y_train,
validation_split=0.2,
epochs=epochs,
batch_size=batch_size,
verbose=2,
callbacks=[callback])
print('\n results of ' + RunName + ' on Model ' + model +
' with data set ' + Testfilename)
print('\n epochs: ' + str(epochs) + '\n batch size: ' + str(batch_size) +
'\n stop patience:' + str(StopPatience) + ' \n scaling: ' +
str(DataScaling))
FP, FN, TP, TN = d_Eval.get_overall_results([(X_test, y_test)], m)
m_Eval.eval_all([history], epochs, RunName, m, Savepath, TestData)
MCC = d_Eval.get_MCC(FP, FN, TP, TN)
print('&y&' + str(MCC)[0:4] + '&' + str(TP) + '&' + str(TN) + '&' +
str(FP) + '&' + str(FN) + '\\' + '\\')
SaveInfo.loc[RunName, 'MCC'] = MCC
SaveInfo.loc[RunName, 'TP'] = TP
SaveInfo.loc[RunName, 'TN'] = TN
SaveInfo.loc[RunName, 'FP'] = FP
SaveInfo.loc[RunName, 'FN'] = FN
SaveInfo.loc[RunName, 'model'] = model
###### find best Models
NumberOfModels = 10
ModelNameList = []
MCC_list = pd.to_numeric(SaveInfo.loc[:, 'MCC'])
while len(ModelNameList) < NumberOfModels:
test_data = list()
epochs = 100
for currData in Data:
seed = 0
X = pp.shape_Data_to_LSTM_format(currData[0], dropChannels)
y = pp.shape_Labels_to_LSTM_format(currData[1])
#y = np.reshape(pp.reduceLabel(y).values, (X.shape[0], 1, 1))
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=seed)
batch_size = 5
if X_train.shape[0] >= 2:
hist = m.fit(X_train,
y_train,
validation_split=0.2,
epochs=epochs,
batch_size=batch_size,
verbose=2)
test_data.append((X_test, y_test))
m.save('my_model.h5')
json_string = m.to_json()
FP, FN, TP, TN = eval.get_overall_results(test_data, m)
print('\nMCC: ' + str(eval.get_MCC(FP, FN, TP, TN)))
print('\n' + str(TP) + ' ' + str(FN))
print('\n' + str(FP) + ' ' + str(TN))
#print('\n%s: %.2f%%' % matthews_corrcoef(y_true, y_pred))
#print('\n%s: %.2f%%' % confusion_matrix(y_true, y_pred))