Created
May 23, 2017 09:15
-
-
Save ukeshchawal/dd563c258cbf07324b8ecfd7f66e5abd to your computer and use it in GitHub Desktop.
sample
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Using TensorFlow backend.\n" ] } ], "source": [ "import numpy as np\n", "\n", "from keras.models import Sequential\n", "from keras.layers import Dense, LSTM, Dropout\n", "from sklearn.preprocessing import MinMaxScaler\n", "\n", "import matplotlib.pyplot as plt\n", "\n", "import theano" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYYAAAD8CAYAAABzTgP2AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\npEiRYhNSxZAiRYoUKTbh/wecFOk5xsLSRQAAAABJRU5ErkJggg==\n", "text/plain": [ "<matplotlib.figure.Figure at 0x7a5c3c8>" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "dataset = np.cos(np.arange(1000)*(20*np.pi/1000))[:,None]\n", "plt.plot(dataset)\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "# convert an array of values into a dataset matrix\n", "def create_dataset(dataset, look_back=1):\n", " dataX, dataY = [], []\n", " for i in range(len(dataset)-look_back):\n", " dataX.append(dataset[i:(i+look_back), 0])\n", " dataY.append(dataset[i + look_back, 0])\n", " return np.array(dataX), np.array(dataY)" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "collapsed": true }, "outputs": [], "source": [ "look_back = 20\n", "scaler = MinMaxScaler(feature_range=(0, 1))\n", "dataset = scaler.fit_transform(dataset)\n", "\n", "# split into train and test sets\n", "train_size = int(len(dataset) * 0.67)\n", "test_size = len(dataset) - train_size\n", "train, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]\n", "\n", "trainX, trainY = create_dataset(train, look_back)\n", "testX, testY = create_dataset(test, look_back)\n", "\n", "trainX = np.reshape(trainX, (trainX.shape[0], trainX.shape[1], 1))\n", "testX = np.reshape(testX, (testX.shape[0], testX.shape[1], 1))" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": true }, "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": "3.5.3" } }, "nbformat": 4, "nbformat_minor": 2} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment