autogluon.timeseries 1.4.1b20250906__py3-none-any.whl → 1.4.1b20251210__py3-none-any.whl

autogluon/timeseries/models/ensemble/weighted/abstract.py

@@ -0,0 +1,40 @@
+import functools
+from abc import ABC
+
+import numpy as np
+
+from autogluon.timeseries.dataset import TimeSeriesDataFrame
+
+from ..abstract import AbstractTimeSeriesEnsembleModel
+
+
+class AbstractWeightedTimeSeriesEnsembleModel(AbstractTimeSeriesEnsembleModel, ABC):
+    """Abstract class for weighted ensembles which assign one (global) weight per model."""
+
+    def __init__(self, name: str | None = None, **kwargs):
+        super().__init__(name=name, **kwargs)
+        self.model_to_weight: dict[str, float] = {}
+
+    @property
+    def model_names(self) -> list[str]:
+        return list(self.model_to_weight.keys())
+
+    @property
+    def model_weights(self) -> np.ndarray:
+        return np.array(list(self.model_to_weight.values()), dtype=np.float64)
+
+    def _predict(self, data: dict[str, TimeSeriesDataFrame], **kwargs) -> TimeSeriesDataFrame:
+        weighted_predictions = [data[model_name] * weight for model_name, weight in self.model_to_weight.items()]
+        return functools.reduce(lambda x, y: x + y, weighted_predictions)
+
+    def get_info(self) -> dict:
+        info = super().get_info()
+        info["model_weights"] = self.model_to_weight.copy()
+        return info
+
+    def remap_base_models(self, model_refit_map: dict[str, str]) -> None:
+        updated_weights = {}
+        for model, weight in self.model_to_weight.items():
+            model_full_name = model_refit_map.get(model, model)
+            updated_weights[model_full_name] = weight
+        self.model_to_weight = updated_weights

autogluon/timeseries/models/ensemble/{basic.py → weighted/basic.py}

@@ -1,4 +1,4 @@
-from typing import Any, Optional
+from typing import Any
 
 import numpy as np
 
@@ -10,17 +10,12 @@ from .abstract import AbstractWeightedTimeSeriesEnsembleModel
 class SimpleAverageEnsemble(AbstractWeightedTimeSeriesEnsembleModel):
     """Constructs a weighted ensemble using a simple average of the constituent models' predictions."""
 
-    def __init__(self, name: Optional[str] = None, **kwargs):
-        if name is None:
-            name = "SimpleAverageEnsemble"
-        super().__init__(name=name, **kwargs)
-
     def _fit(
         self,
         predictions_per_window: dict[str, list[TimeSeriesDataFrame]],
         data_per_window: list[TimeSeriesDataFrame],
-        model_scores: Optional[dict[str, float]] = None,
-        time_limit: Optional[float] = None,
+        model_scores: dict[str, float] | None = None,
+        time_limit: float | None = None,
     ):
         self.model_to_weight = {}
         num_models = len(predictions_per_window)
@@ -47,11 +42,6 @@ class PerformanceWeightedEnsemble(AbstractWeightedTimeSeriesEnsembleModel):
         36.1 (2020): 93-97.
     """
 
-    def __init__(self, name: Optional[str] = None, **kwargs):
-        if name is None:
-            name = "PerformanceWeightedEnsemble"
-        super().__init__(name=name, **kwargs)
-
     def _get_default_hyperparameters(self) -> dict[str, Any]:
         return {"weight_scheme": "sqrt"}
 
@@ -59,12 +49,12 @@ class PerformanceWeightedEnsemble(AbstractWeightedTimeSeriesEnsembleModel):
         self,
         predictions_per_window: dict[str, list[TimeSeriesDataFrame]],
         data_per_window: list[TimeSeriesDataFrame],
-        model_scores: Optional[dict[str, float]] = None,
-        time_limit: Optional[float] = None,
+        model_scores: dict[str, float] | None = None,
+        time_limit: float | None = None,
     ):
         assert model_scores is not None
 
-        weight_scheme = self.get_hyperparameters()["weight_scheme"]
+        weight_scheme = self.get_hyperparameter("weight_scheme")
 
         # drop NaNs
         model_scores = {k: v for k, v in model_scores.items() if np.isfinite(v)}

autogluon/timeseries/models/ensemble/weighted/greedy.py

@@ -0,0 +1,57 @@
+import logging
+import pprint
+from typing import Any
+
+from autogluon.timeseries import TimeSeriesDataFrame
+
+from ..ensemble_selection import fit_time_series_ensemble_selection
+from .abstract import AbstractWeightedTimeSeriesEnsembleModel
+
+logger = logging.getLogger(__name__)
+
+
+class GreedyEnsemble(AbstractWeightedTimeSeriesEnsembleModel):
+    """Constructs a weighted ensemble using the greedy Ensemble Selection algorithm by
+    Caruana et al. [Car2004]
+
+    Other Parameters
+    ----------------
+    ensemble_size: int, default = 100
+        Number of models (with replacement) to include in the ensemble.
+
+    References
+    ----------
+    .. [Car2024] Caruana, Rich, et al. "Ensemble selection from libraries of models."
+        Proceedings of the twenty-first international conference on Machine learning. 2004.
+    """
+
+    def __init__(self, name: str | None = None, **kwargs):
+        if name is None:
+            # FIXME: the name here is kept for backward compatibility. it will be called
+            # GreedyEnsemble in v1.4 once ensemble choices are exposed
+            name = "WeightedEnsemble"
+        super().__init__(name=name, **kwargs)
+
+    def _get_default_hyperparameters(self) -> dict[str, Any]:
+        return {"ensemble_size": 100}
+
+    def _fit(
+        self,
+        predictions_per_window: dict[str, list[TimeSeriesDataFrame]],
+        data_per_window: list[TimeSeriesDataFrame],
+        model_scores: dict[str, float] | None = None,
+        time_limit: float | None = None,
+    ):
+        model_to_weight = fit_time_series_ensemble_selection(
+            data_per_window=data_per_window,
+            predictions_per_window=predictions_per_window,
+            ensemble_size=self.get_hyperparameter("ensemble_size"),
+            eval_metric=self.eval_metric,
+            prediction_length=self.prediction_length,
+            target=self.target,
+            time_limit=time_limit,
+        )
+        self.model_to_weight = {model: weight for model, weight in model_to_weight.items() if weight > 0}
+
+        weights_for_printing = {model: round(float(weight), 2) for model, weight in self.model_to_weight.items()}
+        logger.info(f"\tEnsemble weights: {pprint.pformat(weights_for_printing, width=200)}")

autogluon/timeseries/models/gluonts/abstract.py

@@ -3,7 +3,7 @@ import os
 import shutil
 from datetime import timedelta
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, Callable, Optional, Type, Union, cast, overload
+from typing import TYPE_CHECKING, Any, Callable, Type, cast, overload
 
 import gluonts
 import gluonts.core.settings
@@ -21,7 +21,7 @@ from autogluon.core.hpo.constants import RAY_BACKEND
 from autogluon.tabular.models.tabular_nn.utils.categorical_encoders import (
     OneHotMergeRaresHandleUnknownEncoder as OneHotEncoder,
 )
-from autogluon.timeseries.dataset.ts_dataframe import ITEMID, TimeSeriesDataFrame
+from autogluon.timeseries.dataset import TimeSeriesDataFrame
 from autogluon.timeseries.models.abstract import AbstractTimeSeriesModel
 from autogluon.timeseries.utils.warning_filters import disable_root_logger, warning_filter
 
@@ -72,12 +72,12 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
 
     def __init__(
         self,
-        freq: Optional[str] = None,
+        freq: str | None = None,
         prediction_length: int = 1,
-        path: Optional[str] = None,
-        name: Optional[str] = None,
-        eval_metric: Optional[str] = None,
-        hyperparameters: Optional[dict[str, Any]] = None,
+        path: str | None = None,
+        name: str | None = None,
+        eval_metric: str | None = None,
+        hyperparameters: dict[str, Any] | None = None,
         **kwargs,  # noqa
     ):
         super().__init__(
@@ -89,9 +89,9 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
             hyperparameters=hyperparameters,
             **kwargs,
         )
-        self.gts_predictor: Optional[GluonTSPredictor] = None
-        self._ohe_generator_known: Optional[OneHotEncoder] = None
-        self._ohe_generator_past: Optional[OneHotEncoder] = None
+        self.gts_predictor: GluonTSPredictor | None = None
+        self._ohe_generator_known: OneHotEncoder | None = None
+        self._ohe_generator_past: OneHotEncoder | None = None
         self.callbacks = []
         # Following attributes may be overridden during fit() based on train_data & model parameters
         self.num_feat_static_cat = 0
@@ -105,7 +105,7 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
         self.past_feat_dynamic_cat_cardinality: list[int] = []
         self.negative_data = True
 
-    def save(self, path: Optional[str] = None, verbose: bool = True) -> str:
+    def save(self, path: str | None = None, verbose: bool = True) -> str:
         # we flush callbacks instance variable if it has been set. it can keep weak references which breaks training
         self.callbacks = []
         # The GluonTS predictor is serialized using custom logic
@@ -277,8 +277,8 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
 
         return torch.cuda.is_available()
 
-    def get_minimum_resources(self, is_gpu_available: bool = False) -> dict[str, Union[int, float]]:
-        minimum_resources: dict[str, Union[int, float]] = {"num_cpus": 1}
+    def get_minimum_resources(self, is_gpu_available: bool = False) -> dict[str, int | float]:
+        minimum_resources: dict[str, int | float] = {"num_cpus": 1}
         # if GPU is available, we train with 1 GPU per trial
         if is_gpu_available:
             minimum_resources["num_gpus"] = 1
@@ -289,8 +289,8 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
     @overload
     def _to_gluonts_dataset(self, time_series_df: TimeSeriesDataFrame, known_covariates=None) -> GluonTSDataset: ...
     def _to_gluonts_dataset(
-        self, time_series_df: Optional[TimeSeriesDataFrame], known_covariates: Optional[TimeSeriesDataFrame] = None
-    ) -> Optional[GluonTSDataset]:
+        self, time_series_df: TimeSeriesDataFrame | None, known_covariates: TimeSeriesDataFrame | None = None
+    ) -> GluonTSDataset | None:
         if time_series_df is not None:
             # TODO: Preprocess real-valued features with StdScaler?
             if self.num_feat_static_cat > 0:
@@ -388,10 +388,10 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
     def _fit(
         self,
         train_data: TimeSeriesDataFrame,
-        val_data: Optional[TimeSeriesDataFrame] = None,
-        time_limit: Optional[float] = None,
-        num_cpus: Optional[int] = None,
-        num_gpus: Optional[int] = None,
+        val_data: TimeSeriesDataFrame | None = None,
+        time_limit: float | None = None,
+        num_cpus: int | None = None,
+        num_gpus: int | None = None,
         verbosity: int = 2,
         **kwargs,
     ) -> None:
@@ -438,8 +438,8 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
 
     def _get_callbacks(
         self,
-        time_limit: Optional[float],
-        early_stopping_patience: Optional[int] = None,
+        time_limit: float | None,
+        early_stopping_patience: int | None = None,
     ) -> list[Callable]:
         """Retrieve a list of callback objects for the GluonTS trainer"""
         from lightning.pytorch.callbacks import EarlyStopping, Timer
@@ -454,7 +454,7 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
     def _predict(
         self,
         data: TimeSeriesDataFrame,
-        known_covariates: Optional[TimeSeriesDataFrame] = None,
+        known_covariates: TimeSeriesDataFrame | None = None,
         **kwargs,
     ) -> TimeSeriesDataFrame:
         if self.gts_predictor is None:
@@ -471,8 +471,8 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
     def _predict_gluonts_forecasts(
         self,
         data: TimeSeriesDataFrame,
-        known_covariates: Optional[TimeSeriesDataFrame] = None,
-        num_samples: Optional[int] = None,
+        known_covariates: TimeSeriesDataFrame | None = None,
+        num_samples: int | None = None,
     ) -> list[Forecast]:
         assert self.gts_predictor is not None, "GluonTS models must be fit before predicting."
         gts_data = self._to_gluonts_dataset(data, known_covariates=known_covariates)
@@ -566,7 +566,7 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
     ) -> TimeSeriesDataFrame:
         from gluonts.torch.model.forecast import DistributionForecast
 
-        item_ids = forecast_index.unique(level=ITEMID)
+        item_ids = forecast_index.unique(level=TimeSeriesDataFrame.ITEMID)
         if isinstance(forecasts[0], SampleForecast):
             forecast_df = self._stack_sample_forecasts(cast(list[SampleForecast], forecasts), item_ids)
         elif isinstance(forecasts[0], QuantileForecast):

autogluon/timeseries/models/gluonts/dataset.py

@@ -1,11 +1,11 @@
-from typing import Any, Iterator, Optional, Type
+from typing import Any, Iterator, Type
 
 import numpy as np
 import pandas as pd
 from gluonts.dataset.common import Dataset as GluonTSDataset
 from gluonts.dataset.field_names import FieldName
 
-from autogluon.timeseries.dataset.ts_dataframe import TIMESTAMP, TimeSeriesDataFrame
+from autogluon.timeseries.dataset import TimeSeriesDataFrame
 from autogluon.timeseries.utils.datetime import norm_freq_str
 
 
@@ -17,14 +17,14 @@ class SimpleGluonTSDataset(GluonTSDataset):
         target_df: TimeSeriesDataFrame,
         freq: str,
         target_column: str = "target",
-        feat_static_cat: Optional[np.ndarray] = None,
-        feat_static_real: Optional[np.ndarray] = None,
-        feat_dynamic_cat: Optional[np.ndarray] = None,
-        feat_dynamic_real: Optional[np.ndarray] = None,
-        past_feat_dynamic_cat: Optional[np.ndarray] = None,
-        past_feat_dynamic_real: Optional[np.ndarray] = None,
+        feat_static_cat: np.ndarray | None = None,
+        feat_static_real: np.ndarray | None = None,
+        feat_dynamic_cat: np.ndarray | None = None,
+        feat_dynamic_real: np.ndarray | None = None,
+        past_feat_dynamic_cat: np.ndarray | None = None,
+        past_feat_dynamic_real: np.ndarray | None = None,
         includes_future: bool = False,
-        prediction_length: Optional[int] = None,
+        prediction_length: int | None = None,
     ):
         assert target_df is not None
         # Convert TimeSeriesDataFrame to pd.Series for faster processing
@@ -44,11 +44,11 @@ class SimpleGluonTSDataset(GluonTSDataset):
         # Replace inefficient groupby ITEMID with indptr that stores start:end of each time series
         self.item_ids = target_df.item_ids
         self.indptr = target_df.get_indptr()
-        self.start_timestamps = target_df.index[self.indptr[:-1]].to_frame(index=False)[TIMESTAMP]
+        self.start_timestamps = target_df.index[self.indptr[:-1]].to_frame(index=False)[TimeSeriesDataFrame.TIMESTAMP]
         assert len(self.item_ids) == len(self.start_timestamps)
 
     @staticmethod
-    def _astype(array: Optional[np.ndarray], dtype: Type[np.generic]) -> Optional[np.ndarray]:
+    def _astype(array: np.ndarray | None, dtype: Type[np.generic]) -> np.ndarray | None:
         if array is None:
             return None
         else:

autogluon/timeseries/models/local/__init__.py

@@ -1,5 +1,3 @@
-import joblib.externals.loky
-
 from .naive import AverageModel, NaiveModel, SeasonalAverageModel, SeasonalNaiveModel
 from .npts import NPTSModel
 from .statsforecast import (
@@ -15,8 +13,3 @@ from .statsforecast import (
     ThetaModel,
     ZeroModel,
 )
-
-# By default, joblib w/ loky backend kills processes that take >300MB of RAM assuming that this is caused by a memory
-# leak. This leads to problems for some memory-hungry models like AutoARIMA/Theta.
-# This monkey patch removes this undesired behavior
-joblib.externals.loky.process_executor._MAX_MEMORY_LEAK_SIZE = int(3e10)

autogluon/timeseries/models/local/abstract_local_model.py

@@ -1,7 +1,7 @@
 import logging
 import time
 from multiprocessing import TimeoutError
-from typing import Any, Callable, Optional, Union
+from typing import Any, Callable
 
 import numpy as np
 import pandas as pd
@@ -9,19 +9,16 @@ from joblib import Parallel, cpu_count, delayed
 from scipy.stats import norm
 
 from autogluon.core.utils.exceptions import TimeLimitExceeded
-from autogluon.timeseries.dataset.ts_dataframe import ITEMID, TimeSeriesDataFrame
+from autogluon.timeseries.dataset import TimeSeriesDataFrame
 from autogluon.timeseries.metrics import TimeSeriesScorer
 from autogluon.timeseries.models.abstract import AbstractTimeSeriesModel
+from autogluon.timeseries.utils.constants import AG_DEFAULT_N_JOBS
 from autogluon.timeseries.utils.datetime import get_seasonality
 from autogluon.timeseries.utils.warning_filters import warning_filter
 
 logger = logging.getLogger(__name__)
 
 
-# We use the same default n_jobs across AG-TS to ensure that Joblib reuses the process pool
-AG_DEFAULT_N_JOBS = max(cpu_count(only_physical_cores=True), 1)
-
-
 class AbstractLocalModel(AbstractTimeSeriesModel):
     """Abstract class for local forecasting models that are trained separately for each time series.
 
@@ -40,18 +37,18 @@ class AbstractLocalModel(AbstractTimeSeriesModel):
     """
 
     allowed_local_model_args: list[str] = []
-    default_max_ts_length: Optional[int] = 2500
+    default_max_ts_length: int | None = 2500
     default_max_time_limit_ratio = 1.0
     init_time_in_seconds: int = 0
 
     def __init__(
         self,
-        freq: Optional[str] = None,
+        freq: str | None = None,
         prediction_length: int = 1,
-        path: Optional[str] = None,
-        name: Optional[str] = None,
-        eval_metric: Union[str, TimeSeriesScorer, None] = None,
-        hyperparameters: Optional[dict[str, Any]] = None,
+        path: str | None = None,
+        name: str | None = None,
+        eval_metric: str | TimeSeriesScorer | None = None,
+        hyperparameters: dict[str, Any] | None = None,
         **kwargs,  # noqa
     ):
         super().__init__(
@@ -79,10 +76,10 @@ class AbstractLocalModel(AbstractTimeSeriesModel):
     def preprocess(
         self,
         data: TimeSeriesDataFrame,
-        known_covariates: Optional[TimeSeriesDataFrame] = None,
+        known_covariates: TimeSeriesDataFrame | None = None,
         is_train: bool = False,
         **kwargs,
-    ) -> tuple[TimeSeriesDataFrame, Optional[TimeSeriesDataFrame]]:
+    ) -> tuple[TimeSeriesDataFrame, TimeSeriesDataFrame | None]:
         if not self._get_tags()["allow_nan"]:
             data = data.fill_missing_values()
         return data, known_covariates
@@ -95,7 +92,7 @@ class AbstractLocalModel(AbstractTimeSeriesModel):
         }
 
     @staticmethod
-    def _compute_n_jobs(n_jobs: Union[int, float]) -> int:
+    def _compute_n_jobs(n_jobs: int | float) -> int:
         if isinstance(n_jobs, float) and 0 < n_jobs <= 1:
             return max(int(cpu_count() * n_jobs), 1)
         elif isinstance(n_jobs, int):
@@ -103,7 +100,7 @@ class AbstractLocalModel(AbstractTimeSeriesModel):
         else:
             raise ValueError(f"n_jobs must be a float between 0 and 1 or an integer (received n_jobs = {n_jobs})")
 
-    def _fit(self, train_data: TimeSeriesDataFrame, time_limit: Optional[int] = None, **kwargs):
+    def _fit(self, train_data: TimeSeriesDataFrame, time_limit: int | None = None, **kwargs):
         self._check_fit_params()
 
         if time_limit is not None and time_limit < self.init_time_in_seconds:
@@ -145,7 +142,7 @@ class AbstractLocalModel(AbstractTimeSeriesModel):
             data = data.slice_by_timestep(-max_ts_length, None)
 
         indptr = data.get_indptr()
-        target_series = data[self.target].droplevel(level=ITEMID)
+        target_series = data[self.target].droplevel(level=TimeSeriesDataFrame.ITEMID)
         all_series = (target_series[indptr[i] : indptr[i + 1]] for i in range(len(indptr) - 1))
 
         # timeout ensures that no individual job takes longer than time_limit
@@ -184,7 +181,7 @@ class AbstractLocalModel(AbstractTimeSeriesModel):
         self,
         time_series: pd.Series,
         use_fallback_model: bool,
-        end_time: Optional[float] = None,
+        end_time: float | None = None,
     ) -> tuple[pd.DataFrame, bool]:
         if end_time is not None and time.time() >= end_time:
             raise TimeLimitExceeded

autogluon/timeseries/models/local/naive.py

@@ -96,7 +96,7 @@ class AverageModel(AbstractLocalModel):
         When set to a float between 0.0 and 1.0, that fraction of available CPU cores is used.
         When set to a positive integer, that many cores are used.
         When set to -1, all CPU cores are used.
-    max_ts_length : Optional[int], default = None
+    max_ts_length : int | None, default = None
         If not None, only the last ``max_ts_length`` time steps of each time series will be used to train the model.
         This significantly speeds up fitting and usually leads to no change in accuracy.
     """
@@ -136,7 +136,7 @@ class SeasonalAverageModel(AbstractLocalModel):
         When set to a float between 0.0 and 1.0, that fraction of available CPU cores is used.
         When set to a positive integer, that many cores are used.
         When set to -1, all CPU cores are used.
-    max_ts_length : Optional[int], default = None
+    max_ts_length : int | None, default = None
         If not None, only the last ``max_ts_length`` time steps of each time series will be used to train the model.
         This significantly speeds up fitting and usually leads to no change in accuracy.
     """

autogluon/timeseries/models/local/npts.py

@@ -31,7 +31,7 @@ class NPTSModel(AbstractLocalModel):
         When set to a float between 0.0 and 1.0, that fraction of available CPU cores is used.
         When set to a positive integer, that many cores are used.
         When set to -1, all CPU cores are used.
-    max_ts_length : Optional[int], default = 2500
+    max_ts_length : int | None, default = 2500
         If not None, only the last ``max_ts_length`` time steps of each time series will be used to train the model.
         This significantly speeds up fitting and usually leads to no change in accuracy.
     """

autogluon/timeseries/models/local/statsforecast.py

@@ -1,5 +1,5 @@
 import logging
-from typing import Any, Optional, Type
+from typing import Any, Type
 
 import numpy as np
 import pandas as pd
@@ -19,7 +19,7 @@ class AbstractStatsForecastModel(AbstractLocalModel):
         local_model_args["season_length"] = seasonal_period
         return local_model_args
 
