PyPI - autogluon.timeseries - Versions diffs - 1.1.2b20240818__tar.gz → 1.1.2b20240820__tar.gz - Mend

@@ -222,18 +222,22 @@ def seasonal_naive_forecast(
 ) -> pd.DataFrame:
     """Generate seasonal naive forecast, predicting the last observed value from the same period."""
-    def numpy_ffill(arr: np.ndarray) -> np.ndarray:
-        """Fast implementation of forward fill in numpy."""
+    def numpy_fillna(arr: np.ndarray) -> np.ndarray:
+        """Fast implementation of forward fill + avg fill in numpy."""
+        # First apply forward fill
         idx = np.arange(len(arr))
         mask = np.isnan(arr)
         idx[mask] = 0
-        return arr[np.maximum.accumulate(idx)]
+        arr_filled = arr[np.maximum.accumulate(idx)]
+        # Leading NaNs are filled with the mean
+        arr_filled[np.isnan(arr_filled)] = np.nanmean(arr_filled)
+        return arr_filled
     forecast = {}
     # At least seasonal_period + 2 values are required to compute sigma for seasonal naive
     if len(target) > seasonal_period + 1 and seasonal_period > 1:
         if np.isnan(target[-(seasonal_period + 2) :]).any():
-            target = numpy_ffill(target)
+            target = numpy_fillna(target)
         indices = [len(target) - seasonal_period + k % seasonal_period for k in range(prediction_length)]
         forecast["mean"] = target[indices]

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: autogluon.timeseries
-Version: 1.1.2b20240818
+Version: 1.1.2b20240820
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community

@@ -365,7 +365,7 @@ class AbstractMLForecastModel(AbstractTimeSeriesModel):
             Seasonal naive forecast for short series, if there are any in the dataset.
         """
         ts_lengths = data.num_timesteps_per_item()
-        short_series = ts_lengths.index[ts_lengths <= self._sum_of_differences + 1]
+        short_series = ts_lengths.index[ts_lengths <= self._sum_of_differences]
         if len(short_series) > 0:
             logger.warning(
                 f"Warning: {len(short_series)} time series ({len(short_series) / len(ts_lengths):.1%}) are shorter "

@@ -1098,6 +1098,10 @@ class TimeSeriesPredictor(TimeSeriesPredictorDeprecatedMixin):
             raise ValueError("`path` cannot be None or empty in load().")
         path: str = setup_outputdir(path, warn_if_exist=False)
+        predictor_path = Path(path) / cls.predictor_file_name
+        if not predictor_path.exists():
+            raise FileNotFoundError(f"No such file '{predictor_path}'")
         try:
             version_saved = cls._load_version_file(path=path)
         except:
@@ -1116,7 +1120,7 @@ class TimeSeriesPredictor(TimeSeriesPredictorDeprecatedMixin):
         logger.info(f"Loading predictor from path {path}")
         learner = AbstractLearner.load(path)
-        predictor = load_pkl.load(path=os.path.join(learner.path, cls.predictor_file_name))
+        predictor = load_pkl.load(path=str(predictor_path))
         predictor._learner = learner
         predictor.path = learner.path
         return predictor

@@ -1,3 +1,3 @@
 """This is the autogluon version file."""
-__version__ = '1.1.2b20240818'
+__version__ = '1.1.2b20240820'
 __lite__ = False

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: autogluon.timeseries
-Version: 1.1.2b20240818
+Version: 1.1.2b20240820
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community

autogluon.timeseries 1.1.2b20240818tar.gz → 1.1.2b20240820tar.gz

@@ -16,9 +16,9 @@ fugue>=0.9.0
 tqdm<5,>=4.38
 orjson~=3.9
 tensorboard<3,>=2.9
-autogluon.core[raytune]==1.1.2b20240818
-autogluon.common==1.1.2b20240818
-autogluon.tabular[catboost,lightgbm,xgboost]==1.1.2b20240818
+autogluon.core[raytune]==1.1.2b20240820
+autogluon.common==1.1.2b20240820
+autogluon.tabular[catboost,lightgbm,xgboost]==1.1.2b20240820
 [all]
 optimum[onnxruntime]<1.19,>=1.17