8.11. copro.evaluation.get_permutation_importance¶
- copro.evaluation.get_permutation_importance(clf, X_ft, Y, df_feat_imp, out_dir)[source]¶
Returns a dataframe with the mean permutation importance of the features used to train a RF tree model. Dataframe is stored to output directory as csv-file.
- Parameters
clf (classifier) – sklearn-classifier used in the simulation.
X_ft (array) – X-array containing variable values after scaling.
Y (array) – Y-array containing conflict data.
df_feat_imp (dataframe) – dataframe containing feature importances to align names across outputs.
out_dir (str) – path to output folder. If ‘None’, no output is stored.
- Returns
contains mean permutation importance for each feature.
- Return type
dataframe