ANN_for_Human_activity_recognition.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyP3lDXIu/uUB2Px0J2nKePJ",
      "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/Ogunfool/Timeseries-Data-Analysis-and-Forecasting/blob/main/ANN_for_Human_activity_recognition.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Time Series Data Classification with ANN.\n",
        "\n",
        "1.   Take note of the data preparation or how the data is formatted for the ANN.\n",
        "2.   Note the way the model is built - Multi-input ANN Model.\n",
        "\n"
      ],
      "metadata": {
        "id": "QT43L_esBFiB"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "\n",
        "\n",
        "1.   Examine and analyse data. (Plot distributions from one instance to another), check for trends in and out-of-periods, seasonality??\n",
        "2.   Prepare data - Differencing, AR-data, use PACF to decide the order to tune around\n",
        "\n",
        "1.   Follow tensorflow workflow to build model \n",
        "2.   Prediction/forecast functions\n",
        "\n",
        "\n",
        "1.   Model evaluation functions and plots\n",
        "2.   Model selection/hyperparameter tuning\n",
        "\n",
        "1.   Build reusable pipelines - Microsoft Azure (The ANN model building and compilation can be automated but the data preparation and input pipeline is different for different time series data types and problems (Classification, Regresion or Forecasting).\n",
        "2. Save final model and make predictions.\n",
        "\n",
        "\n",
        "\n",
        "\n",
        "\n",
        "\n",
        "\n"
      ],
      "metadata": {
        "id": "GoecrHru9TI-"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "Import Necessary Libraries"
      ],
      "metadata": {
        "id": "rcEp5CbXCiqo"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "UsU8SjI88xPP"
      },
      "outputs": [],
      "source": [
        "import numpy as np\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "import scipy\n",
        "import math\n",
        "import datetime\n",
        "from sklearn.preprocessing import OneHotEncoder, StandardScaler\n",
        "from sklearn.model_selection import train_test_split, cross_val_score, KFold, GridSearchCV\n",
        "from sklearn.metrics import r2_score, mean_squared_error, mean_absolute_error, mean_absolute_percentage_error"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!wget https://archive.ics.uci.edu/ml/datasets/Human+Activity+Recognition+Using+Smartphones"
      ],
      "metadata": {
        "id": "B8AqRG_XRDJ0"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!wget https://lazyprogrammer.me/course_files/timeseries/UCI-HAR.zip"
      ],
      "metadata": {
        "id": "DMwaQc3uEat0",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "36e50177-8a16-4814-be7f-f374c9df54bc"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--2023-04-04 14:16:30--  https://lazyprogrammer.me/course_files/timeseries/UCI-HAR.zip\n",
            "Resolving lazyprogrammer.me (lazyprogrammer.me)... 172.67.213.166, 104.21.23.210, 2606:4700:3030::ac43:d5a6, ...\n",
            "Connecting to lazyprogrammer.me (lazyprogrammer.me)|172.67.213.166|:443... connected.\n",
            "HTTP request sent, awaiting response... 200 OK\n",
            "Length: 60999314 (58M) [application/zip]\n",
            "Saving to: ‘UCI-HAR.zip’\n",
            "\n",
            "UCI-HAR.zip         100%[===================>]  58.17M  26.2MB/s    in 2.2s    \n",
            "\n",
            "2023-04-04 14:16:33 (26.2 MB/s) - ‘UCI-HAR.zip’ saved [60999314/60999314]\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Load data - Data is 3-dimensional."
