,\n          117.0,\n          768.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Pres\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 252.8525053581062,\n        \"min\": 0.0,\n        \"max\": 768.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          69.10546875,\n          72.0,\n          768.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"skin\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 263.7684730531098,\n        \"min\": 0.0,\n        \"max\": 768.0,\n        \"num_unique_values\": 7,\n        \"samples\": [\n          768.0,\n          20.536458333333332,\n          32.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"test\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 350.26059167945886,\n        \"min\": 0.0,\n        \"max\": 846.0,\n        \"num_unique_values\": 7,\n        \"samples\": [\n          768.0,\n          79.79947916666667,\n          127.25\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"mass\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 262.05117817552093,\n        \"min\": 0.0,\n        \"max\": 768.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          31.992578124999998,\n          32.0,\n          768.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"pedi\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 271.3005221658502,\n        \"min\": 0.078,\n        \"max\": 768.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          0.47187630208333325,\n          0.3725,\n          768.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"age\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 260.1941178528413,\n        \"min\": 11.760231540678685,\n        \"max\": 768.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          33.240885416666664,\n          29.0,\n          768.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"class\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 271.3865920388932,\n        \"min\": 0.0,\n        \"max\": 768.0,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          0.3489583333333333,\n          1.0,\n          0.47695137724279896\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X = data.drop('class',axis=1)"
      ],
      "metadata": {
        "id": "OVx8I3_IIk2T"
      },
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "poUtkSqtI1BH",
        "outputId": "87788103-4e25-4bb6-9c2b-0c7749c3a562"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   Preg  Plas  Pres  skin  test  mass   pedi  age\n",
              "0     6   148    72    35     0  33.6  0.627   50\n",
              "1     1    85    66    29     0  26.6  0.351   31\n",
              "2     8   183    64     0     0  23.3  0.672   32\n",
              "3     1    89    66    23    94  28.1  0.167   21\n",
              "4     0   137    40    35   168  43.1  2.288   33"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-9e2a5c26-84e8-43f2-b8a5-8cd4594b5c8e\" 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>Preg</th>\n",
              "      <th>Plas</th>\n",
              "      <th>Pres</th>\n",
              "      <th>skin</th>\n",
              "      <th>test</th>\n",
              "      <th>mass</th>\n",
              "      <th>pedi</th>\n",
              "      <th>age</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>6</td>\n",
              "      <td>148</td>\n",
              "      <td>72</td>\n",
              "      <td>35</td>\n",
              "      <td>0</td>\n",
              "      <td>33.6</td>\n",
              "      <td>0.627</td>\n",
              "      <td>50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>85</td>\n",
              "      <td>66</td>\n",
              "      <td>29</td>\n",
              "      <td>0</td>\n",
              "      <td>26.6</td>\n",
              "      <td>0.351</td>\n",
              "      <td>31</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>8</td>\n",
              "      <td>183</td>\n",
              "      <td>64</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>23.3</td>\n",
              "      <td>0.672</td>\n",
              "      <td>32</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1</td>\n",
              "      <td>89</td>\n",
              "      <td>66</td>\n",
              "      <td>23</td>\n",
              "      <td>94</td>\n",
              "      <td>28.1</td>\n",
              "      <td>0.167</td>\n",
              "      <td>21</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0</td>\n",
              "      <td>137</td>\n",
              "      <td>40</td>\n",
              "      <td>35</td>\n",
              "      <td>168</td>\n",
              "      <td>43.1</td>\n",
              "      <td>2.288</td>\n",
              "      <td>33</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-9e2a5c26-84e8-43f2-b8a5-8cd4594b5c8e')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-9e2a5c26-84e8-43f2-b8a5-8cd4594b5c8e 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-9e2a5c26-84e8-43f2-b8a5-8cd4594b5c8e');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-656f4b9b-aed8-4f6b-a218-15d173397064\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-656f4b9b-aed8-4f6b-a218-15d173397064')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-656f4b9b-aed8-4f6b-a218-15d173397064 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "X",
              "summary": "{\n  \"name\": \"X\",\n  \"rows\": 768,\n  \"fields\": [\n    {\n      \"column\": \"Preg\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 3,\n        \"min\": 0,\n        \"max\": 17,\n        \"num_unique_values\": 17,\n        \"samples\": [\n          6,\n          1,\n          3\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Plas\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 31,\n        \"min\": 0,\n        \"max\": 199,\n        \"num_unique_values\": 136,\n        \"samples\": [\n          151,\n          101,\n          112\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Pres\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 19,\n        \"min\": 0,\n        \"max\": 122,\n        \"num_unique_values\": 47,\n        \"samples\": [\n          86,\n          46,\n          85\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"skin\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 15,\n        \"min\": 0,\n        \"max\": 99,\n        \"num_unique_values\": 51,\n        \"samples\": [\n          7,\n          12,\n          48\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"test\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 115,\n        \"min\": 0,\n        \"max\": 846,\n        \"num_unique_values\": 186,\n        \"samples\": [\n          52,\n          41,\n          183\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"mass\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 7.884160320375446,\n        \"min\": 0.0,\n        \"max\": 67.1,\n        \"num_unique_values\": 248,\n        \"samples\": [\n          19.9,\n          31.0,\n          38.1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"pedi\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.3313285950127749,\n        \"min\": 0.078,\n        \"max\": 2.42,\n        \"num_unique_values\": 517,\n        \"samples\": [\n          1.731,\n          0.426,\n          0.138\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"age\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 11,\n        \"min\": 21,\n        \"max\": 81,\n        \"num_unique_values\": 52,\n        \"samples\": [\n          60,\n          47,\n          72\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y = data[['class']]"
      ],
      "metadata": {
        "id": "aIfAN1RFI2iq"
      },
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "y.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "fRq25F-SI7Il",
        "outputId": "12ab5437-8f1d-4031-edcf-dedc068cf863"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   class\n",
              "0      1\n",
              "1      0\n",
              "2      1\n",
              "3      0\n",
              "4      1"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-fac4bfc1-a3e7-482c-8248-22f9afda3047\" 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>class</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-fac4bfc1-a3e7-482c-8248-22f9afda3047')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-fac4bfc1-a3e7-482c-8248-22f9afda3047 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-fac4bfc1-a3e7-482c-8248-22f9afda3047');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-6c4ebcfb-a586-4197-8d88-0658d14f8a92\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-6c4ebcfb-a586-4197-8d88-0658d14f8a92')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-6c4ebcfb-a586-4197-8d88-0658d14f8a92 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "y",
              "summary": "{\n  \"name\": \"y\",\n  \"rows\": 768,\n  \"fields\": [\n    {\n      \"column\": \"class\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0,\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow.keras.layers import Dense"
      ],
      "metadata": {
        "id": "paNg7lMII9PE"
      },
      "execution_count": 11,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow.keras.models import Sequential"
      ],
      "metadata": {
        "id": "iwRPbHJpJUZD"
      },
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model = Sequential()"
      ],
      "metadata": {
        "id": "1MmGSTSmJpbZ"
      },
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model.add(Dense(12,activation='relu',input_dim=8))\n",
        "model.add(Dense(10,activation='relu'))\n",
        "model.add(Dense(1,activation='sigmoid'))\n"
      ],
      "metadata": {
        "id": "QTysE0RIJ1Tq"
      },
      "execution_count": 15,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model.summary()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8QgBNa2AKxb-",
        "outputId": "733fe4e0-6c17-4915-cc1f-dcc6fb636465"
      },
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model: \"sequential\"\n",
            "_________________________________________________________________\n",
            " Layer (type)                Output Shape              Param #   \n",
            "=================================================================\n",
            " dense (Dense)               (None, 12)                108       \n",
            "                                                                 \n",
            " dense_1 (Dense)             (None, 10)                130       \n",
            "                                                                 \n",
            " dense_2 (Dense)             (None, 1)                 11        \n",
            "                                                                 \n",
            "=================================================================\n",
            "Total params: 249 (996.00 Byte)\n",
            "Trainable params: 249 (996.00 Byte)\n",
            "Non-trainable params: 0 (0.00 Byte)\n",
            "_________________________________________________________________\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])"
      ],
      "metadata": {
        "id": "9TJDJvTpK0or"
      },
      "execution_count": 31,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import train_test_split"
      ],
      "metadata": {
        "id": "kebxf56mL7j-"
      },
      "execution_count": 32,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=40)"
      ],
      "metadata": {
        "id": "CI2sqKB-MXPJ"
      },
      "execution_count": 33,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X_train.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "epzOxg1UMq89",
        "outputId": "c9e17597-46d5-4134-cfae-8e3e255bbf8c"
      },
      "execution_count": 34,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(614, 8)"
            ]
          },
          "metadata": {},
          "execution_count": 34
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X_test.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "aobQr3VHMtBh",
        "outputId": "a2fa95b3-53f0-4379-b4a8-cba04394efdf"
      },
      "execution_count": 35,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(154, 8)"
            ]
          },
          "metadata": {},
          "execution_count": 35
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "H = model.fit(X_train,y_train,epochs=500,batch_size=46,validation_data=(X_test,y_test))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "amJELoRdMvwH",
        "outputId": "fd288625-bd91-4aff-cd82-c304b854888d"
      },
      "execution_count": 36,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/500\n",
            "14/14 [==============================] - 1s 25ms/step - loss: 2.3065 - accuracy: 0.6254 - val_loss: 1.4190 - val_accuracy: 0.7013\n",
            "Epoch 2/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 1.8026 - accuracy: 0.6221 - val_loss: 1.2917 - val_accuracy: 0.6558\n",
            "Epoch 3/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 1.4369 - accuracy: 0.6303 - val_loss: 1.0013 - val_accuracy: 0.6818\n",
            "Epoch 4/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 1.1122 - accuracy: 0.6221 - val_loss: 0.9299 - val_accuracy: 0.6494\n",
            "Epoch 5/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.9916 - accuracy: 0.6270 - val_loss: 0.8219 - val_accuracy: 0.6169\n",
            "Epoch 6/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.8841 - accuracy: 0.6270 - val_loss: 0.7915 - val_accuracy: 0.6364\n",
            "Epoch 7/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.8421 - accuracy: 0.6417 - val_loss: 0.8951 - val_accuracy: 0.6169\n",
            "Epoch 8/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.7786 - accuracy: 0.6482 - val_loss: 0.7503 - val_accuracy: 0.6169\n",
            "Epoch 9/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.7491 - accuracy: 0.6254 - val_loss: 0.7751 - val_accuracy: 0.5974\n",
            "Epoch 10/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.7206 - accuracy: 0.6417 - val_loss: 0.7711 - val_accuracy: 0.6104\n",
            "Epoch 11/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.7192 - accuracy: 0.6515 - val_loss: 0.7271 - val_accuracy: 0.6234\n",
            "Epoch 12/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.6994 - accuracy: 0.6629 - val_loss: 0.7444 - val_accuracy: 0.5909\n",
            "Epoch 13/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.6988 - accuracy: 0.6498 - val_loss: 0.7800 - val_accuracy: 0.6169\n",
            "Epoch 14/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.6936 - accuracy: 0.6629 - val_loss: 0.7410 - val_accuracy: 0.6039\n",
            "Epoch 15/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.6802 - accuracy: 0.6612 - val_loss: 0.7063 - val_accuracy: 0.6234\n",
            "Epoch 16/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.6805 - accuracy: 0.6384 - val_loss: 0.7210 - val_accuracy: 0.5974\n",
            "Epoch 17/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.6697 - accuracy: 0.6629 - val_loss: 0.7251 - val_accuracy: 0.5974\n",
            "Epoch 18/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.6679 - accuracy: 0.6629 - val_loss: 0.7701 - val_accuracy: 0.6234\n",
            "Epoch 19/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.6828 - accuracy: 0.6710 - val_loss: 0.6992 - val_accuracy: 0.6234\n",
            "Epoch 20/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.6636 - accuracy: 0.6726 - val_loss: 0.7938 - val_accuracy: 0.6104\n",
            "Epoch 21/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.6741 - accuracy: 0.6645 - val_loss: 0.7043 - val_accuracy: 0.6429\n",
            "Epoch 22/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.6646 - accuracy: 0.6808 - val_loss: 0.7891 - val_accuracy: 0.6299\n",
            "Epoch 23/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.6723 - accuracy: 0.6889 - val_loss: 0.6865 - val_accuracy: 0.6364\n",
            "Epoch 24/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.6661 - accuracy: 0.6759 - val_loss: 0.6875 - val_accuracy: 0.6234\n",
            "Epoch 25/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.6576 - accuracy: 0.6661 - val_loss: 0.6773 - val_accuracy: 0.6234\n",
            "Epoch 26/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.6428 - accuracy: 0.6808 - val_loss: 0.6740 - val_accuracy: 0.6299\n",
            "Epoch 27/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.6332 - accuracy: 0.6824 - val_loss: 0.6945 - val_accuracy: 0.6169\n",
            "Epoch 28/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.6291 - accuracy: 0.6938 - val_loss: 0.6738 - val_accuracy: 0.6234\n",
            "Epoch 29/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.6316 - accuracy: 0.6873 - val_loss: 0.6811 - val_accuracy: 0.6234\n",
            "Epoch 30/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.6499 - accuracy: 0.6759 - val_loss: 0.6783 - val_accuracy: 0.6299\n",
            "Epoch 31/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.6283 - accuracy: 0.6759 - val_loss: 0.7005 - val_accuracy: 0.6364\n",
            "Epoch 32/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.6247 - accuracy: 0.6824 - val_loss: 0.6997 - val_accuracy: 0.6364\n",
            "Epoch 33/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.6253 - accuracy: 0.6889 - val_loss: 0.6669 - val_accuracy: 0.6364\n",
            "Epoch 34/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.6147 - accuracy: 0.6824 - val_loss: 0.6608 - val_accuracy: 0.6364\n",
            "Epoch 35/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.6120 - accuracy: 0.6954 - val_loss: 0.6661 - val_accuracy: 0.6234\n",
            "Epoch 36/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.6177 - accuracy: 0.6808 - val_loss: 0.6598 - val_accuracy: 0.6299\n",
            "Epoch 37/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.6065 - accuracy: 0.6987 - val_loss: 0.6850 - val_accuracy: 0.6364\n",
            "Epoch 38/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.6194 - accuracy: 0.6938 - val_loss: 0.6864 - val_accuracy: 0.6364\n",
            "Epoch 39/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.6082 - accuracy: 0.6971 - val_loss: 0.6525 - val_accuracy: 0.6364\n",
            "Epoch 40/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.6053 - accuracy: 0.6954 - val_loss: 0.6697 - val_accuracy: 0.6364\n",
            "Epoch 41/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.6067 - accuracy: 0.7003 - val_loss: 0.6490 - val_accuracy: 0.6364\n",
            "Epoch 42/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5989 - accuracy: 0.6906 - val_loss: 0.6537 - val_accuracy: 0.6364\n",
            "Epoch 43/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5996 - accuracy: 0.7003 - val_loss: 0.6479 - val_accuracy: 0.6364\n",
            "Epoch 44/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5987 - accuracy: 0.6889 - val_loss: 0.6501 - val_accuracy: 0.6494\n",
            "Epoch 45/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.6016 - accuracy: 0.6971 - val_loss: 0.6525 - val_accuracy: 0.6364\n",
            "Epoch 46/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5970 - accuracy: 0.7101 - val_loss: 0.6476 - val_accuracy: 0.6299\n",
            "Epoch 47/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.5986 - accuracy: 0.7101 - val_loss: 0.6461 - val_accuracy: 0.6299\n",
            "Epoch 48/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.5951 - accuracy: 0.7085 - val_loss: 0.6474 - val_accuracy: 0.6364\n",
            "Epoch 49/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.6034 - accuracy: 0.7117 - val_loss: 0.6407 - val_accuracy: 0.6364\n",
            "Epoch 50/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.6037 - accuracy: 0.6987 - val_loss: 0.6653 - val_accuracy: 0.6299\n",
            "Epoch 51/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.5952 - accuracy: 0.7134 - val_loss: 0.6507 - val_accuracy: 0.6494\n",
            "Epoch 52/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.5848 - accuracy: 0.7101 - val_loss: 0.6321 - val_accuracy: 0.6494\n",
            "Epoch 53/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.5964 - accuracy: 0.6987 - val_loss: 0.6632 - val_accuracy: 0.6364\n",
            "Epoch 54/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.6051 - accuracy: 0.7036 - val_loss: 0.6854 - val_accuracy: 0.6429\n",
            "Epoch 55/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.6071 - accuracy: 0.7150 - val_loss: 0.6438 - val_accuracy: 0.6429\n",
            "Epoch 56/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.5877 - accuracy: 0.7101 - val_loss: 0.6345 - val_accuracy: 0.6623\n",
            "Epoch 57/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5960 - accuracy: 0.7134 - val_loss: 0.6597 - val_accuracy: 0.6623\n",
            "Epoch 58/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.6008 - accuracy: 0.7068 - val_loss: 0.6400 - val_accuracy: 0.6688\n",
            "Epoch 59/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.5947 - accuracy: 0.7052 - val_loss: 0.6332 - val_accuracy: 0.6429\n",
            "Epoch 60/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.5790 - accuracy: 0.7052 - val_loss: 0.6227 - val_accuracy: 0.6299\n",
            "Epoch 61/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.5790 - accuracy: 0.7117 - val_loss: 0.6254 - val_accuracy: 0.6494\n",
            "Epoch 62/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.5985 - accuracy: 0.7085 - val_loss: 0.6482 - val_accuracy: 0.6688\n",
            "Epoch 63/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.6033 - accuracy: 0.7068 - val_loss: 0.6218 - val_accuracy: 0.6688\n",
            "Epoch 64/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.6084 - accuracy: 0.7020 - val_loss: 0.6468 - val_accuracy: 0.6494\n",
            "Epoch 65/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.6115 - accuracy: 0.7101 - val_loss: 0.8318 - val_accuracy: 0.6364\n",
            "Epoch 66/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.6182 - accuracy: 0.6775 - val_loss: 0.6258 - val_accuracy: 0.6558\n",
            "Epoch 67/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.5810 - accuracy: 0.7231 - val_loss: 0.6280 - val_accuracy: 0.6429\n",
            "Epoch 68/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.5930 - accuracy: 0.7134 - val_loss: 0.6318 - val_accuracy: 0.6818\n",
            "Epoch 69/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.5941 - accuracy: 0.7182 - val_loss: 0.6215 - val_accuracy: 0.6558\n",
            "Epoch 70/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5887 - accuracy: 0.7052 - val_loss: 0.6896 - val_accuracy: 0.6558\n",
            "Epoch 71/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5719 - accuracy: 0.7231 - val_loss: 0.6192 - val_accuracy: 0.6364\n",
            "Epoch 72/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5762 - accuracy: 0.7199 - val_loss: 0.6451 - val_accuracy: 0.6494\n",
            "Epoch 73/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5761 - accuracy: 0.7231 - val_loss: 0.6204 - val_accuracy: 0.6364\n",
            "Epoch 74/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5713 - accuracy: 0.7264 - val_loss: 0.6169 - val_accuracy: 0.6494\n",
            "Epoch 75/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5634 - accuracy: 0.7296 - val_loss: 0.6251 - val_accuracy: 0.6429\n",
            "Epoch 76/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5642 - accuracy: 0.7231 - val_loss: 0.6186 - val_accuracy: 0.6494\n",
            "Epoch 77/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5655 - accuracy: 0.7231 - val_loss: 0.6286 - val_accuracy: 0.6623\n",
            "Epoch 78/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5710 - accuracy: 0.7231 - val_loss: 0.6740 - val_accuracy: 0.6494\n",
            "Epoch 79/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5670 - accuracy: 0.7362 - val_loss: 0.6206 - val_accuracy: 0.6429\n",
