diff --git a/Regression using ANN/CCPP_ANN.ipynb b/Regression using ANN/CCPP_ANN.ipynb
index e13d71c5..91f48fc5 100644
--- a/Regression using ANN/CCPP_ANN.ipynb
+++ b/Regression using ANN/CCPP_ANN.ipynb
@@ -4,7 +4,7 @@
"metadata": {
"colab": {
"provenance": [],
- "include_colab_link": true
+ "gpuType": "T4"
},
"kernelspec": {
"name": "python3",
@@ -12,14 +12,14 @@
},
"language_info": {
"name": "python"
- }
+ },
+ "accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
- "id": "view-in-github",
- "colab_type": "text"
+ "id": "view-in-github"
},
"source": [
"![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\")
"
@@ -34,63 +34,46 @@
"id": "vKB9yAxzMYJd"
}
},
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "id": "0V0y2N8XVtuo"
- },
- "outputs": [],
- "source": [
- "import tensorflow as tf\n",
- "import numpy as np\n",
- "import pandas as pd"
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "data = pd.read_excel(\"/content/drive/MyDrive/Colab Notebooks/ANN/Folds5x2_pp.xlsx\")"
- ],
- "metadata": {
- "id": "qsVE5AxoDVSL"
- },
- "execution_count": null,
- "outputs": []
- },
{
"cell_type": "code",
"source": [
- "from google.colab import drive\n",
- "drive.mount('/content/drive')"
+ "! pip install ucimlrepo\n",
+ "!pip install keras-tuner\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
- "id": "-2IshJ60qqEE",
- "outputId": "c08ba8c7-7fcf-4a0f-8002-a8a73070a1ca"
+ "id": "cHuLWgylCmFX",
+ "outputId": "4b57b777-a367-44e5-afd7-35a77f5544b7"
},
- "execution_count": null,
+ "execution_count": 2,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
- "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
+ "Collecting ucimlrepo\n",
+ " Downloading ucimlrepo-0.0.7-py3-none-any.whl.metadata (5.5 kB)\n",
+ "Requirement already satisfied: pandas>=1.0.0 in /usr/local/lib/python3.12/dist-packages (from ucimlrepo) (2.2.2)\n",
+ "Requirement already satisfied: certifi>=2020.12.5 in /usr/local/lib/python3.12/dist-packages (from ucimlrepo) (2026.6.17)\n",
+ "Requirement already satisfied: numpy>=1.26.0 in /usr/local/lib/python3.12/dist-packages (from pandas>=1.0.0->ucimlrepo) (2.0.2)\n",
+ "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas>=1.0.0->ucimlrepo) (2.9.0.post0)\n",
+ "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas>=1.0.0->ucimlrepo) (2025.2)\n",
+ "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas>=1.0.0->ucimlrepo) (2026.3)\n",
+ "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas>=1.0.0->ucimlrepo) (1.17.0)\n",
+ "Downloading ucimlrepo-0.0.7-py3-none-any.whl (8.0 kB)\n",
+ "Installing collected packages: ucimlrepo\n",
+ "Successfully installed ucimlrepo-0.0.7\n"
]
}
]
},
{
"cell_type": "code",
- "source": [
- "#seperating values of dataset \n",
- "X = data.iloc[:,:-1].values\n",
- "Y = data.iloc[:,-1].values"
- ],
+ "source": [],
"metadata": {
- "id": "JG22B2v2V5Qb"
+ "id": "GNkGvW2aE_3G"
},
"execution_count": null,
"outputs": []
@@ -98,90 +81,195 @@
{
"cell_type": "code",
"source": [
- "#splitting the dataset into train set and test set\n",
- "from sklearn.model_selection import train_test_split as tts\n",
- "X_train,X_test,Y_train,Y_test = tts(X,Y, test_size = 0.2, random_state = 0)"
+ "import tensorflow as tf\n",
+ "import numpy as np\n",
+ "import pandas as pd\n",
+ "from ucimlrepo import fetch_ucirepo\n",
+ "import keras_tuner as kt"
],
"metadata": {
- "id": "GSQpRA70_EnV"
+ "id": "N3SlI5I8DDKr"
},
- "execution_count": null,
+ "execution_count": 15,
"outputs": []
},
{
"cell_type": "code",
"source": [
- "ann = tf.keras.models.Sequential()"
+ "combined_cycle_power_plant = fetch_ucirepo(id=294)\n",
+ "\n",
+ "# data (as pandas dataframes)\n",
+ "X = combined_cycle_power_plant.data.features\n",
+ "y = combined_cycle_power_plant.data.targets\n",
+ "\n",
+ "# metadata\n",
+ "# print(combined_cycle_power_plant.metadata)\n",
+ "\n",
+ "# # variable information\n",
+ "# print(combined_cycle_power_plant.variables)\n"
],
"metadata": {
- "id": "9nRKGjws_E27"
+ "id": "TdOtEmrJCo3E"
},
- "execution_count": null,
+ "execution_count": 5,
"outputs": []
},
- {
- "cell_type": "markdown",
- "source": [
- "The tf.keras.models.Sequential() function returns a new sequential model object that can be used to define\n",
