From 0e08311c9670b2c3e75f2767743ae52a0a21caab Mon Sep 17 00:00:00 2001
From: Dina Merlia Efendi <131696633+dinamerlia@users.noreply.github.com>
Date: Thu, 18 Jul 2024 20:40:04 +0700
Subject: [PATCH] Delete ANN/ANN_MODEL_with_normalization_layer.ipynb

Delete and update
---
 ANN/ANN_MODEL_with_normalization_layer.ipynb | 1382 ------------------
 1 file changed, 1382 deletions(-)
 delete mode 100644 ANN/ANN_MODEL_with_normalization_layer.ipynb

diff --git a/ANN/ANN_MODEL_with_normalization_layer.ipynb b/ANN/ANN_MODEL_with_normalization_layer.ipynb
deleted file mode 100644
index 28e60a0..0000000
--- a/ANN/ANN_MODEL_with_normalization_layer.ipynb
+++ /dev/null
@@ -1,1382 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "q_GO9V2TCFgz"
-      },
-      "outputs": [],
-      "source": [
-        "import pandas as pd\n",
-        "import numpy as np\n",
-        "from sklearn.model_selection import train_test_split\n",
-        "from sklearn.preprocessing import OneHotEncoder\n",
-        "from sklearn.compose import ColumnTransformer\n",
-        "from keras.models import Sequential\n",
-        "from keras.layers import Dense\n",
-        "from sklearn.metrics import accuracy_score, classification_report\n",
-        "from google.colab import files\n",
-        "from keras.layers.experimental.preprocessing import Normalization"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 424
-        },
-        "id": "jig5pnmbCeta",
-        "outputId": "18abf0e5-04c0-460b-f9a0-3df41277ff56"
-      },
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "       Tavg  RH_avg     RR    ss  soil_type  plant_type\n",
-              "0     28.62   60.18  11.73  5.86          3           6\n",
-              "1     28.62   60.18  11.73  5.86          5           6\n",
-              "2     28.62   60.18  11.73  5.86          1           6\n",
-              "3     28.62   60.18  11.73  5.86          4           6\n",
-              "4     28.62   60.18  11.73  5.86          2           6\n",
-              "...     ...     ...    ...   ...        ...         ...\n",
-              "1560  25.30  100.00  35.00  0.80          3           2\n",
-              "1561  25.30  100.00  35.00  0.80          5           2\n",
-              "1562  25.30  100.00  35.00  0.80          1           2\n",
-              "1563  25.30  100.00  35.00  0.80          4           2\n",
-              "1564  25.30  100.00  35.00  0.80          2           2\n",
-              "\n",
-              "[1565 rows x 6 columns]"
-            ],
-            "text/html": [
-              "\n",
-              "  <div id=\"df-a4df3793-de4a-4da6-8d31-46f2232bad37\" 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>Tavg</th>\n",
-              "      <th>RH_avg</th>\n",
-              "      <th>RR</th>\n",
-              "      <th>ss</th>\n",
-              "      <th>soil_type</th>\n",
-              "      <th>plant_type</th>\n",
-              "    </tr>\n",
-              "  </thead>\n",
-              "  <tbody>\n",
-              "    <tr>\n",
-              "      <th>0</th>\n",
-              "      <td>28.62</td>\n",
-              "      <td>60.18</td>\n",
-              "      <td>11.73</td>\n",
-              "      <td>5.86</td>\n",
-              "      <td>3</td>\n",
-              "      <td>6</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>1</th>\n",
-              "      <td>28.62</td>\n",
-              "      <td>60.18</td>\n",
-              "      <td>11.73</td>\n",
-              "      <td>5.86</td>\n",
-              "      <td>5</td>\n",
-              "      <td>6</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>2</th>\n",
-              "      <td>28.62</td>\n",
-              "      <td>60.18</td>\n",
-              "      <td>11.73</td>\n",
-              "      <td>5.86</td>\n",
-              "      <td>1</td>\n",
-              "      <td>6</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>3</th>\n",
-              "      <td>28.62</td>\n",
-              "      <td>60.18</td>\n",
-              "      <td>11.73</td>\n",
-              "      <td>5.86</td>\n",
-              "      <td>4</td>\n",
-              "      <td>6</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>4</th>\n",
-              "      <td>28.62</td>\n",
-              "      <td>60.18</td>\n",
-              "      <td>11.73</td>\n",
-              "      <td>5.86</td>\n",
-              "      <td>2</td>\n",
-              "      <td>6</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>...</th>\n",
-              "      <td>...</td>\n",
-              "      <td>...</td>\n",
-              "      <td>...</td>\n",
-              "      <td>...</td>\n",
-              "      <td>...</td>\n",
-              "      <td>...</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>1560</th>\n",
-              "      <td>25.30</td>\n",
-              "      <td>100.00</td>\n",
-              "      <td>35.00</td>\n",
-              "      <td>0.80</td>\n",
-              "      <td>3</td>\n",
-              "      <td>2</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>1561</th>\n",
-              "      <td>25.30</td>\n",
-              "      <td>100.00</td>\n",
-              "      <td>35.00</td>\n",
-              "      <td>0.80</td>\n",
-              "      <td>5</td>\n",
-              "      <td>2</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>1562</th>\n",
-              "      <td>25.30</td>\n",
-              "      <td>100.00</td>\n",
-              "      <td>35.00</td>\n",
-              "      <td>0.80</td>\n",
-              "      <td>1</td>\n",
-              "      <td>2</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>1563</th>\n",
-              "      <td>25.30</td>\n",
-              "      <td>100.00</td>\n",