            "Epoch 80/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5637 - accuracy: 0.7378 - val_loss: 0.6244 - val_accuracy: 0.6753\n",
            "Epoch 81/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.5857 - accuracy: 0.7068 - val_loss: 0.6094 - val_accuracy: 0.6688\n",
            "Epoch 82/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5822 - accuracy: 0.7134 - val_loss: 0.6131 - val_accuracy: 0.6623\n",
            "Epoch 83/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5757 - accuracy: 0.7313 - val_loss: 0.6858 - val_accuracy: 0.6364\n",
            "Epoch 84/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5813 - accuracy: 0.7313 - val_loss: 0.6081 - val_accuracy: 0.6623\n",
            "Epoch 85/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5738 - accuracy: 0.7134 - val_loss: 0.6123 - val_accuracy: 0.6364\n",
            "Epoch 86/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5617 - accuracy: 0.7313 - val_loss: 0.6229 - val_accuracy: 0.6494\n",
            "Epoch 87/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5561 - accuracy: 0.7264 - val_loss: 0.6462 - val_accuracy: 0.6494\n",
            "Epoch 88/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5637 - accuracy: 0.7101 - val_loss: 0.6505 - val_accuracy: 0.6429\n",
            "Epoch 89/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5650 - accuracy: 0.7248 - val_loss: 0.6230 - val_accuracy: 0.6558\n",
            "Epoch 90/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5518 - accuracy: 0.7329 - val_loss: 0.6141 - val_accuracy: 0.6753\n",
            "Epoch 91/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5611 - accuracy: 0.7410 - val_loss: 0.6167 - val_accuracy: 0.6818\n",
            "Epoch 92/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5514 - accuracy: 0.7313 - val_loss: 0.6529 - val_accuracy: 0.6429\n",
            "Epoch 93/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5682 - accuracy: 0.7264 - val_loss: 0.6624 - val_accuracy: 0.6558\n",
            "Epoch 94/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5523 - accuracy: 0.7362 - val_loss: 0.6130 - val_accuracy: 0.6364\n",
            "Epoch 95/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5524 - accuracy: 0.7296 - val_loss: 0.6125 - val_accuracy: 0.6429\n",
            "Epoch 96/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5609 - accuracy: 0.7394 - val_loss: 0.6153 - val_accuracy: 0.6883\n",
            "Epoch 97/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5591 - accuracy: 0.7394 - val_loss: 0.6436 - val_accuracy: 0.6818\n",
            "Epoch 98/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5842 - accuracy: 0.7280 - val_loss: 0.6243 - val_accuracy: 0.6364\n",
            "Epoch 99/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5460 - accuracy: 0.7248 - val_loss: 0.6159 - val_accuracy: 0.6623\n",
            "Epoch 100/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5448 - accuracy: 0.7427 - val_loss: 0.6265 - val_accuracy: 0.6364\n",
            "Epoch 101/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.5478 - accuracy: 0.7362 - val_loss: 0.6124 - val_accuracy: 0.6234\n",
            "Epoch 102/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.5480 - accuracy: 0.7410 - val_loss: 0.6224 - val_accuracy: 0.6429\n",
            "Epoch 103/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5530 - accuracy: 0.7378 - val_loss: 0.6130 - val_accuracy: 0.6494\n",
            "Epoch 104/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5577 - accuracy: 0.7215 - val_loss: 0.7214 - val_accuracy: 0.6688\n",
            "Epoch 105/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5748 - accuracy: 0.7394 - val_loss: 0.6798 - val_accuracy: 0.6623\n",
            "Epoch 106/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5550 - accuracy: 0.7296 - val_loss: 0.6833 - val_accuracy: 0.6623\n",
            "Epoch 107/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5443 - accuracy: 0.7476 - val_loss: 0.6147 - val_accuracy: 0.6494\n",
            "Epoch 108/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5385 - accuracy: 0.7394 - val_loss: 0.6049 - val_accuracy: 0.6623\n",
            "Epoch 109/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5365 - accuracy: 0.7492 - val_loss: 0.6339 - val_accuracy: 0.6623\n",
            "Epoch 110/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5444 - accuracy: 0.7362 - val_loss: 0.6119 - val_accuracy: 0.6623\n",
            "Epoch 111/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5450 - accuracy: 0.7443 - val_loss: 0.6150 - val_accuracy: 0.6818\n",
            "Epoch 112/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5378 - accuracy: 0.7362 - val_loss: 0.6751 - val_accuracy: 0.6623\n",
            "Epoch 113/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5413 - accuracy: 0.7410 - val_loss: 0.6100 - val_accuracy: 0.6364\n",
            "Epoch 114/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5344 - accuracy: 0.7345 - val_loss: 0.6074 - val_accuracy: 0.6299\n",
            "Epoch 115/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5340 - accuracy: 0.7476 - val_loss: 0.6031 - val_accuracy: 0.6429\n",
            "Epoch 116/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5352 - accuracy: 0.7476 - val_loss: 0.6100 - val_accuracy: 0.6494\n",
            "Epoch 117/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5301 - accuracy: 0.7410 - val_loss: 0.6238 - val_accuracy: 0.6299\n",
            "Epoch 118/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5338 - accuracy: 0.7345 - val_loss: 0.6089 - val_accuracy: 0.6883\n",
            "Epoch 119/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5526 - accuracy: 0.7459 - val_loss: 0.6401 - val_accuracy: 0.6494\n",
            "Epoch 120/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5259 - accuracy: 0.7443 - val_loss: 0.6060 - val_accuracy: 0.6623\n",
            "Epoch 121/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5364 - accuracy: 0.7492 - val_loss: 0.6628 - val_accuracy: 0.6299\n",
            "Epoch 122/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5361 - accuracy: 0.7524 - val_loss: 0.6442 - val_accuracy: 0.6558\n",
            "Epoch 123/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.5360 - accuracy: 0.7410 - val_loss: 0.6098 - val_accuracy: 0.6494\n",
            "Epoch 124/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.5342 - accuracy: 0.7459 - val_loss: 0.6411 - val_accuracy: 0.6364\n",
            "Epoch 125/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.5328 - accuracy: 0.7410 - val_loss: 0.6107 - val_accuracy: 0.6623\n",
            "Epoch 126/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.5440 - accuracy: 0.7427 - val_loss: 0.6029 - val_accuracy: 0.6688\n",
            "Epoch 127/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5374 - accuracy: 0.7410 - val_loss: 0.6034 - val_accuracy: 0.6883\n",
            "Epoch 128/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.5283 - accuracy: 0.7459 - val_loss: 0.6230 - val_accuracy: 0.6234\n",
            "Epoch 129/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5314 - accuracy: 0.7296 - val_loss: 0.6234 - val_accuracy: 0.6364\n",
            "Epoch 130/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5273 - accuracy: 0.7492 - val_loss: 0.6150 - val_accuracy: 0.6494\n",
            "Epoch 131/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5237 - accuracy: 0.7606 - val_loss: 0.6063 - val_accuracy: 0.6623\n",
            "Epoch 132/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5387 - accuracy: 0.7427 - val_loss: 0.6025 - val_accuracy: 0.6818\n",
            "Epoch 133/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5367 - accuracy: 0.7378 - val_loss: 0.6084 - val_accuracy: 0.6883\n",
            "Epoch 134/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5356 - accuracy: 0.7410 - val_loss: 0.6057 - val_accuracy: 0.6623\n",
            "Epoch 135/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5563 - accuracy: 0.7362 - val_loss: 0.8335 - val_accuracy: 0.6494\n",
            "Epoch 136/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5552 - accuracy: 0.7476 - val_loss: 0.6138 - val_accuracy: 0.6753\n",
            "Epoch 137/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.5349 - accuracy: 0.7296 - val_loss: 0.6283 - val_accuracy: 0.6234\n",
            "Epoch 138/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.5324 - accuracy: 0.7573 - val_loss: 0.6174 - val_accuracy: 0.6494\n",
            "Epoch 139/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5449 - accuracy: 0.7427 - val_loss: 0.6041 - val_accuracy: 0.6753\n",
            "Epoch 140/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5550 - accuracy: 0.7345 - val_loss: 0.6234 - val_accuracy: 0.6948\n",
            "Epoch 141/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.5344 - accuracy: 0.7476 - val_loss: 0.6503 - val_accuracy: 0.6688\n",
            "Epoch 142/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.5207 - accuracy: 0.7476 - val_loss: 0.6599 - val_accuracy: 0.6688\n",
            "Epoch 143/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5189 - accuracy: 0.7443 - val_loss: 0.6333 - val_accuracy: 0.6364\n",
            "Epoch 144/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5160 - accuracy: 0.7443 - val_loss: 0.6170 - val_accuracy: 0.6429\n",
            "Epoch 145/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5170 - accuracy: 0.7492 - val_loss: 0.6055 - val_accuracy: 0.6623\n",
            "Epoch 146/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.5300 - accuracy: 0.7573 - val_loss: 0.6065 - val_accuracy: 0.6494\n",
            "Epoch 147/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5221 - accuracy: 0.7459 - val_loss: 0.6629 - val_accuracy: 0.6818\n",
            "Epoch 148/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5310 - accuracy: 0.7443 - val_loss: 0.6543 - val_accuracy: 0.6364\n",
            "Epoch 149/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5188 - accuracy: 0.7459 - val_loss: 0.6016 - val_accuracy: 0.6558\n",
            "Epoch 150/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5180 - accuracy: 0.7410 - val_loss: 0.6186 - val_accuracy: 0.6299\n",
            "Epoch 151/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5106 - accuracy: 0.7459 - val_loss: 0.6021 - val_accuracy: 0.6753\n",
            "Epoch 152/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5227 - accuracy: 0.7443 - val_loss: 0.6257 - val_accuracy: 0.6558\n",
            "Epoch 153/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5156 - accuracy: 0.7443 - val_loss: 0.6241 - val_accuracy: 0.6494\n",
            "Epoch 154/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.5137 - accuracy: 0.7508 - val_loss: 0.6443 - val_accuracy: 0.6558\n",
            "Epoch 155/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5093 - accuracy: 0.7541 - val_loss: 0.6183 - val_accuracy: 0.6299\n",
            "Epoch 156/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5112 - accuracy: 0.7508 - val_loss: 0.6062 - val_accuracy: 0.6494\n",
            "Epoch 157/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5290 - accuracy: 0.7427 - val_loss: 0.6569 - val_accuracy: 0.6558\n",
            "Epoch 158/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5263 - accuracy: 0.7345 - val_loss: 0.6342 - val_accuracy: 0.6558\n",
            "Epoch 159/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5176 - accuracy: 0.7508 - val_loss: 0.7120 - val_accuracy: 0.6688\n",
            "Epoch 160/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5226 - accuracy: 0.7508 - val_loss: 0.6652 - val_accuracy: 0.6623\n",
            "Epoch 161/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5127 - accuracy: 0.7459 - val_loss: 0.6224 - val_accuracy: 0.6429\n",
            "Epoch 162/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5258 - accuracy: 0.7476 - val_loss: 0.6019 - val_accuracy: 0.6429\n",
            "Epoch 163/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.5038 - accuracy: 0.7524 - val_loss: 0.6540 - val_accuracy: 0.6623\n",
            "Epoch 164/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.5286 - accuracy: 0.7476 - val_loss: 0.5975 - val_accuracy: 0.6623\n",
            "Epoch 165/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5127 - accuracy: 0.7541 - val_loss: 0.6539 - val_accuracy: 0.6753\n",
            "Epoch 166/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5301 - accuracy: 0.7410 - val_loss: 0.6858 - val_accuracy: 0.6753\n",
            "Epoch 167/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5302 - accuracy: 0.7459 - val_loss: 0.5940 - val_accuracy: 0.6753\n",
            "Epoch 168/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5081 - accuracy: 0.7573 - val_loss: 0.5965 - val_accuracy: 0.6753\n",
            "Epoch 169/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.5094 - accuracy: 0.7476 - val_loss: 0.6278 - val_accuracy: 0.6623\n",
            "Epoch 170/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5315 - accuracy: 0.7362 - val_loss: 0.8003 - val_accuracy: 0.6623\n",
            "Epoch 171/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5335 - accuracy: 0.7492 - val_loss: 0.6018 - val_accuracy: 0.6753\n",
            "Epoch 172/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5043 - accuracy: 0.7541 - val_loss: 0.5941 - val_accuracy: 0.6753\n",
            "Epoch 173/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.5022 - accuracy: 0.7508 - val_loss: 0.6454 - val_accuracy: 0.6623\n",
            "Epoch 174/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.5031 - accuracy: 0.7557 - val_loss: 0.6199 - val_accuracy: 0.6753\n",
            "Epoch 175/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.5076 - accuracy: 0.7541 - val_loss: 0.6120 - val_accuracy: 0.6753\n",
            "Epoch 176/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.5060 - accuracy: 0.7476 - val_loss: 0.6014 - val_accuracy: 0.6623\n",
            "Epoch 177/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.5043 - accuracy: 0.7410 - val_loss: 0.5870 - val_accuracy: 0.6753\n",
            "Epoch 178/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.5250 - accuracy: 0.7394 - val_loss: 0.6042 - val_accuracy: 0.6753\n",
            "Epoch 179/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.5115 - accuracy: 0.7508 - val_loss: 0.6602 - val_accuracy: 0.6688\n",
            "Epoch 180/500\n",
            "14/14 [==============================] - 0s 12ms/step - loss: 0.5053 - accuracy: 0.7541 - val_loss: 0.6862 - val_accuracy: 0.6818\n",
            "Epoch 181/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.5125 - accuracy: 0.7459 - val_loss: 0.6112 - val_accuracy: 0.6818\n",
            "Epoch 182/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.4996 - accuracy: 0.7524 - val_loss: 0.6406 - val_accuracy: 0.6753\n",
            "Epoch 183/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.4987 - accuracy: 0.7573 - val_loss: 0.5880 - val_accuracy: 0.6688\n",
            "Epoch 184/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.5015 - accuracy: 0.7492 - val_loss: 0.6421 - val_accuracy: 0.6818\n",
            "Epoch 185/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4998 - accuracy: 0.7476 - val_loss: 0.6567 - val_accuracy: 0.6753\n",
            "Epoch 186/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.5138 - accuracy: 0.7524 - val_loss: 0.6865 - val_accuracy: 0.6818\n",
            "Epoch 187/500\n",
            "14/14 [==============================] - 0s 13ms/step - loss: 0.5093 - accuracy: 0.7736 - val_loss: 0.5821 - val_accuracy: 0.6883\n",
            "Epoch 188/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.5088 - accuracy: 0.7524 - val_loss: 0.5910 - val_accuracy: 0.6753\n",
            "Epoch 189/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.5124 - accuracy: 0.7476 - val_loss: 0.6439 - val_accuracy: 0.6753\n",
            "Epoch 190/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.5006 - accuracy: 0.7541 - val_loss: 0.5969 - val_accuracy: 0.6753\n",
            "Epoch 191/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4984 - accuracy: 0.7606 - val_loss: 0.5936 - val_accuracy: 0.7013\n",
            "Epoch 192/500\n",
            "14/14 [==============================] - 0s 12ms/step - loss: 0.5224 - accuracy: 0.7541 - val_loss: 0.6422 - val_accuracy: 0.6883\n",
            "Epoch 193/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4978 - accuracy: 0.7590 - val_loss: 0.5959 - val_accuracy: 0.6623\n",
            "Epoch 194/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4938 - accuracy: 0.7573 - val_loss: 0.6496 - val_accuracy: 0.6753\n",
            "Epoch 195/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.5058 - accuracy: 0.7557 - val_loss: 0.6375 - val_accuracy: 0.6753\n",
            "Epoch 196/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5076 - accuracy: 0.7492 - val_loss: 0.5914 - val_accuracy: 0.6753\n",
            "Epoch 197/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5102 - accuracy: 0.7622 - val_loss: 0.6010 - val_accuracy: 0.6753\n",
            "Epoch 198/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5001 - accuracy: 0.7573 - val_loss: 0.5900 - val_accuracy: 0.6688\n",
            "Epoch 199/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5055 - accuracy: 0.7638 - val_loss: 0.6824 - val_accuracy: 0.6883\n",
            "Epoch 200/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5107 - accuracy: 0.7524 - val_loss: 0.6330 - val_accuracy: 0.6818\n",
            "Epoch 201/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5004 - accuracy: 0.7492 - val_loss: 0.5969 - val_accuracy: 0.6753\n",
            "Epoch 202/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4937 - accuracy: 0.7573 - val_loss: 0.6202 - val_accuracy: 0.6948\n",
            "Epoch 203/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.4984 - accuracy: 0.7557 - val_loss: 0.6399 - val_accuracy: 0.6753\n",
            "Epoch 204/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4988 - accuracy: 0.7638 - val_loss: 0.5982 - val_accuracy: 0.6753\n",
            "Epoch 205/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.4921 - accuracy: 0.7524 - val_loss: 0.6462 - val_accuracy: 0.6818\n",
            "Epoch 206/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.5034 - accuracy: 0.7573 - val_loss: 0.6267 - val_accuracy: 0.6753\n",
            "Epoch 207/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5001 - accuracy: 0.7508 - val_loss: 0.6410 - val_accuracy: 0.6623\n",
            "Epoch 208/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5041 - accuracy: 0.7573 - val_loss: 0.5989 - val_accuracy: 0.6818\n",
            "Epoch 209/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4951 - accuracy: 0.7557 - val_loss: 0.6084 - val_accuracy: 0.6688\n",
            "Epoch 210/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4946 - accuracy: 0.7557 - val_loss: 0.6301 - val_accuracy: 0.6753\n",
            "Epoch 211/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5037 - accuracy: 0.7606 - val_loss: 0.5826 - val_accuracy: 0.6883\n",
            "Epoch 212/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4920 - accuracy: 0.7590 - val_loss: 0.5910 - val_accuracy: 0.6883\n",
            "Epoch 213/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4976 - accuracy: 0.7508 - val_loss: 0.5843 - val_accuracy: 0.6948\n",
            "Epoch 214/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5038 - accuracy: 0.7590 - val_loss: 0.6015 - val_accuracy: 0.6753\n",
            "Epoch 215/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.4898 - accuracy: 0.7590 - val_loss: 0.6087 - val_accuracy: 0.6623\n",
            "Epoch 216/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.4930 - accuracy: 0.7622 - val_loss: 0.6193 - val_accuracy: 0.6818\n",
            "Epoch 217/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4906 - accuracy: 0.7590 - val_loss: 0.6037 - val_accuracy: 0.6688\n",
            "Epoch 218/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.4915 - accuracy: 0.7524 - val_loss: 0.5988 - val_accuracy: 0.6753\n",
            "Epoch 219/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4879 - accuracy: 0.7622 - val_loss: 0.7152 - val_accuracy: 0.6818\n",
            "Epoch 220/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5078 - accuracy: 0.7590 - val_loss: 0.6209 - val_accuracy: 0.6753\n",
            "Epoch 221/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4884 - accuracy: 0.7541 - val_loss: 0.5805 - val_accuracy: 0.6948\n",
            "Epoch 222/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4946 - accuracy: 0.7622 - val_loss: 0.5778 - val_accuracy: 0.6818\n",
            "Epoch 223/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4870 - accuracy: 0.7638 - val_loss: 0.6248 - val_accuracy: 0.6818\n",
            "Epoch 224/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4955 - accuracy: 0.7590 - val_loss: 0.5884 - val_accuracy: 0.6818\n",
            "Epoch 225/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4891 - accuracy: 0.7622 - val_loss: 0.5929 - val_accuracy: 0.6558\n",
            "Epoch 226/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4887 - accuracy: 0.7638 - val_loss: 0.6535 - val_accuracy: 0.6818\n",
            "Epoch 227/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4915 - accuracy: 0.7638 - val_loss: 0.5893 - val_accuracy: 0.6688\n",
            "Epoch 228/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4860 - accuracy: 0.7638 - val_loss: 0.5871 - val_accuracy: 0.6818\n",
            "Epoch 229/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4901 - accuracy: 0.7606 - val_loss: 0.5855 - val_accuracy: 0.6753\n",
            "Epoch 230/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4990 - accuracy: 0.7557 - val_loss: 0.5989 - val_accuracy: 0.6753\n",
            "Epoch 231/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5104 - accuracy: 0.7427 - val_loss: 0.7081 - val_accuracy: 0.6883\n",
            "Epoch 232/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5039 - accuracy: 0.7704 - val_loss: 0.6358 - val_accuracy: 0.6883\n",
            "Epoch 233/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4850 - accuracy: 0.7687 - val_loss: 0.5834 - val_accuracy: 0.6948\n",
            "Epoch 234/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5172 - accuracy: 0.7427 - val_loss: 0.5788 - val_accuracy: 0.6818\n",
            "Epoch 235/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.4925 - accuracy: 0.7590 - val_loss: 0.5836 - val_accuracy: 0.6818\n",
            "Epoch 236/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5000 - accuracy: 0.7638 - val_loss: 0.5677 - val_accuracy: 0.6948\n",
            "Epoch 237/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.5096 - accuracy: 0.7638 - val_loss: 0.5902 - val_accuracy: 0.7013\n",
            "Epoch 238/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4883 - accuracy: 0.7606 - val_loss: 0.6566 - val_accuracy: 0.6883\n",
            "Epoch 239/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.5029 - accuracy: 0.7557 - val_loss: 0.6185 - val_accuracy: 0.6818\n",
            "Epoch 240/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4889 - accuracy: 0.7638 - val_loss: 0.6014 - val_accuracy: 0.6623\n",
            "Epoch 241/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4921 - accuracy: 0.7704 - val_loss: 0.5973 - val_accuracy: 0.6688\n",
            "Epoch 242/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4916 - accuracy: 0.7720 - val_loss: 0.6165 - val_accuracy: 0.6818\n",
            "Epoch 243/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4969 - accuracy: 0.7541 - val_loss: 0.6567 - val_accuracy: 0.6818\n",
            "Epoch 244/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4988 - accuracy: 0.7476 - val_loss: 0.6346 - val_accuracy: 0.6688\n",
