autogluon.timeseries 1.2b20241205__py3-none-any.whl → 1.2.1b20241207__py3-none-any.whl

autogluon/timeseries/dataset/ts_dataframe.py

@@ -561,7 +561,7 @@ class TimeSeriesDataFrame(pd.DataFrame, TimeSeriesDataFrameDeprecatedMixin):
         """Length of each time series in the dataframe."""
         return self.groupby(level=ITEMID, sort=False).size()
 
-    def copy(self: TimeSeriesDataFrame, deep: bool = True) -> pd.DataFrame:  # noqa
+    def copy(self: TimeSeriesDataFrame, deep: bool = True) -> pd.DataFrame:  # type: ignore # noqa
         """Make a copy of the TimeSeriesDataFrame.
 
         When ``deep=True`` (default), a new object will be created with a copy of the calling object's data and
@@ -849,7 +849,7 @@ class TimeSeriesDataFrame(pd.DataFrame, TimeSeriesDataFrameDeprecatedMixin):
             )
         return TimeSeriesDataFrame(filled_df, static_features=self.static_features)
 
-    def dropna(self, how: str = "any") -> TimeSeriesDataFrame:
+    def dropna(self, how: str = "any") -> TimeSeriesDataFrame:  # type: ignore[override]
         """Drop rows containing NaNs.
 
         Parameters

autogluon/timeseries/metrics/point.py

@@ -392,7 +392,9 @@ class WCD(TimeSeriesScorer):
             f"{self.name} is an experimental metric. Its behavior may change in the future version of AutoGluon."
         )
 
-    def save_past_metrics(self, data_past: TimeSeriesDataFrame, **kwargs) -> None:
+    def save_past_metrics(
+        self, data_past: TimeSeriesDataFrame, target: str = "target", seasonal_period: int = 1, **kwargs
+    ) -> None:
         self.num_items = data_past.num_items
 
     def _fast_cumsum(self, y: np.ndarray) -> np.ndarray:

autogluon/timeseries/models/chronos/model.py

@@ -184,8 +184,8 @@ class ChronosModel(AbstractTimeSeriesModel):
         prediction_length: int = 1,
         path: Optional[str] = None,
         name: Optional[str] = None,
-        eval_metric: str = None,
-        hyperparameters: Dict[str, Any] = None,
+        eval_metric: Optional[str] = None,
+        hyperparameters: Optional[Dict[str, Any]] = None,
         **kwargs,  # noqa
     ):
         hyperparameters = hyperparameters if hyperparameters is not None else {}
@@ -237,13 +237,13 @@ class ChronosModel(AbstractTimeSeriesModel):
             **kwargs,
         )
 
-        self.model_pipeline: Optional[Any] = None  # of type BaseChronosPipeline
+        self._model_pipeline: Optional[Any] = None  # of type BaseChronosPipeline
 
-    def save(self, path: str = None, verbose: bool = True) -> str:
-        pipeline = self.model_pipeline
-        self.model_pipeline = None
+    def save(self, path: Optional[str] = None, verbose: bool = True) -> str:
+        pipeline = self._model_pipeline
+        self._model_pipeline = None
         path = super().save(path=path, verbose=verbose)
-        self.model_pipeline = pipeline
+        self._model_pipeline = pipeline
 
         return str(path)
 
@@ -265,6 +265,13 @@ class ChronosModel(AbstractTimeSeriesModel):
 
         return torch.cuda.is_available()
 
+    @property
+    def model_pipeline(self) -> Any:  # of type BaseChronosPipeline
+        """The model pipeline used for inference. If the model is not loaded, this will be None."""
+        if self._model_pipeline is None:
+            self.load_model_pipeline()  # load model pipeline to device memory
+        return self._model_pipeline
+
     @property
     def ag_default_config(self) -> Dict[str, Any]:
         """The default configuration of the model used by AutoGluon if the model is one of those
@@ -295,7 +302,7 @@ class ChronosModel(AbstractTimeSeriesModel):
         return self.ag_default_config.get("default_torch_dtype", "auto")
 
     def get_minimum_resources(self, is_gpu_available: bool = False) -> Dict[str, Union[int, float]]:
-        minimum_resources = {"num_cpus": 1}
+        minimum_resources: Dict[str, Union[int, float]] = {"num_cpus": 1}
         # if GPU is available, we train with 1 GPU per trial
         if is_gpu_available:
             minimum_resources["num_gpus"] = self.min_num_gpus
@@ -323,7 +330,7 @@ class ChronosModel(AbstractTimeSeriesModel):
             torch_dtype=self.torch_dtype,
         )
 