-              "      <td>35.00</td>\n",
-              "      <td>0.80</td>\n",
-              "      <td>4</td>\n",
-              "      <td>2</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>1564</th>\n",
-              "      <td>25.30</td>\n",
-              "      <td>100.00</td>\n",
-              "      <td>35.00</td>\n",
-              "      <td>0.80</td>\n",
-              "      <td>2</td>\n",
-              "      <td>2</td>\n",
-              "    </tr>\n",
-              "  </tbody>\n",
-              "</table>\n",
-              "<p>1565 rows × 6 columns</p>\n",
-              "</div>\n",
-              "    <div class=\"colab-df-buttons\">\n",
-              "\n",
-              "  <div class=\"colab-df-container\">\n",
-              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-a4df3793-de4a-4da6-8d31-46f2232bad37')\"\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-a4df3793-de4a-4da6-8d31-46f2232bad37 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-a4df3793-de4a-4da6-8d31-46f2232bad37');\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-bce48ba4-a42e-4bee-bda0-aff84c3584cb\">\n",
-              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-bce48ba4-a42e-4bee-bda0-aff84c3584cb')\"\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-bce48ba4-a42e-4bee-bda0-aff84c3584cb button');\n",
-              "      quickchartButtonEl.style.display =\n",
-              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
-              "    })();\n",
-              "  </script>\n",
-              "</div>\n",
-              "\n",
-              "  <div id=\"id_eff98546-828c-433f-85e6-bd8d36a34568\">\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('df')\"\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_eff98546-828c-433f-85e6-bd8d36a34568 button.colab-df-generate');\n",
-              "      buttonEl.style.display =\n",
-              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
-              "\n",
-              "      buttonEl.onclick = () => {\n",
-              "        google.colab.notebook.generateWithVariable('df');\n",
-              "      }\n",
-              "      })();\n",
-              "    </script>\n",
-              "  </div>\n",
-              "\n",
-              "    </div>\n",
-              "  </div>\n"
-            ],
-            "application/vnd.google.colaboratory.intrinsic+json": {
-              "type": "dataframe",
-              "variable_name": "df",
-              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 1565,\n  \"fields\": [\n    {\n      \"column\": \"Tavg\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2.7408717728829064,\n        \"min\": 19.4,\n        \"max\": 33.24,\n        \"num_unique_values\": 111,\n        \"samples\": [\n          29.3,\n          29.91,\n          33.24\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"RH_avg\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 7.479371829509177,\n        \"min\": 60.18,\n        \"max\": 100.0,\n        \"num_unique_values\": 60,\n        \"samples\": [\n          60.18,\n          62.77,\n          80.22\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"RR\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 13.675674050277426,\n        \"min\": 0.0,\n        \"max\": 89.1,\n        \"num_unique_values\": 121,\n        \"samples\": [\n          4.1,\n          2.2,\n          10.75\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"ss\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2.854922280301032,\n        \"min\": 0.0,\n        \"max\": 10.8,\n        \"num_unique_values\": 125,\n        \"samples\": [\n          3.84,\n          7.29,\n          5.3\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"soil_type\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1,\n        \"min\": 1,\n        \"max\": 5,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          5,\n          2,\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"plant_type\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1,\n        \"min\": 1,\n        \"max\": 6,\n        \"num_unique_values\": 6,\n        \"samples\": [\n          6,\n          5,\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
-            }
-          },
-          "metadata": {},
-          "execution_count": 4
-        }
-      ],
-      "source": [
-        "df = pd.read_excel(\"dataset_real.xlsx\")\n",
-        "df"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "ACwx4mHpCi-D"
-      },
-      "outputs": [],
-      "source": [
-        "X = df.iloc[:, 0:5].values\n",
-        "y = df.iloc[:, 5].values.reshape(-1, 1)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "GtDF3LjzCljX",
-        "outputId": "e6e7a3e1-dc76-4b89-a377-c0628fc4c07d"
-      },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stderr",
-          "text": [
-            "/usr/local/lib/python3.10/dist-packages/sklearn/preprocessing/_encoders.py:868: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
-            "  warnings.warn(\n"
-          ]
-        }
-      ],
-      "source": [
-        "# One-Hot Encoding\n",
-        "encoder = OneHotEncoder(sparse=False)\n",
-        "y = encoder.fit_transform(y)\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "y"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "uet5XnQr1MJf",
-        "outputId": "24a749d5-f07e-43fe-db06-4a3363eacf89"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "array([[0., 0., 0., 0., 0., 1.],\n",
-              "       [0., 0., 0., 0., 0., 1.],\n",
-              "       [0., 0., 0., 0., 0., 1.],\n",
-              "       ...,\n",
-              "       [0., 1., 0., 0., 0., 0.],\n",
-              "       [0., 1., 0., 0., 0., 0.],\n",
-              "       [0., 1., 0., 0., 0., 0.]])"