            "Epoch 245/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5204 - accuracy: 0.7590 - val_loss: 0.5829 - val_accuracy: 0.6883\n",
            "Epoch 246/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5240 - accuracy: 0.7573 - val_loss: 0.6356 - val_accuracy: 0.6883\n",
            "Epoch 247/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.5133 - accuracy: 0.7476 - val_loss: 0.6616 - val_accuracy: 0.6753\n",
            "Epoch 248/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4963 - accuracy: 0.7687 - val_loss: 0.5805 - val_accuracy: 0.6948\n",
            "Epoch 249/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4875 - accuracy: 0.7687 - val_loss: 0.5855 - val_accuracy: 0.7013\n",
            "Epoch 250/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4935 - accuracy: 0.7638 - val_loss: 0.6184 - val_accuracy: 0.6753\n",
            "Epoch 251/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4919 - accuracy: 0.7638 - val_loss: 0.6969 - val_accuracy: 0.6883\n",
            "Epoch 252/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4916 - accuracy: 0.7606 - val_loss: 0.6114 - val_accuracy: 0.6753\n",
            "Epoch 253/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4834 - accuracy: 0.7720 - val_loss: 0.5861 - val_accuracy: 0.6948\n",
            "Epoch 254/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4785 - accuracy: 0.7801 - val_loss: 0.5800 - val_accuracy: 0.6948\n",
            "Epoch 255/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4828 - accuracy: 0.7655 - val_loss: 0.5649 - val_accuracy: 0.6818\n",
            "Epoch 256/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4864 - accuracy: 0.7704 - val_loss: 0.6225 - val_accuracy: 0.6818\n",
            "Epoch 257/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5006 - accuracy: 0.7687 - val_loss: 0.5789 - val_accuracy: 0.7078\n",
            "Epoch 258/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.5208 - accuracy: 0.7606 - val_loss: 0.5900 - val_accuracy: 0.7013\n",
            "Epoch 259/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4902 - accuracy: 0.7606 - val_loss: 0.6128 - val_accuracy: 0.6688\n",
            "Epoch 260/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4850 - accuracy: 0.7704 - val_loss: 0.5747 - val_accuracy: 0.6883\n",
            "Epoch 261/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4853 - accuracy: 0.7687 - val_loss: 0.6274 - val_accuracy: 0.6818\n",
            "Epoch 262/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4801 - accuracy: 0.7704 - val_loss: 0.5786 - val_accuracy: 0.6883\n",
            "Epoch 263/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4835 - accuracy: 0.7720 - val_loss: 0.5805 - val_accuracy: 0.6753\n",
            "Epoch 264/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4786 - accuracy: 0.7638 - val_loss: 0.5940 - val_accuracy: 0.6883\n",
            "Epoch 265/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4812 - accuracy: 0.7687 - val_loss: 0.6110 - val_accuracy: 0.6753\n",
            "Epoch 266/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.4860 - accuracy: 0.7573 - val_loss: 0.5995 - val_accuracy: 0.6688\n",
            "Epoch 267/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.5022 - accuracy: 0.7638 - val_loss: 0.5835 - val_accuracy: 0.6948\n",
            "Epoch 268/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4871 - accuracy: 0.7606 - val_loss: 0.5690 - val_accuracy: 0.7013\n",
            "Epoch 269/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4888 - accuracy: 0.7769 - val_loss: 0.5778 - val_accuracy: 0.6948\n",
            "Epoch 270/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4924 - accuracy: 0.7606 - val_loss: 0.5818 - val_accuracy: 0.7078\n",
            "Epoch 271/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.4889 - accuracy: 0.7524 - val_loss: 0.6059 - val_accuracy: 0.6688\n",
            "Epoch 272/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.4858 - accuracy: 0.7557 - val_loss: 0.6651 - val_accuracy: 0.6883\n",
            "Epoch 273/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4877 - accuracy: 0.7720 - val_loss: 0.6044 - val_accuracy: 0.6818\n",
            "Epoch 274/500\n",
            "14/14 [==============================] - 0s 5ms/step - loss: 0.4867 - accuracy: 0.7671 - val_loss: 0.5866 - val_accuracy: 0.6753\n",
            "Epoch 275/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4807 - accuracy: 0.7769 - val_loss: 0.5738 - val_accuracy: 0.7078\n",
            "Epoch 276/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4837 - accuracy: 0.7769 - val_loss: 0.5813 - val_accuracy: 0.6948\n",
            "Epoch 277/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4899 - accuracy: 0.7638 - val_loss: 0.6430 - val_accuracy: 0.6818\n",
            "Epoch 278/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4749 - accuracy: 0.7736 - val_loss: 0.5842 - val_accuracy: 0.7338\n",
            "Epoch 279/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4897 - accuracy: 0.7573 - val_loss: 0.5859 - val_accuracy: 0.6883\n",
            "Epoch 280/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4753 - accuracy: 0.7655 - val_loss: 0.5731 - val_accuracy: 0.7078\n",
            "Epoch 281/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4821 - accuracy: 0.7671 - val_loss: 0.5680 - val_accuracy: 0.7078\n",
            "Epoch 282/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4801 - accuracy: 0.7704 - val_loss: 0.6065 - val_accuracy: 0.6753\n",
            "Epoch 283/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4721 - accuracy: 0.7752 - val_loss: 0.5731 - val_accuracy: 0.7078\n",
            "Epoch 284/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4797 - accuracy: 0.7687 - val_loss: 0.6023 - val_accuracy: 0.6818\n",
            "Epoch 285/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4729 - accuracy: 0.7687 - val_loss: 0.5689 - val_accuracy: 0.7208\n",
            "Epoch 286/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4788 - accuracy: 0.7736 - val_loss: 0.6648 - val_accuracy: 0.6948\n",
            "Epoch 287/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4894 - accuracy: 0.7557 - val_loss: 0.6526 - val_accuracy: 0.6948\n",
            "Epoch 288/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.5048 - accuracy: 0.7655 - val_loss: 0.5934 - val_accuracy: 0.6818\n",
            "Epoch 289/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4820 - accuracy: 0.7704 - val_loss: 0.5921 - val_accuracy: 0.6883\n",
            "Epoch 290/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4715 - accuracy: 0.7736 - val_loss: 0.5803 - val_accuracy: 0.7013\n",
            "Epoch 291/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4788 - accuracy: 0.7704 - val_loss: 0.5834 - val_accuracy: 0.7143\n",
            "Epoch 292/500\n",
            "14/14 [==============================] - 0s 12ms/step - loss: 0.4730 - accuracy: 0.7606 - val_loss: 0.6558 - val_accuracy: 0.6883\n",
            "Epoch 293/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.4822 - accuracy: 0.7801 - val_loss: 0.5900 - val_accuracy: 0.6753\n",
            "Epoch 294/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4807 - accuracy: 0.7687 - val_loss: 0.5735 - val_accuracy: 0.6948\n",
            "Epoch 295/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4876 - accuracy: 0.7557 - val_loss: 0.5801 - val_accuracy: 0.6883\n",
            "Epoch 296/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4750 - accuracy: 0.7671 - val_loss: 0.5747 - val_accuracy: 0.7078\n",
            "Epoch 297/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4746 - accuracy: 0.7866 - val_loss: 0.5724 - val_accuracy: 0.7013\n",
            "Epoch 298/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4885 - accuracy: 0.7671 - val_loss: 0.6078 - val_accuracy: 0.6818\n",
            "Epoch 299/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4873 - accuracy: 0.7622 - val_loss: 0.7121 - val_accuracy: 0.6753\n",
            "Epoch 300/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4907 - accuracy: 0.7655 - val_loss: 0.5927 - val_accuracy: 0.7013\n",
            "Epoch 301/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4871 - accuracy: 0.7638 - val_loss: 0.5793 - val_accuracy: 0.7013\n",
            "Epoch 302/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4878 - accuracy: 0.7638 - val_loss: 0.5783 - val_accuracy: 0.7078\n",
            "Epoch 303/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4848 - accuracy: 0.7687 - val_loss: 0.5714 - val_accuracy: 0.7143\n",
            "Epoch 304/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4736 - accuracy: 0.7801 - val_loss: 0.6021 - val_accuracy: 0.6818\n",
            "Epoch 305/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4728 - accuracy: 0.7671 - val_loss: 0.5973 - val_accuracy: 0.6753\n",
            "Epoch 306/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4764 - accuracy: 0.7704 - val_loss: 0.6467 - val_accuracy: 0.6883\n",
            "Epoch 307/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4783 - accuracy: 0.7720 - val_loss: 0.5744 - val_accuracy: 0.7013\n",
            "Epoch 308/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4792 - accuracy: 0.7720 - val_loss: 0.5814 - val_accuracy: 0.7013\n",
            "Epoch 309/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.4676 - accuracy: 0.7834 - val_loss: 0.5783 - val_accuracy: 0.6818\n",
            "Epoch 310/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.4770 - accuracy: 0.7671 - val_loss: 0.5893 - val_accuracy: 0.7013\n",
            "Epoch 311/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4716 - accuracy: 0.7752 - val_loss: 0.5836 - val_accuracy: 0.6818\n",
            "Epoch 312/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4722 - accuracy: 0.7850 - val_loss: 0.5837 - val_accuracy: 0.6883\n",
            "Epoch 313/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4725 - accuracy: 0.7687 - val_loss: 0.6313 - val_accuracy: 0.6948\n",
            "Epoch 314/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4941 - accuracy: 0.7785 - val_loss: 0.6268 - val_accuracy: 0.7013\n",
            "Epoch 315/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4888 - accuracy: 0.7524 - val_loss: 0.6083 - val_accuracy: 0.6883\n",
            "Epoch 316/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.4966 - accuracy: 0.7687 - val_loss: 0.5849 - val_accuracy: 0.6948\n",
            "Epoch 317/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4767 - accuracy: 0.7704 - val_loss: 0.5957 - val_accuracy: 0.6818\n",
            "Epoch 318/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4683 - accuracy: 0.7638 - val_loss: 0.6587 - val_accuracy: 0.6948\n",
            "Epoch 319/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4785 - accuracy: 0.7720 - val_loss: 0.5920 - val_accuracy: 0.6948\n",
            "Epoch 320/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4685 - accuracy: 0.7704 - val_loss: 0.5834 - val_accuracy: 0.6753\n",
            "Epoch 321/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4721 - accuracy: 0.7655 - val_loss: 0.6473 - val_accuracy: 0.6948\n",
            "Epoch 322/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4812 - accuracy: 0.7638 - val_loss: 0.6542 - val_accuracy: 0.6948\n",
            "Epoch 323/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4708 - accuracy: 0.7818 - val_loss: 0.5669 - val_accuracy: 0.7143\n",
            "Epoch 324/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4700 - accuracy: 0.7899 - val_loss: 0.5871 - val_accuracy: 0.6883\n",
            "Epoch 325/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4654 - accuracy: 0.7785 - val_loss: 0.6218 - val_accuracy: 0.7013\n",
            "Epoch 326/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4765 - accuracy: 0.7622 - val_loss: 0.6059 - val_accuracy: 0.6883\n",
            "Epoch 327/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4810 - accuracy: 0.7606 - val_loss: 0.5956 - val_accuracy: 0.7013\n",
