autogluon.timeseries 1.0.1b20240408__tar.gz → 1.1.0b20240410__tar.gz

{autogluon.timeseries-1.0.1b20240408 → autogluon.timeseries-1.1.0b20240410}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.1
 Name: autogluon.timeseries
-Version: 1.0.1b20240408
-Summary: AutoML for Image, Text, and Tabular Data
+Version: 1.1.0b20240410
+Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community
 License: Apache-2.0
@@ -14,7 +14,7 @@ Description:
         <div align="center">
         <img src="https://user-images.githubusercontent.com/16392542/77208906-224aa500-6aba-11ea-96bd-e81806074030.png" width="350">
         
-        ## AutoML for Image, Text, Time Series, and Tabular Data
+        ## Fast and Accurate ML in 3 Lines of Code
         
         [![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)

{autogluon.timeseries-1.0.1b20240408 → autogluon.timeseries-1.1.0b20240410}/setup.py

@@ -56,17 +56,16 @@ extras_require = {
         "black~=23.0",
     ],
     "chronos-openvino": [  # for faster CPU inference in pretrained models with OpenVINO
-        "optimum-intel[openvino,nncf]>=1.16,<1.17",
-        "optimum[openvino,nncf]>=1.18,<1.19",
+        "optimum-intel[openvino,nncf]>=1.15,<1.17",
+        "optimum[openvino,nncf]>=1.17,<1.19",
     ],
     "chronos-onnx": [  # for faster CPU inference in pretrained models with ONNX
-        "optimum[onnxruntime]>=1.18,<1.19",
+        "optimum[onnxruntime]>=1.17,<1.19",
     ],
 }
 
-extras_require["all"] = list(
-    set.union(*(set(extras_require[extra]) for extra in ["chronos-onnx", "chronos-openvino"]))
-)
+# TODO: add openvino back to "all" after dependency versions are relaxed
+extras_require["all"] = list(set.union(*(set(extras_require[extra]) for extra in ["chronos-onnx"])))
 
 install_requires = ag.get_dependency_version_ranges(install_requires)
 

{autogluon.timeseries-1.0.1b20240408 → autogluon.timeseries-1.1.0b20240410}/src/autogluon/timeseries/models/abstract/abstract_timeseries_model.py

@@ -373,13 +373,14 @@ class AbstractTimeSeriesModel(AbstractModel):
         val_data: TimeSeriesDataFrame,
         store_val_score: bool = False,
         store_predict_time: bool = False,
+        **predict_kwargs,
     ) -> 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
         )
         predict_start_time = time.time()
-        oof_predictions = self.predict(past_data, known_covariates=known_covariates)
+        oof_predictions = self.predict(past_data, known_covariates=known_covariates, **predict_kwargs)
         self._oof_predictions = [oof_predictions]
         if store_predict_time:
             self.predict_time = time.time() - predict_start_time

{autogluon.timeseries-1.0.1b20240408 → autogluon.timeseries-1.1.0b20240410}/src/autogluon/timeseries/models/autogluon_tabular/mlforecast.py

@@ -174,6 +174,21 @@ class AbstractMLForecastModel(AbstractTimeSeriesModel):
         """
         return df
 
+    def _add_scale_as_static_feature(self, data: TimeSeriesDataFrame) -> TimeSeriesDataFrame:
+        """Add mean/std of the target column for each series as a static feature."""
+        data = data.copy(deep=False)
+        scale_features = (
+            data[self.target]
+            .groupby(ITEMID, sort=False)
+            .agg(["mean", "std"])
+            .rename(columns={"mean": "__target_mean", "std": "__target_scale"})
+        )
+        if data.static_features is None:
+            data.static_features = scale_features
+        else:
+            data.static_features = pd.concat([data.static_features, scale_features], axis=1)
+        return data
+
     @staticmethod
     def _shorten_all_series(mlforecast_df: pd.DataFrame, max_length: int):
         logger.debug(f"Shortening all series to at most {max_length}")
@@ -252,6 +267,11 @@ class AbstractMLForecastModel(AbstractTimeSeriesModel):
         if static_features is not None:
             df = pd.merge(df, static_features, how="left", on=ITEMID, suffixes=(None, "_static_feat"))
 