      ],
      "metadata": {
        "id": "GwIGmgj2U2fq"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "!unzip /content/UCI-HAR.zip"
      ],
      "metadata": {
        "id": "ViG2FP2eDshI"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!unzip -nq UCI-HAR.zip"
      ],
      "metadata": {
        "id": "1zCQUGmEFIzs"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!ls"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dnpsmZ-tE1pj",
        "outputId": "3c52961f-a933-40b1-aecf-1cec218dc9bd"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            " Human+Activity+Recognition+Using+Smartphones   sample_data\t   UCI-HAR.zip\n",
            " __MACOSX\t\t\t\t       'UCI HAR Dataset'\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!ls 'UCI HAR Dataset'"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "L-cMAHIIFah4",
        "outputId": "8b488302-18ac-4c62-e406-e1c0ac210121"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "activity_labels.txt  features_info.txt\tfeatures.txt  README.txt  test\ttrain\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!ls 'UCI HAR Dataset/train'"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nBpfWGYOFscd",
        "outputId": "b21ae3c1-d843-4b51-e308-7510556b1d1a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "'Inertial Signals'   subject_train.txt\t X_train.txt   y_train.txt\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!head 'UCI HAR Dataset/train/X_train.txt'"
      ],
      "metadata": {
        "id": "cpSFdWdIGCRf"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Load data with numpy\n",
        "hum_train = pd.read_csv('/content/UCI HAR Dataset/train/Inertial Signals/body_acc_x_train.txt', header=None, \n",
        "                     delim_whitespace=True)\n",
        "hum_train.head()"
      ],
      "metadata": {
        "id": "n7WF6iUPRa1x",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 299
        },
        "outputId": "840aca26-c411-4d1f-a133-339edee79890"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "        0         1         2         3         4         5         6    \\\n",
              "0  0.000181  0.010139  0.009276  0.005066  0.010810  0.004045  0.004757   \n",
              "1  0.001094  0.004550  0.002879  0.002247  0.003305  0.002416  0.001619   \n",
              "2  0.003531  0.002285 -0.000420 -0.003738 -0.006706 -0.003148  0.000733   \n",
              "3 -0.001772 -0.001311  0.000388  0.000408 -0.000355  0.000998  0.001109   \n",
              "4  0.000087 -0.000272  0.001022  0.003126  0.002284  0.000885  0.001933   \n",
              "\n",
              "        7         8         9    ...       118       119       120       121  \\\n",
              "0  0.006214  0.003307  0.007572  ...  0.001412 -0.001509  0.000060  0.000435   \n",
              "1  0.000981  0.000009 -0.000363  ... -0.000104 -0.000141  0.001333  0.001541   \n",
              "2  0.000668  0.002162 -0.000946  ...  0.000661  0.001853 -0.000268 -0.000394   \n",
              "3 -0.003149 -0.008882 -0.010483  ...  0.000458  0.002103  0.001358  0.000820   \n",
              "4  0.002270  0.002247  0.002175  ...  0.002529  0.003518 -0.000248 -0.002761   \n",
              "\n",
              "        122       123       124       125       126       127  \n",
              "0 -0.000819  0.000228 -0.000300 -0.001147 -0.000222  0.001576  \n",
              "1  0.001077 -0.000736 -0.003767 -0.004646 -0.002941 -0.001599  \n",
              "2 -0.000279 -0.000316  0.000144  0.001246  0.003117  0.002178  \n",
              "3 -0.000212 -0.001915 -0.001631 -0.000867 -0.001172 -0.000028  \n",
              "4  0.000252  0.003752  0.001626 -0.000698 -0.001223 -0.003328  \n",
              "\n",
              "[5 rows x 128 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-d7b27450-f54e-428e-9026-567349eed18a\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>0</th>\n",
              "      <th>1</th>\n",
              "      <th>2</th>\n",
              "      <th>3</th>\n",
              "      <th>4</th>\n",
              "      <th>5</th>\n",
              "      <th>6</th>\n",
              "      <th>7</th>\n",
              "      <th>8</th>\n",
              "      <th>9</th>\n",
              "      <th>...</th>\n",
              "      <th>118</th>\n",
              "      <th>119</th>\n",
              "      <th>120</th>\n",
              "      <th>121</th>\n",
              "      <th>122</th>\n",
              "      <th>123</th>\n",
              "      <th>124</th>\n",
              "      <th>125</th>\n",
              "      <th>126</th>\n",
              "      <th>127</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0.000181</td>\n",
              "      <td>0.010139</td>\n",
              "      <td>0.009276</td>\n",
              "      <td>0.005066</td>\n",
              "      <td>0.010810</td>\n",
              "      <td>0.004045</td>\n",
              "      <td>0.004757</td>\n",
              "      <td>0.006214</td>\n",
              "      <td>0.003307</td>\n",
              "      <td>0.007572</td>\n",
              "      <td>...</td>\n",
              "      <td>0.001412</td>\n",
              "      <td>-0.001509</td>\n",
              "      <td>0.000060</td>\n",
              "      <td>0.000435</td>\n",
              "      <td>-0.000819</td>\n",
              "      <td>0.000228</td>\n",
              "      <td>-0.000300</td>\n",
              "      <td>-0.001147</td>\n",
              "      <td>-0.000222</td>\n",
              "      <td>0.001576</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0.001094</td>\n",
              "      <td>0.004550</td>\n",
              "      <td>0.002879</td>\n",
              "      <td>0.002247</td>\n",
              "      <td>0.003305</td>\n",
              "      <td>0.002416</td>\n",
              "      <td>0.001619</td>\n",
              "      <td>0.000981</td>\n",
              "      <td>0.000009</td>\n",
              "      <td>-0.000363</td>\n",
              "      <td>...</td>\n",
              "      <td>-0.000104</td>\n",