            "Epoch 328/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.5423 - accuracy: 0.7362 - val_loss: 0.5824 - val_accuracy: 0.7143\n",
            "Epoch 329/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4823 - accuracy: 0.7720 - val_loss: 0.5780 - val_accuracy: 0.6948\n",
            "Epoch 330/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4659 - accuracy: 0.7818 - val_loss: 0.5720 - val_accuracy: 0.7013\n",
            "Epoch 331/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4685 - accuracy: 0.7720 - val_loss: 0.5746 - val_accuracy: 0.6948\n",
            "Epoch 332/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4642 - accuracy: 0.7769 - val_loss: 0.6064 - val_accuracy: 0.6883\n",
            "Epoch 333/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4844 - accuracy: 0.7687 - val_loss: 0.5934 - val_accuracy: 0.6818\n",
            "Epoch 334/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4836 - accuracy: 0.7818 - val_loss: 0.5843 - val_accuracy: 0.6818\n",
            "Epoch 335/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4714 - accuracy: 0.7671 - val_loss: 0.6379 - val_accuracy: 0.6948\n",
            "Epoch 336/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4702 - accuracy: 0.7655 - val_loss: 0.5809 - val_accuracy: 0.6818\n",
            "Epoch 337/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4811 - accuracy: 0.7866 - val_loss: 0.5705 - val_accuracy: 0.7143\n",
            "Epoch 338/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4718 - accuracy: 0.7736 - val_loss: 0.5737 - val_accuracy: 0.7078\n",
            "Epoch 339/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4645 - accuracy: 0.7752 - val_loss: 0.6127 - val_accuracy: 0.6883\n",
            "Epoch 340/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4679 - accuracy: 0.7769 - val_loss: 0.5766 - val_accuracy: 0.7013\n",
            "Epoch 341/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4679 - accuracy: 0.7785 - val_loss: 0.5752 - val_accuracy: 0.6883\n",
            "Epoch 342/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4811 - accuracy: 0.7704 - val_loss: 0.5696 - val_accuracy: 0.7078\n",
            "Epoch 343/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4714 - accuracy: 0.7752 - val_loss: 0.5667 - val_accuracy: 0.7078\n",
            "Epoch 344/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4673 - accuracy: 0.7866 - val_loss: 0.5758 - val_accuracy: 0.6883\n",
            "Epoch 345/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4740 - accuracy: 0.7752 - val_loss: 0.5686 - val_accuracy: 0.7078\n",
            "Epoch 346/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4775 - accuracy: 0.7655 - val_loss: 0.6259 - val_accuracy: 0.6948\n",
            "Epoch 347/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4703 - accuracy: 0.7736 - val_loss: 0.6109 - val_accuracy: 0.6818\n",
            "Epoch 348/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4824 - accuracy: 0.7704 - val_loss: 0.7577 - val_accuracy: 0.6623\n",
            "Epoch 349/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.5109 - accuracy: 0.7541 - val_loss: 0.6399 - val_accuracy: 0.7013\n",
            "Epoch 350/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4891 - accuracy: 0.7573 - val_loss: 0.6602 - val_accuracy: 0.7078\n",
            "Epoch 351/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4893 - accuracy: 0.7720 - val_loss: 0.5626 - val_accuracy: 0.7338\n",
            "Epoch 352/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4848 - accuracy: 0.7704 - val_loss: 0.5807 - val_accuracy: 0.6818\n",
            "Epoch 353/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4821 - accuracy: 0.7769 - val_loss: 0.5693 - val_accuracy: 0.7013\n",
            "Epoch 354/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4875 - accuracy: 0.7736 - val_loss: 0.5753 - val_accuracy: 0.7013\n",
            "Epoch 355/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4788 - accuracy: 0.7818 - val_loss: 0.5700 - val_accuracy: 0.7013\n",
            "Epoch 356/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4615 - accuracy: 0.7834 - val_loss: 0.6002 - val_accuracy: 0.6818\n",
            "Epoch 357/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4698 - accuracy: 0.7671 - val_loss: 0.5720 - val_accuracy: 0.6948\n",
            "Epoch 358/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4621 - accuracy: 0.7850 - val_loss: 0.5886 - val_accuracy: 0.6818\n",
            "Epoch 359/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4590 - accuracy: 0.7850 - val_loss: 0.5823 - val_accuracy: 0.6883\n",
            "Epoch 360/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4770 - accuracy: 0.7736 - val_loss: 0.6109 - val_accuracy: 0.7143\n",
            "Epoch 361/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4707 - accuracy: 0.7687 - val_loss: 0.6654 - val_accuracy: 0.7013\n",
            "Epoch 362/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4668 - accuracy: 0.7834 - val_loss: 0.5911 - val_accuracy: 0.6948\n",
            "Epoch 363/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4720 - accuracy: 0.7850 - val_loss: 0.6233 - val_accuracy: 0.7078\n",
            "Epoch 364/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4726 - accuracy: 0.7818 - val_loss: 0.6269 - val_accuracy: 0.7143\n",
            "Epoch 365/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4662 - accuracy: 0.7720 - val_loss: 0.5960 - val_accuracy: 0.6818\n",
            "Epoch 366/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4598 - accuracy: 0.7834 - val_loss: 0.5632 - val_accuracy: 0.7143\n",
            "Epoch 367/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4597 - accuracy: 0.7850 - val_loss: 0.5935 - val_accuracy: 0.6883\n",
            "Epoch 368/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4600 - accuracy: 0.7850 - val_loss: 0.5843 - val_accuracy: 0.7013\n",
            "Epoch 369/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4600 - accuracy: 0.7899 - val_loss: 0.5686 - val_accuracy: 0.7078\n",
            "Epoch 370/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4619 - accuracy: 0.7818 - val_loss: 0.6255 - val_accuracy: 0.7013\n",
            "Epoch 371/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4796 - accuracy: 0.7671 - val_loss: 0.5780 - val_accuracy: 0.7013\n",
            "Epoch 372/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4679 - accuracy: 0.7866 - val_loss: 0.5834 - val_accuracy: 0.7013\n",
            "Epoch 373/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4794 - accuracy: 0.7752 - val_loss: 0.5897 - val_accuracy: 0.6818\n",
            "Epoch 374/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4763 - accuracy: 0.7720 - val_loss: 0.5627 - val_accuracy: 0.7208\n",
            "Epoch 375/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4705 - accuracy: 0.7915 - val_loss: 0.6014 - val_accuracy: 0.6883\n",
            "Epoch 376/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4637 - accuracy: 0.7850 - val_loss: 0.6130 - val_accuracy: 0.6818\n",
            "Epoch 377/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4681 - accuracy: 0.7801 - val_loss: 0.6577 - val_accuracy: 0.6753\n",
            "Epoch 378/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4735 - accuracy: 0.7769 - val_loss: 0.5945 - val_accuracy: 0.6818\n",
            "Epoch 379/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4576 - accuracy: 0.7866 - val_loss: 0.5709 - val_accuracy: 0.6948\n",
            "Epoch 380/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4632 - accuracy: 0.7915 - val_loss: 0.5834 - val_accuracy: 0.6948\n",
            "Epoch 381/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4584 - accuracy: 0.7752 - val_loss: 0.5814 - val_accuracy: 0.6883\n",
            "Epoch 382/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4539 - accuracy: 0.7866 - val_loss: 0.5676 - val_accuracy: 0.7143\n",
            "Epoch 383/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4691 - accuracy: 0.7850 - val_loss: 0.5868 - val_accuracy: 0.7078\n",
            "Epoch 384/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4721 - accuracy: 0.7736 - val_loss: 0.5629 - val_accuracy: 0.7143\n",
            "Epoch 385/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4601 - accuracy: 0.7915 - val_loss: 0.5650 - val_accuracy: 0.7078\n",
            "Epoch 386/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4625 - accuracy: 0.7769 - val_loss: 0.6620 - val_accuracy: 0.7078\n",
            "Epoch 387/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4635 - accuracy: 0.7785 - val_loss: 0.6210 - val_accuracy: 0.7013\n",
            "Epoch 388/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4571 - accuracy: 0.7850 - val_loss: 0.5925 - val_accuracy: 0.7013\n",
            "Epoch 389/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4590 - accuracy: 0.7818 - val_loss: 0.5708 - val_accuracy: 0.6948\n",
            "Epoch 390/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4570 - accuracy: 0.7915 - val_loss: 0.6016 - val_accuracy: 0.6948\n",
            "Epoch 391/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4574 - accuracy: 0.7980 - val_loss: 0.6104 - val_accuracy: 0.6818\n",
            "Epoch 392/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4578 - accuracy: 0.7818 - val_loss: 0.6240 - val_accuracy: 0.6948\n",
            "Epoch 393/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4622 - accuracy: 0.7752 - val_loss: 0.5742 - val_accuracy: 0.6948\n",
            "Epoch 394/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4671 - accuracy: 0.7834 - val_loss: 0.5771 - val_accuracy: 0.7013\n",
            "Epoch 395/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4661 - accuracy: 0.7704 - val_loss: 0.5891 - val_accuracy: 0.6948\n",
            "Epoch 396/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4533 - accuracy: 0.7834 - val_loss: 0.5821 - val_accuracy: 0.7013\n",
            "Epoch 397/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4622 - accuracy: 0.7883 - val_loss: 0.5872 - val_accuracy: 0.6948\n",
            "Epoch 398/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4545 - accuracy: 0.7818 - val_loss: 0.5865 - val_accuracy: 0.6948\n",
            "Epoch 399/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4524 - accuracy: 0.7915 - val_loss: 0.5883 - val_accuracy: 0.6883\n",
            "Epoch 400/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4537 - accuracy: 0.7785 - val_loss: 0.5914 - val_accuracy: 0.6818\n",
            "Epoch 401/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4575 - accuracy: 0.7899 - val_loss: 0.5822 - val_accuracy: 0.7013\n",
            "Epoch 402/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4555 - accuracy: 0.7980 - val_loss: 0.5721 - val_accuracy: 0.7013\n",
            "Epoch 403/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4556 - accuracy: 0.7883 - val_loss: 0.6357 - val_accuracy: 0.7013\n",
            "Epoch 404/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4788 - accuracy: 0.7687 - val_loss: 0.6556 - val_accuracy: 0.6818\n",
            "Epoch 405/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4719 - accuracy: 0.7850 - val_loss: 0.6897 - val_accuracy: 0.6623\n",
            "Epoch 406/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4759 - accuracy: 0.7752 - val_loss: 0.5752 - val_accuracy: 0.7013\n",
            "Epoch 407/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4543 - accuracy: 0.7801 - val_loss: 0.5742 - val_accuracy: 0.7143\n",
            "Epoch 408/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4568 - accuracy: 0.7785 - val_loss: 0.5843 - val_accuracy: 0.7013\n",
            "Epoch 409/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4574 - accuracy: 0.7720 - val_loss: 0.6143 - val_accuracy: 0.7078\n",
            "Epoch 410/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4520 - accuracy: 0.7883 - val_loss: 0.5718 - val_accuracy: 0.7208\n",