+        for col in self.metadata.known_covariates_real:
+            # Normalize non-boolean features using mean_abs scaling
+            if not df[col].isin([0, 1]).all():
+                df[f"__scaled_{col}"] = df[col] / df[col].abs().groupby(df[ITEMID]).mean().reindex(df[ITEMID]).values
+
         # We assume that df is sorted by 'unique_id' inside `TimeSeriesPredictor._check_and_prepare_data_frame`
         return df.rename(columns=column_name_mapping)
 
@@ -265,6 +285,8 @@ class AbstractMLForecastModel(AbstractTimeSeriesModel):
     ) -> None:
         from mlforecast import MLForecast
 
+        train_data = self._add_scale_as_static_feature(train_data)
+
         self._check_fit_params()
         fit_start_time = time.time()
         self._train_target_median = train_data[self.target].median()
@@ -463,6 +485,7 @@ class DirectTabularModel(AbstractMLForecastModel):
         known_covariates: Optional[TimeSeriesDataFrame] = None,
         **kwargs,
     ) -> TimeSeriesDataFrame:
+        data = self._add_scale_as_static_feature(data)
         original_item_id_order = data.item_ids
         data, known_covariates, forecast_for_short_series = self._remove_short_ts_and_generate_fallback_forecast(
             data=data, known_covariates=known_covariates
@@ -479,7 +502,7 @@ class DirectTabularModel(AbstractMLForecastModel):
         # MLForecast raises exception of target contains NaN. We use inf as placeholder, replace them by NaN afterwards
         data_future[self.target] = float("inf")
         data_extended = pd.concat([data, data_future])
-        mlforecast_df = self._to_mlforecast_df(data_extended, data.static_features)
+        mlforecast_df = self._to_mlforecast_df(data_extended, data_extended.static_features)
         if self._max_ts_length is not None:
             # We appended `prediction_length` time steps to each series, so increase length
             mlforecast_df = self._shorten_all_series(mlforecast_df, self._max_ts_length + self.prediction_length)
@@ -594,6 +617,7 @@ class RecursiveTabularModel(AbstractMLForecastModel):
         known_covariates: Optional[TimeSeriesDataFrame] = None,
         **kwargs,
     ) -> TimeSeriesDataFrame:
+        data = self._add_scale_as_static_feature(data)
         original_item_id_order = data.item_ids
         data, known_covariates, forecast_for_short_series = self._remove_short_ts_and_generate_fallback_forecast(
             data=data, known_covariates=known_covariates

{autogluon.timeseries-1.0.1b20240408 → autogluon.timeseries-1.1.0b20240410}/src/autogluon/timeseries/models/chronos/model.py

@@ -53,42 +53,6 @@ MODEL_ALIASES = {
 }
 
 
-class ChronosInferenceDataset:
-    """A container for time series datasets that implements the ``torch.utils.data.Dataset`` interface"""
-
-    def __init__(
-        self,
-        target_df: TimeSeriesDataFrame,
-        context_length: int,
-        target_column: str = "target",
-    ):
-        assert context_length > 0
-        self.context_length = context_length
-        self.target_array = target_df[target_column].to_numpy(dtype=np.float32)
-        self.freq = target_df.freq
-
-        # store pointer to start:end of each time series
-        cum_sizes = target_df.num_timesteps_per_item().values.cumsum()
-        self.indptr = np.append(0, cum_sizes).astype(np.int32)
-
-    def __len__(self):
-        return len(self.indptr) - 1  # noqa
-
-    def _get_context(self, a: np.ndarray, pad_value=np.nan):
-        a = a[-self.context_length :]
-        pad_size = self.context_length - len(a)
-        if pad_size > 0:
-            pad = np.full(shape=(pad_size,), fill_value=pad_value)
-            a = np.concatenate((pad, a))
-        return a
-
-    def __getitem__(self, idx) -> np.ndarray:
-        start_idx = self.indptr[idx]
-        end_idx = self.indptr[idx + 1]
-
-        return self._get_context(self.target_array[start_idx:end_idx])
-
-
 class ChronosModel(AbstractTimeSeriesModel):
     """Chronos pretrained time series forecasting models, based on the original
     `ChronosModel <https://github.com/amazon-science/chronos-forecasting>`_ implementation.
@@ -196,6 +160,7 @@ class ChronosModel(AbstractTimeSeriesModel):
         )
 
