def test_generateMultipleSequence(dataGenerator, numSequences,
minSequenceLength, maxSequenceLength):
""" Tests Utility.generateMultipleSequence """
dataSeq = Utility.generateMultipleSequence(dataGenerator, numSequences,
minSequenceLength,
maxSequenceLength)
assert len(dataSeq) == numSequences
for seq in dataSeq:
assert minSequenceLength <= seq.shape[0] <= maxSequenceLength
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)