autogluon.timeseries 1.2.1b20250210__tar.gz → 1.2.1b20250212__tar.gz

{autogluon.timeseries-1.2.1b20250210 → autogluon.timeseries-1.2.1b20250212}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: autogluon.timeseries
-Version: 1.2.1b20250210
+Version: 1.2.1b20250212
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community

{autogluon.timeseries-1.2.1b20250210 → autogluon.timeseries-1.2.1b20250212}/src/autogluon/timeseries/models/local/statsforecast.py

@@ -51,15 +51,7 @@ class AbstractProbabilisticStatsForecastModel(AbstractStatsForecastModel):
         time_series: pd.Series,
         local_model_args: dict,
     ) -> pd.DataFrame:
-        # Code does conversion between confidence levels and quantiles
-        levels = []
-        quantile_to_key = {}
-        for q in self.quantile_levels:
-            level = round(abs(q - 0.5) * 200, 1)
-            suffix = "lo" if q < 0.5 else "hi"
-            levels.append(level)
-            quantile_to_key[str(q)] = f"{suffix}-{level}"
-        levels = sorted(list(set(levels)))
+        levels, quantile_to_key = self._get_confidence_levels()
 
         forecast = self._get_local_model(local_model_args).forecast(
             h=self.prediction_length, y=time_series.values.ravel(), level=levels
@@ -69,6 +61,18 @@ class AbstractProbabilisticStatsForecastModel(AbstractStatsForecastModel):
             predictions[q] = forecast[key]
         return pd.DataFrame(predictions)
 
+    def _get_confidence_levels(self) -> tuple[list[float], dict[str, str]]:
+        """Get StatsForecast compatible levels from quantiles"""
+        levels = []
+        quantile_to_key = {}
+        for q in self.quantile_levels:
+            level = round(abs(q - 0.5) * 200, 1)
+            suffix = "lo" if q < 0.5 else "hi"
+            levels.append(level)
+            quantile_to_key[str(q)] = f"{suffix}-{level}"
+        levels = sorted(list(set(levels)))
+        return levels, quantile_to_key
+
 
 class AutoARIMAModel(AbstractProbabilisticStatsForecastModel):
     """Automatically tuned ARIMA model.

{autogluon.timeseries-1.2.1b20250210 → autogluon.timeseries-1.2.1b20250212}/src/autogluon/timeseries/version.py

@@ -1,4 +1,4 @@
 """This is the autogluon version file."""
 
-__version__ = "1.2.1b20250210"
+__version__ = "1.2.1b20250212"
 __lite__ = False

{autogluon.timeseries-1.2.1b20250210 → autogluon.timeseries-1.2.1b20250212}/src/autogluon.timeseries.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: autogluon.timeseries
-Version: 1.2.1b20250210
+Version: 1.2.1b20250212
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community

{autogluon.timeseries-1.2.1b20250210 → autogluon.timeseries-1.2.1b20250212}/src/autogluon.timeseries.egg-info/requires.txt

@@ -17,9 +17,9 @@ fugue>=0.9.0
 tqdm<5,>=4.38
 orjson~=3.9
 tensorboard<3,>=2.9
-autogluon.core[raytune]==1.2.1b20250210
-autogluon.common==1.2.1b20250210
-autogluon.tabular[catboost,lightgbm,xgboost]==1.2.1b20250210
+autogluon.core[raytune]==1.2.1b20250212
+autogluon.common==1.2.1b20250212
+autogluon.tabular[catboost,lightgbm,xgboost]==1.2.1b20250212
 
 [all]