{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import pandas\n", "from keras.models import Sequential\n", "from keras.layers import Dense\n", "from keras.wrappers.scikit_learn import KerasClassifier\n", "from keras.utils import np_utils\n", "from sklearn.model_selection import cross_val_score\n", "from sklearn.model_selection import KFold\n", "from sklearn.preprocessing import LabelEncoder\n", "from sklearn.pipeline import Pipeline" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "# load dataset\n", "dataframe = pandas.read_excel(r\"C:\\Users\\math\\Desktop\\anawork\\scada\\scadadata5.xls\", header=None)\n", "dataset = dataframe.values\n", "X = dataset[:,0:3].astype(float)\n", "Y = dataset[:,3]" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "# encode class values as integers\n", "encoder = LabelEncoder()\n", "encoder.fit(Y)\n", "encoded_Y = encoder.transform(Y)\n", "# convert integers to dummy variables (i.e. one hot encoded)\n", "dummy_y = np_utils.to_categorical(encoded_Y)" ] }, { "cell_type": "code", "execution_count": 52, "metadata": {}, "outputs": [], "source": [ "# define baseline model\n", "def baseline_model():\n", "# create model\n", "\tmodel = Sequential()\n", "\tmodel.add(Dense(45, input_dim=3, activation='relu'))\n", "\tmodel.add(Dense(20, activation='softmax'))\n", "# Compile model\n", "#model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])\n", "\tmodel.compile(loss='mse', optimizer='adam', metrics=['mae'])\n", "# 'categorical_crossentropy' 'mse'\n", "\treturn model" ] }, { "cell_type": "code", "execution_count": 58, "metadata": {}, "outputs": [], "source": [ "#import seaborn as sns\n", "#sns.lineplot(data=results)\n", "#print(results.shape)\n", "import matplotlib.pyplot as plt\n", "plotmodel= baseline_model()\n", "history = plotmodel.fit(X, dummy_y, epochs=150, batch_size=50, verbose=0)\n", "#history = plotmodel.fit(X, dummy_y, epochs=500, batch_size=len(X), verbose=2)\n", "#pyplot.plot(history.history['mean_squared_error'])\n", "#pyplot.plot(history.history['mean_absolute_error'])\n", "#pyplot.plot(history.history['mean_absolute_percentage_error'])\n", "#pyplot.plot(history.history['cosine_proximity'])\n", "#pyplot.show()" ] }, { "cell_type": "code", "execution_count": 59, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "dict_keys(['loss', 'mae'])\n" ] } ], "source": [ "print(history.history.keys())" ] }, { "cell_type": "code", "execution_count": 60, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plt.plot(history.history['mae'])\n", "#plt.plot(history.history['val_accuracy'])\n", "plt.title('Model Mean Absolute Error (MAE)')\n", "plt.ylabel('MAE')\n", "plt.xlabel('epoch')\n", "#plt.legend(['train', 'test'], loc='upper left')\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 61, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plt.plot(history.history['loss'])\n", "#plt.plot(history.history['val_accuracy'])\n", "plt.title('Model Loss')\n", "plt.ylabel('Loss')\n", "plt.xlabel('epoch')\n", "#plt.legend(['train', 'test'], loc='upper left')\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 62, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0.05003522778550784\n", "0.08366949751973152\n" ] } ], "source": [ "import numpy as np\n", "print(np.mean(history.history['loss']))\n", "print(np.mean(history.history['mae']))" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.5" } }, "nbformat": 4, "nbformat_minor": 4 }