- "the architecture of a neural network. Once initialized, you can add layers to the model using the add() method.\n"
- ],
- "metadata": {
- "id": "hMNEpujq32n4"
- }
- },
{
"cell_type": "code",
"source": [
- "ann.add(tf.keras.layers.Dense(units = 6, activation=\"relu\"))"
+ "df = pd.concat([X, y], axis=1)\n",
+ "\n",
+ "print(df.head())"
],
"metadata": {
- "id": "NAWN0NEo_FQi"
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "8540otb-C7ol",
+ "outputId": "275c2720-0e38-469a-def8-49132ce71858"
},
- "execution_count": null,
- "outputs": []
+ "execution_count": 6,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ " AT V AP RH PE\n",
+ "0 14.96 41.76 1024.07 73.17 463.26\n",
+ "1 25.18 62.96 1020.04 59.08 444.37\n",
+ "2 5.11 39.40 1012.16 92.14 488.56\n",
+ "3 20.86 57.32 1010.24 76.64 446.48\n",
+ "4 10.82 37.50 1009.23 96.62 473.90\n"
+ ]
+ }
+ ]
},
{
"cell_type": "code",
"source": [
- "ann.add(tf.keras.layers.Dense(units = 6, activation=\"relu\"))"
+ "#seperating values of dataset\n",
+ "X = df.iloc[:,:-1].values\n",
+ "Y = df.iloc[:,-1].values"
],
"metadata": {
- "id": "o-tEk4mk_FaV"
+ "id": "JG22B2v2V5Qb"
},
- "execution_count": null,
+ "execution_count": 7,
"outputs": []
},
{
"cell_type": "code",
"source": [
- "ann.add(tf.keras.layers.Dense(units = 1))"
+ "from sklearn.model_selection import train_test_split\n",
+ "from sklearn.preprocessing import StandardScaler\n",
+ "\n",
+ "X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.2, random_state=42)\n",
+ "\n",
+ "# Initialize Scaler\n",
+ "scaler = StandardScaler()\n",
+ "\n",
+ "# Fit on training data AND transform it\n",
+ "X_train_scaled = scaler.fit_transform(X_train)\n",
+ "\n",
+ "# Transform test data using the SAME fitted scaler\n",
+ "X_test_scaled = scaler.transform(X_test)"
],
"metadata": {
- "id": "DWQYEAEf_Fe9"
+ "id": "hEXq3Zd0EBeU"
},
- "execution_count": null,
+ "execution_count": 12,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
- "The Adam optimizer is a widely used optimization algorithm for training deep learning models. It uses a combination of momentum and adaptive learning rates to efficiently navigate the high-dimensional parameter space and converge to a good solution.\n"
+ "The tf.keras.models.Sequential() function returns a new sequential model object that can be used to define\n",
+ "the architecture of a neural network. Once initialized, you can add layers to the model using the add() method.\n"
],
"metadata": {
- "id": "ySqtFMiIIww6"
+ "id": "hMNEpujq32n4"
}
},
{
"cell_type": "code",
"source": [
- "ann.compile(optimizer = 'adam', loss = 'mean_squared_error')"
+ "def build_model(hp):\n",
+ " model = tf.keras.models.Sequential()\n",
+ "\n",
+ " # Automatically tune the number of hidden layers (e.g., between 1 and 4)\n",
+ " for i in range(hp.Int('num_layers', min_value=1, max_value=4)):\n",
+ " model.add(\n",
+ " tf.keras.layers.Dense(\n",
+ " # Automatically tune the number of units/neurons per layer\n",
+ " units=hp.Int(f'units_{i}', min_value=8, max_value=128, step=8),\n",
+ " # Automatically test different activation functions\n",
+ " activation=hp.Choice(f'activation_{i}', values=['relu', 'tanh'])\n",
+ " )\n",
+ " )\n",
+ "\n",
+ " # Output layer for regression (1 unit, no activation function)\n",
+ " model.add(tf.keras.layers.Dense(units=1))\n",
+ "\n",
+ " # Automatically tune the learning rate for the Adam optimizer\n",
+ " hp_learning_rate = hp.Choice('learning_rate', values=[1e-2, 1e-3, 1e-4])\n",
+ "\n",
+ " model.compile(\n",
+ " optimizer=tf.keras.optimizers.Adam(learning_rate=hp_learning_rate),\n",
+ " loss='mean_squared_error',\n",
+ " metrics=['mean_absolute_error']\n",
+ " )\n",
+ "\n",
+ " return model"
],
"metadata": {
- "id": "khFLNcH0GuAR"
+ "collapsed": true,
+ "id": "qjPvj8GYE58e"
},
- "execution_count": null,
+ "execution_count": 16,
"outputs": []
},
+ {
+ "cell_type": "code",
+ "source": [
+ "tuner = kt.Hyperband(\n",
+ " build_model,\n",
+ " objective='val_loss',\n",
+ " max_epochs=20,\n",
+ " factor=3,\n",
+ " directory='keras_tuner_dir',\n",
+ " project_name='ccpp_tuning'\n",
+ ")\n",
+ "tuner.search(\n",
+ " X_train_scaled,\n",
+ " y_train,\n",
+ " epochs=20,\n",
+ " validation_data=(X_test_scaled, y_test)\n",
+ ")\n",
+ "best_model = tuner.get_best_models(num_models=1)[0]"
+ ],
+ "metadata": {
+ "id": "NAWN0NEo_FQi",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "collapsed": true,
+ "outputId": "58bf29e6-f27f-4223-cea7-3e453af03528"
+ },
+ "execution_count": 17,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Trial 30 Complete [00h 00m 23s]\n",
+ "val_loss: 17.565309524536133\n",
+ "\n",
+ "Best val_loss So Far: 16.797618865966797\n",
+ "Total elapsed time: 00h 05m 47s\n"
+ ]
+ }
+ ]
+ },
{
"cell_type": "markdown",
"source": [
@@ -194,263 +282,245 @@
{
"cell_type": "code",
"source": [
- "ann.fit(X_train, Y_train, batch_size = 32, epochs = 100)"
+ "history = best_model.fit(X_train_scaled, y_train, epochs=100, batch_size=32, validation_data=(X_test_scaled, y_test))\n",
+ "\n",
+ "loss_df = pd.DataFrame(history.history)\n",
+ "\n",
+ "# Add Epoch column starting at 1\n",
+ "loss_df.index = loss_df.index + 1\n",
+ "loss_df.index.name = 'Epoch'\n",
+ "\n",
+ "# Display the loss values\n",
+ "print(loss_df)"
],
"metadata": {
- "id": "rlNrNm0__FlT",
"colab": {
"base_uri": "https://localhost:8080/"
},
- "outputId": "2c126d38-17ce-438e-d8f5-f5b13e515098"
+ "id": "NTQkWvpSvYfU",
+ "outputId": "07cf4137-7b68-4552-e408-b6bd7616975f"
},
- "execution_count": null,
+ "execution_count": 18,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/100\n",
- "240/240 [==============================] - 1s 2ms/step - loss: 87643.6719\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 11ms/step - loss: 18.3178 - mean_absolute_error: 3.3199 - val_loss: 18.4678 - val_mean_absolute_error: 3.2960\n",
"Epoch 2/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 267.0827\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 3ms/step - loss: 18.4355 - mean_absolute_error: 3.3252 - val_loss: 20.0764 - val_mean_absolute_error: 3.5339\n",
"Epoch 3/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 225.0462\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 18.7356 - mean_absolute_error: 3.3569 - val_loss: 22.9946 - val_mean_absolute_error: 3.8140\n",
"Epoch 4/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 218.9589\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 18.7002 - mean_absolute_error: 3.3512 - val_loss: 20.5898 - val_mean_absolute_error: 3.6000\n",
"Epoch 5/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 211.9290\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 18.5721 - mean_absolute_error: 3.3498 - val_loss: 17.1752 - val_mean_absolute_error: 3.2526\n",
"Epoch 6/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 204.1414\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 18.3797 - mean_absolute_error: 3.3233 - val_loss: 17.8122 - val_mean_absolute_error: 3.2625\n",
"Epoch 7/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 195.1124\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 18.4118 - mean_absolute_error: 3.3255 - val_loss: 17.0099 - val_mean_absolute_error: 3.2465\n",
"Epoch 8/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 185.7437\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 18.1923 - mean_absolute_error: 3.3109 - val_loss: 17.8171 - val_mean_absolute_error: 3.3171\n",
"Epoch 9/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 175.2805\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.8804 - mean_absolute_error: 3.2701 - val_loss: 17.0761 - val_mean_absolute_error: 3.2503\n",
"Epoch 10/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 165.0381\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 18.3804 - mean_absolute_error: 3.3021 - val_loss: 17.3709 - val_mean_absolute_error: 3.3093\n",
"Epoch 11/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 153.9754\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 18.0527 - mean_absolute_error: 3.2931 - val_loss: 16.9568 - val_mean_absolute_error: 3.2407\n",
"Epoch 12/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 143.2326\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - loss: 18.2192 - mean_absolute_error: 3.3030 - val_loss: 18.7883 - val_mean_absolute_error: 3.4111\n",
"Epoch 13/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 132.4496\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - loss: 18.0092 - mean_absolute_error: 3.2921 - val_loss: 17.0024 - val_mean_absolute_error: 3.2374\n",
"Epoch 14/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 122.1509\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - loss: 17.8316 - mean_absolute_error: 3.2690 - val_loss: 21.0703 - val_mean_absolute_error: 3.5564\n",
"Epoch 15/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 111.8504\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 18.1136 - mean_absolute_error: 3.2859 - val_loss: 16.9130 - val_mean_absolute_error: 3.2391\n",
"Epoch 16/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 102.4270\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.7318 - mean_absolute_error: 3.2568 - val_loss: 19.7436 - val_mean_absolute_error: 3.4556\n",
"Epoch 17/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 94.0232\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.8528 - mean_absolute_error: 3.2774 - val_loss: 17.3111 - val_mean_absolute_error: 3.2751\n",
"Epoch 18/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 85.3746\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.9363 - mean_absolute_error: 3.2730 - val_loss: 16.9114 - val_mean_absolute_error: 3.1885\n",
"Epoch 19/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 77.8924\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.7905 - mean_absolute_error: 3.2607 - val_loss: 18.0174 - val_mean_absolute_error: 3.3286\n",
"Epoch 20/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 71.0033\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.8079 - mean_absolute_error: 3.2619 - val_loss: 17.5210 - val_mean_absolute_error: 3.3102\n",
"Epoch 21/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 64.9267\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 18.4696 - mean_absolute_error: 3.3235 - val_loss: 17.1580 - val_mean_absolute_error: 3.2717\n",
"Epoch 22/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 59.5436\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.8167 - mean_absolute_error: 3.2683 - val_loss: 17.0482 - val_mean_absolute_error: 3.2196\n",
"Epoch 23/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 54.3075\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 18.4594 - mean_absolute_error: 3.3265 - val_loss: 17.0118 - val_mean_absolute_error: 3.2384\n",
"Epoch 24/100\n",
- "240/240 [==============================] - 1s 2ms/step - loss: 50.2759\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.8246 - mean_absolute_error: 3.2602 - val_loss: 16.7081 - val_mean_absolute_error: 3.1914\n",
"Epoch 25/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 46.5180\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - loss: 17.9689 - mean_absolute_error: 3.2740 - val_loss: 16.9617 - val_mean_absolute_error: 3.2012\n",
"Epoch 26/100\n",
- "240/240 [==============================] - 1s 2ms/step - loss: 43.8271\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - loss: 17.7611 - mean_absolute_error: 3.2614 - val_loss: 16.5995 - val_mean_absolute_error: 3.1885\n",
"Epoch 27/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 41.6056\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - loss: 17.4984 - mean_absolute_error: 3.2303 - val_loss: 17.3453 - val_mean_absolute_error: 3.2222\n",
"Epoch 28/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 39.7205\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - loss: 17.6914 - mean_absolute_error: 3.2506 - val_loss: 17.3249 - val_mean_absolute_error: 3.2619\n",
"Epoch 29/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 38.0673\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.8228 - mean_absolute_error: 3.2626 - val_loss: 16.7402 - val_mean_absolute_error: 3.2221\n",
"Epoch 30/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 37.1770\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.7672 - mean_absolute_error: 3.2614 - val_loss: 16.8953 - val_mean_absolute_error: 3.2319\n",
"Epoch 31/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 35.8520\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - loss: 17.8726 - mean_absolute_error: 3.2652 - val_loss: 17.3750 - val_mean_absolute_error: 3.2869\n",
