def trainWithLSTM(params):
inSeqLen = params['inSeqLen']
outSeqLen = params['outSeqLen']
numFeatures = params['numFeatures']
lstm_layers = params['lstm_layers']
datasetObj = params['datasetObj']
allRecords = params['allRecords']
csvRecordInfo = params['csvRecordInfo']
epochSeconds = params['epochSeconds']
slidingWindowSeconds = params['slidingWindowSeconds']
priorSeconds = params['priorSeconds']
postSeconds = params['postSeconds']
trainingEpochs = params['trainingEpochs']
trainingBatchSize = params['trainingBatchSize']
validation_split = params['validation_split']
modelOutputDir = params['modelOutputDir']
savedModelFilePrefix = params['savedModelFilePrefix']
lstmObj = eegLSTM("encoder_decoder_sequence")
# lstmObj = eegLSTM("stacked_LSTM")
lstmObj.createModel(inSeqLen, outSeqLen, numFeatures, lstm_layers)
if (dataFormat == "CSV"):
numSamples = lstmObj.prepareDataSubset_fromCSV(datasetObj, allRecords,
csvRecordInfo, (epochSeconds*1000), (slidingWindowSeconds*1000),
priorSeconds, postSeconds)
# If the number of samples is too low, there is no point in training with this dataset
if (numSamples <= 10):
print ("numSamples ({}) is too low! Returning without creating a saved model!".format(numSamples))
return
else:
print ("LSTM model for EDF format is not yet implemented in this version")
exit(-1)
lstmObj.fit(trainingEpochs, trainingBatchSize, validation_split)
lstmObj.saveModel(modelOutputDir, savedModelFilePrefix)
return
def testWithLSTM(modelFile, weightsFile, numFeaturesInTestFiles, allFiles):
lstmObj = eegLSTM("encoder_decoder_sequence")
lstmObj.loadModel(modelFile, weightsFile)
print("Loaded LSTM model from disk")
if (numFeaturesInTestFiles != lstmObj.numFeatures):
print ("number of features in testfiles ", numFeaturesInTestFiles,
"!= number of feature in loaded model ", lstmObj.numFeatures)
for testFilePath in allFiles.values():
print ("testFilePath = ", testFilePath)
lstmObj.prepareDataset_fullfile(testFilePath)
# dataset = np.loadtxt(testFile, delimiter=',')
# X = dataset[:,:19]
# y = dataset[:,19]
lstmObj.evaluate()
if (dataSubset == "fulldata"):
print("Will be training on full data")
priorSeconds = postSeconds = -1
elif (re.search("seizure\-(\d+), seizure\+(\d+)", dataSubset) != None):
m = re.match("seizure\-(\d+), seizure\+(\d+)", dataSubset)
priorSeconds = int(m.group(1))
postSeconds = int(m.group(2))
print("data subset = [seizure-" + str(priorSeconds),
", seizure+" + str(postSeconds) + "]")
# Verify that all the records have same features
features = tuhd.recordInfo[allRecords[0]]['channelLabels']
featuresSet = set(features)
for recordID in allRecords:
tmpSet = set(tuhd.recordInfo[recordID]['channelLabels'])
xorSet = featuresSet.symmetric_difference(tmpSet)
if (len(xorSet) > 0):
print("features are not common between", allRecords[0], "and",
recordID)
exit(-1)
print("features are common between all the records!")
