Class Pool

catboost/python-package/catboost/core.py:603–1519

Pool used in CatBoost as a data structure to train model from.

class Pool(_PoolBase):
    """
    Pool used in CatBoost as a data structure to train model from.
    """

    def __init__(
        self,
        data,
        label=None,
        cat_features=None,
        text_features=None,
        embedding_features=None,
        embedding_features_data=None,
        column_description=None,
        pairs=None,
        graph=None,
        delimiter='\t',
        has_header=False,
        ignore_csv_quoting=False,
        weight=None,
        group_id=None,
        group_weight=None,
        subgroup_id=None,
        pairs_weight=None,
        baseline=None,
        timestamp=None,
        feature_names=None,
        feature_tags=None,
        thread_count=-1,
        log_cout=None,
        log_cerr=None,
        data_can_be_none=False
    ):
        """
        Pool is an internal data structure that is used by CatBoost.
        You can construct Pool from list, numpy.ndarray, pandas.DataFrame, pandas.Series.

        Parameters
        ----------
        data : list or numpy.ndarray or pandas.DataFrame or pandas.Series or polars.DataFrame or FeaturesData or string or os.PathLike
            Data source of Pool.
            If list or numpy.ndarrays or pandas.DataFrame or pandas.Series or polars.DataFrame,
              giving 2 dimensional array like data.
            If FeaturesData - see FeaturesData description for details, 'cat_features' and 'feature_names'
              parameters must be equal to None in this case
            If string or os.PathLike, giving the path to the file with data in catboost format.
              If string starts with "quantized://", the file has to contain quantized dataset saved with Pool.save().

        label : list or numpy.ndarrays or pandas.DataFrame or pandas.Series or polars.DataFrame or polars.Series, optional (default=None)
            Labels data.
            If not None, can be a single- or two- dimensional array with either:
              - numerical values - for regression (including multiregression), ranking and binary classification problems
              - class labels (boolean, integer or string) - for classification (including multiclassification) problems
            If `data` parameter points to a file, Label data is loaded from it as well. This parameter must
              be None in this case.

        cat_features : list or numpy.ndarray, optional (default=None)
            If not None, giving the list of Categ features indices or names.