Object importances

Object importances

CatBoost provides the following types of object importances calculation:

Choose the implementation for more details.


Class	Class purpose	Method
CatBoost	Training and applying models.	get_object_importance
CatBoostClassifier	Training and applying models for the classification problems. When using the applying methods only the probability that the object belongs to the class is returned. Provides compatibility with the scikit-learn tools.	get_object_importance
CatBoostRegressor	Training and applying models for the regression problems. When using the applying methods only the predicted class is returned. Provides compatibility with the scikit-learn tools.	get_object_importance


Class	Class purpose	Method
CatBoost	Training and applying models.	get_object_importance
CatBoostClassifier	Training and applying models for the classification problems. When using the applying methods only the probability that the object belongs to the class is returned. Provides compatibility with the scikit-learn tools.	get_object_importance
CatBoostRegressor	Training and applying models for the regression problems. When using the applying methods only the predicted class is returned. Provides compatibility with the scikit-learn tools.	get_object_importance


Method	Purpose
catboost.get_object_importance	Calculate the effect of objects from the train dataset on the optimized metric values for the objects from the input dataset: Positive values reflect that the optimized metric increases. Negative values reflect that the optimized metric decreases.


Method	Purpose
catboost.get_object_importance	Calculate the effect of objects from the train dataset on the optimized metric values for the objects from the input dataset: Positive values reflect that the optimized metric increases. Negative values reflect that the optimized metric decreases.


Command	Purpose
catboost ostr	Calculate the effect of objects from the training dataset on the optimized metric values for the objects from the validation dataset: Positive values reflect that the optimized metric increases. Negative values reflect that the optimized metric decreases. The higher the deviation from 0, the bigger the impact that an object has on the optimized metric.


Command	Purpose
catboost ostr	Calculate the effect of objects from the training dataset on the optimized metric values for the objects from the validation dataset: Positive values reflect that the optimized metric increases. Negative values reflect that the optimized metric decreases. The higher the deviation from 0, the bigger the impact that an object has on the optimized metric.