| catboost.get_feature_importance {catboost} | R Documentation |
Calculate the feature importances (see https://tech.yandex.com/catboost/doc/dg/concepts/fstr-docpage/#fstr) (Regular feature importance (see https://tech.yandex.com/catboost/doc/dg/concepts/output-data_feature-importance-docpage/#per-feature-importance) and Feature interaction strength (see https://tech.yandex.com/catboost/doc/dg/concepts/output-data_feature-interaction-strength-docpage/#output-data_feature-interaction-strength) ).
catboost.get_feature_importance(model, pool = NULL, fstr_type = "FeatureImportance", thread_count = -1)
model |
The model obtained as the result of training. Default value: Required argument |
pool |
The input dataset. The feature importance for the training dataset is calculated if this argument is not specified. Default value: NULL |
fstr_type |
The fstr type. Possible values:
Default value: 'FeatureImportance' |
thread_count |
The number of threads to use when applying the model. If -1, then the number of threads is set to the number of cores. Allows you to optimize the speed of execution. This parameter doesn't affect results. Default value: -1 |
https://tech.yandex.com/catboost/doc/dg/concepts/r-reference_catboost-importance-docpage/