|
@@ -0,0 +1,88 @@
|
|
|
+import numpy
|
|
|
+import matplotlib.pyplot as plt
|
|
|
+import pandas
|
|
|
+import math
|
|
|
+from keras.models import Sequential
|
|
|
+from keras.layers import Dense
|
|
|
+from keras.layers import LSTM
|
|
|
+from sklearn.preprocessing import MinMaxScaler
|
|
|
+from sklearn.metrics import mean_squared_error
|
|
|
+
|
|
|
+numpy.random.seed(7)
|
|
|
+
|
|
|
+# convert an array of values into a dataset matrix
|
|
|
+def create_dataset(dataset, look_back=1):
|
|
|
+ dataX, dataY = [], []
|
|
|
+ for i in range(len(dataset)-look_back-1):
|
|
|
+ a = dataset[i:(i+look_back-12)]
|
|
|
+ dataX.append(a)
|
|
|
+ dataY.append(dataset[i + look_back])
|
|
|
+ return numpy.array(dataX), numpy.array(dataY)
|
|
|
+
|
|
|
+def predict(src2month):
|
|
|
+
|
|
|
+ pkg_num = len(src2month)
|
|
|
+ training_num = len(src2month['linux'])-12
|
|
|
+ dataset = src2month['openjdk']
|
|
|
+ past = dataset[:len(dataset)-12]
|
|
|
+ dataset = pandas.rolling_mean(dataset, window=12)
|
|
|
+ dataset = dataset[12:]
|
|
|
+
|
|
|
+ # normalize the dataset
|
|
|
+ scaler = MinMaxScaler(feature_range=(0, 1))
|
|
|
+ dataset = scaler.fit_transform(dataset)
|
|
|
+
|
|
|
+ train_size = int(len(dataset) * 0.80)
|
|
|
+ test_size = len(dataset) - train_size
|
|
|
+ train, test = dataset[0:train_size], dataset[train_size:len(dataset)]
|
|
|
+ print(len(train), len(test))
|
|
|
+
|
|
|
+ # reshape into X=t and Y=t+1
|
|
|
+ look_back = 36
|
|
|
+ trainX, trainY = create_dataset(train, look_back)
|
|
|
+ testX, testY = create_dataset(test, look_back)
|
|
|
+
|
|
|
+ print(dataset)
|
|
|
+ print(testX, testY)
|
|
|
+
|
|
|
+ # reshape input to be [samples, time steps, features]
|
|
|
+ trainX = numpy.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
|
|
|
+ testX = numpy.reshape(testX, (testX.shape[0], 1, testX.shape[1]))
|
|
|
+
|
|
|
+ # create and fit the LSTM network
|
|
|
+ model = Sequential()
|
|
|
+ model.add(LSTM(4, input_dim=look_back-12))
|
|
|
+ model.add(Dense(1))
|
|
|
+ model.compile(loss='mean_squared_error', optimizer='adam')
|
|
|
+ model.fit(trainX, trainY, nb_epoch=100, batch_size=1, verbose=2)
|
|
|
+
|
|
|
+
|
|
|
+ # make predictions
|
|
|
+ trainPredict = model.predict(trainX)
|
|
|
+ testPredict = model.predict(testX)
|
|
|
+ print(type(testPredict))
|
|
|
+ # invert predictions
|
|
|
+ trainPredict = scaler.inverse_transform(trainPredict)
|
|
|
+ trainY = scaler.inverse_transform([trainY])
|
|
|
+ testPredict = scaler.inverse_transform(testPredict)
|
|
|
+ testY = scaler.inverse_transform([testY])
|
|
|
+ # calculate root mean squared error
|
|
|
+ trainScore = math.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))
|
|
|
+ print('Train Score: %.2f RMSE' % (trainScore))
|
|
|
+ testScore = math.sqrt(mean_squared_error(testY[0], testPredict[:,0]))
|
|
|
+ print('Test Score: %.2f RMSE' % (testScore))
|
|
|
+
|
|
|
+
|
|
|
+ # shift train predictions for plotting
|
|
|
+ trainPredictPlot = numpy.empty_like(dataset)
|
|
|
+ trainPredictPlot[:] = numpy.nan
|
|
|
+ trainPredictPlot[look_back:len(trainPredict)+look_back] = trainPredict[:, 0]
|
|
|
+ # shift test predictions for plotting
|
|
|
+ testPredictPlot = numpy.empty_like(dataset)
|
|
|
+ testPredictPlot[:] = numpy.nan
|
|
|
+ testPredictPlot[len(trainPredict)+(look_back*2)+1:len(dataset)-1] = testPredict[:, 0]
|
|
|
+ # plot baseline and predictions
|
|
|
+ plt.plot(scaler.inverse_transform(dataset))
|
|
|
+ plt.plot(trainPredictPlot)
|
|
|
+ plt.plot(testPredictPlot)
|
|
|
+ plt.show()
|