Python sklearn.model_selection.BaseCrossValidator() Examples

The following are 7 code examples of sklearn.model_selection.BaseCrossValidator(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module sklearn.model_selection , or try the search function .
Example #1
Source File: build_model.py    From gordo with GNU Affero General Public License v3.0 5 votes vote down vote up 
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
Example #2
Source File: split.py    From nyaggle with MIT License 5 votes vote down vote up 
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)
Example #3
Source File: split.py    From nyaggle with MIT License 5 votes vote down vote up 
def __init__(self, n: int, base_validator: BaseCrossValidator):
        self.base_validator = base_validator
        self.n = n
Example #4
Source File: split.py    From nyaggle with MIT License 5 votes vote down vote up 
def __init__(self, n: int, base_validator: BaseCrossValidator):
        self.base_validator = base_validator
        self.n = n
Example #5
Source File: split.py    From nyaggle with MIT License 5 votes vote down vote up 
def __init__(self, n: int, base_validator: BaseCrossValidator):
        assert n > 0, "n is 1-origin and should be greater than 0"
        self.base_validator = Take(1, Skip(n - 1, base_validator))
        self.n = n
Example #6
Source File: target_encoder.py    From nyaggle with MIT License 5 votes vote down vote up 
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
Example #7
Source File: optimize.py    From optuna with MIT License 4 votes vote down vote up 
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