         self.model_pipeline: Optional[Any] = None  # of type OptimizedChronosPipeline
+        self.time_limit: Optional[float] = None
 
     def save(self, path: str = None, verbose: bool = True) -> str:
         pipeline = self.model_pipeline
@@ -288,14 +253,16 @@ class ChronosModel(AbstractTimeSeriesModel):
         **kwargs,
     ) -> None:
         self._check_fit_params()
+        self.time_limit = time_limit
 
     def _get_inference_data_loader(
         self,
         data: TimeSeriesDataFrame,
         context_length: int,
         num_workers: int = 0,
+        time_limit: Optional[float] = None,
     ):
-        import torch
+        from .utils import ChronosInferenceDataLoader, ChronosInferenceDataset, timeout_callback
 
         chronos_dataset = ChronosInferenceDataset(
             target_df=data,
@@ -303,11 +270,12 @@ class ChronosModel(AbstractTimeSeriesModel):
             context_length=context_length,
         )
 
-        return torch.utils.data.DataLoader(
+        return ChronosInferenceDataLoader(
             chronos_dataset,
             batch_size=self.batch_size,
             shuffle=False,
             num_workers=num_workers,
+            on_batch=timeout_callback(seconds=time_limit),
         )
 
     def _predict(
@@ -333,6 +301,12 @@ class ChronosModel(AbstractTimeSeriesModel):
                 # load model pipeline to device memory
                 self.load_model_pipeline(context_length=context_length)
 
+            inference_data_loader = self._get_inference_data_loader(
+                data=data,
+                num_workers=self.data_loader_num_workers,
+                context_length=context_length,
+                time_limit=kwargs.get("time_limit"),
+            )
             self.model_pipeline.model.eval()
             with torch.inference_mode():
                 prediction_samples = [
@@ -345,11 +319,7 @@ class ChronosModel(AbstractTimeSeriesModel):
                     .detach()
                     .cpu()
                     .numpy()
-                    for batch in self._get_inference_data_loader(
-                        data=data,
-                        num_workers=self.data_loader_num_workers,
-                        context_length=context_length,
-                    )
+                    for batch in inference_data_loader
                 ]
 
         samples = np.concatenate(prediction_samples, axis=0).swapaxes(1, 2).reshape(-1, self.num_samples)
@@ -367,3 +337,16 @@ class ChronosModel(AbstractTimeSeriesModel):
 
     def _more_tags(self) -> Dict:
         return {"allow_nan": True}
+
+    def score_and_cache_oof(
+        self,
+        val_data: TimeSeriesDataFrame,
+        store_val_score: bool = False,
+        store_predict_time: bool = False,
+        **predict_kwargs,
+    ) -> None:
+        # All computation happens during inference, so we provide the time_limit at prediction time
+        # TODO: Once custom predict_kwargs is allowed, make sure that `time_limit` is not among the keys
+        super().score_and_cache_oof(
+            val_data, store_val_score, store_predict_time, time_limit=self.time_limit, **predict_kwargs
+        )

autogluon.timeseries-1.1.0b20240410/src/autogluon/timeseries/models/chronos/utils.py

