autogluon.timeseries 1.1.2b20241016__py3-none-any.whl → 1.1.2b20241018__py3-none-any.whl

autogluon/timeseries/dataset/ts_dataframe.py

@@ -7,6 +7,7 @@ import reprlib
 from collections.abc import Iterable
 from itertools import islice
 from pathlib import Path
+from pprint import pformat
 from typing import Any, List, Optional, Tuple, Type, Union
 
 import pandas as pd
@@ -476,28 +477,82 @@ class TimeSeriesDataFrame(pd.DataFrame, TimeSeriesDataFrameDeprecatedMixin):
 
         self._static_features = value
 
+    def infer_frequency(self, num_items: Optional[int] = 100, raise_if_irregular: bool = False) -> str:
+        """Infer the time series frequency based on the timestamps of the observations.
+
+        Parameters
+        ----------
+        num_items : int or None, default = 100
+            Number of items (individual time series) randomly selected to infer the frequency. Lower values speed up
+            the method, but increase the chance that some items with invalid frequency are missed by subsampling.
+
+            If set to `None`, all items will be used for inferring the frequency.
+        raise_if_irregular : bool, default = False
+            If True, an exception will be raised if some items have an irregular frequency, or if different items have
+            different frequencies.
+
+        Returns
+        -------
+        freq : str
+            If all time series have a regular frequency, returns a pandas-compatible `frequency alias <https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases>`_.
+
+            If some items have an irregular frequency or if different items have different frequencies, returns string
+            `IRREG`.
+        """
+
+        df = pd.DataFrame(self)
+        if num_items is not None:
+            all_item_ids = self.item_ids
+            if len(all_item_ids) > num_items:
+                items_subset = all_item_ids.to_series().sample(n=num_items, random_state=123)
+                df = df.loc[items_subset]
+
+        candidate_freq = df.index.levels[1].freq
+        index_df = df.index.to_frame(index=False)
+
+        def get_freq(series: pd.Series) -> Optional[str]:
+            dt_index = pd.DatetimeIndex(series)
+            inferred_freq = dt_index.inferred_freq
+            # Fallback option: maybe original index has a `freq` attribute that pandas fails to infer (e.g., 'SME')
+            if inferred_freq is None and candidate_freq is not None:
+                try:
+                    # If this line does not raise an exception, then candidate_freq is a compatible frequency
+                    dt_index.freq = candidate_freq
+                except ValueError:
+                    inferred_freq = None
+                else:
+                    inferred_freq = candidate_freq
+            return inferred_freq
+
+        freq_for_each_item = index_df.groupby(ITEMID, sort=False).agg(get_freq)[TIMESTAMP]
+        freq = freq_for_each_item.iloc[0]
+        if len(set(freq_for_each_item)) > 1 or freq is None:
+            if raise_if_irregular:
+                items_with_irregular_freq = freq_for_each_item[pd.isnull(freq_for_each_item)]
+                if len(items_with_irregular_freq) > 0:
+                    raise ValueError(
+                        "Cannot infer frequency. Items with irregular frequency: "
+                        f"{pformat(items_with_irregular_freq.index.tolist())}"
+                    )
+                else:
+                    raise ValueError(
+                        "Cannot infer frequency. Multiple frequencies detected in the dataset: "
+                        f"{freq_for_each_item.unique().tolist()}"
+                    )
+            return IRREGULAR_TIME_INDEX_FREQSTR
+        else:
+            return pd.tseries.frequencies.to_offset(freq).freqstr
+
     @property
     def freq(self):
-        if self._cached_freq is not None and self._cached_freq == IRREGULAR_TIME_INDEX_FREQSTR:
+        if self._cached_freq is None:
+            self._cached_freq = self.infer_frequency()
+
+        if self._cached_freq == IRREGULAR_TIME_INDEX_FREQSTR:
             return None  # irregularly sampled time series
-        elif self._cached_freq:
+        else:
             return self._cached_freq
 
