I have a dataset spanning hundreds of values regarding temperature. Obviously, in meteorology, it is helpful to predict what future values will be based on the past.
I have the following stateful model, built in Keras:
look_back = 1
model.add(LSTM(32, batch_input_shape=(batch_size, look_back, 1), stateful=True))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
for i in range(10):
model.fit(trainX, trainY, epochs=4, batch_size=batch_size, verbose=2, shuffle=False)
model.reset_states()
# make predictions
trainPredict = model.predict(trainX, batch_size=batch_size)
I have successfully been able to train and test the model on my dataset to reasonable results, however am struggling to comprehend what is required to predict the next, say, 20 points in the dataset. Obviously, these 20 points are outside of the dataset, and they have yet to "occur".
I would appreciate anything that would be of help; I feel like I am missing some simple functionality in Keras.
Thank you.