-            ]
-          },
-          "metadata": {},
-          "execution_count": 7
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "5W8mDdllCmi3"
-      },
-      "outputs": [],
-      "source": [
-        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "90R7r2peCpHM"
-      },
-      "outputs": [],
-      "source": [
-        "normalizer = Normalization(input_shape=(5,))\n",
-        "normalizer.adapt(X_train)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "X_train"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "SFAPzZJs1Qiw",
-        "outputId": "a18bd102-8777-4a76-bca8-2759122ef63d"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "array([[22.6 , 91.  ,  5.  ,  5.5 ,  3.  ],\n",
-              "       [29.5 , 82.  , 12.2 ,  0.6 ,  3.  ],\n",
-              "       [25.8 , 84.  ,  0.  ,  7.1 ,  1.  ],\n",
-              "       ...,\n",
-              "       [23.15, 83.85,  7.37,  7.28,  3.  ],\n",
-              "       [27.6 , 93.  ,  1.4 ,  0.  ,  2.  ],\n",
-              "       [28.6 , 87.  ,  5.3 ,  4.  ,  5.  ]])"
-            ]
-          },
-          "metadata": {},
-          "execution_count": 10
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "X_test"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "9732UyqV1SMC",
-        "outputId": "72285a59-38bd-403f-d03f-45e8fc2e1a8a"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "array([[27.2 , 81.  ,  0.  ,  6.5 ,  1.  ],\n",
-              "       [30.  , 77.  , 89.1 ,  5.7 ,  5.  ],\n",
-              "       [23.2 , 92.  , 68.7 ,  5.6 ,  1.  ],\n",
-              "       ...,\n",
-              "       [28.4 , 86.  ,  8.3 ,  5.2 ,  4.  ],\n",
-              "       [29.4 , 81.  ,  0.5 ,  8.6 ,  4.  ],\n",
-              "       [22.54, 64.58, 10.53,  6.17,  4.  ]])"
-            ]
-          },
-          "metadata": {},
-          "execution_count": 11
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "viqyeYGCCrll"
-      },
-      "outputs": [],
-      "source": [
-        "model = Sequential(name=\"ANN_Model_for_Crop_Recommendation\")\n",
-        "model.add(normalizer)\n",
-        "model.add(Dense(units=32, activation='relu', input_dim=X_train.shape[1]))\n",
-        "model.add(Dense(units=16, activation='relu'))\n",
-        "model.add(Dense(units=y_train.shape[1], activation='softmax'))\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "OD5Y6ib_NckZ",
-        "outputId": "2ad5a010-9982-4d7b-9da6-2953fca60850"
-      },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Model: \"ANN_Model_for_Crop_Recommendation\"\n",
-            "_________________________________________________________________\n",
-            " Layer (type)                Output Shape              Param #   \n",
-            "=================================================================\n",
-            " normalization (Normalizati  (None, 5)                 11        \n",
-            " on)                                                             \n",
-            "                                                                 \n",
-            " dense_6 (Dense)             (None, 32)                192       \n",
-            "                                                                 \n",
-            " dense_7 (Dense)             (None, 16)                528       \n",
-            "                                                                 \n",
-            " dense_8 (Dense)             (None, 6)                 102       \n",
-            "                                                                 \n",
-            "=================================================================\n",
-            "Total params: 833 (3.26 KB)\n",
-            "Trainable params: 822 (3.21 KB)\n",
-            "Non-trainable params: 11 (48.00 Byte)\n",
-            "_________________________________________________________________\n"
-          ]
-        }
-      ],
-      "source": [
-        "model.summary()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "uXN_Kxl8CtMz"
-      },
-      "outputs": [],
-      "source": [
-        "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "jF8YG5hUCvkG",
-        "outputId": "ec876dc7-8c93-4371-83fc-e298efef0342"
-      },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Epoch 1/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0062 - accuracy: 0.9968 - val_loss: 0.0184 - val_accuracy: 0.9904\n",
-            "Epoch 2/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0072 - accuracy: 0.9960 - val_loss: 0.0200 - val_accuracy: 0.9904\n",
-            "Epoch 3/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0068 - accuracy: 0.9976 - val_loss: 0.0197 - val_accuracy: 0.9904\n",
-            "Epoch 4/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0074 - accuracy: 0.9968 - val_loss: 0.0189 - val_accuracy: 0.9936\n",
-            "Epoch 5/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0063 - accuracy: 0.9968 - val_loss: 0.0170 - val_accuracy: 0.9936\n",
-            "Epoch 6/100\n",
-            "79/79 [==============================] - 0s 4ms/step - loss: 0.0065 - accuracy: 0.9976 - val_loss: 0.0181 - val_accuracy: 0.9936\n",
-            "Epoch 7/100\n",
-            "79/79 [==============================] - 0s 4ms/step - loss: 0.0058 - accuracy: 0.9992 - val_loss: 0.0229 - val_accuracy: 0.9840\n",
-            "Epoch 8/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0064 - accuracy: 0.9976 - val_loss: 0.0186 - val_accuracy: 0.9904\n",