            "Epoch 411/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4644 - accuracy: 0.7834 - val_loss: 0.6273 - val_accuracy: 0.6948\n",
            "Epoch 412/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4680 - accuracy: 0.7638 - val_loss: 0.6026 - val_accuracy: 0.6948\n",
            "Epoch 413/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.4520 - accuracy: 0.7964 - val_loss: 0.6181 - val_accuracy: 0.6948\n",
            "Epoch 414/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4544 - accuracy: 0.7785 - val_loss: 0.5891 - val_accuracy: 0.7013\n",
            "Epoch 415/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4613 - accuracy: 0.7834 - val_loss: 0.6001 - val_accuracy: 0.6818\n",
            "Epoch 416/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.4595 - accuracy: 0.7801 - val_loss: 0.5723 - val_accuracy: 0.6948\n",
            "Epoch 417/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4529 - accuracy: 0.7899 - val_loss: 0.5827 - val_accuracy: 0.6948\n",
            "Epoch 418/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4659 - accuracy: 0.7736 - val_loss: 0.5737 - val_accuracy: 0.7013\n",
            "Epoch 419/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4651 - accuracy: 0.7932 - val_loss: 0.5968 - val_accuracy: 0.7013\n",
            "Epoch 420/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.4689 - accuracy: 0.7752 - val_loss: 0.5720 - val_accuracy: 0.7013\n",
            "Epoch 421/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.4691 - accuracy: 0.7720 - val_loss: 0.6415 - val_accuracy: 0.6948\n",
            "Epoch 422/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.4676 - accuracy: 0.7752 - val_loss: 0.6939 - val_accuracy: 0.6883\n",
            "Epoch 423/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4644 - accuracy: 0.7687 - val_loss: 0.5932 - val_accuracy: 0.6883\n",
            "Epoch 424/500\n",
            "14/14 [==============================] - 0s 13ms/step - loss: 0.4496 - accuracy: 0.7769 - val_loss: 0.5796 - val_accuracy: 0.7143\n",
            "Epoch 425/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.4628 - accuracy: 0.7785 - val_loss: 0.6240 - val_accuracy: 0.6818\n",
            "Epoch 426/500\n",
            "14/14 [==============================] - 0s 17ms/step - loss: 0.4781 - accuracy: 0.7622 - val_loss: 0.7595 - val_accuracy: 0.6688\n",
            "Epoch 427/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.4749 - accuracy: 0.7752 - val_loss: 0.6268 - val_accuracy: 0.7013\n",
            "Epoch 428/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.4733 - accuracy: 0.7834 - val_loss: 0.5697 - val_accuracy: 0.7078\n",
            "Epoch 429/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.5068 - accuracy: 0.7704 - val_loss: 0.6703 - val_accuracy: 0.6753\n",
            "Epoch 430/500\n",
            "14/14 [==============================] - 0s 12ms/step - loss: 0.5286 - accuracy: 0.7606 - val_loss: 0.5859 - val_accuracy: 0.7078\n",
            "Epoch 431/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.5017 - accuracy: 0.7590 - val_loss: 0.5885 - val_accuracy: 0.7013\n",
            "Epoch 432/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4837 - accuracy: 0.7704 - val_loss: 0.5929 - val_accuracy: 0.7013\n",
            "Epoch 433/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4766 - accuracy: 0.7785 - val_loss: 0.6079 - val_accuracy: 0.7013\n",
            "Epoch 434/500\n",
            "14/14 [==============================] - 0s 12ms/step - loss: 0.4566 - accuracy: 0.7785 - val_loss: 0.5676 - val_accuracy: 0.7143\n",
            "Epoch 435/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4638 - accuracy: 0.7736 - val_loss: 0.5958 - val_accuracy: 0.7013\n",
            "Epoch 436/500\n",
            "14/14 [==============================] - 0s 11ms/step - loss: 0.4489 - accuracy: 0.7899 - val_loss: 0.5873 - val_accuracy: 0.6883\n",
            "Epoch 437/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4523 - accuracy: 0.7899 - val_loss: 0.6201 - val_accuracy: 0.7013\n",
            "Epoch 438/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4549 - accuracy: 0.7866 - val_loss: 0.5666 - val_accuracy: 0.7078\n",
            "Epoch 439/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4505 - accuracy: 0.7915 - val_loss: 0.5919 - val_accuracy: 0.6883\n",
            "Epoch 440/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4478 - accuracy: 0.7883 - val_loss: 0.5611 - val_accuracy: 0.7273\n",
            "Epoch 441/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4499 - accuracy: 0.7997 - val_loss: 0.5764 - val_accuracy: 0.7078\n",
            "Epoch 442/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4455 - accuracy: 0.7915 - val_loss: 0.5675 - val_accuracy: 0.7078\n",
            "Epoch 443/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4457 - accuracy: 0.7932 - val_loss: 0.6297 - val_accuracy: 0.7078\n",
            "Epoch 444/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4547 - accuracy: 0.7769 - val_loss: 0.5645 - val_accuracy: 0.7208\n",
            "Epoch 445/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4648 - accuracy: 0.7801 - val_loss: 0.5534 - val_accuracy: 0.7273\n",
            "Epoch 446/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4571 - accuracy: 0.7964 - val_loss: 0.5710 - val_accuracy: 0.7208\n",
            "Epoch 447/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4610 - accuracy: 0.7736 - val_loss: 0.6245 - val_accuracy: 0.7013\n",
            "Epoch 448/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4584 - accuracy: 0.7818 - val_loss: 0.6413 - val_accuracy: 0.6948\n",
            "Epoch 449/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4582 - accuracy: 0.7866 - val_loss: 0.5622 - val_accuracy: 0.7078\n",
            "Epoch 450/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4547 - accuracy: 0.7883 - val_loss: 0.6032 - val_accuracy: 0.7013\n",
            "Epoch 451/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4488 - accuracy: 0.7899 - val_loss: 0.6282 - val_accuracy: 0.7078\n",
            "Epoch 452/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4560 - accuracy: 0.7980 - val_loss: 0.5657 - val_accuracy: 0.7208\n",
            "Epoch 453/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4493 - accuracy: 0.7834 - val_loss: 0.6289 - val_accuracy: 0.7078\n",
            "Epoch 454/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4631 - accuracy: 0.7801 - val_loss: 0.6046 - val_accuracy: 0.7013\n",
            "Epoch 455/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4580 - accuracy: 0.7704 - val_loss: 0.5676 - val_accuracy: 0.7403\n",
            "Epoch 456/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4533 - accuracy: 0.7736 - val_loss: 0.5982 - val_accuracy: 0.7013\n",
            "Epoch 457/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4545 - accuracy: 0.7687 - val_loss: 0.6942 - val_accuracy: 0.6883\n",
            "Epoch 458/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4765 - accuracy: 0.7736 - val_loss: 0.5847 - val_accuracy: 0.7143\n",
            "Epoch 459/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4474 - accuracy: 0.7964 - val_loss: 0.5824 - val_accuracy: 0.7143\n",
            "Epoch 460/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4612 - accuracy: 0.7769 - val_loss: 0.5811 - val_accuracy: 0.7013\n",
            "Epoch 461/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4603 - accuracy: 0.7704 - val_loss: 0.6731 - val_accuracy: 0.7078\n",
            "Epoch 462/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4529 - accuracy: 0.7850 - val_loss: 0.6058 - val_accuracy: 0.6883\n",
            "Epoch 463/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4481 - accuracy: 0.7866 - val_loss: 0.5732 - val_accuracy: 0.6948\n",
            "Epoch 464/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4741 - accuracy: 0.7687 - val_loss: 0.5841 - val_accuracy: 0.7078\n",
            "Epoch 465/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4741 - accuracy: 0.7736 - val_loss: 0.6648 - val_accuracy: 0.7013\n",
            "Epoch 466/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4496 - accuracy: 0.7932 - val_loss: 0.5971 - val_accuracy: 0.7013\n",
            "Epoch 467/500\n",
            "14/14 [==============================] - 0s 10ms/step - loss: 0.4466 - accuracy: 0.7915 - val_loss: 0.5701 - val_accuracy: 0.7143\n",
            "Epoch 468/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4463 - accuracy: 0.8029 - val_loss: 0.5937 - val_accuracy: 0.7013\n",
            "Epoch 469/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4444 - accuracy: 0.7964 - val_loss: 0.6078 - val_accuracy: 0.7078\n",
            "Epoch 470/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4541 - accuracy: 0.7932 - val_loss: 0.5950 - val_accuracy: 0.7078\n",
            "Epoch 471/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4476 - accuracy: 0.7932 - val_loss: 0.6227 - val_accuracy: 0.7013\n",
            "Epoch 472/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4484 - accuracy: 0.7997 - val_loss: 0.6030 - val_accuracy: 0.6948\n",
            "Epoch 473/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4715 - accuracy: 0.7752 - val_loss: 0.5667 - val_accuracy: 0.7143\n",
            "Epoch 474/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4437 - accuracy: 0.7980 - val_loss: 0.6158 - val_accuracy: 0.6948\n",
            "Epoch 475/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4444 - accuracy: 0.7964 - val_loss: 0.6008 - val_accuracy: 0.6883\n",
            "Epoch 476/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4414 - accuracy: 0.7964 - val_loss: 0.5803 - val_accuracy: 0.7078\n",
            "Epoch 477/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4513 - accuracy: 0.7834 - val_loss: 0.5664 - val_accuracy: 0.7143\n",
            "Epoch 478/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4467 - accuracy: 0.7899 - val_loss: 0.5831 - val_accuracy: 0.7013\n",
            "Epoch 479/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4438 - accuracy: 0.7932 - val_loss: 0.6101 - val_accuracy: 0.7078\n",
            "Epoch 480/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4609 - accuracy: 0.7899 - val_loss: 0.5659 - val_accuracy: 0.7273\n",
            "Epoch 481/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4522 - accuracy: 0.7801 - val_loss: 0.5739 - val_accuracy: 0.7143\n",
            "Epoch 482/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4554 - accuracy: 0.7932 - val_loss: 0.5702 - val_accuracy: 0.7338\n",
            "Epoch 483/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4500 - accuracy: 0.7932 - val_loss: 0.5896 - val_accuracy: 0.7013\n",
            "Epoch 484/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4483 - accuracy: 0.7948 - val_loss: 0.5678 - val_accuracy: 0.7078\n",
            "Epoch 485/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4680 - accuracy: 0.7752 - val_loss: 0.5736 - val_accuracy: 0.6948\n",
            "Epoch 486/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4418 - accuracy: 0.7866 - val_loss: 0.5597 - val_accuracy: 0.7273\n",
            "Epoch 487/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4503 - accuracy: 0.7980 - val_loss: 0.5898 - val_accuracy: 0.6948\n",
            "Epoch 488/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4439 - accuracy: 0.7883 - val_loss: 0.6713 - val_accuracy: 0.7078\n",
            "Epoch 489/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4540 - accuracy: 0.7752 - val_loss: 0.5821 - val_accuracy: 0.7273\n",
            "Epoch 490/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4710 - accuracy: 0.7769 - val_loss: 0.5735 - val_accuracy: 0.7078\n",
            "Epoch 491/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4691 - accuracy: 0.7655 - val_loss: 0.6339 - val_accuracy: 0.7143\n",
