autogluon.timeseries 1.1.0b20240411__tar.gz → 1.1.0b20240413__tar.gz

{autogluon.timeseries-1.1.0b20240411 → autogluon.timeseries-1.1.0b20240413}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: autogluon.timeseries
-Version: 1.1.0b20240411
+Version: 1.1.0b20240413
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community

{autogluon.timeseries-1.1.0b20240411 → autogluon.timeseries-1.1.0b20240413}/setup.py

@@ -31,7 +31,7 @@ install_requires = [
     "transformers[sentencepiece]",  # version range defined in `core/_setup_utils.py`
     "accelerate",  # version range defined in `core/_setup_utils.py`
     "statsmodels>=0.13.0,<0.15",
-    "gluonts>=0.14.0,<0.15",
+    "gluonts>=0.14.0,<0.14.4",  # 0.14.4 caps pandas<2.2
     "networkx",  # version range defined in `core/_setup_utils.py`
     # TODO: update statsforecast to v1.5.0 - resolve antlr4-python3-runtime dependency clash with multimodal
     "statsforecast>=1.4.0,<1.5",

{autogluon.timeseries-1.1.0b20240411 → autogluon.timeseries-1.1.0b20240413}/src/autogluon/timeseries/dataset/ts_dataframe.py

@@ -134,7 +134,7 @@ class TimeSeriesDataFrame(pd.DataFrame, TimeSeriesDataFrameDeprecatedMixin):
     ----------
     freq : str
         A pandas-compatible string describing the frequency of the time series. For example ``"D"`` for daily data,
-        ``"H"`` for hourly data, etc. This attribute is determined automatically based on the timestamps. For the full
+        ``"h"`` for hourly data, etc. This attribute is determined automatically based on the timestamps. For the full
         list of possible values, see `pandas documentation <https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases>`_.
     num_items : int
         Number of items (time series) in the data set.
@@ -961,12 +961,12 @@ class TimeSeriesDataFrame(pd.DataFrame, TimeSeriesDataFrameDeprecatedMixin):
                 2021-06-30     6.0
                 2021-09-30     7.0
                 2021-12-31     8.0
-        >>> ts_df.convert_frequency("Y")
+        >>> ts_df.convert_frequency("YE")
                             target
         item_id timestamp
         0       2020-12-31     2.5
                 2021-12-31     6.5
-        >>> ts_df.convert_frequency("Y", agg_numeric="sum")
+        >>> ts_df.convert_frequency("YE", agg_numeric="sum")
                             target
         item_id timestamp
         0       2020-12-31    10.0

{autogluon.timeseries-1.1.0b20240411 → autogluon.timeseries-1.1.0b20240413}/src/autogluon/timeseries/learner.py

@@ -250,8 +250,8 @@ class TimeSeriesLearner(AbstractLearner):
                     raise ValueError(f"Feature {fn} not found in covariate metadata or the dataset.")
 
         if len(set(features)) < len(features):
-            logger.warning(
-                "Duplicate feature names provided to compute feature importance. This will lead to unexpected behavior. "
+            raise ValueError(
+                "Duplicate feature names provided to compute feature importance. "
                 "Please provide unique feature names across both static features and covariates."
             )
 

{autogluon.timeseries-1.1.0b20240411 → autogluon.timeseries-1.1.0b20240413}/src/autogluon/timeseries/models/abstract/abstract_timeseries_model.py

@@ -31,7 +31,7 @@ class AbstractTimeSeriesModel(AbstractModel):
         If None, a new unique time-stamped directory is chosen.
     freq: str
         Frequency string (cf. gluonts frequency strings) describing the frequency
-        of the time series data. For example, "H" for hourly or "D" for daily data.
+        of the time series data. For example, "h" for hourly or "D" for daily data.
     prediction_length: int
         Length of the prediction horizon, i.e., the number of time steps the model
         is fit to forecast.

