autogluon.timeseries 1.0.1b20240408__py3-none-any.whl → 1.1.0b20240409__py3-none-any.whl

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/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/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/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:
@@ -169,11 +170,16 @@ 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:

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/version.py

@@ -1,3 +1,3 @@
 """This is the autogluon version file."""
-__version__ = '1.0.1b20240408'
+__version__ = '1.1.0b20240409'
 __lite__ = False

{autogluon.timeseries-1.0.1b20240408.dist-info → autogluon.timeseries-1.1.0b20240409.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: autogluon.timeseries
-Version: 1.0.1b20240408
+Version: 1.1.0b20240409
 Summary: AutoML for Image, Text, and Tabular Data
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community
@@ -52,18 +52,16 @@ Requires-Dist: utilsforecast <0.0.11,>=0.0.10
 Requires-Dist: tqdm <5,>=4.38
 Requires-Dist: orjson ~=3.9
 Requires-Dist: tensorboard <3,>=2.9
-Requires-Dist: autogluon.core[raytune] ==1.0.1b20240408
-Requires-Dist: autogluon.common ==1.0.1b20240408
-Requires-Dist: autogluon.tabular[catboost,lightgbm,xgboost] ==1.0.1b20240408
+Requires-Dist: autogluon.core[raytune] ==1.1.0b20240409
+Requires-Dist: autogluon.common ==1.1.0b20240409
+Requires-Dist: autogluon.tabular[catboost,lightgbm,xgboost] ==1.1.0b20240409
 Provides-Extra: all
-Requires-Dist: optimum[onnxruntime] <1.19,>=1.18 ; extra == 'all'
-Requires-Dist: optimum-intel[nncf,openvino] <1.17,>=1.16 ; extra == 'all'
-Requires-Dist: optimum[nncf,openvino] <1.19,>=1.18 ; extra == 'all'
+Requires-Dist: optimum[onnxruntime] <1.19,>=1.17 ; extra == 'all'
 Provides-Extra: chronos-onnx
-Requires-Dist: optimum[onnxruntime] <1.19,>=1.18 ; extra == 'chronos-onnx'
+Requires-Dist: optimum[onnxruntime] <1.19,>=1.17 ; extra == 'chronos-onnx'
 Provides-Extra: chronos-openvino
-Requires-Dist: optimum-intel[nncf,openvino] <1.17,>=1.16 ; extra == 'chronos-openvino'
-Requires-Dist: optimum[nncf,openvino] <1.19,>=1.18 ; extra == 'chronos-openvino'
+Requires-Dist: optimum-intel[nncf,openvino] <1.17,>=1.15 ; extra == 'chronos-openvino'
+Requires-Dist: optimum[nncf,openvino] <1.19,>=1.17 ; extra == 'chronos-openvino'
 Provides-Extra: tests
 Requires-Dist: pytest ; extra == 'tests'
 Requires-Dist: ruff >=0.0.285 ; extra == 'tests'

{autogluon.timeseries-1.0.1b20240408.dist-info → autogluon.timeseries-1.1.0b20240409.dist-info}/RECORD

