autogluon.timeseries 1.2.1b20250402__py3-none-any.whl → 1.2.1b20250403__py3-none-any.whl

autogluon/timeseries/trainer.py

@@ -53,6 +53,7 @@ class TimeSeriesTrainer(AbstractTrainer[AbstractTimeSeriesModel]):
         verbosity: int = 2,
         val_splitter: Optional[AbstractWindowSplitter] = None,
         refit_every_n_windows: Optional[int] = 1,
+        # TODO: Set cache_predictions=False by default once all models in default presets have a reasonable inference speed
         cache_predictions: bool = True,
         ensemble_model_type: Optional[Type] = None,
         **kwargs,
@@ -752,6 +753,8 @@ class TimeSeriesTrainer(AbstractTrainer[AbstractTimeSeriesModel]):
             if isinstance(model, AbstractTimeSeriesModel):
                 return model.name
             else:
+                if model not in self.get_model_names():
+                    raise KeyError(f"Model '{model}' not found. Available models: {self.get_model_names()}")
                 return model
 
     def predict(
@@ -1033,7 +1036,6 @@ class TimeSeriesTrainer(AbstractTrainer[AbstractTimeSeriesModel]):
         use_cache
             If False, will ignore the cache even if it's available.
         """
-        # TODO: Unify design of the method with Tabular
         if self.cache_predictions and use_cache:
             dataset_hash = self._compute_dataset_hash(data=data, known_covariates=known_covariates)
             model_pred_dict, pred_time_dict_marginal = self._get_cached_pred_dicts(dataset_hash)
@@ -1105,21 +1107,33 @@ class TimeSeriesTrainer(AbstractTrainer[AbstractTimeSeriesModel]):
         combined_hash = hash_pandas_df(data) + hash_pandas_df(known_covariates) + hash_pandas_df(data.static_features)
         return combined_hash
 
+    def _load_cached_predictions(self) -> dict[str, dict[str, dict[str, Any]]]:
+        """Load cached predictions from disk. If loading fails, an empty dictionary is returned."""
+        if self._cached_predictions_path.exists():
+            try:
+                cached_predictions = load_pkl.load(str(self._cached_predictions_path))
+            except Exception:
+                cached_predictions = {}
+        else:
+            cached_predictions = {}
+        return cached_predictions
+
     def _get_cached_pred_dicts(
         self, dataset_hash: str
     ) -> Tuple[Dict[str, Optional[TimeSeriesDataFrame]], Dict[str, float]]:
-        """Load cached predictions for given dataset_hash from disk, if possible. Otherwise returns empty dicts."""
-        if self._cached_predictions_path.exists():
-            cached_predictions = load_pkl.load(str(self._cached_predictions_path))
-            if dataset_hash in cached_predictions:
+        """Load cached predictions for given dataset_hash from disk, if possible.
+
+        If loading fails for any reason, empty dicts are returned.
+        """
+        cached_predictions = self._load_cached_predictions()
+        if dataset_hash in cached_predictions:
+            try:
                 model_pred_dict = cached_predictions[dataset_hash]["model_pred_dict"]
                 pred_time_dict = cached_predictions[dataset_hash]["pred_time_dict"]
-                if model_pred_dict.keys() == pred_time_dict.keys():
-                    logger.debug(f"Loaded cached predictions for models {list(model_pred_dict.keys())}")
-                    return model_pred_dict, pred_time_dict
-                else:
-                    logger.warning(f"Found corrupted cached predictions in {self._cached_predictions_path}")
-        logger.debug("Found no cached predictions")
+                assert model_pred_dict.keys() == pred_time_dict.keys()
+                return model_pred_dict, pred_time_dict
+            except Exception:
+                logger.warning("Cached predictions are corrupted. Predictions will be made from scratch.")
         return {}, {}
 
     def _save_cached_pred_dicts(
@@ -1128,12 +1142,7 @@ class TimeSeriesTrainer(AbstractTrainer[AbstractTimeSeriesModel]):
         model_pred_dict: Dict[str, Optional[TimeSeriesDataFrame]],
         pred_time_dict: Dict[str, float],
     ) -> None:
-        # TODO: Save separate file for each dataset if _cached_predictions file grows large?
-        if self._cached_predictions_path.exists():
-            logger.debug("Extending existing cached predictions")
-            cached_predictions = load_pkl.load(str(self._cached_predictions_path))
-        else:
-            cached_predictions = {}
+        cached_predictions = self._load_cached_predictions()
         # Do not save results for models that failed
         cached_predictions[dataset_hash] = {
             "model_pred_dict": {k: v for k, v in model_pred_dict.items() if v is not None},

autogluon/timeseries/version.py

@@ -1,4 +1,4 @@
 """This is the autogluon version file."""
 
-__version__ = "1.2.1b20250402"
+__version__ = "1.2.1b20250403"
 __lite__ = False

{autogluon.timeseries-1.2.1b20250402.dist-info → autogluon.timeseries-1.2.1b20250403.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: autogluon.timeseries
-Version: 1.2.1b20250402
+Version: 1.2.1b20250403
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community
@@ -55,9 +55,9 @@ Requires-Dist: fugue>=0.9.0
 Requires-Dist: tqdm<5,>=4.38
 Requires-Dist: orjson~=3.9
 Requires-Dist: tensorboard<3,>=2.9
-Requires-Dist: autogluon.core[raytune]==1.2.1b20250402
-Requires-Dist: autogluon.common==1.2.1b20250402
-Requires-Dist: autogluon.tabular[catboost,lightgbm,xgboost]==1.2.1b20250402
+Requires-Dist: autogluon.core[raytune]==1.2.1b20250403
+Requires-Dist: autogluon.common==1.2.1b20250403
+Requires-Dist: autogluon.tabular[catboost,lightgbm,xgboost]==1.2.1b20250403
 Provides-Extra: all
 Provides-Extra: chronos-onnx
 Requires-Dist: optimum[onnxruntime]<1.20,>=1.17; extra == "chronos-onnx"