            "Epoch 492/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4527 - accuracy: 0.7932 - val_loss: 0.6625 - val_accuracy: 0.7013\n",
            "Epoch 493/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4630 - accuracy: 0.7801 - val_loss: 0.5989 - val_accuracy: 0.6948\n",
            "Epoch 494/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4473 - accuracy: 0.7883 - val_loss: 0.6166 - val_accuracy: 0.6948\n",
            "Epoch 495/500\n",
            "14/14 [==============================] - 0s 7ms/step - loss: 0.4512 - accuracy: 0.7899 - val_loss: 0.5644 - val_accuracy: 0.7208\n",
            "Epoch 496/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4445 - accuracy: 0.7964 - val_loss: 0.5685 - val_accuracy: 0.7078\n",
            "Epoch 497/500\n",
            "14/14 [==============================] - 0s 8ms/step - loss: 0.4415 - accuracy: 0.8062 - val_loss: 0.6033 - val_accuracy: 0.7143\n",
            "Epoch 498/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4485 - accuracy: 0.7850 - val_loss: 0.6556 - val_accuracy: 0.7078\n",
            "Epoch 499/500\n",
            "14/14 [==============================] - 0s 9ms/step - loss: 0.4569 - accuracy: 0.7883 - val_loss: 0.6000 - val_accuracy: 0.6883\n",
            "Epoch 500/500\n",
            "14/14 [==============================] - 0s 6ms/step - loss: 0.4623 - accuracy: 0.7622 - val_loss: 0.5690 - val_accuracy: 0.7143\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import matplotlib.pyplot as plt\n"
      ],
      "metadata": {
        "id": "L5oibeLHNSxh"
      },
      "execution_count": 37,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "plt.figure(figsize=(14,3))\n",
        "plt.subplot(1, 2, 1)\n",
        "plt.suptitle('Optimizer : Adam', fontsize=10)\n",
        "plt.ylabel('Loss', fontsize=16)\n",
        "plt.plot(H.history['loss'], color='b', label='Training Loss')\n",
        "plt.plot(H.history['val_loss'], color='r', label='Validation Loss')\n",
        "plt.legend(loc='upper right')\n",
        "\n",
        "plt.subplot(1, 2, 2)\n",
        "plt.ylabel('Accuracy', fontsize=16)\n",
        "plt.plot(H.history['accuracy'], color='b', label='Training Accuracy')\n",
        "plt.plot(H.history['val_accuracy'], color='r', label='Validation Accuracy')\n",
        "plt.legend(loc='lower right')\n",
        "plt.show()\n",
        ""
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 341
        },
        "id": "eoDdHwW6OT1F",
        "outputId": "6361bbd4-a883-4b42-e65a-effbdb02236d"
      },
      "execution_count": 38,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1400x300 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model_predicted = model.predict(X_test)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4bP3EOkSPJ1l",
        "outputId": "2d60755e-b95e-4716-e07c-d4839e4afcb9"
      },
      "execution_count": 39,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "5/5 [==============================] - 0s 3ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model_predicted"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Be_JfYyLPTFQ",
        "outputId": "7cc82e05-6e10-433b-dfd0-cad9ab08b2a2"
      },
      "execution_count": 40,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.27670878],\n",
              "       [0.6396061 ],\n",
              "       [0.917774  ],\n",
              "       [0.23027271],\n",
              "       [0.01352428],\n",
              "       [0.2538012 ],\n",
              "       [0.92736334],\n",
              "       [0.8770006 ],\n",
              "       [0.22207285],\n",
              "       [0.56428   ],\n",
              "       [0.80312395],\n",
              "       [0.4568204 ],\n",
              "       [0.20689398],\n",
              "       [0.39520594],\n",
              "       [0.33653775],\n",
              "       [0.34850025],\n",
              "       [0.27676284],\n",
              "       [0.20432188],\n",
              "       [0.7094566 ],\n",
              "       [0.18267833],\n",
              "       [0.47581792],\n",
              "       [0.11803851],\n",
              "       [0.28505135],\n",
              "       [0.81412756],\n",
              "       [0.42447063],\n",
              "       [0.4190668 ],\n",
              "       [0.7391356 ],\n",
              "       [0.433609  ],\n",
              "       [0.18179893],\n",
              "       [0.6587139 ],\n",
              "       [0.10659565],\n",
              "       [0.40823963],\n",
              "       [0.3600906 ],\n",
              "       [0.94196874],\n",
              "       [0.05261672],\n",
              "       [0.37235707],\n",
              "       [0.6054999 ],\n",
              "       [0.37164074],\n",
              "       [0.81016594],\n",
              "       [0.964365  ],\n",
              "       [0.81402946],\n",
              "       [0.99884325],\n",
              "       [0.05610085],\n",
              "       [0.11120652],\n",
              "       [0.14691682],\n",
              "       [0.47798884],\n",
              "       [0.05714997],\n",
              "       [0.16287093],\n",
              "       [0.49054065],\n",
              "       [0.29153323],\n",
              "       [0.07883168],\n",
              "       [0.47411227],\n",
              "       [0.35494134],\n",
              "       [0.9836612 ],\n",
              "       [0.9488802 ],\n",
              "       [0.04816018],\n",
              "       [0.14784917],\n",
              "       [0.9152875 ],\n",
              "       [0.03140496],\n",
              "       [0.4399164 ],\n",
              "       [0.24705558],\n",
              "       [0.27103314],\n",
              "       [0.09819575],\n",
              "       [0.5742611 ],\n",
              "       [0.07336903],\n",
              "       [0.21823706],\n",
              "       [0.48028108],\n",
              "       [0.7268841 ],\n",
              "       [0.5868251 ],\n",
              "       [0.44498664],\n",
              "       [0.08759318],\n",
              "       [0.23314413],\n",
              "       [0.26654896],\n",
              "       [0.346402  ],\n",
              "       [0.08899851],\n",
              "       [0.3202426 ],\n",
              "       [0.14091283],\n",
              "       [0.35941562],\n",
              "       [0.8707997 ],\n",
              "       [0.8345911 ],\n",
              "       [0.28507242],\n",
              "       [0.86855596],\n",
              "       [0.41462082],\n",
              "       [0.3038648 ],\n",
              "       [0.26833525],\n",
              "       [0.1693247 ],\n",
              "       [0.03364682],\n",
              "       [0.7925397 ],\n",
              "       [0.8423461 ],\n",
              "       [0.6528777 ],\n",
              "       [0.452298  ],\n",
              "       [0.14775236],\n",
              "       [0.31198663],\n",
              "       [0.12171235],\n",
              "       [0.9497858 ],\n",
              "       [0.6582806 ],\n",
              "       [0.03499826],\n",
              "       [0.27988786],\n",
              "       [0.14933294],\n",
              "       [0.2164838 ],\n",
              "       [0.14536078],\n",
              "       [0.09384692],\n",
              "       [0.32243866],\n",
              "       [0.6395729 ],\n",
              "       [0.3288226 ],\n",
              "       [0.22787708],\n",
              "       [0.7824401 ],\n",
              "       [0.11823787],\n",
              "       [0.16445222],\n",
              "       [0.11195099],\n",
              "       [0.58612895],\n",
              "       [0.42658225],\n",
              "       [0.9313573 ],\n",
              "       [0.1122241 ],\n",
              "       [0.40981126],\n",
              "       [0.3247934 ],\n",
              "       [0.22004087],\n",
              "       [0.10884945],\n",
              "       [0.00530316],\n",
              "       [0.36182374],\n",
              "       [0.9566142 ],\n",
              "       [0.18920545],\n",
              "       [0.41898787],\n",
              "       [0.09093179],\n",
              "       [0.38001668],\n",
              "       [0.3860003 ],\n",
              "       [0.59571904],\n",
              "       [0.79761547],\n",
              "       [0.66912305],\n",
              "       [0.17343265],\n",
              "       [0.1793374 ],\n",
              "       [0.55655533],\n",
              "       [0.1460914 ],\n",
              "       [0.05458397],\n",
              "       [0.7145864 ],\n",
              "       [0.20635   ],\n",
              "       [0.02064297],\n",
              "       [0.54672474],\n",
              "       [0.26442993],\n",
              "       [0.9781365 ],\n",
              "       [0.2486202 ],\n",
              "       [0.31661153],\n",
              "       [0.42578053],\n",
              "       [0.39271954],\n",
              "       [0.99381584],\n",
              "       [0.87780094],\n",
              "       [0.29471672],\n",
              "       [0.8194442 ],\n",
              "       [0.00156632],\n",
              "       [0.3006541 ],\n",
              "       [0.73077065],\n",
              "       [0.26208317],\n",
              "       [0.5197785 ],\n",
              "       [0.22275734]], dtype=float32)"
            ]
          },
          "metadata": {},
          "execution_count": 40
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "predictions = model_predicted > 0.5"
      ],
      "metadata": {
        "id": "Laj_bpb7Pnzm"
      },
      "execution_count": 41,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "predictions"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "pvvq5S6HPaap",
        "outputId": "b254e599-b165-42c3-cfce-c8a13bb28c22"
      },
      "execution_count": 42,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[False],\n",
              "       [ True],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [ True],\n",
              "       [ True],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [ True],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [ True],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False],\n",
              "       [ True],\n",
              "       [False]])"
            ]
          },
          "metadata": {},
          "execution_count": 42
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.metrics import confusion_matrix, classification_report\n",
        "# Calculate how many mis-classifications the model makes\n",
        "tn, fp, fn, tp = confusion_matrix(y_test, predictions).ravel()\n",
        "print(f\"True Positives: {tp}\")\n",
        "print(f\"True Negatives: {tn}\")\n",
        "print(f\"False Positives: {fp}\")\n",
        "print(f\"False Negatives: {fn}\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "FTUPeKi3P1_2",
        "outputId": "90c3678e-dc89-498b-cb1e-4192915d51ad"
      },
      "execution_count": 43,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "True Positives: 31\n",
            "True Negatives: 79\n",
            "False Positives: 16\n",
            "False Negatives: 28\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "report = classification_report(y_test, predictions)"
      ],
      "metadata": {
        "id": "f76cRl_oOgSO"
      },
      "execution_count": 44,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "print(report)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Os3QGHlaQFRB",
        "outputId": "6d1a4ff0-8ca1-4dc0-b1ab-0ccf4b08a392"
      },
      "execution_count": 46,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.74      0.83      0.78        95\n",
            "           1       0.66      0.53      0.58        59\n",
            "\n",
            "    accuracy                           0.71       154\n",
            "   macro avg       0.70      0.68      0.68       154\n",
            "weighted avg       0.71      0.71      0.71       154\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "XpvJMeHcQF9B"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}