8.10. copro.evaluation.get_feature_importance¶
- copro.evaluation.get_feature_importance(clf, config, out_dir)[source]¶
Determines relative importance of each feature (i.e. variable) used. Must be used after model/classifier is fit. Returns dataframe and saves it to csv too.
- Parameters
clf (classifier) – sklearn-classifier used in the simulation.
config (ConfigParser-object) – object containing the parsed configuration-settings of the model.
out_dir (str) – path to output folder. If ‘None’, no output is stored.
- Raises
Warning – raised if the chosen ML model has not built-in feature importances.
- Returns
dataframe containing feature importance.
- Return type
dataframe