This is my first time with Keras and LSTMs and I am working in a project in which I have many time series data to train with.
I have around 13000 rows of data (1 column) with numerical values regarding to a degradation level of a component ending in a failure; and on the other side I have multiple datasets of 100 rows (1 column) with data regarding to a degradation level of a component, but ending some points before a failure.
The challenge is to predict when those datasets will record a failure.
So what I have done, is the next:
from pandas import DataFrame
from pandas import Series
from pandas import concat
from pandas import read_csv
from pandas import datetime
from sklearn.metrics import mean_squared_error
from sklearn.preprocessing import MinMaxScaler
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from math import sqrt
from matplotlib import pyplot
from numpy import array
# convert an array of values into a dataset matrix
def create_dataset(dataset, look_back):
dataX, dataY = [], []
for i in range(len(dataset)-look_back-1):
a = dataset[i:(i+look_back), 0]
dataX.append(a)
dataY.append(dataset[i + look_back, 0])
return numpy.array(dataX), numpy.array(dataY)
look_back = 600
epochs = 500
batch_size = 50
data = np.array(data).reshape(-1,1)
data = data.astype('float32')
# Scale the data
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(data)
# split into train and test sets
train_size = int(len(dataset) * 0.67)
test_size = len(dataset) - train_size
train, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)
# 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(100, activation = 'tanh', inner_activation = 'hard_sigmoid', return_sequences=True))
model.add(LSTM(50, activation = 'tanh', inner_activation = 'hard_sigmoid'))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(trainX, trainY, epochs=epochs, batch_size=batch_size, verbose=2)
# make predictions
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)
# 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))
These line codes represents the training and the evaluation of the dataset, but how can I predict the next (for example) 50 elements of one dataset of 100 rows using that model?