-        self.model_pipeline = pipeline
+        self._model_pipeline = pipeline
 
     def persist(self) -> "ChronosModel":
         self.load_model_pipeline()
@@ -387,7 +394,7 @@ class ChronosModel(AbstractTimeSeriesModel):
         self,
         train_data: TimeSeriesDataFrame,
         val_data: Optional[TimeSeriesDataFrame] = None,
-        time_limit: int = None,
+        time_limit: Optional[int] = None,
         **kwargs,
     ) -> None:
         from transformers.trainer import PrinterCallback, Trainer, TrainingArguments
@@ -452,6 +459,8 @@ class ChronosModel(AbstractTimeSeriesModel):
                         f"\tChronosBolt models can only be fine-tuned with a maximum prediction_length of {model_prediction_length}. "
                         f"Fine-tuning prediction_length has been changed to {fine_tune_prediction_length}."
                     )
+            else:
+                raise ValueError(f"Unsupported model pipeline: {type(self.model_pipeline)}")
 
             fine_tune_trainer_kwargs = fine_tune_args["fine_tune_trainer_kwargs"]
             fine_tune_trainer_kwargs["use_cpu"] = str(self.model_pipeline.inner_model.device) == "cpu"
@@ -593,11 +602,6 @@ class ChronosModel(AbstractTimeSeriesModel):
         with warning_filter(all_warnings=True):
             import torch
 
-            if self.model_pipeline is None:
-                # FIXME: optimization_strategy is ignored when model is fine-tuned
-                # load model pipeline to device memory
-                self.load_model_pipeline()
-
             inference_data_loader = self._get_inference_data_loader(
                 data=data,
                 num_workers=self.data_loader_num_workers,

autogluon/timeseries/models/chronos/pipeline/base.py

@@ -153,7 +153,7 @@ class BaseChronosPipeline(metaclass=PipelineRegistry):
             raise ValueError("Not a Chronos config file")
 
         pipeline_class_name = getattr(config, "chronos_pipeline_class", "ChronosPipeline")
-        class_ = PipelineRegistry.REGISTRY.get(pipeline_class_name)
+        class_: Optional[BaseChronosPipeline] = PipelineRegistry.REGISTRY.get(pipeline_class_name)  # type: ignore
         if class_ is None:
             raise ValueError(f"Trying to load unknown pipeline class: {pipeline_class_name}")
 

autogluon/timeseries/models/chronos/pipeline/chronos.py

@@ -396,8 +396,8 @@ class ChronosPipeline(BaseChronosPipeline):
             or the length of the longest time series, if a list of 1D tensors was
             provided, and the extra 1 is for EOS.
         """
-        context = self._prepare_and_validate_context(context=context)
-        token_ids, attention_mask, tokenizer_state = self.tokenizer.context_input_transform(context)
+        context_tensor = self._prepare_and_validate_context(context=context)
+        token_ids, attention_mask, tokenizer_state = self.tokenizer.context_input_transform(context_tensor)
         embeddings = self.model.encode(
             input_ids=token_ids.to(self.model.device),
             attention_mask=attention_mask.to(self.model.device),
@@ -413,6 +413,7 @@ class ChronosPipeline(BaseChronosPipeline):
         top_k: Optional[int] = None,
         top_p: Optional[float] = None,
         limit_prediction_length: bool = False,
+        **kwargs,
     ) -> torch.Tensor:
         """
         Get forecasts for the given time series.
@@ -451,7 +452,7 @@ class ChronosPipeline(BaseChronosPipeline):
             Tensor of sample forecasts, of shape
             (batch_size, num_samples, prediction_length).
         """
-        context = self._prepare_and_validate_context(context=context)
+        context_tensor = self._prepare_and_validate_context(context=context)
         if prediction_length is None:
             prediction_length = self.model.config.prediction_length
 