{autogluon.timeseries-1.1.0b20240411 → autogluon.timeseries-1.1.0b20240413}/src/autogluon/timeseries/models/autogluon_tabular/mlforecast.py

@@ -337,7 +337,7 @@ 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]
+        short_series = ts_lengths.index[ts_lengths <= self._sum_of_differences + 1]
         if len(short_series) > 0:
             logger.warning(
                 f"Warning: {len(short_series)} time series ({len(short_series) / len(ts_lengths):.1%}) are shorter "

{autogluon.timeseries-1.1.0b20240411 → autogluon.timeseries-1.1.0b20240413}/src/autogluon/timeseries/models/gluonts/abstract_gluonts.py

@@ -15,7 +15,6 @@ from gluonts.dataset.field_names import FieldName
 from gluonts.model.estimator import Estimator as GluonTSEstimator
 from gluonts.model.forecast import Forecast, QuantileForecast, SampleForecast
 from gluonts.model.predictor import Predictor as GluonTSPredictor
-from pandas.tseries.frequencies import to_offset
 from sklearn.compose import ColumnTransformer
 from sklearn.preprocessing import QuantileTransformer, StandardScaler
 
@@ -37,9 +36,6 @@ logger = logging.getLogger(__name__)
 gts_logger = logging.getLogger(gluonts.__name__)
 
 
-GLUONTS_SUPPORTED_OFFSETS = ["Y", "Q", "M", "W", "D", "B", "H", "T", "min", "S"]
-
-
 class SimpleGluonTSDataset(GluonTSDataset):
     """Wrapper for TimeSeriesDataFrame that is compatible with the GluonTS Dataset API."""
 
@@ -66,7 +62,7 @@ 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(freq)
+        self.freq = self._get_freq_for_period(freq)
 
         # Necessary to compute indptr for known_covariates at prediction time
         self.includes_future = includes_future
@@ -89,19 +85,22 @@ class SimpleGluonTSDataset(GluonTSDataset):
             return array.astype(dtype)
 
     @staticmethod
-    def _to_gluonts_freq(freq: str) -> str:
-        # FIXME: GluonTS expects a frequency string, but only supports a limited number of such strings
-        # for feature generation. If the frequency string doesn't match or is not provided, it raises an exception.
-        # Here we bypass this by issuing a default "yearly" frequency, tricking it into not producing
-        # any lags or features.
-        pd_offset = to_offset(freq)
-
-        # normalize freq str to handle peculiarities such as W-SUN
-        offset_base_alias = norm_freq_str(pd_offset)
-        if offset_base_alias not in GLUONTS_SUPPORTED_OFFSETS:
-            return "A"
+    def _get_freq_for_period(freq: str) -> str:
+        """Convert freq to format compatible with pd.Period.
+
+        For example, ME freq must be converted to M when creating a pd.Period.
+        """
+        offset = pd.tseries.frequencies.to_offset(freq)
+        freq_name = norm_freq_str(offset)
+        if freq_name == "SME":
+            # Replace unsupported frequency "SME" with "2W"
+            return "2W"
+        elif freq_name == "bh":
+            # Replace unsupported frequency "bh" with dummy value "Y"
+            return "Y"
         else:
-            return f"{pd_offset.n}{offset_base_alias}"
+            freq_name_for_period = {"YE": "Y", "QE": "Q", "ME": "M"}.get(freq_name, freq_name)
+            return f"{offset.n}{freq_name_for_period}"
 
     def __len__(self):
         return len(self.indptr) - 1  # noqa
@@ -161,6 +160,8 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
     """
 
     gluonts_model_path = "gluon_ts"
+    # we pass dummy freq compatible with pandas 2.1 & 2.2 to GluonTS models
+    _dummy_gluonts_freq = "D"
     # default number of samples for prediction
     default_num_samples: int = 250
     supports_cat_covariates: bool = False
@@ -364,7 +365,7 @@ class AbstractGluonTSModel(AbstractTimeSeriesModel):
         init_args.setdefault("early_stopping_patience", 20)
         init_args.update(
             dict(
-                freq=self.freq,
+                freq=self._dummy_gluonts_freq,
                 prediction_length=self.prediction_length,
                 quantiles=self.quantile_levels,
                 callbacks=self.callbacks,

{autogluon.timeseries-1.1.0b20240411 → autogluon.timeseries-1.1.0b20240413}/src/autogluon/timeseries/models/gluonts/torch/models.py

@@ -423,6 +423,4 @@ class WaveNetModel(AbstractGluonTSModel):
         init_kwargs.setdefault("seasonality", get_seasonality(self.freq))
         init_kwargs.setdefault("time_features", get_time_features_for_frequency(self.freq))
         init_kwargs.setdefault("num_parallel_samples", self.default_num_samples)
-        # WaveNet model fails if an unsupported frequency such as "SM" is provided. We provide a dummy freq instead
-        init_kwargs["freq"] = "H"
         return init_kwargs

