autogluon.timeseries 1.2.1b20250417__tar.gz → 1.2.1b20250419__tar.gz

{autogluon.timeseries-1.2.1b20250417 → autogluon.timeseries-1.2.1b20250419}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: autogluon.timeseries
-Version: 1.2.1b20250417
+Version: 1.2.1b20250419
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community

{autogluon.timeseries-1.2.1b20250417 → autogluon.timeseries-1.2.1b20250419}/src/autogluon/timeseries/learner.py

@@ -88,7 +88,7 @@ class TimeSeriesLearner(AbstractLearner):
                 verbosity=kwargs.get("verbosity", 2),
                 skip_model_selection=kwargs.get("skip_model_selection", False),
                 enable_ensemble=kwargs.get("enable_ensemble", True),
-                metadata=self.feature_generator.covariate_metadata,
+                covariate_metadata=self.feature_generator.covariate_metadata,
                 val_splitter=val_splitter,
                 refit_every_n_windows=refit_every_n_windows,
                 cache_predictions=self.cache_predictions,

{autogluon.timeseries-1.2.1b20250417 → autogluon.timeseries-1.2.1b20250419}/src/autogluon/timeseries/models/abstract/abstract_timeseries_model.py

@@ -49,7 +49,7 @@ class TimeSeriesModelBase(ModelBase, ABC):
         Name of the subdirectory inside path where model will be saved.
         The final model directory will be os.path.join(path, name)
         If None, defaults to the model's class name: self.__class__.__name__
-    metadata: CovariateMetadata
+    covariate_metadata: CovariateMetadata
         A mapping of different covariate types known to autogluon.timeseries to column names
         in the data set.
     eval_metric : Union[str, TimeSeriesScorer], default = "WQL"
@@ -83,7 +83,7 @@ class TimeSeriesModelBase(ModelBase, ABC):
         hyperparameters: Optional[Dict[str, Any]] = None,
         freq: Optional[str] = None,
         prediction_length: int = 1,
-        metadata: Optional[CovariateMetadata] = None,
+        covariate_metadata: Optional[CovariateMetadata] = None,
         target: str = "target",
         quantile_levels: Sequence[float] = (0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9),
         eval_metric: Union[str, TimeSeriesScorer, None] = None,
@@ -105,7 +105,7 @@ class TimeSeriesModelBase(ModelBase, ABC):
         self.eval_metric: TimeSeriesScorer = check_get_evaluation_metric(eval_metric)
         self.eval_metric_seasonal_period = eval_metric_seasonal_period
         self.target: str = target
-        self.metadata = metadata or CovariateMetadata()
+        self.covariate_metadata = covariate_metadata or CovariateMetadata()
 
         self.freq: Optional[str] = freq
         self.prediction_length: int = prediction_length
@@ -253,7 +253,7 @@ class TimeSeriesModelBase(ModelBase, ABC):
         self.target_scaler = get_target_scaler(self.get_hyperparameters().get("target_scaler"), target=self.target)
         self.covariate_scaler = get_covariate_scaler(
             self.get_hyperparameters().get("covariate_scaler"),
-            covariate_metadata=self.metadata,
+            covariate_metadata=self.covariate_metadata,
             use_static_features=self.supports_static_features,
             use_known_covariates=self.supports_known_covariates,
             use_past_covariates=self.supports_past_covariates,
@@ -261,7 +261,7 @@ class TimeSeriesModelBase(ModelBase, ABC):
         self.covariate_regressor = get_covariate_regressor(
             self.get_hyperparameters().get("covariate_regressor"),
             target=self.target,
-            covariate_metadata=self.metadata,
+            covariate_metadata=self.covariate_metadata,
         )
 
     def _get_default_hyperparameters(self) -> dict:
@@ -275,7 +275,6 @@ class TimeSeriesModelBase(ModelBase, ABC):
         """
         Returns a dictionary of numerous fields describing the model.
         """
-        # TODO: Include self.metadata
         info = {
             "name": self.name,
             "model_type": type(self).__name__,
@@ -287,6 +286,7 @@ class TimeSeriesModelBase(ModelBase, ABC):
             "quantile_levels": self.quantile_levels,
             "val_score": self.val_score,
             "hyperparameters": self.get_hyperparameters(),
+            "covariate_metadata": self.covariate_metadata.to_dict(),
         }
         return info
 