-            "Epoch 9/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0067 - accuracy: 0.9976 - val_loss: 0.0239 - val_accuracy: 0.9840\n",
-            "Epoch 10/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0058 - accuracy: 0.9976 - val_loss: 0.0193 - val_accuracy: 0.9936\n",
-            "Epoch 11/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0062 - accuracy: 0.9976 - val_loss: 0.0163 - val_accuracy: 0.9936\n",
-            "Epoch 12/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0060 - accuracy: 0.9984 - val_loss: 0.0231 - val_accuracy: 0.9840\n",
-            "Epoch 13/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0053 - accuracy: 0.9984 - val_loss: 0.0170 - val_accuracy: 0.9936\n",
-            "Epoch 14/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0056 - accuracy: 0.9976 - val_loss: 0.0160 - val_accuracy: 0.9936\n",
-            "Epoch 15/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0056 - accuracy: 0.9984 - val_loss: 0.0167 - val_accuracy: 0.9904\n",
-            "Epoch 16/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0058 - accuracy: 0.9992 - val_loss: 0.0183 - val_accuracy: 0.9936\n",
-            "Epoch 17/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0054 - accuracy: 0.9984 - val_loss: 0.0185 - val_accuracy: 0.9936\n",
-            "Epoch 18/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0053 - accuracy: 0.9984 - val_loss: 0.0245 - val_accuracy: 0.9840\n",
-            "Epoch 19/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0054 - accuracy: 0.9976 - val_loss: 0.0163 - val_accuracy: 0.9936\n",
-            "Epoch 20/100\n",
-            "79/79 [==============================] - 0s 2ms/step - loss: 0.0057 - accuracy: 0.9968 - val_loss: 0.0167 - val_accuracy: 0.9936\n",
-            "Epoch 21/100\n",
-            "79/79 [==============================] - 0s 4ms/step - loss: 0.0053 - accuracy: 0.9984 - val_loss: 0.0149 - val_accuracy: 0.9936\n",
-            "Epoch 22/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0064 - accuracy: 0.9968 - val_loss: 0.0203 - val_accuracy: 0.9904\n",
-            "Epoch 23/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0050 - accuracy: 0.9984 - val_loss: 0.0179 - val_accuracy: 0.9904\n",
-            "Epoch 24/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0049 - accuracy: 0.9992 - val_loss: 0.0299 - val_accuracy: 0.9840\n",
-            "Epoch 25/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0056 - accuracy: 0.9976 - val_loss: 0.0201 - val_accuracy: 0.9904\n",
-            "Epoch 26/100\n",
-            "79/79 [==============================] - 0s 2ms/step - loss: 0.0049 - accuracy: 0.9984 - val_loss: 0.0150 - val_accuracy: 0.9936\n",
-            "Epoch 27/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0046 - accuracy: 0.9992 - val_loss: 0.0173 - val_accuracy: 0.9936\n",
-            "Epoch 28/100\n",
-            "79/79 [==============================] - 0s 4ms/step - loss: 0.0050 - accuracy: 0.9984 - val_loss: 0.0159 - val_accuracy: 0.9936\n",
-            "Epoch 29/100\n",
-            "79/79 [==============================] - 0s 6ms/step - loss: 0.0048 - accuracy: 0.9984 - val_loss: 0.0147 - val_accuracy: 0.9936\n",
-            "Epoch 30/100\n",
-            "79/79 [==============================] - 0s 5ms/step - loss: 0.0044 - accuracy: 0.9984 - val_loss: 0.0162 - val_accuracy: 0.9936\n",
-            "Epoch 31/100\n",
-            "79/79 [==============================] - 0s 5ms/step - loss: 0.0047 - accuracy: 0.9992 - val_loss: 0.0160 - val_accuracy: 0.9904\n",
-            "Epoch 32/100\n",
-            "79/79 [==============================] - 0s 5ms/step - loss: 0.0047 - accuracy: 0.9984 - val_loss: 0.0235 - val_accuracy: 0.9904\n",
-            "Epoch 33/100\n",
-            "79/79 [==============================] - 0s 5ms/step - loss: 0.0053 - accuracy: 0.9984 - val_loss: 0.0158 - val_accuracy: 0.9936\n",
-            "Epoch 34/100\n",
-            "79/79 [==============================] - 1s 8ms/step - loss: 0.0050 - accuracy: 0.9984 - val_loss: 0.0156 - val_accuracy: 0.9936\n",
-            "Epoch 35/100\n",
-            "79/79 [==============================] - 0s 5ms/step - loss: 0.0043 - accuracy: 0.9984 - val_loss: 0.0143 - val_accuracy: 0.9904\n",
-            "Epoch 36/100\n",
-            "79/79 [==============================] - 0s 4ms/step - loss: 0.0044 - accuracy: 0.9984 - val_loss: 0.0170 - val_accuracy: 0.9936\n",
-            "Epoch 37/100\n",
-            "79/79 [==============================] - 0s 2ms/step - loss: 0.0042 - accuracy: 0.9984 - val_loss: 0.0152 - val_accuracy: 0.9936\n",
-            "Epoch 38/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0038 - accuracy: 0.9992 - val_loss: 0.0202 - val_accuracy: 0.9904\n",
-            "Epoch 39/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0045 - accuracy: 0.9984 - val_loss: 0.0164 - val_accuracy: 0.9904\n",
-            "Epoch 40/100\n",
-            "79/79 [==============================] - 0s 4ms/step - loss: 0.0043 - accuracy: 0.9984 - val_loss: 0.0142 - val_accuracy: 0.9936\n",
-            "Epoch 41/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0041 - accuracy: 0.9984 - val_loss: 0.0147 - val_accuracy: 0.9936\n",
-            "Epoch 42/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0049 - accuracy: 0.9984 - val_loss: 0.0140 - val_accuracy: 0.9936\n",
-            "Epoch 43/100\n",