"Epoch 32/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 34.9797\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.9467 - mean_absolute_error: 3.2823 - val_loss: 17.2779 - val_mean_absolute_error: 3.2451\n",
"Epoch 33/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 33.8846\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.6485 - mean_absolute_error: 3.2436 - val_loss: 16.5588 - val_mean_absolute_error: 3.1983\n",
"Epoch 34/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 33.1752\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 18.0054 - mean_absolute_error: 3.2770 - val_loss: 17.8506 - val_mean_absolute_error: 3.2652\n",
"Epoch 35/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 32.3737\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.7183 - mean_absolute_error: 3.2693 - val_loss: 16.6774 - val_mean_absolute_error: 3.1851\n",
"Epoch 36/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 31.9514\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.5528 - mean_absolute_error: 3.2268 - val_loss: 16.7084 - val_mean_absolute_error: 3.2203\n",
"Epoch 37/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 31.7655\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.8398 - mean_absolute_error: 3.2712 - val_loss: 16.6055 - val_mean_absolute_error: 3.1817\n",
"Epoch 38/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 31.0428\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.4855 - mean_absolute_error: 3.2377 - val_loss: 16.7377 - val_mean_absolute_error: 3.1814\n",
"Epoch 39/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 30.6156\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.7298 - mean_absolute_error: 3.2502 - val_loss: 17.0044 - val_mean_absolute_error: 3.1965\n",
"Epoch 40/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 29.7629\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - loss: 17.7183 - mean_absolute_error: 3.2552 - val_loss: 16.6872 - val_mean_absolute_error: 3.2127\n",
"Epoch 41/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 30.0632\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - loss: 17.7786 - mean_absolute_error: 3.2584 - val_loss: 17.7405 - val_mean_absolute_error: 3.2515\n",
"Epoch 42/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 29.0554\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - loss: 17.8554 - mean_absolute_error: 3.2684 - val_loss: 19.3860 - val_mean_absolute_error: 3.4965\n",
"Epoch 43/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 29.1440\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.8908 - mean_absolute_error: 3.2719 - val_loss: 18.3008 - val_mean_absolute_error: 3.2905\n",
"Epoch 44/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 29.3539\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.8258 - mean_absolute_error: 3.2669 - val_loss: 17.0467 - val_mean_absolute_error: 3.2351\n",
"Epoch 45/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 28.3446\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.8252 - mean_absolute_error: 3.2605 - val_loss: 17.2192 - val_mean_absolute_error: 3.2814\n",
"Epoch 46/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 27.9064\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.5644 - mean_absolute_error: 3.2356 - val_loss: 18.9286 - val_mean_absolute_error: 3.4548\n",
"Epoch 47/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 27.7371\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.3903 - mean_absolute_error: 3.2273 - val_loss: 17.0160 - val_mean_absolute_error: 3.2435\n",
"Epoch 48/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 27.9368\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.6739 - mean_absolute_error: 3.2491 - val_loss: 17.5713 - val_mean_absolute_error: 3.2476\n",
"Epoch 49/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 27.8239\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.6631 - mean_absolute_error: 3.2485 - val_loss: 16.7727 - val_mean_absolute_error: 3.2092\n",
"Epoch 50/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 27.2741\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.9788 - mean_absolute_error: 3.2806 - val_loss: 16.8999 - val_mean_absolute_error: 3.2650\n",