@@ -351,7 +351,7 @@ class TimeSeriesModelBase(ModelBase, ABC):
             time steps of each time series.
         """
         past_data, known_covariates = data.get_model_inputs_for_scoring(
-            prediction_length=self.prediction_length, known_covariates_names=self.metadata.known_covariates
+            prediction_length=self.prediction_length, known_covariates_names=self.covariate_metadata.known_covariates
         )
         predictions = self.predict(past_data, known_covariates=known_covariates)
         return self._score_with_predictions(data=data, predictions=predictions, metric=metric)
@@ -365,7 +365,7 @@ class TimeSeriesModelBase(ModelBase, ABC):
     ) -> None:
         """Compute val_score, predict_time and cache out-of-fold (OOF) predictions."""
         past_data, known_covariates = val_data.get_model_inputs_for_scoring(
-            prediction_length=self.prediction_length, known_covariates_names=self.metadata.known_covariates
+            prediction_length=self.prediction_length, known_covariates_names=self.covariate_metadata.known_covariates
         )
         predict_start_time = time.time()
         oof_predictions = self.predict(past_data, known_covariates=known_covariates, **predict_kwargs)
@@ -661,7 +661,7 @@ class AbstractTimeSeriesModel(TimeSeriesModelBase, TimeSeriesTunable, ABC):
             freq=self.freq,
             prediction_length=self.prediction_length,
             quantile_levels=self.quantile_levels,
-            metadata=self.metadata,
+            covariate_metadata=self.covariate_metadata,
             target=self.target,
         )
 

{autogluon.timeseries-1.2.1b20250417 → autogluon.timeseries-1.2.1b20250419}/src/autogluon/timeseries/models/autogluon_tabular/mlforecast.py

@@ -263,7 +263,7 @@ class AbstractMLForecastModel(AbstractTimeSeriesModel):
         Each row contains unique_id, ds, y, and (optionally) known covariates & static features.
         """
         # TODO: Add support for past_covariates
-        selected_columns = self.metadata.known_covariates.copy()
+        selected_columns = self.covariate_metadata.known_covariates.copy()
         column_name_mapping = {ITEMID: MLF_ITEMID, TIMESTAMP: MLF_TIMESTAMP}
         if include_target:
             selected_columns += [self.target]
@@ -297,7 +297,7 @@ class AbstractMLForecastModel(AbstractTimeSeriesModel):
         self._check_fit_params()
         fit_start_time = time.time()
         self._train_target_median = train_data[self.target].median()
-        for col in self.metadata.known_covariates_real:
+        for col in self.covariate_metadata.known_covariates_real:
             if not set(train_data[col].unique()) == set([0, 1]):
                 self._non_boolean_real_covariates.append(col)
         # TabularEstimator is passed to MLForecast later to include tuning_data

{autogluon.timeseries-1.2.1b20250417 → autogluon.timeseries-1.2.1b20250419}/src/autogluon/timeseries/models/gluonts/abstract_gluonts.py

@@ -250,21 +250,21 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
         model_params = self.get_hyperparameters()
         disable_static_features = model_params.get("disable_static_features", False)
         if not disable_static_features:
-            self.num_feat_static_cat = len(self.metadata.static_features_cat)
-            self.num_feat_static_real = len(self.metadata.static_features_real)
+            self.num_feat_static_cat = len(self.covariate_metadata.static_features_cat)
+            self.num_feat_static_real = len(self.covariate_metadata.static_features_real)
             if self.num_feat_static_cat > 0:
                 assert dataset.static_features is not None, (
                     "Static features must be provided if num_feat_static_cat > 0"
                 )
-                feat_static_cat = dataset.static_features[self.metadata.static_features_cat]
+                feat_static_cat = dataset.static_features[self.covariate_metadata.static_features_cat]
                 self.feat_static_cat_cardinality = feat_static_cat.nunique().tolist()
 