@@ -1,10 +1,10 @@
-autogluon.timeseries-1.0.1b20240408-py3.8-nspkg.pth,sha256=cQGwpuGPqg1GXscIwt-7PmME1OnSpD-7ixkikJ31WAY,554
+autogluon.timeseries-1.1.0b20240409-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=fPIV2p0BMWcZr5fwOkNsJrk8RxK-IYUH_VON3_YXKOQ,13750
 autogluon/timeseries/predictor.py,sha256=A-YkJGKrYGXGlmtIHd9CDMmudBSKcBdnOCJK4oGsQr8,81222
 autogluon/timeseries/splitter.py,sha256=eghGwAAN2_cxGk5aJBILgjGWtLzjxJcytMy49gg_q18,3061
-autogluon/timeseries/version.py,sha256=jZBmrJPoADjz7yFzFD1IlaguMPsaJC2NcUT56_rbwBY,90
+autogluon/timeseries/version.py,sha256=ACrO9T3KI3r4-b2HTTFpVrIdjO5Xc59N9PjfRI0dV7Y,90
 autogluon/timeseries/configs/__init__.py,sha256=BTtHIPCYeGjqgOcvqb8qPD4VNX-ICKOg6wnkew1cPOE,98
 autogluon/timeseries/configs/presets_configs.py,sha256=ZVV8BsnGnnHPgjBtJBqF-H35MYUdzRBQ8FP7zA3_11g,1949
 autogluon/timeseries/dataset/__init__.py,sha256=UvnhAN5tjgxXTHoZMQDy64YMDj4Xxa68yY7NP4vAw0o,81
@@ -17,14 +17,15 @@ autogluon/timeseries/metrics/utils.py,sha256=eJ63TCR-UwbeJ1c2Qm7B2q-8B3sFthPgioo
 autogluon/timeseries/models/__init__.py,sha256=HFjDOYKQWaGlgQWiLlOvfwE2dH0uDmeKJFC8GDL987c,1271
 autogluon/timeseries/models/presets.py,sha256=p36ROcuOnixgGsI1zBdr9VM-MH2pKCiJCS2Ofb4xT8o,11243
 autogluon/timeseries/models/abstract/__init__.py,sha256=wvDsQAZIV0N3AwBeMaGItoQ82trEfnT-nol2AAOIxBg,102
-autogluon/timeseries/models/abstract/abstract_timeseries_model.py,sha256=aUXlX1ozc5XghinR5ahGIX94MkhBmmYvgmqmMib5BhU,23391
+autogluon/timeseries/models/abstract/abstract_timeseries_model.py,sha256=q5yVFyFJPaMVtW48tr2Pw-hgedM5upvc-93qjN4Li68,23435
 autogluon/timeseries/models/abstract/model_trial.py,sha256=ENPg_7nsdxIvaNM0o0UShZ3x8jFlRmwRc5m0fGPC0TM,3720
 autogluon/timeseries/models/autogluon_tabular/__init__.py,sha256=r9i6jWcyeLHYClkcMSKRVsfrkBUMxpDrTATNTBc_qgQ,136
 autogluon/timeseries/models/autogluon_tabular/mlforecast.py,sha256=9gNuCWf8vVfVPiXppwG5l_3mLbZZ6i5pHKTM-rSk5Ww,30977
 autogluon/timeseries/models/autogluon_tabular/utils.py,sha256=4-gTrBtizxeMVQlsuscugPqw9unaXWXhS1TVVssfzYY,2125
 autogluon/timeseries/models/chronos/__init__.py,sha256=wT77HzTtmQxW3sw2k0mA5Ot6PSHivX-Uvn5fjM05EU4,60
-autogluon/timeseries/models/chronos/model.py,sha256=8mZBsjZGP6Q1IGneTiSkcSFvkI6eVBFwweT0t6YUzNk,14974
+autogluon/timeseries/models/chronos/model.py,sha256=wG4tlTwpFiADu-KQ3TYg-hz7hGz1vPBU__DzyQrikdI,14643
 autogluon/timeseries/models/chronos/pipeline.py,sha256=caR4tx-MZnrPeiU_Rra566-OP_SpodtOgcU7P0Hw0Vc,20784
+autogluon/timeseries/models/chronos/utils.py,sha256=dl7pytUFmosFVfBcBAGA0JqMJp4cTQ3DmM9Mdjap9no,2124
 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
@@ -33,12 +34,12 @@ autogluon/timeseries/models/gluonts/abstract_gluonts.py,sha256=X1l_MexAoyBNMGiJr
 autogluon/timeseries/models/gluonts/torch/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 autogluon/timeseries/models/gluonts/torch/models.py,sha256=PVDns7CnZtJTbPiCw-FJxahKrDjC-wj0VkwIGsodYY0,19930
 autogluon/timeseries/models/local/__init__.py,sha256=JyckWWgMG1BTIWJqFTW6e1O-eb0LPPOwtXwmb1ErohQ,756
-autogluon/timeseries/models/local/abstract_local_model.py,sha256=lota8MNpfgYC1PftM7sKcjx2gVCVq3K_D_dovBGqksg,11692
