def test_breakSeq(data: np.ndarray, seqLength: int):
""" Tests Utility.breakSeq """
dataSeq = Utility.breakSeq(data, seqLength)
# On concatenating the dataSeq, we should get back data
assert np.array_equal(np.concatenate(dataSeq, axis=0), data)
# length of each seq except the last should be exactly seqLength
for seq in dataSeq[:-1]:
assert seq.shape[0] == seqLength
def main():
n = 21500
trainN = 21000
seqLength = 500
numSeqPlot = 5
trainData, testData = Utility.trainTestSplit(
StandardGenerator('long_term').generate(n),
trainN
)
trainSequences = Utility.breakSeq(trainData, seqLength=seqLength)
# for i in range(numSeqPlot):
# Plot.plotDataCols(trainSequences[
# np.random.randint(0, len(trainSequences))
# ])
model = LstmForecast(
forecastHorizon=1,
stateSize=50,
activation='tanh',
numRnnLayers=3
)
model.model.summary()
loss = model.train(
trainSequences=trainSequences,
numIterations=15,
optimizer=tf.keras.optimizers.Adam(
learning_rate=tf.keras.optimizers.schedules.ExponentialDecay(
0.01,
20,
0.96
)
)
)
Plot.plotLoss(loss)
for i in range(numSeqPlot):
idx = np.random.randint(0, len(trainSequences))
evalLoss, Ypred = model.evaluate(trainSequences[idx], returnPred=True)
Ytrue = trainSequences[idx][1:]
Plot.plotPredTrue(Ypred, Ytrue, 'On Train')
evalLoss, Ypred = model.evaluate(testData, returnPred=True)
Ytrue = testData[1:]
Plot.plotPredTrue(Ypred, Ytrue, 'On Test')
def main():
# The data generator
dataGenerator = StandardGenerator('long_term')
# Data for single-sequence methods
n = 21500
trainN = 21000
trainData, testData = Utility.trainTestSplit(
dataGenerator.generate(n),
train=trainN
)
# Method 1 - train on mutually exclusive sequences
seqLength = 500
trainSequences = Utility.breakSeq(trainData, seqLength)
tryModelOneSeq(trainSequences, testData, 'method1', PLOT_DIR)
# Method 2 - train on randomly sampled contiguous sequences
seqLength = 500
numSeq = 42
trainSequences = [
trainData[startIdx: startIdx + seqLength]
for startIdx in list(np.random.randint(
0,
trainN - seqLength,
size=(numSeq,)
))
]
tryModelOneSeq(trainSequences, testData, 'method2', PLOT_DIR)
# Method 3 - train on the single long sequence
trainSequences = [trainData]
tryModelOneSeq(trainSequences, testData, 'method3', PLOT_DIR)
# Multiple Independent Train Sequences
seqLength = 500
numSeq = 42
trainSequences = Utility.generateMultipleSequence(
dataGenerator=dataGenerator,
numSequences=numSeq,
minSequenceLength=seqLength,
maxSequenceLength=seqLength
)
testData = dataGenerator.generate(seqLength)
tryModelMultiSeq(trainSequences, testData, 'multiseq', PLOT_DIR)