"Epoch 51/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 27.1623\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.8484 - mean_absolute_error: 3.2584 - val_loss: 16.7302 - val_mean_absolute_error: 3.2220\n",
"Epoch 52/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 27.6709\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - loss: 17.5307 - mean_absolute_error: 3.2391 - val_loss: 16.9270 - val_mean_absolute_error: 3.2341\n",
"Epoch 53/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 27.4004\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 18.1089 - mean_absolute_error: 3.2864 - val_loss: 20.4871 - val_mean_absolute_error: 3.5266\n",
"Epoch 54/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 27.7198\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - loss: 17.4772 - mean_absolute_error: 3.2220 - val_loss: 16.5657 - val_mean_absolute_error: 3.1830\n",
"Epoch 55/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 27.2275\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - loss: 17.6393 - mean_absolute_error: 3.2437 - val_loss: 16.7582 - val_mean_absolute_error: 3.1956\n",
"Epoch 56/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 27.2186\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - loss: 17.4562 - mean_absolute_error: 3.2289 - val_loss: 17.2492 - val_mean_absolute_error: 3.2591\n",
"Epoch 57/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.8182\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.4977 - mean_absolute_error: 3.2275 - val_loss: 17.3208 - val_mean_absolute_error: 3.2690\n",
"Epoch 58/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.9084\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.4286 - mean_absolute_error: 3.2173 - val_loss: 16.6321 - val_mean_absolute_error: 3.2145\n",
"Epoch 59/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.8736\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.4749 - mean_absolute_error: 3.2306 - val_loss: 17.3972 - val_mean_absolute_error: 3.2362\n",
"Epoch 60/100\n",
- "240/240 [==============================] - 1s 2ms/step - loss: 27.4942\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.5019 - mean_absolute_error: 3.2218 - val_loss: 16.6388 - val_mean_absolute_error: 3.1951\n",
"Epoch 61/100\n",
- "240/240 [==============================] - 1s 2ms/step - loss: 26.7395\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.6537 - mean_absolute_error: 3.2396 - val_loss: 16.7543 - val_mean_absolute_error: 3.2122\n",
"Epoch 62/100\n",
- "240/240 [==============================] - 1s 2ms/step - loss: 27.5176\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.8443 - mean_absolute_error: 3.2493 - val_loss: 16.3165 - val_mean_absolute_error: 3.1392\n",
"Epoch 63/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.6098\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.5200 - mean_absolute_error: 3.2234 - val_loss: 16.8358 - val_mean_absolute_error: 3.2023\n",
"Epoch 64/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.9977\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.3832 - mean_absolute_error: 3.2038 - val_loss: 16.7020 - val_mean_absolute_error: 3.1989\n",
"Epoch 65/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.7823\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.3563 - mean_absolute_error: 3.2156 - val_loss: 16.5961 - val_mean_absolute_error: 3.1971\n",
"Epoch 66/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 27.2252\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.5102 - mean_absolute_error: 3.2214 - val_loss: 17.0635 - val_mean_absolute_error: 3.1977\n",
"Epoch 67/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.5412\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.5936 - mean_absolute_error: 3.2403 - val_loss: 17.3397 - val_mean_absolute_error: 3.2139\n",
"Epoch 68/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 26.6553\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - loss: 17.9918 - mean_absolute_error: 3.2767 - val_loss: 16.8634 - val_mean_absolute_error: 3.1904\n",
"Epoch 69/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.7763\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - loss: 17.5120 - mean_absolute_error: 3.2338 - val_loss: 17.3211 - val_mean_absolute_error: 3.1990\n",