@@ -469,7 +470,7 @@ class ChronosPipeline(BaseChronosPipeline):
         remaining = prediction_length
 
         while remaining > 0:
-            token_ids, attention_mask, scale = self.tokenizer.context_input_transform(context)
+            token_ids, attention_mask, scale = self.tokenizer.context_input_transform(context_tensor)
             samples = self.model(
                 token_ids.to(self.model.device),
                 attention_mask.to(self.model.device),
@@ -487,7 +488,7 @@ class ChronosPipeline(BaseChronosPipeline):
             if remaining <= 0:
                 break
 
-            context = torch.cat([context, prediction.median(dim=1).values], dim=-1)
+            context_tensor = torch.cat([context_tensor, prediction.median(dim=1).values], dim=-1)
 
         return torch.cat(predictions, dim=-1)
 

autogluon/timeseries/models/chronos/pipeline/utils.py

@@ -312,10 +312,10 @@ class TimeLimitCallback(TrainerCallback):
         self.start_time = None
 
     def on_train_begin(self, args, state, control, **kwargs):
-        self.start_time = time.monotonic()
+        self.start_time = time.monotonic()  # type: ignore
 
     def on_step_end(self, args, state, control, **kwargs):
-        elapsed_time = time.monotonic() - self.start_time
+        elapsed_time = time.monotonic() - self.start_time  # type: ignore
         if elapsed_time > self.time_limit:
             logger.log(15, "Stopping fine-tuning since time_limit is reached")
             control.should_training_stop = True

autogluon/timeseries/trainer/abstract_trainer.py

@@ -1400,7 +1400,7 @@ class AbstractTimeSeriesTrainer(SimpleAbstractTrainer):
     def fit(
         self,
         train_data: TimeSeriesDataFrame,
-        hyperparameters: Dict[str, Any],
+        hyperparameters: Union[str, Dict[str, Any]],
         val_data: Optional[TimeSeriesDataFrame] = None,
         **kwargs,
     ) -> None:

autogluon/timeseries/trainer/auto_trainer.py

@@ -40,6 +40,7 @@ class AutoTimeSeriesTrainer(AbstractTimeSeriesTrainer):
         excluded_model_types: Optional[List[str]] = None,
         time_limit: Optional[float] = None,
         random_seed: Optional[int] = None,
+        **kwargs,
     ):
         """
         Fit a set of timeseries models specified by the `hyperparameters`

autogluon/timeseries/utils/datetime/lags.py

@@ -95,6 +95,9 @@ def get_lags_for_frequency(
     """
 
     offset = pd.tseries.frequencies.to_offset(freq)
+
+    if offset is None:
+        raise ValueError(f"Invalid frequency: {freq}")
     offset_name = norm_freq_str(offset)
 
     if offset_name == "YE":

autogluon/timeseries/utils/datetime/seasonality.py

@@ -28,6 +28,8 @@ def get_seasonality(freq: Union[str, None]) -> int:
         return 1
 
     offset = pd.tseries.frequencies.to_offset(freq)
+
+    assert offset is not None  # offset is only None if freq is None
     offset_name = norm_freq_str(offset)
     base_seasonality = DEFAULT_SEASONALITIES.get(offset_name, 1)
 

autogluon/timeseries/utils/datetime/time_features.py

@@ -27,7 +27,7 @@ def week_of_year(index: pd.DatetimeIndex) -> np.ndarray:
     try:
         week = index.isocalendar().week
     except AttributeError:
-        week = index.week
+        week = index.week  # type: ignore[attr-defined]
 
     return _normalize(week - 1, num=53)
 
@@ -74,5 +74,7 @@ def get_time_features_for_frequency(freq) -> List[Callable]:
         "ns": [second_of_minute, minute_of_hour, hour_of_day, day_of_week, day_of_month, day_of_year],
     }
     offset = pd.tseries.frequencies.to_offset(freq)
+
+    assert offset is not None  # offset is only None if freq is None
     offset_name = norm_freq_str(offset)
     return features_by_offset_name[offset_name]

autogluon/timeseries/utils/features.py

@@ -140,13 +140,13 @@ class TimeSeriesFeatureGenerator:
         self.num_samples = num_samples
 
         self._is_fit = False
-        self.known_covariates_names = list(known_covariates_names)
-        self.past_covariates_names = []
+        self.known_covariates_names: List[str] = list(known_covariates_names)
+        self.past_covariates_names: List[str] = []
         self.known_covariates_pipeline = ContinuousAndCategoricalFeatureGenerator()
         self.past_covariates_pipeline = ContinuousAndCategoricalFeatureGenerator()
         # Cat features with cat_count=1 are fine in static_features since they are repeated for all time steps in a TS
         self.static_feature_pipeline = ContinuousAndCategoricalFeatureGenerator(minimum_cat_count=1)
-        self.covariate_metadata: CovariateMetadata = None
+        self._covariate_metadata: Optional[CovariateMetadata] = None  # type ignore
         self._train_covariates_real_median: Optional[pd.Series] = None
         self._train_static_real_median: Optional[pd.Series] = None
 
