print("Reading Training Data (Cancer Problem)")
# Reading Training data
trainData = utl.readDataSetAsMatrix(utl.BREAST_CANCER_TRAINING_FILE, 1,
',')
# Separating outputs from inputs
inputs = trainData[:, :9]
outputs = trainData[:, 9:]
if debug:
print("Training RBF Model (Cancer problem)")
configuration = utl.RBFTrainProcessConfiguration()
configuration.unitsInHiddenLayer = unitsInHiddenLayer
return utl.trainRBFNetwork(\
inputs,
outputs,
configuration
)
if __name__ == "__main__":
model, errorsByEpoch = trainModel(8)
print("Saving RBF Trained Model (Cancer Problem)")
utl.saveModelAtLocation(\
model,
utl.BREAST_CANCER_RBF_MODEL_FILE
)
)
inputs = trainData[:, 2:]
if debug:
print("Training Model RNN hourly Model (Currency Exchange problem)")
configuration = utl.RecurrentTrainProcessConfiguration()
configuration.unitsInHiddenLayer = unitsInHiddenLayer
configuration.maxEpochs = 100
configuration.learningrate = 0.001
configuration.momentum = 0.95
return utl.trainJordanRecurrentNetwork(\
inputs, 1, configuration
)
if __name__ == "__main__":
model, errorsByEpoch = trainModel(8)
print("Saving RNN Jordan Trained Model (Currency Exchange problem)")
utl.saveModelAtLocation(
model,
utl.CURRENCY_EXCHANGE_RNN_JORDAN_MODEL_FILE(\
utl.SAMPLING_TYPE.HOURLY
)
)
)
inputs = trainData[:, 2:]
if debug:
print("Training Model RNN Elman Model (Currency Exchange problem)")
configuration = utl.RecurrentTrainProcessConfiguration()
configuration.unitsInHiddenLayer = unitsInHiddenLayer
configuration.maxEpochs = 100
configuration.learningrate = 0.001
configuration.momentum = 0.95
return utl.trainELmanRecurrentNetwork(\
inputs, 1, configuration
)
if __name__ == "__main__":
model, errorsByEpoch = trainModel(4)
print("Saving RNN Elman Trained Model (Currency Exchange problem)")
utl.saveModelAtLocation(
model,
utl.CURRENCY_EXCHANGE_RNN_ELMAN_MODEL_FILE(\
utl.SAMPLING_TYPE.AT_CLOSING_DAY
)
)
