Skip to content

ForecasterRecursiveClassifier¶

skforecast.recursive._forecaster_recursive_classifier.ForecasterRecursiveClassifier ¶

ForecasterRecursiveClassifier(
    estimator,
    lags=None,
    window_features=None,
    features_encoding="auto",
    transformer_exog=None,
    categorical_features="auto",
    weight_func=None,
    dropna_from_series=False,
    fit_kwargs=None,
    forecaster_id=None,
)

Bases: ForecasterBase

This class turns any classification estimator compatible with the scikit-learn API into a recursive autoregressive (multi-step) forecaster.

Parameters:

Name Type Description Default
estimator estimator or pipeline compatible with the scikit-learn API

An instance of an estimator or pipeline compatible with the scikit-learn API.

 required
lags int, list, numpy ndarray, range

Lags used as predictors. Index starts at 1, so lag 1 is equal to t-1.

  • int: include lags from 1 to lags (included).
  • list, 1d numpy ndarray or range: include only lags present in lags, all elements must be int.
  • None: no lags are included as predictors.
 None
window_features (object, list)

Instance or list of instances used to create window features. Window features are created from the original time series and are included as predictors. Skforecast provides the RollingFeatures class, but a custom object can also be passed as long as it implements the required interface.

 None
features_encoding str

Encoding method for features derived from the time series (lags and window features that return class values):

  • 'auto': Use categorical dtype if estimator supports native categorical features (LightGBM, CatBoost, XGBoost), otherwise numeric encoding.
  • 'categorical': Force categorical dtype (requires compatible estimator).
  • 'ordinal': Use ordinal encoding (0, 1, 2, ...). The estimator will treat class codes as numeric values, assuming an ordinal relationship between classes (e.g., 'low' < 'medium' < 'high').

Note: This only affects features derived from the target series (y) not exogenous variables.

 'auto'
transformer_exog object transformer (preprocessor)

An instance of a transformer (preprocessor) compatible with the scikit-learn preprocessing API. The transformation is applied to exog before training the forecaster. inverse_transform is not available when using ColumnTransformers.

 None
categorical_features (str, list)

Specifies which exogenous variables should be treated as categorical by the estimator's native categorical feature handling.

  • 'auto': Automatically detect categorical columns (non-numeric, non-bool) after transformer_exog.
  • list: Explicit list of column names to treat as categorical.
  • None: No categorical feature handling for exogenous variables.
 'auto'
weight_func Callable

Function that defines the individual weights for each sample based on the index. For example, a function that assigns a lower weight to certain dates. Ignored if estimator does not have the argument sample_weight in its fit method. The resulting sample_weight cannot have negative values.

 None
dropna_from_series bool

Determine whether NaN detected in the training matrices will be dropped. Relevant when y or exog contain interspersed NaN values.

  • If True, drop NaNs in X_train and same rows in y_train.
  • If False, leave NaNs in X_train and warn the user.
 False
fit_kwargs dict

Additional arguments to be passed to the fit method of the estimator.

 None
forecaster_id (str, int)

Name used as an identifier of the forecaster.

 None

Attributes:

Name Type Description
estimator estimator or pipeline compatible with the scikit-learn API

An instance of an estimator or pipeline compatible with the scikit-learn API.
lags numpy ndarray

Lags used as predictors.
lags_names list

Names of the lags used as predictors.
max_lag int

Maximum lag included in lags.
window_features list

Class or list of classes used to create window features.
window_features_names list

Names of the window features to be included in the X_train matrix.
window_features_class_names list

Names of the classes used to create the window features.
max_size_window_features int

Maximum window size required by the window features.
window_size int

The window size needed to create the predictors. It is calculated as the maximum value between max_lag and max_size_window_features.
features_encoding str

Encoding method for features derived from the time series (lags and window features that return class values).
use_native_categoricals bool

Indicates whether the estimator supports native categorical features.
classes_ list

List of class labels seen during training.
class_codes_ list

List of class codes assigned by the OrdinalEncoder during training.
n_classes_ int

Number of classes seen during training.
encoder OrdinalEncoder

Instance of OrdinalEncoder used to encode target variable class labels.
encoding_mapping_ dict

Mapping of original class labels to encoded values.
code_to_class_mapping_ dict

Mapping of encoded values to original class labels.
transformer_exog object transformer (preprocessor)

An instance of a transformer (preprocessor) compatible with the scikit-learn preprocessing API. The transformation is applied to exog before training the forecaster. inverse_transform is not available when using ColumnTransformers.
categorical_features (str, list)

Specifies which exogenous variables should be treated as categorical.
categorical_features_names_in_ list

Names of the exogenous variables considered as categorical during training.
categorical_encoder OrdinalEncoder

Instance of OrdinalEncoder used to encode categorical exogenous variables.
weight_func Callable

Function that defines the individual weights for each sample based on the index. For example, a function that assigns a lower weight to certain dates. Ignored if estimator does not have the argument sample_weight in its fit method. The resulting sample_weight cannot have negative values.
source_code_weight_func str

Source code of the custom function used to create weights.
dropna_from_series bool

Determine whether NaN detected in the training matrices will be dropped.
last_window_ pandas DataFrame

This window represents the most recent data observed by the predictor during its training phase. It contains the values needed to predict the next step immediately after the training data. These values are stored in the original scale of the time series before undergoing any transformation.
index_type_ type

Type of index of the input used in training.
index_freq_ str

Frequency of Index of the input used in training.
training_range_ pandas Index

First and last values of index of the data used during training.
series_name_in_ str

Name of the series provided by the user during training.
exog_in_ bool

If the forecaster has been trained using exogenous variable/s.
exog_names_in_ list

Names of the exogenous variables used during training.
exog_type_in_ type

Type of exogenous data (pandas Series or DataFrame) used in training.
exog_dtypes_in_ dict

Type of each exogenous variable/s used in training before the transformation applied by transformer_exog. If transformer_exog is not used, it is equal to exog_dtypes_out_.
exog_dtypes_out_ dict

Type of each exogenous variable/s used in training after the transformation applied by transformer_exog. If transformer_exog is not used, it is equal to exog_dtypes_in_.
X_train_window_features_names_out_ list

Names of the window features included in the matrix X_train created internally for training.
X_train_exog_names_out_ list

Names of the exogenous variables included in the matrix X_train created internally for training. It can be different from exog_names_in_ if some exogenous variables are transformed during the training process.
X_train_features_names_out_ list

Names of columns of the matrix created internally for training.
fit_kwargs dict

Additional arguments to be passed to the fit method of the estimator.
creation_date str

Date of creation.
is_fitted bool

Tag to identify if the estimator has been fitted (trained).
fit_date str

Date of last fit.
skforecast_version str

Version of skforecast library used to create the forecaster.
python_version str

Version of python used to create the forecaster.
forecaster_id (str, int)

Name used as an identifier of the forecaster.
__skforecast_tags__ dict

Tags associated with the forecaster.
_probabilistic_mode (str, bool)

Private attribute used to indicate whether the forecaster should perform some calculations during backtesting.
transformer_y Ignored

Not used, present here for API consistency by convention.
differentiation Ignored

Not used, present here for API consistency by convention.
differentiation_max Ignored

Not used, present here for API consistency by convention.
Notes

features_encoding: Controls how features derived from the target series (lags and window features that return class values) are treated by the estimator. When set to 'auto' or 'categorical', the encoded class codes (integers) are communicated as categorical to the estimator's native categorical handling (e.g., LightGBM, CatBoost). When set to 'ordinal', they are treated as numeric values. Related attributes: encoder (OrdinalEncoder), encoding_mapping_, code_to_class_mapping_, classes_, class_codes_, n_classes_.

categorical_features: Controls which exogenous variables should be treated as categorical. These columns are encoded and their indices are combined with the lag indices when configuring the estimator's native categorical handling. Related attributes: categorical_encoder (OrdinalEncoder), categorical_features_names_in_.

All exogenous categorical management must be done through this parameter. Setting categorical features directly on the estimator or via fit_kwargs is not supported, as the forecaster always overwrites the estimator's categorical configuration during fit to include both autoregressive and exogenous categorical indices.

Difference between features_encoding and categorical_features:

  • features_encoding: Applies to features derived from the target series (lags and window features that return class codes).
  • categorical_features: Applies to exogenous variables (exog).

Methods:

Name Description
create_train_X_y

Create training matrices from univariate time series and exogenous
create_sample_weights

Create weights for each observation according to the forecaster's attribute
fit

Training Forecaster.
create_predict_X

Create the predictors needed to predict steps ahead. As it is a recursive
predict

Predict n steps ahead. It is a recursive process in which, each prediction,
predict_proba

Predict class probabilities n steps ahead. It is a recursive process in

set_params

Set new values to the parameters of the scikit-learn model stored in the
set_lags

Set new value to the attribute lags. Attributes lags_names,

set_window_features

Set new value to the attribute window_features. Attributes

set_fit_kwargs

Set new values for the additional keyword arguments passed to the fit

get_feature_importances

Return feature importances of the estimator stored in the forecaster.
Source code in skforecast/recursive/_forecaster_recursive_classifier.py 
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
def __init__(
    self,
    estimator: object,
    lags: int | list[int] | np.ndarray[int] | range[int] | None = None,
    window_features: object | list[object] | None = None,
    features_encoding: str = 'auto',
    transformer_exog: object | None = None,
    categorical_features: str | list[str] | None = 'auto',
    weight_func: Callable | None = None,
    dropna_from_series: bool = False,
    fit_kwargs: dict[str, object] | None = None,
    forecaster_id: str | int | None = None
) -> None:

    self.estimator                          = clone(estimator)
    self.transformer_exog                   = transformer_exog
    self.categorical_features               = categorical_features
    self.weight_func                        = weight_func
    self.source_code_weight_func            = None
    self.dropna_from_series                 = dropna_from_series
    self.last_window_                       = None
    self.index_type_                        = None
    self.index_freq_                        = None
    self.training_range_                    = None
    self.series_name_in_                    = None
    self.exog_in_                           = False
    self.exog_names_in_                     = None
    self.exog_type_in_                      = None
    self.exog_dtypes_in_                    = None
    self.exog_dtypes_out_                   = None
    self.X_train_window_features_names_out_ = None
    self.X_train_exog_names_out_            = None
    self.X_train_features_names_out_        = None
    self.categorical_features_names_in_     = None
    self.creation_date                      = pd.Timestamp.today().strftime('%Y-%m-%d %H:%M:%S')
    self.is_fitted                          = False
    self.fit_date                           = None
    self.skforecast_version                 = skforecast.__version__
    self.python_version                     = sys.version.split(" ")[0]
    self.forecaster_id                      = forecaster_id
    self._probabilistic_mode                = False  # NOTE: Ignored in this forecaster
    self.transformer_y                      = None  # NOTE: Ignored in this forecaster
    self.differentiation                    = None  # NOTE: Ignored in this forecaster
    self.differentiation_max                = None  # NOTE: Ignored in this forecaster

    self.features_encoding                  = features_encoding
    self.use_native_categoricals            = False
    self.classes_                           = None
    self.class_codes_                       = None
    self.n_classes_                         = None
    self.encoding_mapping_                  = None
    self.code_to_class_mapping_             = None

    valid_encodings = ['auto', 'categorical', 'ordinal']
    if features_encoding not in valid_encodings:
        raise ValueError(
            f"`features_encoding` must be one of {valid_encodings}. "
            f"Got '{features_encoding}'."
        )

    supports_categorical = self._check_categorical_support(estimator)
    if features_encoding == 'categorical':
        if supports_categorical:
            self.use_native_categoricals = True
        else:
            raise ValueError(
                f"`features_encoding='categorical'` requires a estimator that "
                f"supports native categorical features (LightGBM, CatBoost, XGBoost). "
                f"Got {type(estimator).__name__}. Use 'auto' or 'ordinal' instead."
            )
    elif features_encoding == 'auto':
        if supports_categorical:
            self.use_native_categoricals = True

    self.encoder = OrdinalEncoder(
                       categories = 'auto',
                       dtype      = int
                   )

    self.lags, self.lags_names, self.max_lag = initialize_lags(type(self).__name__, lags)
    self.lags_are_contiguous = (
        self.lags is not None
        and np.array_equal(self.lags, np.arange(1, self.max_lag + 1))
    )
    self.window_features, self.window_features_names, self.max_size_window_features = (
        initialize_window_features(window_features)
    )
    if self.window_features is None and self.lags is None:
        raise ValueError(
            "At least one of the arguments `lags` or `window_features` "
            "must be different from None. This is required to create the "
            "predictors used in training the forecaster."
        )

    self.window_size = max(
        [ws for ws in [self.max_lag, self.max_size_window_features] 
         if ws is not None]
    )
    self.window_features_class_names = None
    if window_features is not None:
        self.window_features_class_names = [
            type(wf).__name__ for wf in self.window_features
        ]

    if categorical_features is not None:
        if not (
            (isinstance(categorical_features, str) and categorical_features == 'auto')
            or isinstance(categorical_features, list)
        ):
            raise ValueError(
                f"Argument `categorical_features` must be `'auto'`, a list of "
                f"column names, or `None`. Got {categorical_features}."
            )
        if isinstance(categorical_features, list):
            if len(categorical_features) == 0:
                raise ValueError(
                    "Argument `categorical_features` must not be an empty list. "
                    "Use `None` to disable categorical encoding."
                )