"Epoch 70/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 27.2166\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - loss: 17.3473 - mean_absolute_error: 3.2149 - val_loss: 17.6489 - val_mean_absolute_error: 3.2729\n",
"Epoch 71/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.4494\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.5272 - mean_absolute_error: 3.2256 - val_loss: 16.6752 - val_mean_absolute_error: 3.1972\n",
"Epoch 72/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.5784\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.4464 - mean_absolute_error: 3.2192 - val_loss: 17.7752 - val_mean_absolute_error: 3.2345\n",
"Epoch 73/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.7082\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.3705 - mean_absolute_error: 3.2149 - val_loss: 18.5547 - val_mean_absolute_error: 3.3510\n",
"Epoch 74/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.8492\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.4548 - mean_absolute_error: 3.2248 - val_loss: 16.2061 - val_mean_absolute_error: 3.1271\n",
"Epoch 75/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.8747\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.1265 - mean_absolute_error: 3.1886 - val_loss: 17.7625 - val_mean_absolute_error: 3.2468\n",
"Epoch 76/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 26.6791\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - loss: 17.1426 - mean_absolute_error: 3.1860 - val_loss: 18.6191 - val_mean_absolute_error: 3.3436\n",
"Epoch 77/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.6648\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.0712 - mean_absolute_error: 3.1956 - val_loss: 17.9095 - val_mean_absolute_error: 3.2641\n",
"Epoch 78/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.6983\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.0770 - mean_absolute_error: 3.1766 - val_loss: 16.6120 - val_mean_absolute_error: 3.1794\n",
"Epoch 79/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.9250\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.1119 - mean_absolute_error: 3.1870 - val_loss: 17.0590 - val_mean_absolute_error: 3.1598\n",
"Epoch 80/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 27.0190\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.2549 - mean_absolute_error: 3.2030 - val_loss: 17.4997 - val_mean_absolute_error: 3.2446\n",
"Epoch 81/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 26.7804\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.0627 - mean_absolute_error: 3.1719 - val_loss: 16.0001 - val_mean_absolute_error: 3.1279\n",
"Epoch 82/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.5667\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - loss: 17.0441 - mean_absolute_error: 3.1831 - val_loss: 18.4255 - val_mean_absolute_error: 3.3235\n",
"Epoch 83/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.6470\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - loss: 17.2492 - mean_absolute_error: 3.1916 - val_loss: 16.7408 - val_mean_absolute_error: 3.1640\n",
"Epoch 84/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 27.1911\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - loss: 17.1250 - mean_absolute_error: 3.1827 - val_loss: 16.1321 - val_mean_absolute_error: 3.0987\n",
"Epoch 85/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.6923\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.3562 - mean_absolute_error: 3.2068 - val_loss: 16.3293 - val_mean_absolute_error: 3.1449\n",
"Epoch 86/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.5327\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.2027 - mean_absolute_error: 3.1973 - val_loss: 16.0960 - val_mean_absolute_error: 3.1348\n",
"Epoch 87/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 27.0401\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 16.9979 - mean_absolute_error: 3.1678 - val_loss: 16.1081 - val_mean_absolute_error: 3.1470\n",
"Epoch 88/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 26.7529\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 16.8781 - mean_absolute_error: 3.1609 - val_loss: 19.1579 - val_mean_absolute_error: 3.4493\n",