@@ -154,6 +154,11 @@ class TimeSeriesFeatureGenerator:
     def required_column_names(self) -> List[str]:
         return [self.target] + list(self.known_covariates_names) + list(self.past_covariates_names)
 
+    @property
+    def covariate_metadata(self) -> CovariateMetadata:
+        assert self._covariate_metadata is not None, "covariate_metadata is not set. Did you call fit?"
+        return self._covariate_metadata
+
     def fit(self, data: TimeSeriesDataFrame) -> None:
         self.fit_transform(data)
 
@@ -231,7 +236,7 @@ class TimeSeriesFeatureGenerator:
                 "\nTo learn how to fix incorrectly inferred types, please see documentation for TimeSeriesPredictor.fit"
             )
 
-        self.covariate_metadata = CovariateMetadata(
+        self._covariate_metadata = CovariateMetadata(
             known_covariates_cat=known_covariates_cat,
             known_covariates_real=known_covariates_real,
             past_covariates_cat=past_covariates_cat,
@@ -340,13 +345,13 @@ class TimeSeriesFeatureGenerator:
     @staticmethod
     def _detect_and_log_column_types(transformed_df: pd.DataFrame) -> Tuple[List[str], List[str]]:
         """Log & return names of categorical and real-valued columns in the DataFrame."""
-        cat_column_names = []
-        real_column_names = []
+        cat_column_names: List[str] = []
+        real_column_names: List[str] = []
         for column_name, column_dtype in transformed_df.dtypes.items():
             if isinstance(column_dtype, pd.CategoricalDtype):
-                cat_column_names.append(column_name)
+                cat_column_names.append(str(column_name))
             elif pd.api.types.is_numeric_dtype(column_dtype):
-                real_column_names.append(column_name)
+                real_column_names.append(str(column_name))
 
         logger.info(f"\t\tcategorical:        {reprlib.repr(cat_column_names)}")
         logger.info(f"\t\tcontinuous (float): {reprlib.repr(real_column_names)}")
@@ -386,7 +391,11 @@ class AbstractFeatureImportanceTransform:
         self.covariate_metadata: CovariateMetadata = covariate_metadata
         self.prediction_length: int = prediction_length
 
-    def _transform_series(self, data: pd.Series, is_categorical: bool, **kwargs) -> TimeSeriesDataFrame:
+    def _transform_static_series(self, feature_data: pd.Series, is_categorical: bool) -> Any:
+        """Transforms a series with the same index as the pandas DataFrame"""
+        raise NotImplementedError
+
+    def _transform_series(self, feature_data: pd.Series, is_categorical: bool) -> TimeSeriesDataFrame:
         """Transforms a series with the same index as the pandas DataFrame"""
         raise NotImplementedError
 

autogluon/timeseries/utils/forecast.py

@@ -11,7 +11,10 @@ def get_forecast_horizon_index_single_time_series(
     past_timestamps: pd.DatetimeIndex, freq: str, prediction_length: int
 ) -> pd.DatetimeIndex:
     """Get timestamps for the next prediction_length many time steps of the time series with given frequency."""
-    start_ts = past_timestamps.max() + 1 * pd.tseries.frequencies.to_offset(freq)
+    offset = pd.tseries.frequencies.to_offset(freq)
+    if offset is None:
+        raise ValueError(f"Invalid frequency: {freq}")
+    start_ts = past_timestamps.max() + 1 * offset
     return pd.date_range(start=start_ts, periods=prediction_length, freq=freq, name=TIMESTAMP)
 