-            "79/79 [==============================] - 0s 4ms/step - loss: 0.0035 - accuracy: 1.0000 - val_loss: 0.0329 - val_accuracy: 0.9840\n",
-            "Epoch 44/100\n",
-            "79/79 [==============================] - 0s 4ms/step - loss: 0.0041 - accuracy: 0.9968 - val_loss: 0.0229 - val_accuracy: 0.9872\n",
-            "Epoch 45/100\n",
-            "79/79 [==============================] - 0s 2ms/step - loss: 0.0056 - accuracy: 0.9968 - val_loss: 0.0165 - val_accuracy: 0.9936\n",
-            "Epoch 46/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0050 - accuracy: 0.9992 - val_loss: 0.0149 - val_accuracy: 0.9904\n",
-            "Epoch 47/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0040 - accuracy: 1.0000 - val_loss: 0.0218 - val_accuracy: 0.9904\n",
-            "Epoch 48/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0047 - accuracy: 0.9984 - val_loss: 0.0158 - val_accuracy: 0.9904\n",
-            "Epoch 49/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0043 - accuracy: 0.9984 - val_loss: 0.0155 - val_accuracy: 0.9904\n",
-            "Epoch 50/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0039 - accuracy: 0.9992 - val_loss: 0.0172 - val_accuracy: 0.9936\n",
-            "Epoch 51/100\n",
-            "79/79 [==============================] - 0s 2ms/step - loss: 0.0037 - accuracy: 0.9984 - val_loss: 0.0143 - val_accuracy: 0.9904\n",
-            "Epoch 52/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0044 - accuracy: 0.9984 - val_loss: 0.0146 - val_accuracy: 0.9936\n",
-            "Epoch 53/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0038 - accuracy: 0.9984 - val_loss: 0.0139 - val_accuracy: 0.9936\n",
-            "Epoch 54/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0036 - accuracy: 0.9992 - val_loss: 0.0132 - val_accuracy: 0.9936\n",
-            "Epoch 55/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0041 - accuracy: 0.9976 - val_loss: 0.0150 - val_accuracy: 0.9936\n",
-            "Epoch 56/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0040 - accuracy: 0.9976 - val_loss: 0.0180 - val_accuracy: 0.9936\n",
-            "Epoch 57/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0038 - accuracy: 0.9984 - val_loss: 0.0150 - val_accuracy: 0.9904\n",
-            "Epoch 58/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0031 - accuracy: 1.0000 - val_loss: 0.0248 - val_accuracy: 0.9904\n",
-            "Epoch 59/100\n",
-            "79/79 [==============================] - 0s 2ms/step - loss: 0.0032 - accuracy: 0.9992 - val_loss: 0.0145 - val_accuracy: 0.9936\n",
-            "Epoch 60/100\n",
-            "79/79 [==============================] - 0s 4ms/step - loss: 0.0044 - accuracy: 0.9984 - val_loss: 0.0161 - val_accuracy: 0.9936\n",
-            "Epoch 61/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0034 - accuracy: 0.9984 - val_loss: 0.0242 - val_accuracy: 0.9904\n",
-            "Epoch 62/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0036 - accuracy: 0.9992 - val_loss: 0.0160 - val_accuracy: 0.9936\n",
-            "Epoch 63/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0041 - accuracy: 0.9984 - val_loss: 0.0150 - val_accuracy: 0.9904\n",
-            "Epoch 64/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0044 - accuracy: 0.9984 - val_loss: 0.0173 - val_accuracy: 0.9904\n",
-            "Epoch 65/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0077 - accuracy: 0.9968 - val_loss: 0.0260 - val_accuracy: 0.9904\n",
-            "Epoch 66/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0052 - accuracy: 0.9976 - val_loss: 0.0146 - val_accuracy: 0.9904\n",
-            "Epoch 67/100\n",
-            "79/79 [==============================] - 0s 2ms/step - loss: 0.0037 - accuracy: 0.9992 - val_loss: 0.0133 - val_accuracy: 0.9936\n",
-            "Epoch 68/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0030 - accuracy: 0.9992 - val_loss: 0.0194 - val_accuracy: 0.9904\n",
-            "Epoch 69/100\n",
-            "79/79 [==============================] - 0s 2ms/step - loss: 0.0035 - accuracy: 0.9984 - val_loss: 0.0138 - val_accuracy: 0.9936\n",
-            "Epoch 70/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0034 - accuracy: 0.9992 - val_loss: 0.0140 - val_accuracy: 0.9936\n",
-            "Epoch 71/100\n",
-            "79/79 [==============================] - 0s 2ms/step - loss: 0.0033 - accuracy: 0.9984 - val_loss: 0.0116 - val_accuracy: 0.9936\n",
-            "Epoch 72/100\n",
-            "79/79 [==============================] - 0s 2ms/step - loss: 0.0031 - accuracy: 0.9984 - val_loss: 0.0159 - val_accuracy: 0.9904\n",
-            "Epoch 73/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0033 - accuracy: 0.9984 - val_loss: 0.0182 - val_accuracy: 0.9904\n",
-            "Epoch 74/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0038 - accuracy: 0.9984 - val_loss: 0.0147 - val_accuracy: 0.9936\n",
-            "Epoch 75/100\n",
-            "79/79 [==============================] - 0s 2ms/step - loss: 0.0030 - accuracy: 0.9984 - val_loss: 0.0158 - val_accuracy: 0.9936\n",
-            "Epoch 76/100\n",
-            "79/79 [==============================] - 0s 2ms/step - loss: 0.0036 - accuracy: 0.9984 - val_loss: 0.0158 - val_accuracy: 0.9968\n",
-            "Epoch 77/100\n",
-            "79/79 [==============================] - 0s 5ms/step - loss: 0.0043 - accuracy: 0.9976 - val_loss: 0.0146 - val_accuracy: 0.9904\n",
-            "Epoch 78/100\n",