              "      <td>-0.000141</td>\n",
              "      <td>0.001333</td>\n",
              "      <td>0.001541</td>\n",
              "      <td>0.001077</td>\n",
              "      <td>-0.000736</td>\n",
              "      <td>-0.003767</td>\n",
              "      <td>-0.004646</td>\n",
              "      <td>-0.002941</td>\n",
              "      <td>-0.001599</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0.003531</td>\n",
              "      <td>0.002285</td>\n",
              "      <td>-0.000420</td>\n",
              "      <td>-0.003738</td>\n",
              "      <td>-0.006706</td>\n",
              "      <td>-0.003148</td>\n",
              "      <td>0.000733</td>\n",
              "      <td>0.000668</td>\n",
              "      <td>0.002162</td>\n",
              "      <td>-0.000946</td>\n",
              "      <td>...</td>\n",
              "      <td>0.000661</td>\n",
              "      <td>0.001853</td>\n",
              "      <td>-0.000268</td>\n",
              "      <td>-0.000394</td>\n",
              "      <td>-0.000279</td>\n",
              "      <td>-0.000316</td>\n",
              "      <td>0.000144</td>\n",
              "      <td>0.001246</td>\n",
              "      <td>0.003117</td>\n",
              "      <td>0.002178</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>-0.001772</td>\n",
              "      <td>-0.001311</td>\n",
              "      <td>0.000388</td>\n",
              "      <td>0.000408</td>\n",
              "      <td>-0.000355</td>\n",
              "      <td>0.000998</td>\n",
              "      <td>0.001109</td>\n",
              "      <td>-0.003149</td>\n",
              "      <td>-0.008882</td>\n",
              "      <td>-0.010483</td>\n",
              "      <td>...</td>\n",
              "      <td>0.000458</td>\n",
              "      <td>0.002103</td>\n",
              "      <td>0.001358</td>\n",
              "      <td>0.000820</td>\n",
              "      <td>-0.000212</td>\n",
              "      <td>-0.001915</td>\n",
              "      <td>-0.001631</td>\n",
              "      <td>-0.000867</td>\n",
              "      <td>-0.001172</td>\n",
              "      <td>-0.000028</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0.000087</td>\n",
              "      <td>-0.000272</td>\n",
              "      <td>0.001022</td>\n",
              "      <td>0.003126</td>\n",
              "      <td>0.002284</td>\n",
              "      <td>0.000885</td>\n",
              "      <td>0.001933</td>\n",
              "      <td>0.002270</td>\n",
              "      <td>0.002247</td>\n",
              "      <td>0.002175</td>\n",
              "      <td>...</td>\n",
              "      <td>0.002529</td>\n",
              "      <td>0.003518</td>\n",
              "      <td>-0.000248</td>\n",
              "      <td>-0.002761</td>\n",
              "      <td>0.000252</td>\n",
              "      <td>0.003752</td>\n",
              "      <td>0.001626</td>\n",
              "      <td>-0.000698</td>\n",
              "      <td>-0.001223</td>\n",
              "      <td>-0.003328</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 128 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-d7b27450-f54e-428e-9026-567349eed18a')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-d7b27450-f54e-428e-9026-567349eed18a 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-d7b27450-f54e-428e-9026-567349eed18a');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# NxT for a single feature\n",
        "hum_train.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "MxbxgTAzG4qf",
        "outputId": "7e94f0ad-77cf-4c86-840c-9f230f8d9f29"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(7352, 128)"
            ]
          },
          "metadata": {},
          "execution_count": 30
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "hum_train.info()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7QD0TivtH-zD",
        "outputId": "0d2000ea-c1c2-49f2-8429-86bb241c7ca4"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 7352 entries, 0 to 7351\n",
            "Columns: 128 entries, 0 to 127\n",
            "dtypes: float64(128)\n",
            "memory usage: 7.2 MB\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "hum_train.loc[:3].T.plot()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 447
        },
        "id": "kWzB4k9xIs76",
        "outputId": "fa6291f9-05f6-46bd-b1cc-c18c02367baa"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<Axes: >"
            ]
          },
          "metadata": {},
          "execution_count": 32
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "hum_y = pd.read_csv('/content/UCI HAR Dataset/train/y_train.txt')\n",
        "hum_y.head()"
      ],
      "metadata": {
        "id": "2ixDDMylLNOa"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "hum_y.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "c7p17GjWMB5S",
        "outputId": "5878cc63-94fe-4dcc-cd51-851b1e725488"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(7351, 1)"
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "np.unique(hum_y)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Ur5E7i2HULCM",
        "outputId": "847088fd-87a6-4e60-d7f1-be9ab3f3898f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([1, 2, 3, 4, 5, 6])"
            ]
          },
          "metadata": {},
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Understanding the data and feature engineering: Depending on the domain knowledge, some features acn be extracted from the timeseries data; kurtosis, skewness, mean etc. They are commonly referred to as time domain or frequency domain features; see https://www.mathworks.com/help/predmaint/ug/wind-turbine-high-speed-bearing-prognosis.html\n",
        "But they require some domain expertise/knowledge."
      ],
      "metadata": {
        "id": "SdegZb35Uy4A"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "Prepare Your Data:Create an array of size NxTxD.\n",
        "We don't need to create NxTxD first then list of NxT, we can just create a list of NxT directly."