 
@@ -36,5 +39,5 @@ def get_forecast_horizon_index_ts_dataframe(
     # Non-vectorized offsets like BusinessDay may produce a PerformanceWarning - we filter them
     with warnings.catch_warnings():
         warnings.simplefilter("ignore", category=pd.errors.PerformanceWarning)
-        timestamps = np.dstack([last_ts + step * offset for step in range(1, prediction_length + 1)]).ravel()
+        timestamps = np.dstack([last_ts + step * offset for step in range(1, prediction_length + 1)]).ravel()  # type: ignore[operator]
     return pd.MultiIndex.from_arrays([item_ids, timestamps], names=[ITEMID, TIMESTAMP])

autogluon/timeseries/utils/warning_filters.py

@@ -75,7 +75,7 @@ def disable_stdout():
 
 class DuplicateLogFilter:
     def __init__(self, max_count: int = 1):
-        self.messages = Counter()
+        self.messages: Counter[str] = Counter()
         self.max_count = max_count
 
     def filter(self, record):

autogluon/timeseries/version.py

@@ -1,3 +1,3 @@
 """This is the autogluon version file."""
-__version__ = '1.2b20241205'
+__version__ = '1.2.1b20241207'
 __lite__ = False

{autogluon.timeseries-1.2b20241205.dist-info → autogluon.timeseries-1.2.1b20241207.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: autogluon.timeseries
-Version: 1.2b20241205
+Version: 1.2.1b20241207
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community
@@ -53,9 +53,9 @@ 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]==1.2b20241205
-Requires-Dist: autogluon.common==1.2b20241205
-Requires-Dist: autogluon.tabular[catboost,lightgbm,xgboost]==1.2b20241205
+Requires-Dist: autogluon.core[raytune]==1.2.1b20241207
+Requires-Dist: autogluon.common==1.2.1b20241207
+Requires-Dist: autogluon.tabular[catboost,lightgbm,xgboost]==1.2.1b20241207
 Provides-Extra: all
 Provides-Extra: chronos-onnx
 Requires-Dist: optimum[onnxruntime]<1.20,>=1.17; extra == "chronos-onnx"
@@ -77,7 +77,7 @@ Requires-Dist: pytest-timeout<3,>=2.1; extra == "tests"
 
 [![Latest Release](https://img.shields.io/github/v/release/autogluon/autogluon)](https://github.com/autogluon/autogluon/releases)
 [![Conda Forge](https://img.shields.io/conda/vn/conda-forge/autogluon.svg)](https://anaconda.org/conda-forge/autogluon)
-[![Python Versions](https://img.shields.io/badge/python-3.8%20%7C%203.9%20%7C%203.10%20%7C%203.11-blue)](https://pypi.org/project/autogluon/)
+[![Python Versions](https://img.shields.io/badge/python-3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12-blue)](https://pypi.org/project/autogluon/)
 [![Downloads](https://pepy.tech/badge/autogluon/month)](https://pepy.tech/project/autogluon)
 [![GitHub license](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](./LICENSE)
 [![Discord](https://img.shields.io/discord/1043248669505368144?logo=discord&style=flat)](https://discord.gg/wjUmjqAc2N)
@@ -92,7 +92,7 @@ AutoGluon automates machine learning tasks enabling you to easily achieve strong
 
 ## 💾 Installation
 
-AutoGluon is supported on Python 3.8 - 3.11 and is available on Linux, MacOS, and Windows.
+AutoGluon is supported on Python 3.9 - 3.12 and is available on Linux, MacOS, and Windows.
 
 You can install AutoGluon with:
 
@@ -126,7 +126,8 @@ Below is a curated list of recent tutorials and talks on AutoGluon. A comprehens
 
