Method fit

catboost/python-package/catboost/core.py:5435–5550

Fit the CatBoostClassifier model. Parameters ---------- X : catboost.Pool or list or numpy.ndarray or pandas.DataFrame or pandas.Series or polars.DataFrame If not catboost.Pool, 2 dimensional Feature matrix or string - file with dataset. y : lis

(self, X, y=None, cat_features=None, text_features=None, embedding_features=None, graph=None, sample_weight=None, baseline=None, use_best_model=None,
            eval_set=None, verbose=None, logging_level=None, plot=False, plot_file=None, column_description=None,
            verbose_eval=None, metric_period=None, silent=None, early_stopping_rounds=None,
            save_snapshot=None, snapshot_file=None, snapshot_interval=None, init_model=None, callbacks=None,
            log_cout=None, log_cerr=None)

        super(CatBoostClassifier, self).__init__(params)

    def fit(self, X, y=None, cat_features=None, text_features=None, embedding_features=None, graph=None, sample_weight=None, baseline=None, use_best_model=None,
            eval_set=None, verbose=None, logging_level=None, plot=False, plot_file=None, column_description=None,
            verbose_eval=None, metric_period=None, silent=None, early_stopping_rounds=None,
            save_snapshot=None, snapshot_file=None, snapshot_interval=None, init_model=None, callbacks=None,
            log_cout=None, log_cerr=None):
        """
        Fit the CatBoostClassifier model.

        Parameters
        ----------
        X : catboost.Pool or list or numpy.ndarray or pandas.DataFrame or pandas.Series or polars.DataFrame
            If not catboost.Pool, 2 dimensional Feature matrix or string - file with dataset.

        y : list or numpy.ndarray or pandas.DataFrame or pandas.Series or polars.DataFrame or polars.Series, optional (default=None)
            Labels of the training data.
            If not None, can be a single- or two- dimensional array with either:
              - numerical values - for binary classification problems
              - class labels (boolean, integer or string)
            Use only if X is not catboost.Pool and does not point to a file.

        cat_features : list or numpy.ndarray, optional (default=None)
            If not None, giving the list of Categ columns indices.
            Use only if X is not catboost.Pool.

        text_features : list or numpy.ndarray, optional (default=None)
            If not None, giving the list of Text columns indices.
            Use only if X is not catboost.Pool.

        embedding_features : list or numpy.ndarray, optional (default=None)
            If not None, giving the list of Embedding columns indices.
            Use only if X is not catboost.Pool.

        graph : list or numpy.ndarray or pandas.DataFrame or polars.DataFrame
            The graph edges list description.
            If list or numpy.ndarrays or pandas.DataFrame, giving 2 dimensional.

        sample_weight : list or numpy.ndarray or pandas.DataFrame or pandas.Series or polars.Series, optional (default=None)
            Instance weights, 1 dimensional array like.

        baseline : list or numpy.ndarray or polars.DataFrame or polars.Series, optional (default=None)
            If not None, giving 2 dimensional array like data.
            Use only if X is not catboost.Pool.

        use_best_model : bool, optional (default=None)
            Flag to use best model

        eval_set : catboost.Pool or list of catboost.Pool or tuple (X, y) or list [(X, y)], optional (default=None)
            Validation dataset or datasets for metrics calculation and possibly early stopping.

        metric_period : int
            Frequency of evaluating metrics.

        verbose : bool or int
            If verbose is bool, then if set to True, logging_level is set to Verbose,
            if set to False, logging_level is set to Silent.
            If verbose is int, it determines the frequency of writing metrics to output and
            logging_level is set to Verbose.