      ],
      "metadata": {
        "id": "drKL6VPqZu7J"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "T = hum_train.shape[1]   # Sample duration\n",
        "Ntrain = hum_train.shape[0]  # No of samples\n",
        "D = 9  # No of features per smaple\n",
        "K = np.unique(hum_y).shape[0]  # No of classes\n",
        "Ntest = 2947\n",
        "# print(T, Ntrain, D, K)"
      ],
      "metadata": {
        "id": "7BmGdtVzTzc0"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "T = 128\n",
        "Ntrain = 7352\n",
        "D = 9\n",
        "K = 6\n",
        "Ntest = 2947"
      ],
      "metadata": {
        "id": "gwoI6u3_s2WK"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Load Data, Form NxTxK array and/or list of inputs into the model.\n",
        "def load_data():\n",
        "  # Returns:\n",
        "  # Xtrain (Ntrain x T x D), Ytrain (Ntrain)\n",
        "  # Xtest (Ntest x T x D), Ytest (Ntest)\n",
        "  # Model input list for train and test\n",
        "\n",
        "  Xtrain = np.zeros((Ntrain, T, D))\n",
        "  Xtest = np.zeros((Ntest, T, D))\n",
        "  x_train = []\n",
        "  x_test = []\n",
        "\n",
        "  # train data\n",
        "  ts_filenames = [\n",
        "    'body_acc_x_train.txt', 'body_gyro_x_train.txt', 'total_acc_x_train.txt',\n",
        "    'body_acc_y_train.txt', 'body_gyro_y_train.txt', 'total_acc_y_train.txt',\n",
        "    'body_acc_z_train.txt', 'body_gyro_z_train.txt', 'total_acc_z_train.txt',\n",
        "  ]\n",
        "\n",
        "  ts_file_prefix = '/content/UCI HAR Dataset/train/'\n",
        "\n",
        "  for d, fn in enumerate(ts_filenames):\n",
        "    df = pd.read_csv(f'{ts_file_prefix}Inertial Signals/{fn}', header=None, delim_whitespace=True)\n",
        "\n",
        "    # Ntrain x T array\n",
        "    x = df.to_numpy()\n",
        "    Xtrain[:, :, d] = x\n",
        "\n",
        "    # list of arrays\n",
        "    x_train.append(x)\n",
        "  \n",
        "  # train labels\n",
        "  Ytrain = pd.read_csv(f'{ts_file_prefix}y_train.txt', header=None).to_numpy() - 1   #Classes change from 1-6 to 0-5\n",
        "  Ytrain = Ytrain.flatten()\n",
        "\n",
        "  # test data\n",
        "  ts_filenames = [\n",
        "    'body_acc_x_test.txt', 'body_gyro_x_test.txt', 'total_acc_x_test.txt',\n",
        "    'body_acc_y_test.txt', 'body_gyro_y_test.txt', 'total_acc_y_test.txt',\n",
        "    'body_acc_z_test.txt', 'body_gyro_z_test.txt', 'total_acc_z_test.txt',\n",
        "  ]\n",
        "\n",
        "  ts_file_prefix = '/content/UCI HAR Dataset/test/'\n",
        "\n",
        "  for d, fn in enumerate(ts_filenames):\n",
        "    df = pd.read_csv(f'{ts_file_prefix}Inertial Signals/{fn}', header=None, delim_whitespace=True)\n",
        "\n",
        "    # Ntrain x T array\n",
        "    x = df.to_numpy()\n",
        "    Xtest[:, :, d] = x\n",
        "\n",
        "    x_test.append(x)\n",
        "  \n",
        "  # test labels\n",
        "  Ytest = pd.read_csv(f'{ts_file_prefix}y_test.txt', header=None).to_numpy() - 1\n",
        "  Ytest = Ytest.flatten()\n",
        "\n",
        "  return Xtrain, Ytrain, Xtest, Ytest, x_train, x_test"
      ],
      "metadata": {
        "id": "QPFfLygLo19Z"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "Xtrain, Ytrain, Xtest, Ytest, x_train, x_test = load_data()"
      ],
      "metadata": {
        "id": "ji2vU4d5sbOo"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "print(Xtrain.shape, Ytrain.shape, Xtest.shape, Ytest.shape)\n",
        "print(len(x_train), len(x_test))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "zFsusnRysVeU",
        "outputId": "fca16482-dd0e-4fb7-8fde-409b79ed08ec"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(7352, 128, 9) (7352,) (2947, 128, 9) (2947,)\n",
            "9 9\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "x_train[0].shape"
      ],
      "metadata": {
        "id": "vaRqDn7etVol"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "THE ANN Model using the keras functional API: Note the following;\n",
        "\n",
        "\n",
        "1.   The functional API uses symbolic tensors that store evry operation performed on them after initialization.\n",
        "2.   The model accepts the inputs and output arguments. The inputs can be a list and so is the output.\n",
        "\n",
        "\n",
        "\n",
        "1.   Each input layer expects a shape (T,) nd the model expects a list of inputs of shape (T,). The point here is during prediction, for each feature, a (T,) shpe is required. So this model can be used for classification and regression not forecasting where the complete T, dataset is unknown. \n",
        "\n",
        "1.   Note how we pass the variables around just as we would when we create a function.\n",
        "\n",
        "\n",
        "1.  You can plot your model. \n",
        "\n",
        "\n",
        "\n",
        "\n",
        "\n",
        "\n",
        "\n",
        "\n",
        "\n",
        "\n",
        "\n"
      ],
      "metadata": {
        "id": "St6IDDHYRQRH"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf\n",
        "from tensorflow import keras\n",
        "from tensorflow.keras.layers import Input, Dense, Concatenate\n",
        "from tensorflow.keras.models import Model, Sequential\n",
        "from tensorflow.keras.losses import SparseCategoricalCrossentropy, categorical_crossentropy, mean_squared_error\n",
        "from tensorflow.keras.optimizers import Adam, RMSprop, Adagrad, SGD\n",
        "from tensorflow.keras.metrics import Accuracy, Recall\n",
        "from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping"
      ],
      "metadata": {
        "id": "us_mU-BYWjre"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# The ANN Model development - Multi-Input/Multi-tail ANN\n",
        "# You have to keep track of the input and the output of the model\n",
        "inputs = []\n",
        "features = []\n",
        "\n",
        "# Build a dense ANN model for each feature - \n",
        "# If you use the input layers in a for loop, different unique instances of the symbolic tensors are automatically created - So they can have their unique function flow\n",
        "for _ in range(D):\n",
        "  i = Input(shape=(T,))\n",
        "  x = Dense(32, activation='relu')(i)\n",
        "  x = Dense(32, activation='relu')(x)\n",
        "  inputs.append(i)\n",
        "  features.append(x)\n",
        "\n",
        "# recall, we want to concatenate the outputs of the multi-unit ANN models\n",
        "# N x (FxD)\n",
        "x = Concatenate()(features)\n",
        "# Now start working on this\n",
        "x = Dense(K)(x)\n",
        "\n",
        "# Instantiate Model\n",
        "model = Model(inputs, x)"
      ],
      "metadata": {
        "id": "LJwMOqWXUgZg"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "features"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "e6-ioVq_bKgP",
        "outputId": "0931d1b0-debc-4548-9684-16897f05bf5a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[<KerasTensor: shape=(None, 32) dtype=float32 (created by layer 'dense_1')>,\n",
              " <KerasTensor: shape=(None, 32) dtype=float32 (created by layer 'dense_3')>,\n",
              " <KerasTensor: shape=(None, 32) dtype=float32 (created by layer 'dense_5')>,\n",
              " <KerasTensor: shape=(None, 32) dtype=float32 (created by layer 'dense_7')>,\n",
              " <KerasTensor: shape=(None, 32) dtype=float32 (created by layer 'dense_9')>,\n",
              " <KerasTensor: shape=(None, 32) dtype=float32 (created by layer 'dense_11')>,\n",
              " <KerasTensor: shape=(None, 32) dtype=float32 (created by layer 'dense_13')>,\n",
              " <KerasTensor: shape=(None, 32) dtype=float32 (created by layer 'dense_15')>,\n",
              " <KerasTensor: shape=(None, 32) dtype=float32 (created by layer 'dense_17')>]"
            ]
          },
          "metadata": {},
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model.summary()"
      ],
      "metadata": {
        "id": "HQ6Mqs0RXtrZ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "tf.keras.utils.plot_model(model)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 337
        },
        "id": "PMWn98iIbJ2_",
        "outputId": "3cbf0d98-f4bc-4ead-ce22-b737c557af2d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<IPython.core.display.Image object>"
            ]
          },
          "metadata": {},
          "execution_count": 24
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Let's try another method - The method is ok, but the above is more intuitive so I prefer it."
      ],
      "metadata": {
        "id": "BodKFx9rbvw5"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Build a dense ANN model for each feature - \n",
        "# If you use the input layers in a for loop, different unique instances of the symbolic tensors are automatically created - So they can have their unique function flow\n",
        "for _ in range(D):\n",
        "  i = Input(shape=(T,))\n",
        "  x = Dense(32, activation='relu')(i)\n",
        "  x = Dense(32, activation='relu')(x)\n",
        "  inputs.append(i)\n",
        "  features.append(x)\n",
        "\n",
        "# Merge models rather than concatenate\n",
        "merged = tf.keras.layers.add(features)\n",
        "\n",
        "# define functional model\n",
        "model = Model(inputs, merged)"
      ],
      "metadata": {
        "id": "ZmBIC5KLbyFe"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "tf.keras.utils.plot_model(model)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 157
        },
        "id": "q2OOBrZnckqO",
        "outputId": "288ff385-422d-481a-d9b8-61b414f66d3a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<IPython.core.display.Image object>"
            ]
          },
          "metadata": {},
          "execution_count": 50
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Compile, Fit, Predict and Evaluate Model."