 | Title                                                                                                                    | Format   | Location                                                                         | Date       |
 |--------------------------------------------------------------------------------------------------------------------------|----------|----------------------------------------------------------------------------------|------------|
-| :tv: [AutoGluon 1.0: Shattering the AutoML Ceiling with Zero Lines of Code](https://www.youtube.com/watch?v=5tvp_Ihgnuk) | Tutorial | [AutoML Conf 2023](https://2023.automl.cc/)                                      | 2023/09/12 |
+| :tv: [AutoGluon: Towards No-Code Automated Machine Learning](https://www.youtube.com/watch?v=SwPq9qjaN2Q)                | Tutorial | [AutoML 2024](https://2024.automl.cc/)                                           | 2024/09/09 |
+| :tv: [AutoGluon 1.0: Shattering the AutoML Ceiling with Zero Lines of Code](https://www.youtube.com/watch?v=5tvp_Ihgnuk) | Tutorial | [AutoML 2023](https://2023.automl.cc/)                                           | 2023/09/12 |
 | :sound: [AutoGluon: The Story](https://automlpodcast.com/episode/autogluon-the-story)                                    | Podcast  | [The AutoML Podcast](https://automlpodcast.com/)                                 | 2023/09/05 |
 | :tv: [AutoGluon: AutoML for Tabular, Multimodal, and Time Series Data](https://youtu.be/Lwu15m5mmbs?si=jSaFJDqkTU27C0fa) | Tutorial | PyData Berlin                                                                    | 2023/06/20 | 
 | :tv: [Solving Complex ML Problems in a few Lines of Code with AutoGluon](https://www.youtube.com/watch?v=J1UQUCPB88I)    | Tutorial | PyData Seattle                                                                   | 2023/06/20 | 

{autogluon.timeseries-1.2b20241205.dist-info → autogluon.timeseries-1.2.1b20241207.dist-info}/RECORD