    self.categorical_encoder = OrdinalEncoder(
                                   dtype                 = float,
                                   handle_unknown        = 'use_encoded_value',
                                   unknown_value         = np.nan,
                                   encoded_missing_value = np.nan
                               ).set_output(transform="pandas")

    self.weight_func, self.source_code_weight_func, _ = initialize_weights(
        forecaster_name = type(self).__name__, 
        estimator       = estimator, 
        weight_func     = weight_func, 
        series_weights  = None
    )

    self.fit_kwargs = check_select_fit_kwargs(
                          estimator  = estimator,
                          fit_kwargs = fit_kwargs
                      )

    self.__skforecast_tags__ = {
        "library": "skforecast",
        "forecaster_name": "ForecasterRecursiveClassifier",
        "forecaster_task": "classification",
        "forecasting_scope": "single-series",  # single-series | global
        "forecasting_strategy": "recursive",   # recursive | direct | deep_learning | foundation
        "multiple_estimators": False,
        "index_types_supported": ["pandas.RangeIndex", "pandas.DatetimeIndex"],
        "requires_index_frequency": True,

        "allowed_input_types_series": ["pandas.Series"],
        "supports_exog": True,
        "allowed_input_types_exog": ["pandas.Series", "pandas.DataFrame"],
        "handles_missing_values_series": True, 
        "handles_missing_values_exog": True, 

        "supports_lags": True,
        "supports_window_features": True,
        "supports_transformer_series": False,
        "supports_transformer_exog": True,
        "supports_categorical_features": True,
        "supports_weight_func": True,
        "supports_differentiation": False,

        "prediction_types": ["point", "probabilities"],
        "supports_probabilistic": True,
        "probabilistic_methods": ["class-probabilities"],
        "handles_binned_residuals": False
    }

Attributes¶

estimator instance-attribute ¶

estimator = clone(estimator)

transformer_exog instance-attribute ¶

transformer_exog = transformer_exog

categorical_features instance-attribute ¶

categorical_features = categorical_features

weight_func instance-attribute ¶

weight_func = weight_func

source_code_weight_func instance-attribute ¶

source_code_weight_func = None

dropna_from_series instance-attribute ¶

dropna_from_series = dropna_from_series

last_window_ instance-attribute ¶

last_window_ = None

index_type_ instance-attribute ¶

index_type_ = None

index_freq_ instance-attribute ¶

index_freq_ = None

training_range_ instance-attribute ¶

training_range_ = None

series_name_in_ instance-attribute ¶

series_name_in_ = None

exog_in_ instance-attribute ¶

exog_in_ = False

exog_names_in_ instance-attribute ¶

exog_names_in_ = None

exog_type_in_ instance-attribute ¶

exog_type_in_ = None

exog_dtypes_in_ instance-attribute ¶

exog_dtypes_in_ = None

exog_dtypes_out_ instance-attribute ¶

exog_dtypes_out_ = None

X_train_window_features_names_out_ instance-attribute ¶

X_train_window_features_names_out_ = None

X_train_exog_names_out_ instance-attribute ¶

X_train_exog_names_out_ = None

X_train_features_names_out_ instance-attribute ¶

X_train_features_names_out_ = None

categorical_features_names_in_ instance-attribute ¶

categorical_features_names_in_ = None

creation_date instance-attribute ¶

creation_date = pd.Timestamp.today().strftime(
    "%Y-%m-%d %H:%M:%S"
)

is_fitted instance-attribute ¶

is_fitted = False

fit_date instance-attribute ¶

fit_date = None

skforecast_version instance-attribute ¶

skforecast_version = skforecast.__version__

python_version instance-attribute ¶

python_version = sys.version.split(' ')[0]

forecaster_id instance-attribute ¶

forecaster_id = forecaster_id

transformer_y instance-attribute ¶

transformer_y = None

differentiation instance-attribute ¶

differentiation = None

differentiation_max instance-attribute ¶

differentiation_max = None

features_encoding instance-attribute ¶

features_encoding = features_encoding

use_native_categoricals instance-attribute ¶

use_native_categoricals = False

classes_ instance-attribute ¶

classes_ = None

class_codes_ instance-attribute ¶

class_codes_ = None

n_classes_ instance-attribute ¶

n_classes_ = None

encoding_mapping_ instance-attribute ¶

encoding_mapping_ = None

code_to_class_mapping_ instance-attribute ¶

code_to_class_mapping_ = None

encoder instance-attribute ¶

encoder = OrdinalEncoder(categories='auto', dtype=int)

lags_are_contiguous instance-attribute ¶

lags_are_contiguous = (
    self.lags is not None
    and np.array_equal(
        self.lags, np.arange(1, self.max_lag + 1)
    )
)

window_size instance-attribute ¶

window_size = max(
    [
        ws
        for ws in [
            self.max_lag,
            self.max_size_window_features,
        ]
        if ws is not None
    ]
)

window_features_class_names instance-attribute ¶

window_features_class_names = None

categorical_encoder instance-attribute ¶

categorical_encoder = OrdinalEncoder(
    dtype=float,
    handle_unknown="use_encoded_value",
    unknown_value=np.nan,
    encoded_missing_value=np.nan,
).set_output(transform="pandas")

fit_kwargs instance-attribute ¶

fit_kwargs = check_select_fit_kwargs(
    estimator=estimator, fit_kwargs=fit_kwargs
)

Methods:¶

create_train_X_y ¶

create_train_X_y(y, exog=None, encoded=True)

Create training matrices from univariate time series and exogenous variables.

Parameters:

Name Type Description Default
y pandas Series

Training time series.

 required
exog pandas Series, pandas DataFrame

Exogenous variable/s included as predictor/s. Must have the same number of observations as y and their indexes must be aligned.

 None
encoded bool

Whether to return the target (y_train) and lag features encoded as integers (as used during training) or decoded to their original categories. This only affects features derived from y (lags and y_train); exogenous variables encoded via categorical_features are always returned in their encoded form.

 True

Returns:

Name Type Description
X_train pandas DataFrame

Training values (predictors).
y_train pandas Series

Values of the time series related to each row of X_train.
Notes

Autoregressive Features (features_encoding) During training, target class labels are ordinal-encoded as integers using encoder (OrdinalEncoder). When features_encoding is 'auto' or 'categorical', lag features and window features returning class codes (e.g., mode) are communicated as categorical to the estimator's native categorical handling (e.g., LightGBM, CatBoost). When set to 'ordinal', they are treated as numeric values. Related attributes: encoder (OrdinalEncoder), encoding_mapping_, code_to_class_mapping_, classes_, class_codes_, n_classes_.

Exogenous Features (categorical_features) Exogenous variables specified via categorical_features are ordinal- encoded using categorical_encoder (OrdinalEncoder) and their column indices are combined with the autoregressive categorical indices when configuring the estimator's native categorical handling. The forecaster always overwrites the estimator's categorical configuration to include both autoregressive and exogenous categorical indices. Related attributes: categorical_encoder (OrdinalEncoder), categorical_features_names_in_.

Handling Missing Values If y or exog contain interspersed NaN values, rows where y_train is NaN are always removed. Rows where X_train contains NaN (from lagged NaN in y or from NaN in exog) are removed only if dropna_from_series=True; otherwise a warning is issued.

Source code in skforecast/recursive/_forecaster_recursive_classifier.py 
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
def create_train_X_y(
    self,
    y: pd.Series,
    exog: pd.Series | pd.DataFrame | None = None,
    encoded: bool = True
) -> tuple[pd.DataFrame, pd.Series]:
    """
    Create training matrices from univariate time series and exogenous
    variables.

    Parameters
    ----------
    y : pandas Series
        Training time series.
    exog : pandas Series, pandas DataFrame, default None
        Exogenous variable/s included as predictor/s. Must have the same
        number of observations as `y` and their indexes must be aligned.
    encoded : bool, default True
        Whether to return the target (`y_train`) and lag features encoded
        as integers (as used during training) or decoded to their original
        categories. This only affects features derived from `y` (lags and
        `y_train`); exogenous variables encoded via `categorical_features`
        are always returned in their encoded form.

    Returns
    -------
    X_train : pandas DataFrame
        Training values (predictors).
    y_train : pandas Series
        Values of the time series related to each row of `X_train`.

    Notes
    -----
    **Autoregressive Features (`features_encoding`)**
    During training, target class labels are ordinal-encoded as integers
    using `encoder` (`OrdinalEncoder`). When `features_encoding` is `'auto'` 
    or `'categorical'`, lag features and window features returning class
    codes (e.g., mode) are communicated as categorical to the estimator's
    native categorical handling (e.g., LightGBM, CatBoost). When set to
    `'ordinal'`, they are treated as numeric values.
    Related attributes: `encoder` (`OrdinalEncoder`), `encoding_mapping_`, 
    `code_to_class_mapping_`, `classes_`, `class_codes_`, `n_classes_`.

    **Exogenous Features (`categorical_features`)**
    Exogenous variables specified via `categorical_features` are ordinal-
    encoded using `categorical_encoder` (`OrdinalEncoder`) and their column 
    indices are combined with the autoregressive categorical indices when 
    configuring the estimator's native categorical handling. The forecaster 
    always overwrites the estimator's categorical configuration to include 
    both autoregressive and exogenous categorical indices.
    Related attributes: `categorical_encoder` (`OrdinalEncoder`), 
    `categorical_features_names_in_`.

    **Handling Missing Values**
    If `y` or `exog` contain interspersed NaN values, rows where `y_train`
    is NaN are always removed. Rows where `X_train` contains NaN (from
    lagged NaN in `y` or from NaN in `exog`) are removed only if
    `dropna_from_series=True`; otherwise a warning is issued.

    """

    (
        X_train,
        y_train,
        train_index,
        _,
        _,
        _,
        _,
        _,
        X_train_features_names_out_,
        _,
        exog_dtypes_out_,
        _
    ) = self._create_train_X_y(y=y, exog=exog)

    X_train = pd.DataFrame(
                  data    = X_train,
                  index   = train_index,
                  columns = X_train_features_names_out_
              )

    if exog_dtypes_out_ is not None:
        X_train_dtypes = {col: float for col in X_train_features_names_out_}
        X_train_dtypes.update(exog_dtypes_out_)
        X_train = X_train.astype(X_train_dtypes, copy=False)

    y_train = pd.Series(
                  data  = y_train,
                  index = train_index,
                  name  = 'y'
              )

    if not encoded:

        for col in self.lags_names:
            X_train[col] = self.encoder.inverse_transform(
                X_train[col].to_numpy().reshape(-1, 1)
            ).ravel()

        y_train = pd.Series(
                      data  = self.encoder.inverse_transform(y_train.to_numpy().reshape(-1, 1)).ravel(),
                      index = y_train.index,
                      name  = y_train.name
                  )

    return X_train, y_train

create_sample_weights ¶

create_sample_weights(X_train)

Create weights for each observation according to the forecaster's attribute weight_func.

Parameters:

Name Type Description Default
X_train pandas DataFrame, pandas Index

Dataframe created with the create_train_X_y method, first return, or the index of the DataFrame.

 required

Returns:

Name Type Description
sample_weight numpy ndarray

Weights to use in fit method.
Source code in skforecast/recursive/_forecaster_recursive_classifier.py 
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
def create_sample_weights(
    self,
    X_train: pd.DataFrame | pd.Index,
) -> np.ndarray:
    """
    Create weights for each observation according to the forecaster's attribute
    `weight_func`.

    Parameters
    ----------
    X_train : pandas DataFrame, pandas Index
        Dataframe created with the `create_train_X_y` method, first return, 
        or the index of the DataFrame.

    Returns
    -------
    sample_weight : numpy ndarray
        Weights to use in `fit` method.

    """

    sample_weight = None

    if self.weight_func is not None:
        sample_weight = self.weight_func(
            X_train.index if isinstance(X_train, pd.DataFrame) else X_train
        )

    if sample_weight is not None:
        if np.isnan(sample_weight).any():
            raise ValueError(
                "The resulting `sample_weight` cannot have NaN values."
            )
        if np.any(sample_weight < 0):
            raise ValueError(
                "The resulting `sample_weight` cannot have negative values."
            )
        if np.sum(sample_weight) == 0:
            raise ValueError(
                "The resulting `sample_weight` cannot be normalized because "
                "the sum of the weights is zero."
            )

    return sample_weight

fit ¶

fit(
    y,
    exog=None,
    store_last_window=True,
    store_in_sample_residuals=None,
    suppress_warnings=False,
)

Training Forecaster.

Additional arguments to be passed to the fit method of the estimator can be added with the fit_kwargs argument when initializing the forecaster.

Parameters:

Name Type Description Default
y pandas Series

Training time series.

 required
exog pandas Series, pandas DataFrame

Exogenous variable/s included as predictor/s. Must have the same number of observations as y and their indexes must be aligned so that y[i] is regressed on exog[i].

 None
store_last_window bool

Whether or not to store the last window (last_window_) of training data.

 True
store_in_sample_residuals Ignored

Not used, present here for API consistency by convention.

 None
suppress_warnings bool

If True, skforecast warnings are suppressed during execution. See skforecast.exceptions.warn_skforecast_categories for the list of warnings that are suppressed.

 False

Returns:

Type Description
None
Notes

Autoregressive Features (features_encoding) During training, target class labels are ordinal-encoded as integers using encoder (OrdinalEncoder). When features_encoding is 'auto' or 'categorical', lag features and window features returning class codes (e.g., mode) are communicated as categorical to the estimator's native categorical handling (e.g., LightGBM, CatBoost). When set to 'ordinal', they are treated as numeric values. Related attributes: encoder (OrdinalEncoder), encoding_mapping_, code_to_class_mapping_, classes_, class_codes_, n_classes_.

Exogenous Features (categorical_features) Exogenous variables specified via categorical_features are ordinal- encoded using categorical_encoder (OrdinalEncoder) and their column indices are combined with the autoregressive categorical indices when configuring the estimator's native categorical handling. The forecaster always overwrites the estimator's categorical configuration to include both autoregressive and exogenous categorical indices. Related attributes: categorical_encoder (OrdinalEncoder), categorical_features_names_in_.

Source code in skforecast/recursive/_forecaster_recursive_classifier.py 
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
@manage_warnings
def fit(
    self,
    y: pd.Series,
    exog: pd.Series | pd.DataFrame | None = None,
    store_last_window: bool = True,
    store_in_sample_residuals: Any = None,
    suppress_warnings: bool = False
) -> None:
    """
    Training Forecaster.

    Additional arguments to be passed to the `fit` method of the estimator 
    can be added with the `fit_kwargs` argument when initializing the forecaster.

    Parameters
    ----------
    y : pandas Series
        Training time series.
    exog : pandas Series, pandas DataFrame, default None
        Exogenous variable/s included as predictor/s. Must have the same
        number of observations as `y` and their indexes must be aligned so
        that y[i] is regressed on exog[i].
    store_last_window : bool, default True
        Whether or not to store the last window (`last_window_`) of training data.
    store_in_sample_residuals : Ignored
        Not used, present here for API consistency by convention.
    suppress_warnings : bool, default False
        If `True`, skforecast warnings are suppressed during execution.
        See `skforecast.exceptions.warn_skforecast_categories` for the
        list of warnings that are suppressed.

    Returns
    -------
    None

    Notes
    -----
    **Autoregressive Features (`features_encoding`)**
    During training, target class labels are ordinal-encoded as integers
    using `encoder` (`OrdinalEncoder`). When `features_encoding` is `'auto'` 
    or `'categorical'`, lag features and window features returning class
    codes (e.g., mode) are communicated as categorical to the estimator's
    native categorical handling (e.g., LightGBM, CatBoost). When set to
    `'ordinal'`, they are treated as numeric values.
    Related attributes: `encoder` (`OrdinalEncoder`), `encoding_mapping_`, 
    `code_to_class_mapping_`, `classes_`, `class_codes_`, `n_classes_`.

    **Exogenous Features (`categorical_features`)**
    Exogenous variables specified via `categorical_features` are ordinal-
    encoded using `categorical_encoder` (`OrdinalEncoder`) and their column 
    indices are combined with the autoregressive categorical indices when 
    configuring the estimator's native categorical handling. The forecaster 
    always overwrites the estimator's categorical configuration to include 
    both autoregressive and exogenous categorical indices.
    Related attributes: `categorical_encoder` (`OrdinalEncoder`), 
    `categorical_features_names_in_`.

    """

    self.last_window_                       = None
    self.index_type_                        = None
    self.index_freq_                        = None
    self.training_range_                    = None
    self.series_name_in_                    = None
    self.exog_in_                           = False
    self.exog_names_in_                     = None
    self.exog_type_in_                      = None
    self.exog_dtypes_in_                    = None
    self.exog_dtypes_out_                   = None
    self.categorical_features_names_in_     = None
    self.X_train_window_features_names_out_ = None
    self.X_train_exog_names_out_            = None
    self.X_train_features_names_out_        = None
    self.is_fitted                          = False
    self.fit_date                           = None
    self.classes_                           = None
    self.class_codes_                       = None
    self.n_classes_                         = None
    self.encoding_mapping_                  = None
    self.code_to_class_mapping_             = None

    (
        X_train,
        y_train,
        train_index,
        y_encoding_info_,
        exog_names_in_,
        categorical_features_names_in_,
        X_train_window_features_names_out_,
        X_train_exog_names_out_,
        X_train_features_names_out_,
        exog_dtypes_in_,
        exog_dtypes_out_,
        last_window_
    ) = self._create_train_X_y(
            y=y, exog=exog, store_last_window=store_last_window
        )

    sample_weight = self.create_sample_weights(X_train=train_index)

    all_categorical_names = []
    if self.use_native_categoricals and self.lags is not None:
        all_categorical_names.extend(self.lags_names)
    if self.use_native_categoricals and X_train_window_features_names_out_:
        # NOTE: Window features whose name contains 'mode' are treated as
        # categorical (they return class codes).
        all_categorical_names.extend(
            [name for name in X_train_window_features_names_out_
             if 'mode' in name]
        )
    if categorical_features_names_in_:
        all_categorical_names.extend(categorical_features_names_in_)

    if self.categorical_features is not None or self.use_native_categoricals:
        fit_kwargs = configure_estimator_categorical_features(
                         estimator                      = self.estimator,
                         categorical_features_names_in_ = all_categorical_names,
                         X_train_features_names_out_    = X_train_features_names_out_,
                         fit_kwargs                     = {**self.fit_kwargs}
                     )
    else:
        fit_kwargs = {**self.fit_kwargs}

    X_train = cast_catboost_categorical_columns(
        X=X_train, fit_kwargs=fit_kwargs, estimator=self.estimator
    )

    if sample_weight is not None:
        self.estimator.fit(
            X             = X_train,
            y             = y_train,
            sample_weight = sample_weight,
            **fit_kwargs
        )
    else:
        self.estimator.fit(X=X_train, y=y_train, **fit_kwargs)

    self.classes_ = y_encoding_info_['classes_']
    self.class_codes_ = y_encoding_info_['class_codes_']
    self.n_classes_ = y_encoding_info_['n_classes_']
    self.encoding_mapping_ = y_encoding_info_['encoding_mapping_']
    self.code_to_class_mapping_ = {
        code: cls for cls, code in self.encoding_mapping_.items()
    }

    self.X_train_window_features_names_out_ = X_train_window_features_names_out_
    self.X_train_features_names_out_ = X_train_features_names_out_

    self.is_fitted = True
    self.series_name_in_ = y.name if y.name is not None else 'y'
    self.fit_date = pd.Timestamp.today().strftime('%Y-%m-%d %H:%M:%S')
    self.training_range_ = y.index[[0, -1]]
    self.index_type_ = type(y.index)
    if isinstance(y.index, pd.DatetimeIndex):
        self.index_freq_ = y.index.freq
    else: 
        self.index_freq_ = y.index.step

    if exog is not None:
        self.exog_in_ = True
        self.exog_type_in_ = type(exog)
        self.exog_names_in_ = exog_names_in_
        self.exog_dtypes_in_ = exog_dtypes_in_
        self.exog_dtypes_out_ = exog_dtypes_out_
        self.categorical_features_names_in_ = categorical_features_names_in_
        self.X_train_exog_names_out_ = X_train_exog_names_out_

    if store_last_window:
        self.last_window_ = last_window_

create_predict_X ¶

create_predict_X(
    steps,
    last_window=None,
    exog=None,
    check_inputs=True,
    suppress_warnings=False,
)

Create the predictors needed to predict steps ahead. As it is a recursive process, the predictors are created at each iteration of the prediction process.

Parameters:

Name Type Description Default
steps int, str, pandas Timestamp

Number of steps to predict.

  • If steps is int, number of steps to predict.
  • If str or pandas Datetime, the prediction will be up to that date.
 required
last_window pandas Series, pandas DataFrame

Series values used to create the predictors (lags) needed in the first iteration of the prediction (t + 1). If last_window = None, the values stored in self.last_window_ are used to calculate the initial predictors, and the predictions start right after training data.

 None
exog pandas Series, pandas DataFrame

Exogenous variable/s included as predictor/s.

 None
check_inputs bool

If True, the input is checked for possible warnings and errors with the check_predict_input function. This argument is created for internal use and is not recommended to be changed.

 True
suppress_warnings bool

If True, skforecast warnings are suppressed during execution. See skforecast.exceptions.warn_skforecast_categories for the list of warnings that are suppressed.

 False

Returns:

Name Type Description
X_predict pandas DataFrame

Pandas DataFrame with the predictors for each step. The index is the same as the prediction index.
Source code in skforecast/recursive/_forecaster_recursive_classifier.py 
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
@manage_warnings
def create_predict_X(
    self,
    steps: int,
    last_window: pd.Series | pd.DataFrame | None = None,
    exog: pd.Series | pd.DataFrame | None = None,
    check_inputs: bool = True,
    suppress_warnings: bool = False
) -> pd.DataFrame:
    """
    Create the predictors needed to predict `steps` ahead. As it is a recursive
    process, the predictors are created at each iteration of the prediction 
    process.

    Parameters
    ----------
    steps : int, str, pandas Timestamp
        Number of steps to predict. 

        - If steps is int, number of steps to predict. 
        - If str or pandas Datetime, the prediction will be up to that date.
    last_window : pandas Series, pandas DataFrame, default None
        Series values used to create the predictors (lags) needed in the 
        first iteration of the prediction (t + 1).
        If `last_window = None`, the values stored in `self.last_window_` are
        used to calculate the initial predictors, and the predictions start
        right after training data.
    exog : pandas Series, pandas DataFrame, default None
        Exogenous variable/s included as predictor/s.
    check_inputs : bool, default True
        If `True`, the input is checked for possible warnings and errors 
        with the `check_predict_input` function. This argument is created 
        for internal use and is not recommended to be changed.
    suppress_warnings : bool, default False
        If `True`, skforecast warnings are suppressed during execution.
        See `skforecast.exceptions.warn_skforecast_categories` for the
        list of warnings that are suppressed.

    Returns
    -------
    X_predict : pandas DataFrame
        Pandas DataFrame with the predictors for each step. The index 
        is the same as the prediction index.

    """

    (
        last_window_values,
        exog_values,
        prediction_index,
        steps
    ) = self._create_predict_inputs(
            steps        = steps,
            last_window  = last_window,
            exog         = exog,
            check_inputs = check_inputs,
        )

    with warnings.catch_warnings():
        warnings.filterwarnings(
            "ignore", 
            message="X does not have valid feature names", 
            category=UserWarning
        )
        predictions = self._recursive_predict(
                          steps              = steps,
                          last_window_values = last_window_values,
                          exog_values        = exog_values,
                          predict_proba      = False
                      )

    X_predict = []
    full_predictors = np.concatenate((last_window_values, predictions))

    if self.lags is not None:
        idx = np.arange(-steps, 0)[:, None] - self.lags
        X_lags = full_predictors[idx + len(full_predictors)]
        X_predict.append(X_lags)

    if self.window_features is not None:
        X_window_features = np.full(
            shape      = (steps, len(self.X_train_window_features_names_out_)), 
            fill_value = np.nan, 
            order      = 'C',
            dtype      = float
        )
        for i in range(steps):
            X_window_features[i, :] = np.concatenate(
                [wf.transform(full_predictors[i:-(steps - i)]) 
                 for wf in self.window_features]
            )
        X_predict.append(X_window_features)

    if exog is not None:
        X_predict.append(exog_values)

    X_predict = pd.DataFrame(
                    data    = np.concatenate(X_predict, axis=1),
                    columns = self.X_train_features_names_out_,
                    index   = prediction_index
                )

    if self.exog_in_:
        X_predict_dtypes = {col: float for col in self.X_train_features_names_out_}
        X_predict_dtypes.update(self.exog_dtypes_out_)
        X_predict = X_predict.astype(X_predict_dtypes, copy=False)

    if self.transformer_exog is not None:
        warnings.warn(
            "The output matrix is in the transformed scale due to the "
            "inclusion of transformations (`transformer_exog`) in the Forecaster. "
            "As a result, any predictions generated using this matrix will also "
            "be in the transformed scale. Please refer to the documentation "
            "for more details: "
            "https://skforecast.org/latest/user_guides/training-and-prediction-matrices.html",
            DataTransformationWarning
        )

    return X_predict

predict ¶

predict(steps, last_window=None, exog=None)

Predict n steps ahead. It is a recursive process in which, each prediction, is used as a predictor for the next step.

Parameters:

Name Type Description Default
steps int, str, pandas Timestamp

Number of steps to predict.

  • If steps is int, number of steps to predict.
  • If str or pandas Datetime, the prediction will be up to that date.
 required
last_window pandas Series, pandas DataFrame

Series values used to create the predictors (lags) needed in the first iteration of the prediction (t + 1). If last_window = None, the values stored in self.last_window_ are used to calculate the initial predictors, and the predictions start right after training data.

 None
exog pandas Series, pandas DataFrame

Exogenous variable/s included as predictor/s.

 None

Returns:

Name Type Description
predictions pandas Series

Predicted values (class labels).
Source code in skforecast/recursive/_forecaster_recursive_classifier.py 
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
def predict(
    self,
    steps: int | str | pd.Timestamp,
    last_window: pd.Series | pd.DataFrame | None = None,
    exog: pd.Series | pd.DataFrame | None = None
) -> pd.Series:
    """
    Predict n steps ahead. It is a recursive process in which, each prediction,
    is used as a predictor for the next step.

