autogluon.timeseries 1.1.0b20240409__tar.gz → 1.1.0b20240411__tar.gz

{autogluon.timeseries-1.1.0b20240409 → autogluon.timeseries-1.1.0b20240411}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.1
 Name: autogluon.timeseries
-Version: 1.1.0b20240409
-Summary: AutoML for Image, Text, and Tabular Data
+Version: 1.1.0b20240411
+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-1.1.0b20240409 → autogluon.timeseries-1.1.0b20240411}/src/autogluon/timeseries/dataset/ts_dataframe.py

@@ -759,12 +759,6 @@ class TimeSeriesDataFrame(pd.DataFrame, TimeSeriesDataFrameDeprecatedMixin):
                 2019-02-07     4.0
 
         """
-        if self.freq is None:
-            raise ValueError(
-                "Please make sure that all time series have a regular index before calling `fill_missing_values`"
-                "(for example, using the `convert_frequency` method)."
-            )
-
         # Convert to pd.DataFrame for faster processing
         df = pd.DataFrame(self)
 
@@ -772,6 +766,12 @@ class TimeSeriesDataFrame(pd.DataFrame, TimeSeriesDataFrameDeprecatedMixin):
         if not df.isna().any(axis=None):
             return self
 
+        if not self.index.is_monotonic_increasing:
+            logger.warning(
+                "Trying to fill missing values in an unsorted dataframe. "
+                "It is highly recommended to call `ts_df.sort_index()` before calling `ts_df.fill_missing_values()`"
+            )
+
         grouped_df = df.groupby(level=ITEMID, sort=False, group_keys=False)
         if method == "auto":
             filled_df = grouped_df.ffill()

{autogluon.timeseries-1.1.0b20240409 → autogluon.timeseries-1.1.0b20240411}/src/autogluon/timeseries/learner.py

@@ -43,6 +43,7 @@ class TimeSeriesLearner(AbstractLearner):
         self.prediction_length = prediction_length
         self.quantile_levels = kwargs.get("quantile_levels", [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9])
         self.cache_predictions = cache_predictions
+        self.freq: Optional[str] = None
 
         self.feature_generator = TimeSeriesFeatureGenerator(
             target=self.target, known_covariates_names=self.known_covariates_names
@@ -87,6 +88,8 @@ class TimeSeriesLearner(AbstractLearner):
         if val_data is not None:
             val_data = self.feature_generator.transform(val_data, data_frame_name="tuning_data")
 
+        self.freq = train_data.freq
+
         trainer_init_kwargs = kwargs.copy()
         trainer_init_kwargs.update(
             dict(
@@ -155,7 +158,9 @@ class TimeSeriesLearner(AbstractLearner):
                 f"known_covariates are missing information for the following item_ids: {reprlib.repr(missing_item_ids.to_list())}."
             )
 
-        forecast_index = get_forecast_horizon_index_ts_dataframe(data, prediction_length=self.prediction_length)
+        forecast_index = get_forecast_horizon_index_ts_dataframe(
+            data, prediction_length=self.prediction_length, freq=self.freq
+        )
         try:
             known_covariates = known_covariates.loc[forecast_index]
         except KeyError:

{autogluon.timeseries-1.1.0b20240409 → autogluon.timeseries-1.1.0b20240411}/src/autogluon/timeseries/models/autogluon_tabular/mlforecast.py

@@ -252,6 +252,11 @@ 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)
 
@@ -474,7 +479,7 @@ class DirectTabularModel(AbstractMLForecastModel):
         if known_covariates is not None:
             data_future = known_covariates.copy()
         else:
-            future_index = get_forecast_horizon_index_ts_dataframe(data, self.prediction_length)
+            future_index = get_forecast_horizon_index_ts_dataframe(data, self.prediction_length, freq=self.freq)
             data_future = pd.DataFrame(columns=[self.target], index=future_index, dtype="float32")
         # MLForecast raises exception of target contains NaN. We use inf as placeholder, replace them by NaN afterwards
         data_future[self.target] = float("inf")
@@ -606,7 +611,7 @@ class RecursiveTabularModel(AbstractMLForecastModel):
         if self._max_ts_length is not None:
             new_df = self._shorten_all_series(new_df, self._max_ts_length)
         if known_covariates is None:
-            future_index = get_forecast_horizon_index_ts_dataframe(data, self.prediction_length)
+            future_index = get_forecast_horizon_index_ts_dataframe(data, self.prediction_length, freq=self.freq)
             known_covariates = pd.DataFrame(columns=[self.target], index=future_index, dtype="float32")
         X_df = self._to_mlforecast_df(known_covariates, data.static_features, include_target=False)
         # If both covariates & static features are missing, set X_df = None to avoid exception from MLForecast