-            "79/79 [==============================] - 0s 4ms/step - loss: 0.0038 - accuracy: 0.9976 - val_loss: 0.0131 - val_accuracy: 0.9936\n",
-            "Epoch 79/100\n",
-            "79/79 [==============================] - 0s 4ms/step - loss: 0.0032 - accuracy: 0.9984 - val_loss: 0.0131 - val_accuracy: 0.9936\n",
-            "Epoch 80/100\n",
-            "79/79 [==============================] - 0s 4ms/step - loss: 0.0027 - accuracy: 0.9992 - val_loss: 0.0149 - val_accuracy: 0.9904\n",
-            "Epoch 81/100\n",
-            "79/79 [==============================] - 0s 5ms/step - loss: 0.0030 - accuracy: 0.9984 - val_loss: 0.0124 - val_accuracy: 0.9936\n",
-            "Epoch 82/100\n",
-            "79/79 [==============================] - 0s 5ms/step - loss: 0.0033 - accuracy: 0.9992 - val_loss: 0.0131 - val_accuracy: 0.9936\n",
-            "Epoch 83/100\n",
-            "79/79 [==============================] - 0s 5ms/step - loss: 0.0030 - accuracy: 0.9984 - val_loss: 0.0111 - val_accuracy: 0.9968\n",
-            "Epoch 84/100\n",
-            "79/79 [==============================] - 0s 4ms/step - loss: 0.0029 - accuracy: 0.9992 - val_loss: 0.0129 - val_accuracy: 0.9936\n",
-            "Epoch 85/100\n",
-            "79/79 [==============================] - 0s 5ms/step - loss: 0.0029 - accuracy: 0.9992 - val_loss: 0.0111 - val_accuracy: 0.9936\n",
-            "Epoch 86/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0030 - accuracy: 0.9992 - val_loss: 0.0119 - val_accuracy: 0.9936\n",
-            "Epoch 87/100\n",
-            "79/79 [==============================] - 0s 2ms/step - loss: 0.0042 - accuracy: 0.9976 - val_loss: 0.0114 - val_accuracy: 0.9936\n",
-            "Epoch 88/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0028 - accuracy: 0.9992 - val_loss: 0.0111 - val_accuracy: 0.9936\n",
-            "Epoch 89/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0029 - accuracy: 0.9992 - val_loss: 0.0135 - val_accuracy: 0.9936\n",
-            "Epoch 90/100\n",
-            "79/79 [==============================] - 0s 2ms/step - loss: 0.0025 - accuracy: 1.0000 - val_loss: 0.0237 - val_accuracy: 0.9904\n",
-            "Epoch 91/100\n",
-            "79/79 [==============================] - 0s 2ms/step - loss: 0.0035 - accuracy: 0.9984 - val_loss: 0.0199 - val_accuracy: 0.9904\n",
-            "Epoch 92/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0034 - accuracy: 0.9984 - val_loss: 0.0139 - val_accuracy: 0.9904\n",
-            "Epoch 93/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0028 - accuracy: 0.9984 - val_loss: 0.0110 - val_accuracy: 0.9936\n",
-            "Epoch 94/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0027 - accuracy: 0.9984 - val_loss: 0.0103 - val_accuracy: 0.9968\n",
-            "Epoch 95/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0028 - accuracy: 0.9992 - val_loss: 0.0122 - val_accuracy: 0.9936\n",
-            "Epoch 96/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0029 - accuracy: 0.9992 - val_loss: 0.0106 - val_accuracy: 0.9936\n",
-            "Epoch 97/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0036 - accuracy: 0.9984 - val_loss: 0.0114 - val_accuracy: 0.9936\n",
-            "Epoch 98/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0029 - accuracy: 0.9992 - val_loss: 0.0109 - val_accuracy: 0.9936\n",
-            "Epoch 99/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0026 - accuracy: 0.9992 - val_loss: 0.0112 - val_accuracy: 0.9904\n",
-            "Epoch 100/100\n",
-            "79/79 [==============================] - 0s 3ms/step - loss: 0.0026 - accuracy: 0.9992 - val_loss: 0.0122 - val_accuracy: 0.9936\n"
-          ]
-        }
-      ],
-      "source": [
-        "history = model.fit(X_train, y_train, epochs=100, batch_size=16, validation_data=(X_test, y_test))"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "T60N9GPoCxPI",
-        "outputId": "4f3a1c21-7630-4ebf-9a27-1f874689158a"
-      },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "10/10 [==============================] - 0s 2ms/step - loss: 0.0122 - accuracy: 0.9936\n",
-            "Test Accuracy: 99.36%\n"
-          ]
-        }
-      ],
-      "source": [
-        "#evaluation\n",
-        "loss, accuracy = model.evaluate(X_test, y_test)\n",
-        "print(f'Test Accuracy: {accuracy * 100:.2f}%')"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "f6A5EDJCOft6",
-        "outputId": "be93d0fa-df74-4ffe-f616-993fd4053f1f"
-      },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "10/10 [==============================] - 0s 2ms/step\n"
-          ]
-        }
-      ],
-      "source": [
-        "# Predictions\n",
-        "y_pred = model.predict(X_test)\n",
-        "y_pred_classes = np.argmax(y_pred, axis=1)\n",
-        "y_test_classes = np.argmax(y_test, axis=1)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "uMdhcA53OypK",
-        "outputId": "9c2bb45d-fabe-4674-a568-3d33e4348d6c"
-      },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "              precision    recall  f1-score   support\n",
-            "\n",
-            "           0       1.00      1.00      1.00        81\n",
-            "           1       1.00      1.00      1.00        97\n",
-            "           2       0.99      0.99      0.99        91\n",
-            "           3       0.95      0.95      0.95        22\n",
-            "           4       1.00      1.00      1.00        15\n",