    Parameters
    ----------
    steps : int, str, pandas Timestamp
        Number of steps to predict. 

        - If steps is int, number of steps to predict. 
        - If str or pandas Datetime, the prediction will be up to that date.
    last_window : pandas Series, pandas DataFrame, default None
        Series values used to create the predictors (lags) needed in the 
        first iteration of the prediction (t + 1).
        If `last_window = None`, the values stored in `self.last_window_` are
        used to calculate the initial predictors, and the predictions start
        right after training data.
    exog : pandas Series, pandas DataFrame, default None
        Exogenous variable/s included as predictor/s.

    Returns
    -------
    predictions : pandas Series
        Predicted values (class labels).

    """

    (
        last_window_values,
        exog_values,
        prediction_index,
        steps
    ) = self._create_predict_inputs(
            steps       = steps,
            last_window = last_window,
            exog        = exog
        )

    with warnings.catch_warnings():
        warnings.filterwarnings(
            "ignore", 
            message="X does not have valid feature names", 
            category=UserWarning
        )
        predictions = self._recursive_predict(
                          steps              = steps,
                          last_window_values = last_window_values,
                          exog_values        = exog_values,
                          predict_proba      = False
                      )

    predictions = self.encoder.inverse_transform(
        predictions.reshape(-1, 1)
    ).ravel()

    predictions = pd.Series(
                      data  = predictions,
                      index = prediction_index,
                      name  = 'pred'
                  )

    return predictions

predict_proba ¶

predict_proba(
    steps,
    last_window=None,
    exog=None,
    suppress_warnings=False,
)

Predict class probabilities n steps ahead. It is a recursive process in which the predicted class (argmax of probabilities) is used as a predictor for the next step.

Parameters:

Name Type Description Default
steps int, str, pandas Timestamp

Number of steps to predict.

  • If steps is int, number of steps to predict.
  • If str or pandas Datetime, the prediction will be up to that date.
 required
last_window pandas Series, pandas DataFrame

Series values used to create the predictors (lags) needed in the first iteration of the prediction (t + 1). If last_window = None, the values stored in self.last_window_ are used to calculate the initial predictors, and the predictions start right after training data.

 None
exog pandas Series, pandas DataFrame

Exogenous variable/s included as predictor/s.

 None
suppress_warnings bool

If True, skforecast warnings are suppressed during execution. See skforecast.exceptions.warn_skforecast_categories for the list of warnings that are suppressed.

 False

Returns:

Name Type Description
probabilities pandas DataFrame

Predicted probabilities for each class. Shape (steps, n_classes). Columns are the original class labels.
Source code in skforecast/recursive/_forecaster_recursive_classifier.py 
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
@manage_warnings
def predict_proba(
    self,
    steps: int | str | pd.Timestamp,
    last_window: pd.Series | pd.DataFrame | None = None,
    exog: pd.Series | pd.DataFrame | None = None,
    suppress_warnings: bool = False
) -> pd.DataFrame:
    """
    Predict class probabilities n steps ahead. It is a recursive process in 
    which the predicted class (argmax of probabilities) is used as a predictor 
    for the next step.

    Parameters
    ----------
    steps : int, str, pandas Timestamp
        Number of steps to predict.

        - If steps is int, number of steps to predict. 
        - If str or pandas Datetime, the prediction will be up to that date.
    last_window : pandas Series, pandas DataFrame, default None
        Series values used to create the predictors (lags) needed in the 
        first iteration of the prediction (t + 1).
        If `last_window = None`, the values stored in `self.last_window_` are
        used to calculate the initial predictors, and the predictions start
        right after training data.
    exog : pandas Series, pandas DataFrame, default None
        Exogenous variable/s included as predictor/s.
    suppress_warnings : bool, default False
        If `True`, skforecast warnings are suppressed during execution.
        See `skforecast.exceptions.warn_skforecast_categories` for the
        list of warnings that are suppressed.

    Returns
    -------
    probabilities : pandas DataFrame
        Predicted probabilities for each class. Shape (steps, n_classes).
        Columns are the original class labels.

    """

    if not hasattr(self.estimator, 'predict_proba'):
        raise AttributeError(
            f"The estimator {type(self.estimator).__name__} does not have a "
            f"`predict_proba` method. Use a estimator that supports probability "
            f"predictions (e.g., XGBClassifier, HistGradientBoostingClassifier, etc.)."
        )

    (
        last_window_values,
        exog_values,
        prediction_index,
        steps
    ) = self._create_predict_inputs(
            steps       = steps,
            last_window = last_window,
            exog        = exog
        )

    with warnings.catch_warnings():
        warnings.filterwarnings(
            "ignore", 
            message="X does not have valid feature names", 
            category=UserWarning
        )
        probabilities = self._recursive_predict(
                            steps              = steps,
                            last_window_values = last_window_values,
                            exog_values        = exog_values,
                            predict_proba      = True
                        )

    probabilities = pd.DataFrame(
                        data    = probabilities,
                        index   = prediction_index,
                        columns = [f"{cls}_proba" for cls in self.classes_]
                    )

    return probabilities

set_params ¶

set_params(params)

Set new values to the parameters of the scikit-learn model stored in the forecaster. After calling this method, the forecaster is reset to an unfitted state. The fit method must be called before prediction.

Parameters:

Name Type Description Default
params dict

Parameters values.

 required

Returns:

Type Description
None
Source code in skforecast/recursive/_forecaster_recursive_classifier.py 
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
def set_params(
    self, 
    params: dict[str, object]
) -> None:
    """
    Set new values to the parameters of the scikit-learn model stored in the
    forecaster. After calling this method, the forecaster is reset to an 
    unfitted state. The `fit` method must be called before prediction.

    Parameters
    ----------
    params : dict
        Parameters values.

    Returns
    -------
    None

    """

    self.estimator = clone(self.estimator)
    self.estimator.set_params(**params)
    self.is_fitted = False

set_lags ¶

set_lags(lags=None)

Set new value to the attribute lags. Attributes lags_names, max_lag and window_size are also updated.

Parameters:

Name Type Description Default
lags int, list, numpy ndarray, range

Lags used as predictors. Index starts at 1, so lag 1 is equal to t-1.

  • int: include lags from 1 to lags (included).
  • list, 1d numpy ndarray or range: include only lags present in lags, all elements must be int.
  • None: no lags are included as predictors.
 None

Returns:

Type Description
None
Source code in skforecast/recursive/_forecaster_recursive_classifier.py 
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
def set_lags(
    self, 
    lags: int | list[int] | np.ndarray[int] | range[int] | None = None
) -> None:
    """
    Set new value to the attribute `lags`. Attributes `lags_names`, 
    `max_lag` and `window_size` are also updated.