@@ -1,18 +1,18 @@
-autogluon.timeseries-1.2b20241205-py3.8-nspkg.pth,sha256=cQGwpuGPqg1GXscIwt-7PmME1OnSpD-7ixkikJ31WAY,554
+autogluon.timeseries-1.2.1b20241207-py3.8-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=mFnBC750C5PqgkkYNYni9oYQ5a6K8pXSsDLRDXuA7DI,14182
 autogluon/timeseries/predictor.py,sha256=W9RhTUS_WFMAR7BXiHIYblKHCvGlY8WRTfJJ2E0pBn0,85471
 autogluon/timeseries/regressor.py,sha256=tqQ2zWImxpuEyaAM0DeCjOZ-xcWUYZbCXsqd471xXxQ,8351
 autogluon/timeseries/splitter.py,sha256=eghGwAAN2_cxGk5aJBILgjGWtLzjxJcytMy49gg_q18,3061
-autogluon/timeseries/version.py,sha256=dVMGMb9MPH_0CtohbnblJk790Y6IRsZv_BN5spzHVes,88
+autogluon/timeseries/version.py,sha256=7sMUBp9aSa4Sggp0I4tAnoXBPE3ljo3XV_NSY5mKG3k,90
 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
-autogluon/timeseries/dataset/ts_dataframe.py,sha256=9bJQeg3HkPeVnyxzwqAJiTJGYXths7vxUV_3-OsJ6pk,48640
+autogluon/timeseries/dataset/ts_dataframe.py,sha256=4EwvGrsoodrFk8CehhdLkFxBXB88HfF5M06zePe-N-w,48681
 autogluon/timeseries/metrics/__init__.py,sha256=LLGmYaexsx7CregV-QaHc5exjZbsJfBSVOtxHRGC0ho,2139
 autogluon/timeseries/metrics/abstract.py,sha256=9xCFQ3NaR1C0hn01M7oBd72a_CiNV-w6QFcRjwUbKYI,8183
-autogluon/timeseries/metrics/point.py,sha256=b19Ed4dS_ROdkrOZIik_Q3-8deCN9IQSZXtCl8tuxto,15509
+autogluon/timeseries/metrics/point.py,sha256=Pov50UfT3l38j9kiokzFYzb0rAI3X_aIkZsGYqNKTco,15573
 autogluon/timeseries/metrics/quantile.py,sha256=eemdLbo3y2wstnVkuA-f55YXywctUmSW1EhIW4BsoH4,3965
 autogluon/timeseries/metrics/utils.py,sha256=HuDe1BNe8yJU4f_DKM913nNrUueoRaw6zhxm1-S20s0,910
 autogluon/timeseries/models/__init__.py,sha256=MYD9JJ-wUDE5B6jW6E6LU2eXQ6vflfQBvqQJkdzJa3A,1189
@@ -25,12 +25,12 @@ autogluon/timeseries/models/autogluon_tabular/mlforecast.py,sha256=vfWXLdxYlbzjK
 autogluon/timeseries/models/autogluon_tabular/transforms.py,sha256=XVoy8KpvoeX38lHHAXq4Be9LCxKjxZ36SOFeSAICRFM,2524
 autogluon/timeseries/models/autogluon_tabular/utils.py,sha256=Fn3Vu_Q0PCtEUbtNgLp1xIblg7dOdpFlF3W5kLHgruI,63
 autogluon/timeseries/models/chronos/__init__.py,sha256=wT77HzTtmQxW3sw2k0mA5Ot6PSHivX-Uvn5fjM05EU4,60
-autogluon/timeseries/models/chronos/model.py,sha256=jYnUdSWMrxdIWhysy-fEVd5w0Z06dQsIYdkh8alwgR0,30343
+autogluon/timeseries/models/chronos/model.py,sha256=BsAgOK-AzghU-IM3H_XvezFh6JG1_3T3Poql48DY7cE,30642
 autogluon/timeseries/models/chronos/pipeline/__init__.py,sha256=N-YZH9BGBoi99r5cznJe1zEEjwjIg7cOYIHZkKuJq44,247
-autogluon/timeseries/models/chronos/pipeline/base.py,sha256=HlWQTS5q7UMzwbA5Pmg_N01AxuGfTf2tP5xq2jgavqI,5549
-autogluon/timeseries/models/chronos/pipeline/chronos.py,sha256=QmC0ZSHaF85dwAAzbg2elUX10iEhob6gp0Wctfsfq1k,22531
+autogluon/timeseries/models/chronos/pipeline/base.py,sha256=14OAKHmio6LmO4mVom2mPGB0CvIrOjMGJzb-MVSAq-s,5596
+autogluon/timeseries/models/chronos/pipeline/chronos.py,sha256=5IxpdBBEodH3vULyLiBA_1Ost5NSQqNUqveorJkbCso,22591
 autogluon/timeseries/models/chronos/pipeline/chronos_bolt.py,sha256=2MJuik-YFgONZ3X2DciAph5So6ABys5ppQhBC81gLyk,20083
-autogluon/timeseries/models/chronos/pipeline/utils.py,sha256=dENQLSN6dumLrTGQ6sbJMq45irdDFOoCarAnWpTbLjk,13134
+autogluon/timeseries/models/chronos/pipeline/utils.py,sha256=shoVsQR40a5qHyhLVD8PaIvIiI0Y7mVp4dIe0Guu7Ws,13166
 autogluon/timeseries/models/ensemble/__init__.py,sha256=kFr11Gmt7lQJu9Rr8HuIPphQN5l1TsoorfbJm_O3a_s,128
 autogluon/timeseries/models/ensemble/abstract_timeseries_ensemble.py,sha256=tifETwmiEGt-YtQ9eNK7ojJ3fBvtFMUJvisbfkIJ7gw,3393
 autogluon/timeseries/models/ensemble/greedy_ensemble.py,sha256=5HvZuW5osgsZg3V69k82nKEOy_YgeH1JTfQa7F3cU7s,7220
@@ -46,25 +46,25 @@ autogluon/timeseries/models/local/statsforecast.py,sha256=cFJ_A7LR2jTmFNGgMxt3xv
 autogluon/timeseries/models/multi_window/__init__.py,sha256=Bq7AT2Jxdd4WNqmjTdzeqgNiwn1NCyWp4tBIWaM-zfI,60