"Epoch 89/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.7333\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.0356 - mean_absolute_error: 3.1709 - val_loss: 17.0031 - val_mean_absolute_error: 3.2025\n",
"Epoch 90/100\n",
- "240/240 [==============================] - 1s 2ms/step - loss: 26.9290\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.2240 - mean_absolute_error: 3.2034 - val_loss: 19.4953 - val_mean_absolute_error: 3.4736\n",
"Epoch 91/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.8608\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 16.9089 - mean_absolute_error: 3.1614 - val_loss: 16.3104 - val_mean_absolute_error: 3.1395\n",
"Epoch 92/100\n",
- "240/240 [==============================] - 1s 2ms/step - loss: 26.8838\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.0880 - mean_absolute_error: 3.1688 - val_loss: 16.4276 - val_mean_absolute_error: 3.1795\n",
"Epoch 93/100\n",
- "240/240 [==============================] - 1s 2ms/step - loss: 26.5286\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 16.8918 - mean_absolute_error: 3.1556 - val_loss: 15.7847 - val_mean_absolute_error: 3.0918\n",
"Epoch 94/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.5370\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 16.7885 - mean_absolute_error: 3.1350 - val_loss: 18.3563 - val_mean_absolute_error: 3.3793\n",
"Epoch 95/100\n",
- "240/240 [==============================] - 1s 2ms/step - loss: 26.7323\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.1921 - mean_absolute_error: 3.1878 - val_loss: 16.9198 - val_mean_absolute_error: 3.1407\n",
"Epoch 96/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 27.0699\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 17.0178 - mean_absolute_error: 3.1692 - val_loss: 16.3850 - val_mean_absolute_error: 3.1351\n",
"Epoch 97/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 27.2160\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - loss: 17.1277 - mean_absolute_error: 3.1747 - val_loss: 15.8725 - val_mean_absolute_error: 3.1084\n",
"Epoch 98/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 26.4927\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - loss: 16.9026 - mean_absolute_error: 3.1651 - val_loss: 16.1404 - val_mean_absolute_error: 3.0846\n",
"Epoch 99/100\n",
- "240/240 [==============================] - 0s 1ms/step - loss: 27.0903\n",
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - loss: 16.7620 - mean_absolute_error: 3.1412 - val_loss: 16.1462 - val_mean_absolute_error: 3.1264\n",
"Epoch 100/100\n",
- "240/240 [==============================] - 0s 2ms/step - loss: 26.8351\n"
- ]
- },
- {
- "output_type": "execute_result",
- "data": {
- "text/plain": [
- ""
- ]
- },
- "metadata": {},
- "execution_count": 16
- }
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "y_pred = ann.predict(X_test)\n",
- "np.set_printoptions(precision=2)\n",
- "print(np.concatenate((y_pred.reshape(len(y_pred),1),Y_test.reshape(len(Y_test),1)),1))"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "NTQkWvpSvYfU",
- "outputId": "4ddd0393-cdb4-4add-fe69-7044e7978cb8"
- },
- "execution_count": null,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "60/60 [==============================] - 0s 1ms/step\n",
- "[[431.39 431.23]\n",
- " [462.49 460.01]\n",
- " [466. 461.14]\n",
- " ...\n",
- " [473.24 473.26]\n",
- " [440.01 438. ]\n",
- " [459.24 463.28]]\n"
+ "\u001b[1m240/240\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 16.8693 - mean_absolute_error: 3.1588 - val_loss: 17.8827 - val_mean_absolute_error: 3.3236\n",
+ " loss mean_absolute_error val_loss val_mean_absolute_error\n",
+ "Epoch \n",
+ "1 18.317768 3.319866 18.467783 3.296021\n",
+ "2 18.435503 3.325200 20.076435 3.533949\n",
+ "3 18.735590 3.356885 22.994648 3.814006\n",
+ "4 18.700239 3.351227 20.589809 3.600004\n",
+ "5 18.572107 3.349821 17.175203 3.252573\n",
+ "... ... ... ... ...\n",
+ "96 17.017776 3.169248 16.384958 3.135109\n",
+ "97 17.127689 3.174672 15.872488 3.108429\n",
+ "98 16.902554 3.165069 16.140366 3.084615\n",
+ "99 16.762045 3.141158 16.146194 3.126396\n",
+ "100 16.869316 3.158783 17.882736 3.323621\n",
+ "\n",
+ "[100 rows x 4 columns]\n"
]
}
]