Python model_selection.BaseCrossValidator方法代码示例

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import BaseCrossValidator [as 别名]
def build_split_dict(X: pd.DataFrame, split_obj: Type[BaseCrossValidator]) -> dict:
        """
        Get dictionary of cross-validation training dataset split metadata

        Parameters
        ----------
        X: pd.DataFrame
            The training dataset that will be split during cross-validation.
        split_obj: Type[sklearn.model_selection.BaseCrossValidator]
            The cross-validation object that returns train, test indices for splitting.

        Returns
        -------
        split_metadata: Dict[str,Any]
            Dictionary of cross-validation train/test split metadata
        """
        split_metadata: Dict[str, Any] = dict()
        for i, (train_ind, test_ind) in enumerate(split_obj.split(X)):
            split_metadata.update(
                {
                    f"fold-{i+1}-train-start": X.index[train_ind[0]],
                    f"fold-{i+1}-train-end": X.index[train_ind[-1]],
                    f"fold-{i+1}-test-start": X.index[test_ind[0]],
                    f"fold-{i+1}-test-end": X.index[test_ind[-1]],
                }
            )
            split_metadata.update({f"fold-{i+1}-n-train": len(train_ind)})
            split_metadata.update({f"fold-{i+1}-n-test": len(test_ind)})
        return split_metadata 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import BaseCrossValidator [as 别名]
def check_cv(cv: Union[int, Iterable, BaseCrossValidator] = 5,
             y: Optional[Union[pd.Series, np.ndarray]] = None,
             stratified: bool = False,
             random_state: int = 0):
    if cv is None:
        cv = 5
    if isinstance(cv, numbers.Integral):
        if stratified and (y is not None) and (type_of_target(y) in ('binary', 'multiclass')):
            return StratifiedKFold(cv, shuffle=True, random_state=random_state)
        else:
            return KFold(cv, shuffle=True, random_state=random_state)

    return model_selection.check_cv(cv, y, stratified) 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import BaseCrossValidator [as 别名]
def __init__(self, n: int, base_validator: BaseCrossValidator):
        self.base_validator = base_validator
        self.n = n 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import BaseCrossValidator [as 别名]
def __init__(self, base_transformer: BaseEstimator,
                 cv: Optional[Union[int, Iterable, BaseCrossValidator]] = None, return_same_type: bool = True,
                 groups: Optional[pd.Series] = None):
        self.cv = cv
        self.base_transformer = base_transformer

        self.n_splits = None
        self.transformers = None
        self.return_same_type = return_same_type
        self.groups = groups 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import BaseCrossValidator [as 别名]
def __init__(
        self,
        params: Dict[str, Any],
        train_set: "lgb.Dataset",
        num_boost_round: int = 1000,
        folds: Optional[
            Union[
                Generator[Tuple[int, int], None, None],
                Iterator[Tuple[int, int]],
                "BaseCrossValidator",
            ]
        ] = None,
        nfold: int = 5,
        stratified: bool = True,
        shuffle: bool = True,
        fobj: Optional[Callable[..., Any]] = None,
        feval: Optional[Callable[..., Any]] = None,
        feature_name: str = "auto",
        categorical_feature: str = "auto",
        early_stopping_rounds: Optional[int] = None,
        fpreproc: Optional[Callable[..., Any]] = None,
        verbose_eval: Optional[Union[bool, int]] = True,
        show_stdv: bool = True,
        seed: int = 0,
        callbacks: Optional[List[Callable[..., Any]]] = None,
        time_budget: Optional[int] = None,
        sample_size: Optional[int] = None,
        study: Optional[optuna.study.Study] = None,
        optuna_callbacks: Optional[List[Callable[[Study, FrozenTrial], None]]] = None,
        verbosity: int = 1,
    ) -> None:

        super(LightGBMTunerCV, self).__init__(
            params,
            train_set,
            num_boost_round,
            fobj=fobj,
            feval=feval,
            feature_name=feature_name,
            categorical_feature=categorical_feature,
            early_stopping_rounds=early_stopping_rounds,
            verbose_eval=verbose_eval,
            callbacks=callbacks,
            time_budget=time_budget,
            sample_size=sample_size,
            study=study,
            optuna_callbacks=optuna_callbacks,
            verbosity=verbosity,
        )

        self.lgbm_kwargs["folds"] = folds
        self.lgbm_kwargs["nfold"] = nfold
        self.lgbm_kwargs["stratified"] = stratified
        self.lgbm_kwargs["shuffle"] = shuffle
        self.lgbm_kwargs["show_stdv"] = show_stdv
        self.lgbm_kwargs["seed"] = seed
        self.lgbm_kwargs["fpreproc"] = fpreproc