         disable_known_covariates = model_params.get("disable_known_covariates", False)
         if not disable_known_covariates and self.supports_known_covariates:
-            self.num_feat_dynamic_cat = len(self.metadata.known_covariates_cat)
-            self.num_feat_dynamic_real = len(self.metadata.known_covariates_real)
+            self.num_feat_dynamic_cat = len(self.covariate_metadata.known_covariates_cat)
+            self.num_feat_dynamic_real = len(self.covariate_metadata.known_covariates_real)
             if self.num_feat_dynamic_cat > 0:
-                feat_dynamic_cat = dataset[self.metadata.known_covariates_cat]
+                feat_dynamic_cat = dataset[self.covariate_metadata.known_covariates_cat]
                 if self.supports_cat_covariates:
                     self.feat_dynamic_cat_cardinality = feat_dynamic_cat.nunique().tolist()
                 else:
@@ -280,10 +280,10 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
 
         disable_past_covariates = model_params.get("disable_past_covariates", False)
         if not disable_past_covariates and self.supports_past_covariates:
-            self.num_past_feat_dynamic_cat = len(self.metadata.past_covariates_cat)
-            self.num_past_feat_dynamic_real = len(self.metadata.past_covariates_real)
+            self.num_past_feat_dynamic_cat = len(self.covariate_metadata.past_covariates_cat)
+            self.num_past_feat_dynamic_real = len(self.covariate_metadata.past_covariates_real)
             if self.num_past_feat_dynamic_cat > 0:
-                past_feat_dynamic_cat = dataset[self.metadata.past_covariates_cat]
+                past_feat_dynamic_cat = dataset[self.covariate_metadata.past_covariates_cat]
                 if self.supports_cat_covariates:
                     self.past_feat_dynamic_cat_cardinality = past_feat_dynamic_cat.nunique().tolist()
                 else:
@@ -400,7 +400,9 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
                 assert time_series_df.static_features is not None, (
                     "Static features must be provided if num_feat_static_cat > 0"
                 )
-                feat_static_cat = time_series_df.static_features[self.metadata.static_features_cat].to_numpy()
+                feat_static_cat = time_series_df.static_features[
+                    self.covariate_metadata.static_features_cat
+                ].to_numpy()
             else:
                 feat_static_cat = None
 
@@ -408,7 +410,9 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
                 assert time_series_df.static_features is not None, (
                     "Static features must be provided if num_feat_static_real > 0"
                 )
-                feat_static_real = time_series_df.static_features[self.metadata.static_features_real].to_numpy()
+                feat_static_real = time_series_df.static_features[
+                    self.covariate_metadata.static_features_real
+                ].to_numpy()
             else:
                 feat_static_real = None
 
@@ -418,31 +422,31 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
             if known_covariates is not None:
                 known_covariates = pd.DataFrame(known_covariates)  # type: ignore
             if self.num_feat_dynamic_cat > 0:
-                feat_dynamic_cat = df[self.metadata.known_covariates_cat].to_numpy()
+                feat_dynamic_cat = df[self.covariate_metadata.known_covariates_cat].to_numpy()
                 if known_covariates is not None:
                     feat_dynamic_cat = np.concatenate(
-                        [feat_dynamic_cat, known_covariates[self.metadata.known_covariates_cat].to_numpy()]
+                        [feat_dynamic_cat, known_covariates[self.covariate_metadata.known_covariates_cat].to_numpy()]
                     )
                     assert len(feat_dynamic_cat) == expected_known_covariates_len
             else:
                 feat_dynamic_cat = None
 