+autogluon/timeseries/models/local/abstract_local_model.py,sha256=pbuS8G1xUisOSMaKrsfxRdmTsZTBvFjldSTn6inyr_Q,11860
 autogluon/timeseries/models/local/naive.py,sha256=iwRcFMFmJKPWPbD9TWaIUS51oav69F_VAp6-jb_5SUE,7249
 autogluon/timeseries/models/local/npts.py,sha256=Bp74doKnfpGE8ywP4FWOCI_RwRMsmgocYDfGtq764DA,4143
 autogluon/timeseries/models/local/statsforecast.py,sha256=oDYKKM2LZXEQLhPLEgZZWhvSEC1iE1wBexpl8P-Cxwc,32991
 autogluon/timeseries/models/multi_window/__init__.py,sha256=Bq7AT2Jxdd4WNqmjTdzeqgNiwn1NCyWp4tBIWaM-zfI,60
-autogluon/timeseries/models/multi_window/multi_window_model.py,sha256=Thge05cLytJoOpShE7g1MuNa-qlZWUrSvaO0aCbKQbA,11348
+autogluon/timeseries/models/multi_window/multi_window_model.py,sha256=HiujLv8MJ31fWxRM5iXG2PzobFn4Mus0nJPu0MP2Rw4,11374
 autogluon/timeseries/trainer/__init__.py,sha256=lxiOT-Gc6BEnr_yWQqra85kEngeM_wtH2SCaRbmC_qE,170
 autogluon/timeseries/trainer/abstract_trainer.py,sha256=2nPLskmbOGRzkj6ttX0tHVkj9h2Y72MHaZy7L78MBZQ,59100
 autogluon/timeseries/trainer/auto_trainer.py,sha256=psJFZBwWWPlLjNwAgvO4OUJXsRW1sTN2YS9a4pdoeoE,3344
@@ -51,11 +52,11 @@ autogluon/timeseries/utils/datetime/base.py,sha256=MsqIHY14m3QMjSwwtE7Uo1oNwepWU
 autogluon/timeseries/utils/datetime/lags.py,sha256=kcU4liKbHj7KP2ajNU-KLZ8OYSU35EgT4kJjZNSw0Zg,5875
 autogluon/timeseries/utils/datetime/seasonality.py,sha256=kgK_ukw2wCviEB7CZXRVC5HZpBJZu9IsRrvCJ9E_rOE,755
 autogluon/timeseries/utils/datetime/time_features.py,sha256=pROkYyxETQ8rHKfPGhf2paB73C7rWJ2Ui0cCswLqbBg,2562
-autogluon.timeseries-1.0.1b20240408.dist-info/LICENSE,sha256=CeipvOyAZxBGUsFoaFqwkx54aPnIKEtm9a5u2uXxEws,10142
-autogluon.timeseries-1.0.1b20240408.dist-info/METADATA,sha256=6bvEjMigJQz6jN2Ecj2VU9rc-mZC2WNNVlMSFLKxrBk,12685
-autogluon.timeseries-1.0.1b20240408.dist-info/NOTICE,sha256=7nPQuj8Kp-uXsU0S5so3-2dNU5EctS5hDXvvzzehd7E,114
-autogluon.timeseries-1.0.1b20240408.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-autogluon.timeseries-1.0.1b20240408.dist-info/namespace_packages.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
-autogluon.timeseries-1.0.1b20240408.dist-info/top_level.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
-autogluon.timeseries-1.0.1b20240408.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-autogluon.timeseries-1.0.1b20240408.dist-info/RECORD,,
+autogluon.timeseries-1.1.0b20240409.dist-info/LICENSE,sha256=CeipvOyAZxBGUsFoaFqwkx54aPnIKEtm9a5u2uXxEws,10142
+autogluon.timeseries-1.1.0b20240409.dist-info/METADATA,sha256=9so2n3jb0bCI51fpMa01ZCBlBKYr1TTBof2SEaS7XN8,12543
+autogluon.timeseries-1.1.0b20240409.dist-info/NOTICE,sha256=7nPQuj8Kp-uXsU0S5so3-2dNU5EctS5hDXvvzzehd7E,114
+autogluon.timeseries-1.1.0b20240409.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+autogluon.timeseries-1.1.0b20240409.dist-info/namespace_packages.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
+autogluon.timeseries-1.1.0b20240409.dist-info/top_level.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
+autogluon.timeseries-1.1.0b20240409.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+autogluon.timeseries-1.1.0b20240409.dist-info/RECORD,,