{autogluon.timeseries-1.1.0b20240409 → autogluon.timeseries-1.1.0b20240411}/src/autogluon/timeseries/models/chronos/model.py

@@ -330,7 +330,7 @@ class ChronosModel(AbstractTimeSeriesModel):
         df = pd.DataFrame(
             np.concatenate([mean, quantiles], axis=1),
             columns=["mean"] + [str(q) for q in self.quantile_levels],
-            index=get_forecast_horizon_index_ts_dataframe(data, self.prediction_length),
+            index=get_forecast_horizon_index_ts_dataframe(data, self.prediction_length, freq=self.freq),
         )
 
         return TimeSeriesDataFrame(df)

{autogluon.timeseries-1.1.0b20240409 → autogluon.timeseries-1.1.0b20240411}/src/autogluon/timeseries/models/gluonts/abstract_gluonts.py

@@ -46,6 +46,7 @@ class SimpleGluonTSDataset(GluonTSDataset):
     def __init__(
         self,
         target_df: TimeSeriesDataFrame,
+        freq: str,
         target_column: str = "target",
         feat_static_cat: Optional[np.ndarray] = None,
         feat_static_real: Optional[np.ndarray] = None,
@@ -57,7 +58,6 @@ class SimpleGluonTSDataset(GluonTSDataset):
         prediction_length: int = None,
     ):
         assert target_df is not None
-        assert target_df.freq, "Initializing GluonTS data sets without freq is not allowed"
         # Convert TimeSeriesDataFrame to pd.Series for faster processing
         self.target_array = target_df[target_column].to_numpy(np.float32)
         self.feat_static_cat = self._astype(feat_static_cat, dtype=np.int64)
@@ -66,7 +66,7 @@ class SimpleGluonTSDataset(GluonTSDataset):
         self.feat_dynamic_real = self._astype(feat_dynamic_real, dtype=np.float32)
         self.past_feat_dynamic_cat = self._astype(past_feat_dynamic_cat, dtype=np.int64)
         self.past_feat_dynamic_real = self._astype(past_feat_dynamic_real, dtype=np.float32)
-        self.freq = self._to_gluonts_freq(target_df.freq)
+        self.freq = self._to_gluonts_freq(freq)
 
         # Necessary to compute indptr for known_covariates at prediction time
         self.includes_future = includes_future
@@ -234,13 +234,6 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
 
     def _deferred_init_params_aux(self, dataset: TimeSeriesDataFrame) -> None:
         """Update GluonTS specific parameters with information available only at training time."""
-        self.freq = dataset.freq or self.freq
-        if not self.freq:
-            raise ValueError(
-                "Dataset frequency not provided in the dataset, fit arguments or "
-                "during initialization. Please provide a `freq` string to `fit`."
-            )
-
         model_params = self._get_model_params()
         disable_static_features = model_params.get("disable_static_features", False)
         if not disable_static_features:
@@ -502,6 +495,7 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
 
             return SimpleGluonTSDataset(
                 target_df=time_series_df[[self.target]],
+                freq=self.freq,
                 target_column=self.target,
                 feat_static_cat=feat_static_cat,
                 feat_static_real=feat_static_real,
@@ -592,7 +586,7 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
             predicted_targets = self._predict_gluonts_forecasts(data, known_covariates=known_covariates, **kwargs)
             df = self._gluonts_forecasts_to_data_frame(
                 predicted_targets,
-                forecast_index=get_forecast_horizon_index_ts_dataframe(data, self.prediction_length),
+                forecast_index=get_forecast_horizon_index_ts_dataframe(data, self.prediction_length, freq=self.freq),
             )
         return df
 