      ],
      "metadata": {
        "id": "Kt1n1Fhst-gy"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "Compile and callbacks helper function"
      ],
      "metadata": {
        "id": "cXIfsSI1vgIb"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Let's create some helper functions for the training process (We are trying to select a model so, many models will be trained and they have similar execution configurations)\n",
        "# Learning Rate Scheduler:\n",
        "def lr_scheduler(STEPS_PER_EPOCH):\n",
        "  lr_schedule = tf.keras.optimizers.schedules.InverseTimeDecay(\n",
        "    0.001,\n",
        "    decay_steps=STEPS_PER_EPOCH*1000,\n",
        "    decay_rate=1,\n",
        "    staircase=False)\n",
        "  return lr_schedule\n",
        "\n",
        "def get_optimizer(scheduler=None):\n",
        "  if scheduler is None:\n",
        "    return tf.keras.optimizers.Adam(learning_rate=0.001)\n",
        "  return tf.keras.optimizers.Adam(lr_scheduler())\n",
        "\n",
        "# def get_callbacks():\n",
        "#   return [\n",
        "#     tfdocs.modeling.EpochDots(),\n",
        "#     tf.keras.callbacks.EarlyStopping(monitor='accuracy', patience=40),\n",
        "#   ]\n",
        "\n",
        "# Compile and fit\n",
        "# You can pass in a different loss function and optimizer asides from the default adam and sparsecategorical loss I set:\n",
        "def compile(model, optimizer=None, scheduler=None,  loss=None, max_epochs=1000, STEPS_PER_EPOCH=1000):\n",
        "  if optimizer is None:    # that is, i want to set Adam optimizer & learning rate to 0.001 by default or use a lr_scheduler function\n",
        "    optimizer = get_optimizer()\n",
        "  else:\n",
        "    optimizer = optimizer\n",
        "\n",
        "  if loss is None:\n",
        "    loss = keras.losses.SparseCategoricalCrossentropy(from_logits=True)\n",
        "  else:\n",
        "    loss = loss\n",
        "\n",
        "  model.compile(optimizer=optimizer, loss=loss, metrics=['accuracy'])\n",
        "\n",
        "  return model\n"
      ],
      "metadata": {
        "id": "Ua9TtOxUkKS5"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model = compile(model)\n",
        "check_point = ModelCheckpoint(\n",
        "    'best_model.h5', monitor='val_accuracy', save_best_only=True)\n",
        "# model.summary()\n",
        "\n",
        "history = model.fit(x_train, Ytrain, epochs=15, \n",
        "                    validation_data=(x_test, Ytest),\n",
        "                    callbacks=[check_point],\n",
        "                    verbose=2)\n"
      ],
      "metadata": {
        "id": "DOFOKocRxBbV"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Evaluate on test set\n",
        "model.evaluate(x_test, Ytest)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DTEoVfZT2mpo",
        "outputId": "8ade00f1-3380-4853-da27-d2ad7a194ea6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "93/93 [==============================] - 0s 2ms/step - loss: 0.3822 - accuracy: 0.9223\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[0.3821779489517212, 0.9222938418388367]"
            ]
          },
          "metadata": {},
          "execution_count": 37
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Load best model\n",
        "best_model = tf.keras.models.load_model('best_model.h5')\n",
        "\n",
        "# Make predictions with best model \n",
        "y_pred = best_model.predict(x_test)\n",
        "\n",
        "# Evaluate with best model\n",
        "best_model.evaluate(x_test, Ytest)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Zqvp0dyk4MGX",
        "outputId": "b1b82389-28c9-44f8-e4ff-c273f893012e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "93/93 [==============================] - 0s 2ms/step\n",
            "93/93 [==============================] - 1s 3ms/step - loss: 0.3101 - accuracy: 0.9260\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[0.31013360619544983, 0.926026463508606]"
            ]
          },
          "metadata": {},
          "execution_count": 41
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Plots Helper Functions"
      ],
      "metadata": {
        "id": "dJc5tkZYvX_d"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Helper function that plots, saves and shows plots\n",
        "def plot_loss_accuracy(filename):\n",
        "  acc = history.history['accuracy']\n",
        "  val_acc = history.history['val_accuracy']\n",
        "  loss = history.history['loss']\n",
        "  val_loss = history.history['val_loss']\n",
        "\n",
        "  epochs = range(len(acc))\n",
        "\n",
        "  plt.plot(epochs, acc, 'r', label='Training accuracy')\n",
        "  plt.plot(epochs, val_acc, 'b', label='Validation accuracy')\n",
        "  plt.title('Training and validation accuracy')\n",
        "  plt.legend(loc=0)\n",
        "  plt.figure()\n",
        "\n",
        "  plt.plot(epochs, loss, 'r', label='Training loss')\n",
        "  plt.plot(epochs, val_loss, 'b', label='Validation loss')\n",
        "  plt.title('Training and validation accuracy')\n",
        "  plt.legend(loc=0)\n",
        "  plt.figure()\n",
        "\n",
        "  plt.savefig(filename + '.png')\n",
        "  plt.show()"
      ],
      "metadata": {
        "id": "8NAScmNHg70e"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "plot_loss_accuracy(filename='ANN for timeseries classification')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 905
        },
        "id": "26tOUO684XvH",
        "outputId": "868f5ba8-307b-447f-b793-fc960ed824e5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 0 Axes>"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "GbWNwzKg5CIi"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Time and Frequency Domain Signals of the data."