@@ -0,0 +1,66 @@
+import time
+from typing import Callable, Optional
+
+import numpy as np
+import torch
+
+from autogluon.core.utils.exceptions import TimeLimitExceeded
+from autogluon.timeseries.dataset.ts_dataframe import TimeSeriesDataFrame
+
+
+class ChronosInferenceDataset:
+    """A container for time series datasets that implements the ``torch.utils.data.Dataset`` interface"""
+
+    def __init__(
+        self,
+        target_df: TimeSeriesDataFrame,
+        context_length: int,
+        target_column: str = "target",
+    ):
+        assert context_length > 0
+        self.context_length = context_length
+        self.target_array = target_df[target_column].to_numpy(dtype=np.float32)
+        self.freq = target_df.freq
+
+        # store pointer to start:end of each time series
+        cum_sizes = target_df.num_timesteps_per_item().values.cumsum()
+        self.indptr = np.append(0, cum_sizes).astype(np.int32)
+
+    def __len__(self):
+        return len(self.indptr) - 1  # noqa
+
+    def _get_context(self, a: np.ndarray, pad_value=np.nan):
+        a = a[-self.context_length :]
+        pad_size = self.context_length - len(a)
+        if pad_size > 0:
+            pad = np.full(shape=(pad_size,), fill_value=pad_value)
+            a = np.concatenate((pad, a))
+        return a
+
+    def __getitem__(self, idx) -> np.ndarray:
+        start_idx = self.indptr[idx]
+        end_idx = self.indptr[idx + 1]
+
+        return self._get_context(self.target_array[start_idx:end_idx])
+
+
+class ChronosInferenceDataLoader(torch.utils.data.DataLoader):
+    def __init__(self, *args, **kwargs):
+        self.callback: Callable = kwargs.pop("on_batch", lambda: None)
+        super().__init__(*args, **kwargs)
+
+    def __iter__(self):
+        for item in super().__iter__():
+            yield item
+            self.callback()
+
+
+def timeout_callback(seconds: Optional[float]) -> Callable:
+    """Return a callback object that raises an exception if time limit is exceeded."""
+    start_time = time.time()
+
+    def callback() -> None:
+        if seconds is not None and time.time() - start_time > seconds:
+            raise TimeLimitExceeded
+
+    return callback

{autogluon.timeseries-1.0.1b20240408 → autogluon.timeseries-1.1.0b20240410}/src/autogluon/timeseries/models/local/abstract_local_model.py

@@ -144,9 +144,10 @@ class AbstractLocalModel(AbstractTimeSeriesModel):
 
         # timeout ensures that no individual job takes longer than time_limit
         # TODO: a job started late may still exceed time_limit - how to prevent that?
-        timeout = None if self.n_jobs == 1 else self.time_limit
+        time_limit = kwargs.get("time_limit")
+        timeout = None if self.n_jobs == 1 else time_limit
         # end_time ensures that no new jobs are started after time_limit is exceeded
-        end_time = None if self.time_limit is None else time.time() + self.time_limit
+        end_time = None if time_limit is None else time.time() + time_limit
         executor = Parallel(self.n_jobs, timeout=timeout)
 
         try:
@@ -169,19 +170,24 @@ class AbstractLocalModel(AbstractTimeSeriesModel):
         return TimeSeriesDataFrame(predictions_df)
 
     def score_and_cache_oof(
-        self, val_data: TimeSeriesDataFrame, store_val_score: bool = False, store_predict_time: bool = False
+        self,
+        val_data: TimeSeriesDataFrame,
+        store_val_score: bool = False,
+        store_predict_time: bool = False,
+        **predict_kwargs,
     ) -> None:
-        super().score_and_cache_oof(val_data, store_val_score, store_predict_time)
-        # Remove time_limit for future predictions
-        self.time_limit = None
+        # All computation happens during inference, so we provide the time_limit at prediction time
+        super().score_and_cache_oof(
+            val_data, store_val_score, store_predict_time, time_limit=self.time_limit, **predict_kwargs
+        )
 
     def _predict_wrapper(self, time_series: pd.Series, end_time: Optional[float] = None) -> Tuple[pd.DataFrame, bool]:
         if end_time is not None and time.time() >= end_time:
             raise TimeLimitExceeded
 
+        model_failed = False
         if time_series.isna().all():
             result = self._dummy_forecast.copy()
-            model_failed = True
         else:
             try:
                 result = self._predict_with_local_model(
@@ -190,7 +196,6 @@ class AbstractLocalModel(AbstractTimeSeriesModel):
                 )
                 if not np.isfinite(result.values).all():
                     raise RuntimeError("Forecast contains NaN or Inf values.")
-                model_failed = False
             except Exception:
                 if self.use_fallback_model:
                     result = seasonal_naive_forecast(