-            "           5       1.00      1.00      1.00         7\n",
-            "\n",
-            "    accuracy                           0.99       313\n",
-            "   macro avg       0.99      0.99      0.99       313\n",
-            "weighted avg       0.99      0.99      0.99       313\n",
-            "\n"
-          ]
-        }
-      ],
-      "source": [
-        "# Classification Report\n",
-        "print(classification_report(y_test_classes, y_pred_classes))\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "# Predict new data\n",
-        "new_data = np.array([[25, 76, 19, 6, 2]])\n",
-        "new_data"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "B4gbdWipbsgq",
-        "outputId": "b8a2a70e-fa57-4cca-dfc3-309047d3c7c6"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "array([[25, 76, 19,  6,  2]])"
-            ]
-          },
-          "metadata": {},
-          "execution_count": 41
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "y_pred_new = model.predict(new_data)\n",
-        "y_pred_new"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "rcFuMnuJbxMX",
-        "outputId": "a46e5daf-7a3f-41af-9ed3-a57379f864b1"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "1/1 [==============================] - 0s 18ms/step\n"
-          ]
-        },
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "array([[8.5181101e-16, 4.0355042e-04, 9.1281807e-01, 8.6778387e-02,\n",
-              "        1.0230172e-16, 7.0790391e-19]], dtype=float32)"
-            ]
-          },
-          "metadata": {},
-          "execution_count": 42
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "y_pred_label_new = encoder.inverse_transform(y_pred_new)\n",
-        "y_pred_label_new"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "o5xrvr9ld680",
-        "outputId": "49d59d20-776b-4ad4-a17d-64a2a1edc5e1"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "array([[3]])"
-            ]
-          },
-          "metadata": {},
-          "execution_count": 43
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "9Z2wTqxPCzJO",
-        "outputId": "78ffa6c6-5baa-4c72-825c-e19ad2a34362"
-      },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Data baru diprediksi sebagai kelas: 3\n"
-          ]
-        }
-      ],
-      "source": [
-        "print(f\"Data baru diprediksi sebagai kelas: {y_pred_label_new[0][0]}\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 542
-        },
-        "id": "d8-BY9hHO3C7",
-        "outputId": "8610db98-c2cd-46db-d136-e78296391652"
-      },
-      "outputs": [
-        {
-          "output_type": "display_data",
-          "data": {
-            "text/plain": [
-              "<Figure size 1000x600 with 2 Axes>"
-            ],
-            "image/png": "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\n"
-          },
-          "metadata": {}
-        }
-      ],
-      "source": [
-        "from sklearn.metrics import confusion_matrix\n",
-        "import matplotlib.pyplot as plt\n",
-        "import seaborn as sns\n",
-        "# Confusion Matrix\n",
-        "cm = confusion_matrix(y_test_classes, y_pred_classes)\n",
-        "\n",
-        "# Plot confusion matrix\n",
-        "fig, ax = plt.subplots(figsize=(10, 6))\n",
-        "sns.heatmap(cm, annot=True, fmt=\"d\", xticklabels=encoder.categories_[0], yticklabels=encoder.categories_[0])\n",
-        "plt.xlabel('Predicted')\n",
-        "plt.ylabel('True')\n",
-        "plt.show()\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 386
-        },
-        "id": "iqAFIx9wPH39",
-        "outputId": "cd1bd6f1-3b8c-497d-c14c-8687ad4f6143"
-      },
-      "outputs": [
-        {
-          "output_type": "display_data",
-          "data": {
-            "text/plain": [
-              "<Figure size 1200x400 with 2 Axes>"
-            ],
-            "image/png": "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\n"
-          },
-          "metadata": {}
-        }
-      ],
-      "source": [
-        "import matplotlib.pyplot as plt\n",
-        "\n",
-        "# Plot training & validation accuracy values\n",
-        "plt.figure(figsize=(12, 4))\n",
-        "plt.subplot(1, 2, 1)\n",
-        "plt.plot(history.history['accuracy'])\n",
-        "plt.plot(history.history['val_accuracy'])\n",
-        "plt.title('Model Accuracy')\n",
-        "plt.ylabel('Accuracy')\n",
-        "plt.xlabel('Epoch')\n",
-        "plt.legend(['Train', 'Test'], loc='upper left')\n",
-        "\n",
-        "# Plot training & validation loss values\n",
-        "plt.subplot(1, 2, 2)\n",
-        "plt.plot(history.history['loss'])\n",
-        "plt.plot(history.history['val_loss'])\n",
-        "plt.title('Model Loss')\n",
-        "plt.ylabel('Loss')\n",
-        "plt.xlabel('Epoch')\n",
-        "plt.legend(['Train', 'Test'], loc='upper left')\n",
-        "\n",
-        "plt.show()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "brL-8yorLk6T",
-        "outputId": "1624edfd-f410-4c24-c063-33720c20a70c"
-      },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stderr",
-          "text": [
-            "/usr/local/lib/python3.10/dist-packages/keras/src/engine/training.py:3103: UserWarning: You are saving your model as an HDF5 file via `model.save()`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')`.\n",
-            "  saving_api.save_model(\n"
-          ]
-        }
-      ],
-      "source": [
-        "file_h5 = 'ANN_MODEL.h5'\n",