      ],
      "metadata": {
        "id": "mAcTdGPt9YEE"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "X_train = np.loadtxt('/content/UCI HAR Dataset/train/X_train.txt')"
      ],
      "metadata": {
        "id": "IuANAL8L9avl"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X_train.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "FeM3xCsy9loA",
        "outputId": "d692e2f5-5819-4b92-da8b-3a877834d23a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(7352, 561)"
            ]
          },
          "metadata": {},
          "execution_count": 43
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X_train[0]"
      ],
      "metadata": {
        "id": "L2XksrUE97s5"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "We can use this combined model to use the inertia data of shape NxTxD and time & frequency data with shape NxD together."
      ],
      "metadata": {
        "id": "V1doNh3rAMsr"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Combined Model\n",
        "inputs = []\n",
        "features = []\n",
        "\n",
        "# make a neural network for each of the D time series\n",
        "for d in range(D):\n",
        "  i = Input(shape=(T,))\n",
        "  x = Dense(32, activation='relu')(i)\n",
        "  x = Dense(16, activation='relu')(x)\n",
        "  inputs.append(i)\n",
        "  features.append(x)\n",
        "\n",
        "i2 = Input(shape=(561,))\n",
        "x2 = Dense(32, activation='relu')(i2)\n",
        "\n",
        "# output of concatenate will be D * (size of individual ANN output)\n",
        "x = Concatenate()(features + [x2])\n",
        "x = Dense(K)(x)\n",
        "model = Model(inputs + [i2], x)"
      ],
      "metadata": {
        "id": "Z849yvlxALdT"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Finally, How about I just use N x (TxD) as input to a neural network?"
      ],
      "metadata": {
        "id": "rNF06C40CqT6"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Prepare Data - Use x_train list\n",
        "Xtrain = x_train[0]\n",
        "for id in np.arange(1,len(x_train)):\n",
        "  Xtrain = np.concatenate((Xtrain, x_train[id]), axis=1)\n",
        "\n",
        "Xtrain.shape\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "MatWKnMDC1MI",
        "outputId": "7601d8a3-4ccf-4d43-c346-6182f49b4615"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(7352, 1152)"
            ]
          },
          "metadata": {},
          "execution_count": 65
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Prepare Data - Use x_test list\n",
        "Xtest = x_test[0]\n",
        "for id in np.arange(1,len(x_test)):\n",
        "  Xtest = np.concatenate((Xtest, x_test[id]), axis=1)\n",
        "\n",
        "Xtest.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "897hCZPgGU-c",
        "outputId": "032b1858-3c66-4ccf-bf64-3ee50344ed3d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(2947, 1152)"
            ]
          },
          "metadata": {},
          "execution_count": 66
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Basic ANN\n",
        "i = Input(shape=(1152,))\n",
        "x = Dense(32, activation='relu')(i)\n",
        "x = Dense(32, activation='relu')(x)\n",
        "x = Dense(K)(x)\n",
        "model = Model(i, x)"
      ],
      "metadata": {
        "id": "9OKeqtYkGvfn"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model = compile(model)\n",
        "check_point = ModelCheckpoint(\n",
        "    'best_model.h6', monitor='val_accuracy', save_best_only=True)\n",
        "# model.summary()\n",
        "\n",
        "history = model.fit(Xtrain, Ytrain, epochs=15, \n",
        "                    validation_data=(Xtest, Ytest),\n",
        "                    callbacks=[check_point],\n",
        "                    verbose=2)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "iPuPzbTgHIWG",
        "outputId": "7ace0517-01db-4022-c0d4-2a8680199225"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/15\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:Found untraced functions such as _update_step_xla while saving (showing 1 of 1). These functions will not be directly callable after loading.\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "230/230 - 2s - loss: 0.6964 - accuracy: 0.7635 - val_loss: 0.5907 - val_accuracy: 0.8093 - 2s/epoch - 10ms/step\n",
            "Epoch 2/15\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:Found untraced functions such as _update_step_xla while saving (showing 1 of 1). These functions will not be directly callable after loading.\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "230/230 - 1s - loss: 0.2760 - accuracy: 0.9056 - val_loss: 0.4559 - val_accuracy: 0.8446 - 1s/epoch - 6ms/step\n",