-        def get_freq(series):
-            return series.index.freq or series.index.inferred_freq
-
-        # check the frequencies of the first 100 items to see if frequencies are consistent and
-        # can be inferred
-        freq_for_each_series = [get_freq(self.loc[idx]) for idx in self.item_ids[:100]]
-        freq = freq_for_each_series[0]
-        if len(set(freq_for_each_series)) > 1 or freq is None:
-            self._cached_freq = IRREGULAR_TIME_INDEX_FREQSTR
-            return None
-
-        freq = freq.freqstr if isinstance(freq, pd._libs.tslibs.BaseOffset) else freq
-        self._cached_freq = freq
-        return freq
-
     @property
     def num_items(self):
         return len(self.item_ids)

autogluon/timeseries/predictor.py

@@ -252,7 +252,7 @@ class TimeSeriesPredictor(TimeSeriesPredictorDeprecatedMixin):
         self,
         data: Union[TimeSeriesDataFrame, pd.DataFrame, Path, str],
         name: str = "data",
-    ) -> "TimeSeriesDataFrame":
+    ) -> TimeSeriesDataFrame:
         if isinstance(data, TimeSeriesDataFrame):
             return data
         elif isinstance(data, (pd.DataFrame, Path, str)):
@@ -299,7 +299,10 @@ class TimeSeriesPredictor(TimeSeriesPredictorDeprecatedMixin):
 
         # Ensure that data has a regular frequency that matches the predictor frequency
         if self.freq is None:
-            if df.freq is None:
+            try:
+                # Use all items for inferring the frequency
+                self.freq = df.infer_frequency(num_items=None, raise_if_irregular=True)
+            except ValueError:
                 raise ValueError(
                     f"Frequency of {name} is not provided and cannot be inferred. Please set the expected data "
                     f"frequency when creating the predictor with `TimeSeriesPredictor(freq=...)` or ensure that "

autogluon/timeseries/version.py

@@ -1,3 +1,3 @@
 """This is the autogluon version file."""
-__version__ = '1.1.2b20241016'
+__version__ = '1.1.2b20241018'
 __lite__ = False

{autogluon.timeseries-1.1.2b20241016.dist-info → autogluon.timeseries-1.1.2b20241018.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: autogluon.timeseries
-Version: 1.1.2b20241016
+Version: 1.1.2b20241018
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community
@@ -52,9 +52,9 @@ Requires-Dist: fugue>=0.9.0
 Requires-Dist: tqdm<5,>=4.38
 Requires-Dist: orjson~=3.9
 Requires-Dist: tensorboard<3,>=2.9
-Requires-Dist: autogluon.core[raytune]==1.1.2b20241016
-Requires-Dist: autogluon.common==1.1.2b20241016
-Requires-Dist: autogluon.tabular[catboost,lightgbm,xgboost]==1.1.2b20241016
+Requires-Dist: autogluon.core[raytune]==1.1.2b20241018
+Requires-Dist: autogluon.common==1.1.2b20241018
+Requires-Dist: autogluon.tabular[catboost,lightgbm,xgboost]==1.1.2b20241018
 Provides-Extra: all
 Requires-Dist: optimum[onnxruntime]<1.19,>=1.17; extra == "all"
 Provides-Extra: chronos-onnx

{autogluon.timeseries-1.1.2b20241016.dist-info → autogluon.timeseries-1.1.2b20241018.dist-info}/RECORD

