(preprocessedTrainPool, preprocessedEvalPools, ctrsContext)
Additional variant of fit
method that accepts CatBoost's Pool s and allows to specify additional
datasets for computing evaluation metrics and overfitting detection similarily to CatBoost's other APIs.
Additional variant of fit
method that accepts CatBoost's Pool s and allows to specify additional
datasets for computing evaluation metrics and overfitting detection similarily to CatBoost's other APIs.
The input training dataset.
The validation datasets used for the following processes:
trained model
override in descendants if necessary
override in descendants if necessary
(preprocessedTrainPool, preprocessedEvalPools, catBoostTrainingContext)
Class to train CatBoostClassificationModel
The default optimized loss function depends on various conditions:
Logloss
— The label column has only two different values or the targetBorder parameter is specified.MultiClass
— The label column has more than two different values and the targetBorder parameter is not specified.Examples
Binary classification.
Multiclassification.
Serialization
Supports standard Spark MLLib serialization. Data can be saved to distributed filesystem like HDFS or local files.
Examples== Save:
Load: