selected_features.remove('RUL')
rm_columns = ['Setting1', 'Setting2', 'Setting3']
for col in rm_columns:
if col in training_frame and col in testing_frame:
selected_features.remove(col)
training_frame = ProcessData.trainDataToFrame(
training_frame=training_frame,
selected_column_names=selected_features,
moving_k_closest_average=True,
standard_deviation=True,
probability_distribution=True)
testing_frame = ProcessData.testDataToFrame(
testing_frame=testing_frame,
selected_column_names=selected_features,
moving_k_closest_average=True,
standard_deviation=True,
probability_from_file=True)
# Training data columns
del training_frame['UnitNumber']
del training_frame['Time']
# Testing columns
del testing_frame['UnitNumber']
del testing_frame['Time']
training_columns = list(training_frame.columns)
training_columns.remove('RUL')
response_column = 'RUL'
del p_filter['Sensor10']
del p_filter['Sensor16']
del p_filter['Sensor18']
del p_filter['Sensor19']
# Feature engineering process
columns = [
'Sensor14', 'Sensor9', 'Sensor11', 'Sensor12', 'Sensor13', 'Sensor7',
'Sensor4', 'Sensor8', 'Sensor20', 'Sensor21', 'Sensor15', 'Sensor6',
'Sensor2', 'Sensor17', 'Sensor3'
]
p_featured_train = ProcessData.trainDataToFrame(training_frame=p_filter,
selected_column_names=columns,
probability_distribution=True)
p_featured_test = ProcessData.testDataToFrame(testing_frame=p_test,
selected_column_names=columns,
probability_from_file=True)
h_filter = h2o.H2OFrame(p_featured_train)
h_filter.set_names(list(p_featured_train.columns))
h_test = h2o.H2OFrame(p_featured_test)
h_test.set_names(list(p_featured_test.columns))
training_columns = list(p_featured_train.columns)
training_columns.remove('UnitNumber')
training_columns.remove('Time')
training_columns.remove('RUL')
model = H2ODeepLearningEstimator(variable_importances=True)
model.train(x=columns, y='RUL', training_frame=h_filter, nfolds=10)