             if self.num_feat_dynamic_real > 0:
-                feat_dynamic_real = df[self.metadata.known_covariates_real].to_numpy()
+                feat_dynamic_real = df[self.covariate_metadata.known_covariates_real].to_numpy()
                 # Append future values of known covariates
                 if known_covariates is not None:
                     feat_dynamic_real = np.concatenate(
-                        [feat_dynamic_real, known_covariates[self.metadata.known_covariates_real].to_numpy()]
+                        [feat_dynamic_real, known_covariates[self.covariate_metadata.known_covariates_real].to_numpy()]
                     )
                     assert len(feat_dynamic_real) == expected_known_covariates_len
                 # Categorical covariates are one-hot-encoded as real
                 if self._ohe_generator_known is not None:
                     feat_dynamic_cat_ohe: np.ndarray = self._ohe_generator_known.transform(
-                        df[self.metadata.known_covariates_cat]
+                        df[self.covariate_metadata.known_covariates_cat]
                     )  # type: ignore
                     if known_covariates is not None:
                         future_dynamic_cat_ohe: np.ndarray = self._ohe_generator_known.transform(  # type: ignore
-                            known_covariates[self.metadata.known_covariates_cat]
+                            known_covariates[self.covariate_metadata.known_covariates_cat]
                         )
                         feat_dynamic_cat_ohe = np.concatenate([feat_dynamic_cat_ohe, future_dynamic_cat_ohe])
                         assert len(feat_dynamic_cat_ohe) == expected_known_covariates_len
@@ -451,15 +455,15 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
                 feat_dynamic_real = None
 
             if self.num_past_feat_dynamic_cat > 0:
-                past_feat_dynamic_cat = df[self.metadata.past_covariates_cat].to_numpy()
+                past_feat_dynamic_cat = df[self.covariate_metadata.past_covariates_cat].to_numpy()
             else:
                 past_feat_dynamic_cat = None
 
             if self.num_past_feat_dynamic_real > 0:
-                past_feat_dynamic_real = df[self.metadata.past_covariates_real].to_numpy()
+                past_feat_dynamic_real = df[self.covariate_metadata.past_covariates_real].to_numpy()
                 if self._ohe_generator_past is not None:
                     past_feat_dynamic_cat_ohe: np.ndarray = self._ohe_generator_past.transform(  # type: ignore
-                        df[self.metadata.past_covariates_cat]
+                        df[self.covariate_metadata.past_covariates_cat]
                     )
                     past_feat_dynamic_real = np.concatenate(
                         [past_feat_dynamic_real, past_feat_dynamic_cat_ohe], axis=1

{autogluon.timeseries-1.2.1b20250417 → autogluon.timeseries-1.2.1b20250419}/src/autogluon/timeseries/models/presets.py

@@ -186,7 +186,7 @@ def get_preset_models(
     eval_metric_seasonal_period: Optional[int],
     hyperparameters: Union[str, Dict, None],
     hyperparameter_tune: bool,
-    metadata: CovariateMetadata,
+    covariate_metadata: CovariateMetadata,
     all_assigned_names: List[str],
     excluded_model_types: Optional[List[str]],
     multi_window: bool = False,
@@ -261,7 +261,7 @@ def get_preset_models(
                 prediction_length=prediction_length,
                 eval_metric=eval_metric,
                 eval_metric_seasonal_period=eval_metric_seasonal_period,
-                metadata=metadata,
+                covariate_metadata=covariate_metadata,
                 hyperparameters=model_hps,
                 **kwargs,
             )

{autogluon.timeseries-1.2.1b20250417 → autogluon.timeseries-1.2.1b20250419}/src/autogluon/timeseries/predictor.py

@@ -1444,7 +1444,8 @@ class TimeSeriesPredictor:
         }
 
         past_data, known_covariates = test_data.get_model_inputs_for_scoring(
-            prediction_length=self.prediction_length, known_covariates_names=trainer.metadata.known_covariates
+            prediction_length=self.prediction_length,
+            known_covariates_names=trainer.covariate_metadata.known_covariates,
         )
         pred_proba_dict_test, _ = trainer.get_model_pred_dict(
             base_model_names, data=past_data, known_covariates=known_covariates

{autogluon.timeseries-1.2.1b20250417 → autogluon.timeseries-1.2.1b20250419}/src/autogluon/timeseries/regressor.py

@@ -6,7 +6,7 @@ import numpy as np
 import pandas as pd
 
 from autogluon.core.models import AbstractModel
-from autogluon.tabular.trainer.model_presets.presets import MODEL_TYPES as TABULAR_MODEL_TYPES
+from autogluon.tabular.register import ag_model_register as tabular_ag_model_register
 from autogluon.timeseries.dataset.ts_dataframe import ITEMID, TimeSeriesDataFrame
 from autogluon.timeseries.utils.features import CovariateMetadata
 
@@ -85,12 +85,13 @@ class GlobalCovariateRegressor(CovariateRegressor):
         include_static_features: bool = True,
         include_item_id: bool = False,
     ):
-        if model_name not in TABULAR_MODEL_TYPES:
+        tabular_model_types = tabular_ag_model_register.key_to_cls_map()
+        if model_name not in tabular_model_types:
             raise ValueError(
-                f"Tabular model {model_name} not supported. Available models: {list(TABULAR_MODEL_TYPES)}"
+                f"Tabular model {model_name} not supported. Available models: {list(tabular_model_types)}"
             )
         self.target = target
-        self.model_type = TABULAR_MODEL_TYPES[model_name]
+        self.model_type = tabular_model_types[model_name]
         self.model_name = model_name
         self.model_hyperparameters = model_hyperparameters or {}
         self.refit_during_predict = refit_during_predict

{autogluon.timeseries-1.2.1b20250417 → autogluon.timeseries-1.2.1b20250419}/src/autogluon/timeseries/trainer.py

@@ -67,7 +67,7 @@ class TimeSeriesTrainer(AbstractTrainer[AbstractTimeSeriesModel]):
         self.prediction_length = prediction_length
         self.quantile_levels = kwargs.get("quantile_levels", [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9])
         self.target = kwargs.get("target", "target")
-        self.metadata = kwargs.get("metadata", CovariateMetadata())
+        self.covariate_metadata = kwargs.get("covariate_metadata", CovariateMetadata())
         self.is_data_saved = False
         self.skip_model_selection = skip_model_selection
         # Ensemble cannot be fit if val_scores are not computed
@@ -361,7 +361,7 @@ class TimeSeriesTrainer(AbstractTrainer[AbstractTimeSeriesModel]):
             model.fit_time = model.fit_time or (fit_end_time - fit_start_time)
 
             if time_limit is not None:
-                time_limit = fit_end_time - fit_start_time
+                time_limit = time_limit - (fit_end_time - fit_start_time)
             if val_data is not None and not self.skip_model_selection:
                 model.score_and_cache_oof(
                     val_data, store_val_score=True, store_predict_time=True, time_limit=time_limit
@@ -576,7 +576,7 @@ class TimeSeriesTrainer(AbstractTrainer[AbstractTimeSeriesModel]):
             path=self.path,
             freq=data_per_window[0].freq,
             quantile_levels=self.quantile_levels,
-            metadata=self.metadata,
+            covariate_metadata=self.covariate_metadata,
         )
         with warning_filter():
             ensemble.fit_ensemble(model_preds, data_per_window=data_per_window, time_limit=time_limit)
@@ -636,7 +636,8 @@ class TimeSeriesTrainer(AbstractTrainer[AbstractTimeSeriesModel]):
 
         if data is not None:
             past_data, known_covariates = data.get_model_inputs_for_scoring(
-                prediction_length=self.prediction_length, known_covariates_names=self.metadata.known_covariates
+                prediction_length=self.prediction_length,
+                known_covariates_names=self.covariate_metadata.known_covariates,
             )
             logger.info(
                 "Additional data provided, testing on additional data. Resulting leaderboard "
@@ -813,7 +814,7 @@ class TimeSeriesTrainer(AbstractTrainer[AbstractTimeSeriesModel]):
         use_cache: bool = True,
     ) -> Dict[str, float]:
         past_data, known_covariates = data.get_model_inputs_for_scoring(
-            prediction_length=self.prediction_length, known_covariates_names=self.metadata.known_covariates
+            prediction_length=self.prediction_length, known_covariates_names=self.covariate_metadata.known_covariates
         )
         predictions = self.predict(data=past_data, known_covariates=known_covariates, model=model, use_cache=use_cache)
 