{autogluon.timeseries-1.2.1b20250402.dist-info → autogluon.timeseries-1.2.1b20250403.dist-info}/RECORD

@@ -1,12 +1,12 @@
-autogluon.timeseries-1.2.1b20250402-py3.9-nspkg.pth,sha256=cQGwpuGPqg1GXscIwt-7PmME1OnSpD-7ixkikJ31WAY,554
+autogluon.timeseries-1.2.1b20250403-py3.9-nspkg.pth,sha256=cQGwpuGPqg1GXscIwt-7PmME1OnSpD-7ixkikJ31WAY,554
 autogluon/timeseries/__init__.py,sha256=_CrLLc1fkjen7UzWoO0Os8WZoHOgvZbHKy46I8v_4k4,304
 autogluon/timeseries/evaluator.py,sha256=l642tYfTHsl8WVIq_vV6qhgAFVFr9UuZD7gLra3A_Kc,250
 autogluon/timeseries/learner.py,sha256=PDAHFlos6q5JukwRE86tKoH0zxYf3nLzy7qfD_a5NYY,13849
 autogluon/timeseries/predictor.py,sha256=DgKNvDfduVyauR7MXQZk04JyT3fc5erXAGVp3XOwDt4,85288
 autogluon/timeseries/regressor.py,sha256=3MlTpP-M1ayTZ52UQDK0wIMMFUijPep-iEyftlDdKPg,11804
 autogluon/timeseries/splitter.py,sha256=yzPca9p2bWV-_VJAptUyyzQsxu-uixAdpMoGQtDzMD4,3205
-autogluon/timeseries/trainer.py,sha256=L9FT5qERcqlWTgH9IgE6QsO0aBNj2nivRKF2Oy4UJOk,57250
-autogluon/timeseries/version.py,sha256=fIsRdOTHCNt_TXK_xcHoNj9fqSRNcPrRdSWIVcKlEdw,91
+autogluon/timeseries/trainer.py,sha256=EPKyWDpDnKK9ynUNKnnW_Zkg4UyPkxCUarIjngAFLWc,57525
+autogluon/timeseries/version.py,sha256=1df-aoA8H9q3DJauV_Wnd-7USFCO23BO5y92X8TSpDI,91
 autogluon/timeseries/configs/__init__.py,sha256=BTtHIPCYeGjqgOcvqb8qPD4VNX-ICKOg6wnkew1cPOE,98
 autogluon/timeseries/configs/presets_configs.py,sha256=cLat8ecLlWrI-SC5KLBDCX2SbVXaucemy2pjxJAtSY0,2543
 autogluon/timeseries/dataset/__init__.py,sha256=UvnhAN5tjgxXTHoZMQDy64YMDj4Xxa68yY7NP4vAw0o,81
@@ -59,11 +59,11 @@ autogluon/timeseries/utils/datetime/base.py,sha256=3NdsH3NDq4cVAOSoy3XpaNixyNlbj
 autogluon/timeseries/utils/datetime/lags.py,sha256=gQDk5_zmsY5DUWDUpSaCKYkQ9nHKKY-LsywJQRAoYSk,5988
 autogluon/timeseries/utils/datetime/seasonality.py,sha256=YK_2k8hvYIMW-sJPnjGWRtCnvIOthwA2hATB3nwVoD4,834
 autogluon/timeseries/utils/datetime/time_features.py,sha256=MjLi3zQ00uWWJtXH9oGX2GJkTbvjdSiuabSa4kcVuxE,2672
-autogluon.timeseries-1.2.1b20250402.dist-info/LICENSE,sha256=CeipvOyAZxBGUsFoaFqwkx54aPnIKEtm9a5u2uXxEws,10142
-autogluon.timeseries-1.2.1b20250402.dist-info/METADATA,sha256=cVl4vUwel4JJHShEcOzklM5XsvRCS9MQQ44Qc1uxKkQ,12684
-autogluon.timeseries-1.2.1b20250402.dist-info/NOTICE,sha256=7nPQuj8Kp-uXsU0S5so3-2dNU5EctS5hDXvvzzehd7E,114
-autogluon.timeseries-1.2.1b20250402.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-autogluon.timeseries-1.2.1b20250402.dist-info/namespace_packages.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
-autogluon.timeseries-1.2.1b20250402.dist-info/top_level.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
-autogluon.timeseries-1.2.1b20250402.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-autogluon.timeseries-1.2.1b20250402.dist-info/RECORD,,
+autogluon.timeseries-1.2.1b20250403.dist-info/LICENSE,sha256=CeipvOyAZxBGUsFoaFqwkx54aPnIKEtm9a5u2uXxEws,10142
+autogluon.timeseries-1.2.1b20250403.dist-info/METADATA,sha256=cfAyX23oWUcORit7OQ9xGujEioQc-T5ClXIdxnpASiM,12684
+autogluon.timeseries-1.2.1b20250403.dist-info/NOTICE,sha256=7nPQuj8Kp-uXsU0S5so3-2dNU5EctS5hDXvvzzehd7E,114
+autogluon.timeseries-1.2.1b20250403.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+autogluon.timeseries-1.2.1b20250403.dist-info/namespace_packages.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
+autogluon.timeseries-1.2.1b20250403.dist-info/top_level.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
+autogluon.timeseries-1.2.1b20250403.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+autogluon.timeseries-1.2.1b20250403.dist-info/RECORD,,