'data_set': [
'400rpm_v2',
'800rpm_v2',
'1200rpm_v2',
],
'evaluation_function': [
'a2e.evaluation.reconstruction_error_cost',
'a2e.evaluation.keras.reconstruction_error_vs_compression_cost',
'a2e.evaluation.keras.uniform_reconstruction_error_vs_compression_cost'
],
}
config_space = create_config_space()
if __name__ == '__main__':
experiment = Experiment(auto_datetime_directory=True)
experiment.log('config/config', config)
experiment.log('config/run_configs', run_configs)
experiment.log('config/config_space', str(config_space))
def run_callable(run_config: dict):
experiment.print('Loading data')
bearing_dataset = load_data(run_config['data_set'])
train = bearing_dataset.train(column=config['data_column'],
as_numpy=True)
test = bearing_dataset.test(column=config['data_column'],
as_numpy=True)
test_labels = bearing_dataset.test(column=config['data_column'],
add_label=True)['label']
threshold_percentile = config['threshold_percentile']
x_train, x_valid, y_train, y_valid = train_test_split(
train,
],
'data_columns': [
'rms',
#'crest',
#'temperature',
],
}
run_configs = {
'data_set': config['data_sets'],
'data_column': config['data_columns'],
'fit_mode': config['fit_modes'],
'scaling': config['scalings'],
}
experiment = Experiment()
experiment.log('config/config', config)
experiment.log('config/run_configs', run_configs)
output_dimension = config['input_size'] - config['prediction_shift']
model = create_lstm_autoencoder(config['input_size'], output_dimension=config['output_size'])
def run_callable(run_config: dict):
def pre_processing_x(data_frame):
numpy_data = data_frame.to_numpy()
numpy_data = numpy_data[:-config['prediction_shift'], :]
samples = build_samples(numpy_data.flatten(), config['input_size'], target_dimensions=3)
if run_config['scaling'] == 'min_max':
samples = Scaler(MinMaxScaler, fit_mode=run_config['fit_mode']).fit_transform(numpy_data)