 autogluon/timeseries/models/multi_window/multi_window_model.py,sha256=2o_wKNCNP570c0UuNufPhEDYOWQ2mFYwmmHUZzPneRI,11792
 autogluon/timeseries/trainer/__init__.py,sha256=lxiOT-Gc6BEnr_yWQqra85kEngeM_wtH2SCaRbmC_qE,170
-autogluon/timeseries/trainer/abstract_trainer.py,sha256=3DEr4hATu2zNzkuzwO5UeqS25Ak4k5w4OFAtCmYqmAc,61053
-autogluon/timeseries/trainer/auto_trainer.py,sha256=psJFZBwWWPlLjNwAgvO4OUJXsRW1sTN2YS9a4pdoeoE,3344
+autogluon/timeseries/trainer/abstract_trainer.py,sha256=wY53OfKdC5QWfj2KGWV3xWc_3pnwi6gHvGIi7ehWugQ,61065
+autogluon/timeseries/trainer/auto_trainer.py,sha256=NEZ2l6zVsR1j1wYvD05cOZOjMb0kC3kBTbN9NlfUsPI,3362
 autogluon/timeseries/transforms/__init__.py,sha256=Stym_998LZQgKPuFN4_w1AcJFh4_AeaQLXgXLzv53kY,299
 autogluon/timeseries/transforms/covariate_scaler.py,sha256=iscshgfNTCn379Q73BJXyDUFFm1WRclzKdG2MIPTOEc,6587
 autogluon/timeseries/transforms/target_scaler.py,sha256=8gxXy0zavR0ck48UVvnI2UXE8TV6ScFGoZdAvBrIF84,5372
 autogluon/timeseries/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-autogluon/timeseries/utils/features.py,sha256=VvBQzaymSSzxI9khtcXbpir-qo1NWHe51O7F6ynyh_s,21943
-autogluon/timeseries/utils/forecast.py,sha256=p0WKM9Q0nLAwwmCgYZI1zi9mCOWXWJfllEt2lPRQl4M,1882
-autogluon/timeseries/utils/warning_filters.py,sha256=JRitJwTsowvIXhNMEWjYIhLGgmXz1Kkj0J6ON3EVyS4,2508
+autogluon/timeseries/utils/features.py,sha256=FYgcv_i5fFfxGOW86GLLrLanmaIpA2OXoMwUwvPsdkI,22443
+autogluon/timeseries/utils/forecast.py,sha256=fVlWRUg-A29OYQyST5aTzMk-AXYO3R_5HEx28loD-Qk,2006
+autogluon/timeseries/utils/warning_filters.py,sha256=FyXvYW_ylULcZP4R9xNBxojKtvadW3uygXwHK_xHq5g,2522
 autogluon/timeseries/utils/datetime/__init__.py,sha256=bTMR8jLh1LW55vHjbOr1zvWRMF_PqbvxpS-cUcNIDWI,173
 autogluon/timeseries/utils/datetime/base.py,sha256=3NdsH3NDq4cVAOSoy3XpaNixyNlbjy4DJ_YYOGuu9x4,1341
-autogluon/timeseries/utils/datetime/lags.py,sha256=GoLtvcZ8oKb3QkoBJ9E59LSPLOP7Qjxrr2UmMSZgjyw,5909
-autogluon/timeseries/utils/datetime/seasonality.py,sha256=h_4w00iEytAz_N_EpCENQ8RCXy7KQITczrYjBgVqWkQ,764
-autogluon/timeseries/utils/datetime/time_features.py,sha256=PAXbYbQ0z_5GFbkxSNi41zLY_2-U3x0Ynm1m_WhdtGc,2572
-autogluon.timeseries-1.2b20241205.dist-info/LICENSE,sha256=CeipvOyAZxBGUsFoaFqwkx54aPnIKEtm9a5u2uXxEws,10142
-autogluon.timeseries-1.2b20241205.dist-info/METADATA,sha256=16z-h2dhWZFeXJ76yFFdLfhxL2LGueOoHdNw6SzwkSk,12325
-autogluon.timeseries-1.2b20241205.dist-info/NOTICE,sha256=7nPQuj8Kp-uXsU0S5so3-2dNU5EctS5hDXvvzzehd7E,114
-autogluon.timeseries-1.2b20241205.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-autogluon.timeseries-1.2b20241205.dist-info/namespace_packages.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
-autogluon.timeseries-1.2b20241205.dist-info/top_level.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
-autogluon.timeseries-1.2b20241205.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-autogluon.timeseries-1.2b20241205.dist-info/RECORD,,
+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-1.2.1b20241207.dist-info/LICENSE,sha256=CeipvOyAZxBGUsFoaFqwkx54aPnIKEtm9a5u2uXxEws,10142
+autogluon.timeseries-1.2.1b20241207.dist-info/METADATA,sha256=2swtG6OfpCfUwzC1bufiES5kHVkB-M3t-brEcyepZbQ,12566
+autogluon.timeseries-1.2.1b20241207.dist-info/NOTICE,sha256=7nPQuj8Kp-uXsU0S5so3-2dNU5EctS5hDXvvzzehd7E,114
+autogluon.timeseries-1.2.1b20241207.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+autogluon.timeseries-1.2.1b20241207.dist-info/namespace_packages.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
+autogluon.timeseries-1.2.1b20241207.dist-info/top_level.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
+autogluon.timeseries-1.2.1b20241207.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+autogluon.timeseries-1.2.1b20241207.dist-info/RECORD,,