-        "model.save(file_h5)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "# Install TensorFlow Lite Support Library\n",
-        "!pip install tflite-support"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "slin6Td6-Mgc",
-        "outputId": "9e256648-5b70-4052-9d16-ce96d001eb8f"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Requirement already satisfied: tflite-support in /usr/local/lib/python3.10/dist-packages (0.4.4)\n",
-            "Requirement already satisfied: absl-py>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from tflite-support) (1.4.0)\n",
-            "Requirement already satisfied: numpy>=1.20.0 in /usr/local/lib/python3.10/dist-packages (from tflite-support) (1.25.2)\n",
-            "Requirement already satisfied: flatbuffers>=2.0 in /usr/local/lib/python3.10/dist-packages (from tflite-support) (24.3.25)\n",
-            "Requirement already satisfied: protobuf<4,>=3.18.0 in /usr/local/lib/python3.10/dist-packages (from tflite-support) (3.20.3)\n",
-            "Requirement already satisfied: sounddevice>=0.4.4 in /usr/local/lib/python3.10/dist-packages (from tflite-support) (0.4.7)\n",
-            "Requirement already satisfied: pybind11>=2.6.0 in /usr/local/lib/python3.10/dist-packages (from tflite-support) (2.12.0)\n",
-            "Requirement already satisfied: CFFI>=1.0 in /usr/local/lib/python3.10/dist-packages (from sounddevice>=0.4.4->tflite-support) (1.16.0)\n",
-            "Requirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from CFFI>=1.0->sounddevice>=0.4.4->tflite-support) (2.22)\n"
-          ]
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "# Mengonversi model Keras ke TensorFlow Lite\n",
-        "import tensorflow as tf\n",
-        "converter = tf.lite.TFLiteConverter.from_keras_model(model)\n",
-        "tflite_model = converter.convert()"
-      ],
-      "metadata": {
-        "id": "mCHiEmxz-GMf"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "# Menyimpan model TFLite ke file\n",
-        "tflite_model_path = \"ANN_MODEL.tflite\"\n",
-        "with open(tflite_model_path, \"wb\") as f:\n",
-        "    f.write(tflite_model)"
-      ],
-      "metadata": {
-        "id": "WQvOkG34-GrQ"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "# Unduh model dengan metadata ke lokal\n",
-        "from google.colab import files\n",
-        "files.download(tflite_model_path)"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 17
-        },
-        "id": "207ulgRX-LsG",
-        "outputId": "f5b7a95c-1bc0-42f9-a82e-2d578bd0dc47"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "display_data",
-          "data": {
-            "text/plain": [
-              "<IPython.core.display.Javascript object>"
-            ],
-            "application/javascript": [
-              "\n",
-              "    async function download(id, filename, size) {\n",
-              "      if (!google.colab.kernel.accessAllowed) {\n",
-              "        return;\n",
-              "      }\n",
-              "      const div = document.createElement('div');\n",
-              "      const label = document.createElement('label');\n",
-              "      label.textContent = `Downloading \"${filename}\": `;\n",
-              "      div.appendChild(label);\n",
-              "      const progress = document.createElement('progress');\n",
-              "      progress.max = size;\n",
-              "      div.appendChild(progress);\n",
-              "      document.body.appendChild(div);\n",
-              "\n",
-              "      const buffers = [];\n",
-              "      let downloaded = 0;\n",
-              "\n",
-              "      const channel = await google.colab.kernel.comms.open(id);\n",
-              "      // Send a message to notify the kernel that we're ready.\n",
-              "      channel.send({})\n",
-              "\n",
-              "      for await (const message of channel.messages) {\n",
-              "        // Send a message to notify the kernel that we're ready.\n",
-              "        channel.send({})\n",
-              "        if (message.buffers) {\n",
-              "          for (const buffer of message.buffers) {\n",
-              "            buffers.push(buffer);\n",
-              "            downloaded += buffer.byteLength;\n",
-              "            progress.value = downloaded;\n",
-              "          }\n",
-              "        }\n",
-              "      }\n",
-              "      const blob = new Blob(buffers, {type: 'application/binary'});\n",
-              "      const a = document.createElement('a');\n",
-              "      a.href = window.URL.createObjectURL(blob);\n",
-              "      a.download = filename;\n",
-              "      div.appendChild(a);\n",
-              "      a.click();\n",
-              "      div.remove();\n",
-              "    }\n",
-              "  "
-            ]
-          },
-          "metadata": {}
-        },
-        {
-          "output_type": "display_data",
-          "data": {
-            "text/plain": [
-              "<IPython.core.display.Javascript object>"
-            ],
-            "application/javascript": [
-              "download(\"download_55ddbdc6-07cc-4193-9e82-8f74c356d980\", \"ANN_MODEL.tflite\", 6020)"
-            ]
-          },
-          "metadata": {}
-        }
-      ]
-    }
-  ],
-  "metadata": {
-    "colab": {
-      "provenance": []
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}
\ No newline at end of file