            "Epoch 3/15\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:Found untraced functions such as _update_step_xla while saving (showing 1 of 1). These functions will not be directly callable after loading.\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "230/230 - 1s - loss: 0.1863 - accuracy: 0.9304 - val_loss: 0.5012 - val_accuracy: 0.8565 - 1s/epoch - 6ms/step\n",
            "Epoch 4/15\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:Found untraced functions such as _update_step_xla while saving (showing 1 of 1). These functions will not be directly callable after loading.\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "230/230 - 1s - loss: 0.1521 - accuracy: 0.9416 - val_loss: 0.5027 - val_accuracy: 0.8778 - 1s/epoch - 6ms/step\n",
            "Epoch 5/15\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:Found untraced functions such as _update_step_xla while saving (showing 1 of 1). These functions will not be directly callable after loading.\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "230/230 - 2s - loss: 0.1261 - accuracy: 0.9479 - val_loss: 0.5297 - val_accuracy: 0.8836 - 2s/epoch - 9ms/step\n",
            "Epoch 6/15\n",
            "230/230 - 1s - loss: 0.1112 - accuracy: 0.9546 - val_loss: 0.6204 - val_accuracy: 0.8585 - 956ms/epoch - 4ms/step\n",
            "Epoch 7/15\n",
            "230/230 - 1s - loss: 0.1024 - accuracy: 0.9581 - val_loss: 0.6860 - val_accuracy: 0.8571 - 667ms/epoch - 3ms/step\n",
            "Epoch 8/15\n",
            "230/230 - 1s - loss: 0.1005 - accuracy: 0.9582 - val_loss: 0.6800 - val_accuracy: 0.8629 - 629ms/epoch - 3ms/step\n",
            "Epoch 9/15\n",
            "230/230 - 1s - loss: 0.0917 - accuracy: 0.9612 - val_loss: 0.7092 - val_accuracy: 0.8571 - 621ms/epoch - 3ms/step\n",
            "Epoch 10/15\n",
            "230/230 - 1s - loss: 0.0935 - accuracy: 0.9589 - val_loss: 0.7882 - val_accuracy: 0.8575 - 644ms/epoch - 3ms/step\n",
            "Epoch 11/15\n",
            "230/230 - 1s - loss: 0.0887 - accuracy: 0.9614 - val_loss: 0.7587 - val_accuracy: 0.8639 - 635ms/epoch - 3ms/step\n",
            "Epoch 12/15\n",
            "230/230 - 1s - loss: 0.0843 - accuracy: 0.9629 - val_loss: 0.9042 - val_accuracy: 0.8490 - 608ms/epoch - 3ms/step\n",
            "Epoch 13/15\n",
            "230/230 - 1s - loss: 0.0831 - accuracy: 0.9638 - val_loss: 0.9995 - val_accuracy: 0.8534 - 662ms/epoch - 3ms/step\n",
            "Epoch 14/15\n",
            "230/230 - 1s - loss: 0.0891 - accuracy: 0.9603 - val_loss: 0.9669 - val_accuracy: 0.8510 - 645ms/epoch - 3ms/step\n",
            "Epoch 15/15\n",
            "230/230 - 1s - loss: 0.0835 - accuracy: 0.9627 - val_loss: 1.0596 - val_accuracy: 0.8514 - 629ms/epoch - 3ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Evaluate on test set\n",
        "model.evaluate(Xtest, Ytest)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "b53c7ff1-c2ba-4272-e4be-f05c2c6cae51",
        "id": "loNg6O6IHIWG"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "93/93 [==============================] - 0s 3ms/step - loss: 1.0596 - accuracy: 0.8514\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[1.0596213340759277, 0.8513742685317993]"
            ]
          },
          "metadata": {},
          "execution_count": 72
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Load best model\n",
        "best_model = tf.keras.models.load_model('best_model.h6')\n",
        "\n",
        "# Make predictions with best model \n",
        "y_pred = best_model.predict(Xtest)\n",
        "\n",
        "# Evaluate with best model\n",
        "best_model.evaluate(Xtest, Ytest)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "5c3748c5-a651-413a-fe3e-ab9c2d6069d9",
        "id": "EUolH-NPHIWH"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "93/93 [==============================] - 0s 2ms/step\n",
            "93/93 [==============================] - 0s 2ms/step - loss: 0.5297 - accuracy: 0.8836\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[0.5296804308891296, 0.8836104273796082]"
            ]
          },
          "metadata": {},
          "execution_count": 74
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Comment: We can see that the accuracy with this method is much lower. It will require more training and tuning to achieve accuracy close to that of the initial model. Now you see why that initial method is key."
      ],
      "metadata": {
        "id": "43plA7efH9PW"
      }
    }
  ]
}