@@ -1,14 +1,14 @@
-autogluon.timeseries-1.1.2b20241016-py3.8-nspkg.pth,sha256=cQGwpuGPqg1GXscIwt-7PmME1OnSpD-7ixkikJ31WAY,554
+autogluon.timeseries-1.1.2b20241018-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=NXhftyqMD8Bl1QHIBN82UKP0UlCV_ACughZqkmMf4oY,14043
-autogluon/timeseries/predictor.py,sha256=3HdPaxvhS-FatQ0Rf5xvMw5NgU3BXlt8m8nwRgC-b2U,84399
+autogluon/timeseries/predictor.py,sha256=BUjFX5I_tgim9oo43cRgLBAxKY1JfduKtHQxY8BPC-Y,84561
 autogluon/timeseries/splitter.py,sha256=eghGwAAN2_cxGk5aJBILgjGWtLzjxJcytMy49gg_q18,3061
-autogluon/timeseries/version.py,sha256=lDd_TludjpIJTs7S7Uij_tnVikz8lmKZCbK6TpyU69k,90
+autogluon/timeseries/version.py,sha256=vN9WGRyG5Ww78Etq6u3pGSVbJRy2Z_B1iLwyBmf5mNY,90
 autogluon/timeseries/configs/__init__.py,sha256=BTtHIPCYeGjqgOcvqb8qPD4VNX-ICKOg6wnkew1cPOE,98
 autogluon/timeseries/configs/presets_configs.py,sha256=94-yL9teDHKs2irWjP3kpewI7FE1ChYCgEgz9XHJ6gc,1965
 autogluon/timeseries/dataset/__init__.py,sha256=UvnhAN5tjgxXTHoZMQDy64YMDj4Xxa68yY7NP4vAw0o,81
-autogluon/timeseries/dataset/ts_dataframe.py,sha256=QgCwzRx10CRzeWzQREX_zUDAl77-lkdNjM0bT3kK8NU,45595
+autogluon/timeseries/dataset/ts_dataframe.py,sha256=w7wEue_ZALNmvkGSEAnYE-jqbGj8fdsT9YvHpGY9URY,48296
 autogluon/timeseries/metrics/__init__.py,sha256=KzgXNj5or7RB_uadjgC8p5gxyV26zjj2hT58OmvnfmA,1875
 autogluon/timeseries/metrics/abstract.py,sha256=9xCFQ3NaR1C0hn01M7oBd72a_CiNV-w6QFcRjwUbKYI,8183
 autogluon/timeseries/metrics/point.py,sha256=xy8sKrBbuxZ7yTW21TDPayKnEj2FBj1AEseJxUdneqE,13399
@@ -55,11 +55,11 @@ autogluon/timeseries/utils/datetime/base.py,sha256=3NdsH3NDq4cVAOSoy3XpaNixyNlbj
 autogluon/timeseries/utils/datetime/lags.py,sha256=GoLtvcZ8oKb3QkoBJ9E59LSPLOP7Qjxrr2UmMSZgjyw,5909
 autogluon/timeseries/utils/datetime/seasonality.py,sha256=h_4w00iEytAz_N_EpCENQ8RCXy7KQITczrYjBgVqWkQ,764
 autogluon/timeseries/utils/datetime/time_features.py,sha256=PAXbYbQ0z_5GFbkxSNi41zLY_2-U3x0Ynm1m_WhdtGc,2572
-autogluon.timeseries-1.1.2b20241016.dist-info/LICENSE,sha256=CeipvOyAZxBGUsFoaFqwkx54aPnIKEtm9a5u2uXxEws,10142
-autogluon.timeseries-1.1.2b20241016.dist-info/METADATA,sha256=7SY4Fl3Jx7tF8O-a9EZmiko_uVUOP-eiworItj8xwJs,12355
-autogluon.timeseries-1.1.2b20241016.dist-info/NOTICE,sha256=7nPQuj8Kp-uXsU0S5so3-2dNU5EctS5hDXvvzzehd7E,114
-autogluon.timeseries-1.1.2b20241016.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
-autogluon.timeseries-1.1.2b20241016.dist-info/namespace_packages.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
-autogluon.timeseries-1.1.2b20241016.dist-info/top_level.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
-autogluon.timeseries-1.1.2b20241016.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-autogluon.timeseries-1.1.2b20241016.dist-info/RECORD,,
+autogluon.timeseries-1.1.2b20241018.dist-info/LICENSE,sha256=CeipvOyAZxBGUsFoaFqwkx54aPnIKEtm9a5u2uXxEws,10142
+autogluon.timeseries-1.1.2b20241018.dist-info/METADATA,sha256=tHt8_6riIMPcLakUBZ7zCHVMIsQl15u0x2lFa9hDFTQ,12355
+autogluon.timeseries-1.1.2b20241018.dist-info/NOTICE,sha256=7nPQuj8Kp-uXsU0S5so3-2dNU5EctS5hDXvvzzehd7E,114
+autogluon.timeseries-1.1.2b20241018.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
+autogluon.timeseries-1.1.2b20241018.dist-info/namespace_packages.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
+autogluon.timeseries-1.1.2b20241018.dist-info/top_level.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
+autogluon.timeseries-1.1.2b20241018.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+autogluon.timeseries-1.1.2b20241018.dist-info/RECORD,,