{autogluon.timeseries-1.1.0b20240409 → autogluon.timeseries-1.1.0b20240411}/src/autogluon/timeseries/models/local/abstract_local_model.py

@@ -166,7 +166,7 @@ class AbstractLocalModel(AbstractTimeSeriesModel):
                 f"({fraction_failed_models:.1%}). Fallback model SeasonalNaive was used for these time series."
             )
         predictions_df = pd.concat([pred for pred, _ in predictions_with_flags])
-        predictions_df.index = get_forecast_horizon_index_ts_dataframe(data, self.prediction_length)
+        predictions_df.index = get_forecast_horizon_index_ts_dataframe(data, self.prediction_length, freq=self.freq)
         return TimeSeriesDataFrame(predictions_df)
 
     def score_and_cache_oof(
@@ -185,9 +185,9 @@ class AbstractLocalModel(AbstractTimeSeriesModel):
         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(
@@ -196,7 +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-1.1.0b20240409 → autogluon.timeseries-1.1.0b20240411}/src/autogluon/timeseries/utils/forecast.py

@@ -1,4 +1,5 @@
 import warnings
+from typing import Optional
 
 import numpy as np
 import pandas as pd
@@ -15,7 +16,9 @@ def get_forecast_horizon_index_single_time_series(
 
 
 def get_forecast_horizon_index_ts_dataframe(
-    ts_dataframe: TimeSeriesDataFrame, prediction_length: int
+    ts_dataframe: TimeSeriesDataFrame,
+    prediction_length: int,
+    freq: Optional[str] = None,
 ) -> pd.MultiIndex:
     """For each item in the dataframe, get timestamps for the next prediction_length many time steps into the future.
 
@@ -26,7 +29,9 @@ def get_forecast_horizon_index_ts_dataframe(
     last = ts_dataframe.reset_index()[[ITEMID, TIMESTAMP]].groupby(by=ITEMID, sort=False, as_index=False).last()
     item_ids = np.repeat(last[ITEMID], prediction_length)
 
-    offset = pd.tseries.frequencies.to_offset(ts_dataframe.freq)
+    if freq is None:
+        freq = ts_dataframe.freq
+    offset = pd.tseries.frequencies.to_offset(freq)
     last_ts = pd.DatetimeIndex(last[TIMESTAMP])
     # Non-vectorized offsets like BusinessDay may produce a PerformanceWarning - we filter them
     with warnings.catch_warnings():

{autogluon.timeseries-1.1.0b20240409 → autogluon.timeseries-1.1.0b20240411}/src/autogluon/timeseries/version.py

@@ -1,3 +1,3 @@
 """This is the autogluon version file."""
-__version__ = '1.1.0b20240409'
+__version__ = '1.1.0b20240411'
 __lite__ = False

{autogluon.timeseries-1.1.0b20240409 → autogluon.timeseries-1.1.0b20240411}/src/autogluon.timeseries.egg-info/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.1
 Name: autogluon.timeseries
-Version: 1.1.0b20240409
-Summary: AutoML for Image, Text, and Tabular Data
+Version: 1.1.0b20240411
+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-1.1.0b20240409 → autogluon.timeseries-1.1.0b20240411}/src/autogluon.timeseries.egg-info/requires.txt

@@ -16,9 +16,9 @@ utilsforecast<0.0.11,>=0.0.10
 tqdm<5,>=4.38
 orjson~=3.9
 tensorboard<3,>=2.9
-autogluon.core[raytune]==1.1.0b20240409
-autogluon.common==1.1.0b20240409
-autogluon.tabular[catboost,lightgbm,xgboost]==1.1.0b20240409
+autogluon.core[raytune]==1.1.0b20240411
+autogluon.common==1.1.0b20240411
+autogluon.tabular[catboost,lightgbm,xgboost]==1.1.0b20240411
 
 [all]
 optimum[onnxruntime]<1.19,>=1.17