-    def _get_model_type(self, variant: Optional[str] = None) -> Type:
+    def _get_model_type(self, variant: str | None = None) -> Type:
         raise NotImplementedError
 
     def _get_local_model(self, local_model_args: dict):
@@ -162,7 +162,7 @@ class AutoARIMAModel(AbstractProbabilisticStatsForecastModel):
         local_model_args.setdefault("allowmean", True)
         return local_model_args
 
-    def _get_model_type(self, variant: Optional[str] = None):
+    def _get_model_type(self, variant: str | None = None):
         from statsforecast.models import AutoARIMA
 
         return AutoARIMA
@@ -232,7 +232,7 @@ class ARIMAModel(AbstractProbabilisticStatsForecastModel):
         local_model_args.setdefault("order", (1, 1, 1))
         return local_model_args
 
-    def _get_model_type(self, variant: Optional[str] = None):
+    def _get_model_type(self, variant: str | None = None):
         from statsforecast.models import ARIMA
 
         return ARIMA
@@ -277,7 +277,7 @@ class AutoETSModel(AbstractProbabilisticStatsForecastModel):
         "seasonal_period",
     ]
 
-    def _get_model_type(self, variant: Optional[str] = None):
+    def _get_model_type(self, variant: str | None = None):
         from statsforecast.models import AutoETS
 
         return AutoETS
@@ -380,7 +380,7 @@ class DynamicOptimizedThetaModel(AbstractProbabilisticStatsForecastModel):
         "seasonal_period",
     ]
 
-    def _get_model_type(self, variant: Optional[str] = None):
+    def _get_model_type(self, variant: str | None = None):
         from statsforecast.models import DynamicOptimizedTheta
 
         return DynamicOptimizedTheta
@@ -425,7 +425,7 @@ class ThetaModel(AbstractProbabilisticStatsForecastModel):
         "seasonal_period",
     ]
 
-    def _get_model_type(self, variant: Optional[str] = None):
+    def _get_model_type(self, variant: str | None = None):
         from statsforecast.models import Theta
 
         return Theta
@@ -546,7 +546,7 @@ class AutoCESModel(AbstractProbabilisticStatsForecastModel):
         "seasonal_period",
     ]
 
-    def _get_model_type(self, variant: Optional[str] = None):
+    def _get_model_type(self, variant: str | None = None):
         from statsforecast.models import AutoCES
 
         return AutoCES
@@ -610,7 +610,7 @@ class ADIDAModel(AbstractStatsForecastIntermittentDemandModel):
 
     ag_priority = 10
 
-    def _get_model_type(self, variant: Optional[str] = None):
+    def _get_model_type(self, variant: str | None = None):
         from statsforecast.models import ADIDA
 
         return ADIDA
@@ -652,7 +652,7 @@ class CrostonModel(AbstractStatsForecastIntermittentDemandModel):
         "variant",
     ]
 
-    def _get_model_type(self, variant: Optional[str] = None):
+    def _get_model_type(self, variant: str | None = None):
         from statsforecast.models import CrostonClassic, CrostonOptimized, CrostonSBA
 
         model_variants = {
@@ -702,7 +702,7 @@ class IMAPAModel(AbstractStatsForecastIntermittentDemandModel):
 
     ag_priority = 10
 
-    def _get_model_type(self, variant: Optional[str] = None):
+    def _get_model_type(self, variant: str | None = None):
         from statsforecast.models import IMAPA
 
         return IMAPA
@@ -726,7 +726,7 @@ class ZeroModel(AbstractStatsForecastIntermittentDemandModel):
 
     ag_priority = 100
 
-    def _get_model_type(self, variant: Optional[str] = None):
+    def _get_model_type(self, variant: str | None = None):
         # ZeroModel does not depend on a StatsForecast implementation
         raise NotImplementedError