{autogluon.timeseries-1.0.1b20240408 → autogluon.timeseries-1.1.0b20240410}/src/autogluon/timeseries/models/multi_window/multi_window_model.py

@@ -189,6 +189,7 @@ class MultiWindowBacktestingModel(AbstractTimeSeriesModel):
         val_data: TimeSeriesDataFrame,
         store_val_score: bool = False,
         store_predict_time: bool = False,
+        **predict_kwargs,
     ) -> None:
         # self.val_score, self.predict_time, self._oof_predictions already saved during _fit()
         assert self._oof_predictions is not None

{autogluon.timeseries-1.0.1b20240408 → autogluon.timeseries-1.1.0b20240410}/src/autogluon/timeseries/version.py

@@ -1,3 +1,3 @@
 """This is the autogluon version file."""
-__version__ = '1.0.1b20240408'
+__version__ = '1.1.0b20240410'
 __lite__ = False

{autogluon.timeseries-1.0.1b20240408 → autogluon.timeseries-1.1.0b20240410}/src/autogluon.timeseries.egg-info/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.1
 Name: autogluon.timeseries
-Version: 1.0.1b20240408
-Summary: AutoML for Image, Text, and Tabular Data
+Version: 1.1.0b20240410
+Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community
 License: Apache-2.0
@@ -14,7 +14,7 @@ Description:
         <div align="center">
         <img src="https://user-images.githubusercontent.com/16392542/77208906-224aa500-6aba-11ea-96bd-e81806074030.png" width="350">
         
-        ## AutoML for Image, Text, Time Series, and Tabular Data
+        ## Fast and Accurate ML in 3 Lines of Code
         
         [![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)

{autogluon.timeseries-1.0.1b20240408 → autogluon.timeseries-1.1.0b20240410}/src/autogluon.timeseries.egg-info/SOURCES.txt

@@ -32,6 +32,7 @@ src/autogluon/timeseries/models/autogluon_tabular/utils.py
 src/autogluon/timeseries/models/chronos/__init__.py
 src/autogluon/timeseries/models/chronos/model.py
 src/autogluon/timeseries/models/chronos/pipeline.py
+src/autogluon/timeseries/models/chronos/utils.py
 src/autogluon/timeseries/models/ensemble/__init__.py
 src/autogluon/timeseries/models/ensemble/abstract_timeseries_ensemble.py
 src/autogluon/timeseries/models/ensemble/greedy_ensemble.py

{autogluon.timeseries-1.0.1b20240408 → autogluon.timeseries-1.1.0b20240410}/src/autogluon.timeseries.egg-info/requires.txt

@@ -16,21 +16,19 @@ utilsforecast<0.0.11,>=0.0.10
 tqdm<5,>=4.38
 orjson~=3.9
 tensorboard<3,>=2.9
-autogluon.core[raytune]==1.0.1b20240408
-autogluon.common==1.0.1b20240408
-autogluon.tabular[catboost,lightgbm,xgboost]==1.0.1b20240408
+autogluon.core[raytune]==1.1.0b20240410
+autogluon.common==1.1.0b20240410
+autogluon.tabular[catboost,lightgbm,xgboost]==1.1.0b20240410
 
 [all]
-optimum[onnxruntime]<1.19,>=1.18
-optimum-intel[nncf,openvino]<1.17,>=1.16
-optimum[nncf,openvino]<1.19,>=1.18
+optimum[onnxruntime]<1.19,>=1.17
 
 [chronos-onnx]
-optimum[onnxruntime]<1.19,>=1.18
+optimum[onnxruntime]<1.19,>=1.17
 
 [chronos-openvino]
-optimum-intel[nncf,openvino]<1.17,>=1.16
-optimum[nncf,openvino]<1.19,>=1.18
+optimum-intel[nncf,openvino]<1.17,>=1.15
+optimum[nncf,openvino]<1.19,>=1.17
 
 [tests]
 pytest