Feature selection

Select features that are used to build the surrogate mode.

feature_selection.main(config_file=<typer.models.ArgumentInfo object>, preprocessed_data_file=<typer.models.ArgumentInfo object>, estimator_type=<typer.models.OptionInfo object>, output_path=<typer.models.OptionInfo object>)

Select the feature which contribute most to the prediction for the energy or costing values.

Parameters:

• config_file (str) – Location of the .yml config file (default name is input_config.yml).

• preprocessed_data_file (str) – Location and name of a .json preprocessing file to be used.

• estimator_type (str) – The type of feature selection to be performed. The default is lasso, which will be used if nothing is passed. The other options are ‘linear’, ‘elasticnet’, and ‘xgb’.

• output_path (str) – Where output data should be placed. Note that this value should be empty unless this file is called from a pipeline.

Return type:

str

feature_selection.select_features(preprocessed_data_file, estimator_type, output_path)

Select the feature which contribute most to the prediction for the energy and costing values.

Parameters:

• preprocessed_data_file – Location and name of a .json preprocessing file to be used if the preprocessing is skipped.

• estimator_type – The type of feature selection to be performed. The default is lasso, which will be used if nothing is passed. The other options are ‘linear’, ‘elasticnet’, and ‘xgb’.

• output_path – Folder location where output files should be placed.