@@ -874,7 +875,7 @@ class TimeSeriesTrainer(AbstractTrainer[AbstractTimeSeriesModel]):
         )
 
         importance_transform = importance_transform_type(
-            covariate_metadata=self.metadata,
+            covariate_metadata=self.covariate_metadata,
             prediction_length=self.prediction_length,
             random_seed=random_seed,
         )
@@ -937,11 +938,11 @@ class TimeSeriesTrainer(AbstractTrainer[AbstractTimeSeriesModel]):
         """Check if the given model uses the given feature."""
         models_with_ancestors = set(self.get_minimum_model_set(model))
 
-        if feature in self.metadata.static_features:
+        if feature in self.covariate_metadata.static_features:
             return any(self.load_model(m).supports_static_features for m in models_with_ancestors)
-        elif feature in self.metadata.known_covariates:
+        elif feature in self.covariate_metadata.known_covariates:
             return any(self.load_model(m).supports_known_covariates for m in models_with_ancestors)
-        elif feature in self.metadata.past_covariates:
+        elif feature in self.covariate_metadata.past_covariates:
             return any(self.load_model(m).supports_past_covariates for m in models_with_ancestors)
 
         return False
@@ -1260,7 +1261,7 @@ class TimeSeriesTrainer(AbstractTrainer[AbstractTimeSeriesModel]):
             quantile_levels=self.quantile_levels,
             all_assigned_names=self._get_banned_model_names(),
             target=self.target,
-            metadata=self.metadata,
+            covariate_metadata=self.covariate_metadata,
             excluded_model_types=excluded_model_types,
             # if skip_model_selection = True, we skip backtesting
             multi_window=multi_window and not self.skip_model_selection,

{autogluon.timeseries-1.2.1b20250417 → autogluon.timeseries-1.2.1b20250419}/src/autogluon/timeseries/utils/features.py

@@ -1,8 +1,8 @@
 import logging
 import reprlib
 import time
-from dataclasses import dataclass, field
-from typing import Any, List, Literal, Optional, Tuple
+from dataclasses import asdict, dataclass, field
+from typing import Any, Dict, List, Literal, Optional, Tuple
 
 import numpy as np
 import pandas as pd
@@ -67,6 +67,9 @@ class CovariateMetadata:
     def all_features(self) -> List[str]:
         return self.static_features + self.covariates
 
+    def to_dict(self) -> Dict[str, Any]:
+        return asdict(self)
+
 
 class ContinuousAndCategoricalFeatureGenerator(PipelineFeatureGenerator):
     """Generates categorical and continuous features for time series models.

{autogluon.timeseries-1.2.1b20250417 → autogluon.timeseries-1.2.1b20250419}/src/autogluon/timeseries/version.py

@@ -1,4 +1,4 @@
 """This is the autogluon version file."""
 
-__version__ = "1.2.1b20250417"
+__version__ = "1.2.1b20250419"
 __lite__ = False

{autogluon.timeseries-1.2.1b20250417 → autogluon.timeseries-1.2.1b20250419}/src/autogluon.timeseries.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: autogluon.timeseries
-Version: 1.2.1b20250417
+Version: 1.2.1b20250419
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community

{autogluon.timeseries-1.2.1b20250417 → autogluon.timeseries-1.2.1b20250419}/src/autogluon.timeseries.egg-info/requires.txt

@@ -17,9 +17,9 @@ fugue>=0.9.0
 tqdm<5,>=4.38
 orjson~=3.9
 tensorboard<3,>=2.9
-autogluon.core[raytune]==1.2.1b20250417
-autogluon.common==1.2.1b20250417
-autogluon.tabular[catboost,lightgbm,xgboost]==1.2.1b20250417
+autogluon.core[raytune]==1.2.1b20250419
+autogluon.common==1.2.1b20250419
+autogluon.tabular[catboost,lightgbm,xgboost]==1.2.1b20250419
 
 [all]