    Parameters
    ----------
    lags : int, list, numpy ndarray, range, default None
        Lags used as predictors. Index starts at 1, so lag 1 is equal to t-1. 

        - `int`: include lags from 1 to `lags` (included).
        - `list`, `1d numpy ndarray` or `range`: include only lags present in 
        `lags`, all elements must be int.
        - `None`: no lags are included as predictors. 

    Returns
    -------
    None

    """

    if self.window_features is None and lags is None:
        raise ValueError(
            "At least one of the arguments `lags` or `window_features` "
            "must be different from None. This is required to create the "
            "predictors used in training the forecaster."
        )

    self.lags, self.lags_names, self.max_lag = initialize_lags(type(self).__name__, lags)
    self.lags_are_contiguous = (
        self.lags is not None
        and np.array_equal(self.lags, np.arange(1, self.max_lag + 1))
    )
    self.window_size = max(
        [ws for ws in [self.max_lag, self.max_size_window_features] 
         if ws is not None]
    )

set_window_features ¶

set_window_features(window_features=None)

Set new value to the attribute window_features. Attributes max_size_window_features, window_features_names, window_features_class_names and window_size are also updated.

Parameters:

Name Type Description Default
window_features (object, list)

Instance or list of instances used to create window features. Window features are created from the original time series and are included as predictors.

 None

Returns:

Type Description
None
Source code in skforecast/recursive/_forecaster_recursive_classifier.py 
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
def set_window_features(
    self, 
    window_features: object | list[object] | None = None
) -> None:
    """
    Set new value to the attribute `window_features`. Attributes 
    `max_size_window_features`, `window_features_names`, 
    `window_features_class_names` and `window_size` are also updated.

    Parameters
    ----------
    window_features : object, list, default None
        Instance or list of instances used to create window features. Window features
        are created from the original time series and are included as predictors.

    Returns
    -------
    None

    """

    if window_features is None and self.lags is None:
        raise ValueError(
            "At least one of the arguments `lags` or `window_features` "
            "must be different from None. This is required to create the "
            "predictors used in training the forecaster."
        )

    self.window_features, self.window_features_names, self.max_size_window_features = (
        initialize_window_features(window_features)
    )
    self.window_features_class_names = None
    if window_features is not None:
        self.window_features_class_names = [
            type(wf).__name__ for wf in self.window_features
        ] 
    self.window_size = max(
        [ws for ws in [self.max_lag, self.max_size_window_features] 
         if ws is not None]
    )

set_fit_kwargs ¶

set_fit_kwargs(fit_kwargs)

Set new values for the additional keyword arguments passed to the fit method of the estimator.

Parameters:

Name Type Description Default
fit_kwargs dict

Dict of the form {"argument": new_value}.

 required

Returns:

Type Description
None
Source code in skforecast/recursive/_forecaster_recursive_classifier.py 
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
def set_fit_kwargs(
    self, 
    fit_kwargs: dict[str, object]
) -> None:
    """
    Set new values for the additional keyword arguments passed to the `fit` 
    method of the estimator.

    Parameters
    ----------
    fit_kwargs : dict
        Dict of the form {"argument": new_value}.

    Returns
    -------
    None

    """

    self.fit_kwargs = check_select_fit_kwargs(self.estimator, fit_kwargs=fit_kwargs)

get_feature_importances ¶

get_feature_importances(sort_importance=True)

Return feature importances of the estimator stored in the forecaster. Only valid when estimator stores internally the feature importances in the attribute feature_importances_ or coef_. Otherwise, returns None.

Parameters:

Name Type Description Default
sort_importance bool

If True, sorts the feature importances in descending order.

 True

Returns:

Name Type Description
feature_importances pandas DataFrame

Feature importances associated with each predictor.
Source code in skforecast/recursive/_forecaster_recursive_classifier.py 
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
def get_feature_importances(
    self,
    sort_importance: bool = True
) -> pd.DataFrame:
    """
    Return feature importances of the estimator stored in the forecaster.
    Only valid when estimator stores internally the feature importances in the
    attribute `feature_importances_` or `coef_`. Otherwise, returns `None`.

    Parameters
    ----------
    sort_importance: bool, default True
        If `True`, sorts the feature importances in descending order.

    Returns
    -------
    feature_importances : pandas DataFrame
        Feature importances associated with each predictor.

    """

    if not self.is_fitted:
        raise NotFittedError(
            "This forecaster is not fitted yet. Call `fit` with appropriate "
            "arguments before using `get_feature_importances()`."
        )

    estimator = self.estimator
    if isinstance(estimator, Pipeline):
        estimator = estimator[-1]

    # Unify the estimators into a list of tuples: (sub_estimator, cv_fold_index)
    # If it's a single estimator, fold_index is None.
    if type(estimator).__name__ == 'CalibratedClassifierCV':
        if not hasattr(estimator, 'calibrated_classifiers_'):
            warnings.warn(
                "The CalibratedClassifierCV instance is not fitted or does not "
                "expose 'calibrated_classifiers_'. Unable to retrieve importances."
            )
            return None

        estimators_list = [
            (clf.estimator, i) 
            for i, clf in enumerate(estimator.calibrated_classifiers_)
        ]
    else:
        estimators_list = [(estimator, None)]

    dfs_to_concat = []
    for sub_est, fold_idx in estimators_list:

        if hasattr(sub_est, 'feature_importances_'):
            df_fold = pd.DataFrame({
                'feature': self.X_train_features_names_out_,
                'importance': sub_est.feature_importances_
            })
        elif hasattr(sub_est, 'coef_'):
            df_fold = pd.DataFrame(
                data=sub_est.coef_,
                columns=self.X_train_features_names_out_
            )
            df_fold.insert(0, 'classes', self.classes_)
        else:
            continue

        if fold_idx is not None:
            df_fold.insert(0, 'cv_fold', fold_idx)

        dfs_to_concat.append(df_fold)

    # Handle cases where no importances could be extracted
    if not dfs_to_concat:
        warnings.warn(
            f"Impossible to access feature importances for estimator of type "
            f"{type(estimator)}. This method is only valid when the "
            f"estimator stores internally the feature importances in the "
            f"attribute `feature_importances_` or `coef_`."
        )
        return None

    feature_importances = pd.concat(dfs_to_concat, axis=0, ignore_index=True)

    if sort_importance and 'importance' in feature_importances.columns:
        # If it has folds, sort by importance but keep folds grouped nicely? 
        # Usually, just sorting by importance globally is expected, 
        # or (Fold, -Importance). Here we prioritize global importance.
        if 'cv_fold' in feature_importances.columns:
            feature_importances = feature_importances.sort_values(
                by=['cv_fold', 'importance'], ascending=[True, False]
            )
        else:
            feature_importances = feature_importances.sort_values(
                by='importance', ascending=False
            )

    return feature_importances