numFeatures = len(featuresSet)
lstmObj = eegLSTM("encoder_decoder_sequence")
# lstmObj = eegLSTM("stacked_LSTM")
lstmObj.createModel(inSeqLen, outSeqLen, numFeatures, lstmLayers)
lstmObj.prepareDataset_fromTUHedf(tuhd, allRecords, priorSeconds,
postSeconds)
lstmObj.fit(epochs, batchsize)
lstmObj.saveModel(modelOutputDir, recordID + "LSTM")
def testWithHybridModel(lstmModelFile, lstmWeightsFile, dnnModelFile,
dnnWeightsFile, numFeaturesInTestFiles, allFiles,
timeStepsToPredict):
lstmObj = eegLSTM("encoder_decoder_sequence")
lstmObj.loadModel(lstmModelFile, lstmWeightsFile)
print("Loaded LSTM model from disk")
dnnObj = eegDNN("Classifier_3layers")
dnnObj.loadModel(dnnModelFile, dnnWeightsFile)
print("Loaded DNN model from disk")
if (numFeaturesInTestFiles != lstmObj.numFeatures):
print ("number of features in testfiles ", numFeaturesInTestFiles,
"!= number of feature in loaded model ", lstmObj.numFeatures)
if (numFeaturesInTestFiles != dnnObj.numFeatures):
print ("number of features in testfiles ", numFeaturesInTestFiles,
"!= number of feature in loaded model ", dnnObj.numFeatures)
for testFilePath in allFiles.values():
print ("testFilePath = ", testFilePath)
dataset = pd.read_csv(testFilePath)
dataset = dataset.values # Convert to a numpy array from pandas dataframe
numFeatures = lstmObj.numFeatures
inSeqLen = lstmObj.inSeqLen
outSeqLen = lstmObj.outSeqLen
numRowsNeededForTest = max((inSeqLen + outSeqLen), (inSeqLen+timeStepsToPredict))
numRows = dataset.shape[0]
print ("inSeqLen={}, outSeqLen={}, numFeatures={}, numRows={}, numRowsNeededForTest={}".format(
inSeqLen, outSeqLen, numFeatures, numRows, numRowsNeededForTest
))
# lstmObj.prepareDataset_fullfile(testFilePath)
while (numRows > numRowsNeededForTest):
numRemainingRows = min (numRows, (inSeqLen+timeStepsToPredict))
# print ("numRows={}, numFeatures={}, numRemainingRows={}"
# .format(numRows, numFeatures, numRemainingRows))
predictedDataset = np.empty((1, (inSeqLen+timeStepsToPredict), numFeatures))
predictedSeizureValues = np.empty((inSeqLen+timeStepsToPredict))
inputRowStart = 0
inputRowEnd = inputRowStart + inSeqLen
outputRowStart = inputRowEnd
outputRowEnd = outputRowStart + outSeqLen
# print ("inputRowStart={}, inputRowEnd={}, outputRowStart={}, outputRowEnd={}"
# .format(inputRowStart, inputRowEnd, outputRowStart, outputRowEnd))
predictedDataset[0, inputRowStart:inputRowEnd,:numFeatures] = dataset[inputRowStart:inputRowEnd, :numFeatures]
predictedSeizureValues[inputRowStart:inputRowEnd] = dataset[inputRowStart:inputRowEnd, numFeatures]
while (numRemainingRows >= numRowsNeededForTest):
predictedDataset[:, outputRowStart:outputRowEnd, :] = \
lstmObj.getModel().predict(predictedDataset[:, inputRowStart:inputRowEnd, :])
for i in range(outSeqLen):
predictedSeizureValues[outputRowStart+i] = dnnObj.getModel().predict(predictedDataset[:, outputRowStart+i, :])
inputRowStart += outSeqLen
inputRowEnd = inputRowStart + inSeqLen
outputRowStart = inputRowEnd
outputRowEnd = outputRowStart + outSeqLen
numRemainingRows -= outSeqLen
# print ("inputRowStart={}, inputRowEnd={}, outputRowStart={}, outputRowEnd={}"
# .format(inputRowStart, inputRowEnd, outputRowStart, outputRowEnd))
# print ("predictedDataset = ", predictedDataset[0, inSeqLen:min (numRows, (inSeqLen+timeStepsToPredict)), :numFeatures])
# print ("actual dataset = ", dataset[inSeqLen:min (numRows, (inSeqLen+timeStepsToPredict)), :numFeatures])
calculateMetrics(predictedSeizureValues[inSeqLen:], dataset[inSeqLen:,numFeatures])
dataset = np.delete(dataset, list(range(timeStepsToPredict)), axis=0)
numRows = dataset.shape[0]
return