{autogluon.timeseries-1.1.0b20240411 → autogluon.timeseries-1.1.0b20240413}/src/autogluon/timeseries/predictor.py

@@ -69,7 +69,7 @@ class TimeSeriesPredictor(TimeSeriesPredictorDeprecatedMixin):
         models that predict up to 3 days into the future from the most recent observation.
     freq : str, optional
         Frequency of the time series data (see `pandas documentation <https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases>`_
-        for available frequencies). For example, ``"D"`` for daily data or ``"H"`` for hourly data.
+        for available frequencies). For example, ``"D"`` for daily data or ``"h"`` for hourly data.
 
         By default, the predictor will attempt to automatically infer the frequency from the data. This argument should
         only be set in two cases:
@@ -195,7 +195,7 @@ class TimeSeriesPredictor(TimeSeriesPredictorDeprecatedMixin):
         self._min_train_length = max(self.prediction_length + 1, 5)
         self.freq = freq
         if self.freq is not None:
-            # Standardize frequency string (e.g., "min" -> "T", "Y" -> "A-DEC")
+            # Standardize frequency string (e.g., "T" -> "min", "Y" -> "YE")
             std_freq = pd.tseries.frequencies.to_offset(self.freq).freqstr
             if std_freq != str(self.freq):
                 logger.info(f"Frequency '{self.freq}' stored as '{std_freq}'")

autogluon.timeseries-1.1.0b20240413/src/autogluon/timeseries/utils/datetime/base.py

@@ -0,0 +1,57 @@
+import pandas as pd
+
+TO_MAJOR_FREQ = {
+    # sub-daily
+    "H": "h",
+    "BH": "bh",
+    "cbh": "bh",
+    "CBH": "bh",
+    "T": "min",
+    "S": "s",
+    "L": "ms",
+    "U": "us",
+    "N": "ns",
+    # business day
+    "C": "B",
+    # month
+    "M": "ME",
+    "BM": "ME",
+    "BME": "ME",
+    "CBM": "ME",
+    "CBME": "ME",
+    "MS": "ME",
+    "BMS": "ME",
+    "CBMS": "ME",
+    # semi-month
+    "SM": "SME",
+    "SMS": "SME",
+    # quarter
+    "Q": "QE",
+    "BQ": "QE",
+    "BQE": "QE",
+    "QS": "QE",
+    "BQS": "QE",
+    # annual
+    "A": "YE",
+    "Y": "YE",
+    "BA": "YE",
+    "BY": "YE",
+    "BYE": "YE",
+    "AS": "YE",
+    "YS": "YE",
+    "BAS": "YE",
+    "BYS": "YE",
+}
+
+
+def norm_freq_str(offset: pd.DateOffset) -> str:
+    """Obtain frequency string from a pandas.DateOffset object.
+
+    "Non-standard" frequencies are converted to their "standard" counterparts. For example, MS (month start) is mapped
+    to ME (month end) since both correspond to the same seasonality, lags and time features.
+
+    The frequencies are always mapped to the new non-deprecated aliases (pandas>=2.2), e.g., "H" is mapped to "h". The
+    downstream functions like `get_seasonality` handle the new aliases even if older version of pandas is used.
+    """
+    base_freq = offset.name.split("-")[0]
+    return TO_MAJOR_FREQ.get(base_freq, base_freq)

{autogluon.timeseries-1.1.0b20240411 → autogluon.timeseries-1.1.0b20240413}/src/autogluon/timeseries/utils/datetime/lags.py

@@ -1,6 +1,7 @@
 """
 Generate lag indices based on frequency string. Adapted from gluonts.time_feature.lag.
 """
+
 from typing import List, Optional
 
 import numpy as np
@@ -96,13 +97,13 @@ def get_lags_for_frequency(
     offset = pd.tseries.frequencies.to_offset(freq)
     offset_name = norm_freq_str(offset)
 
-    if offset_name == "A":
+    if offset_name == "YE":
         lags = []
-    elif offset_name == "Q":
+    elif offset_name == "QE":
         lags = _make_lags_for_quarter(offset.n)
-    elif offset_name == "M":
+    elif offset_name == "ME":
         lags = _make_lags_for_month(offset.n)
-    elif offset_name == "SM":
+    elif offset_name == "SME":
         lags = _make_lags_for_semi_month(offset.n)
     elif offset_name == "W":
         lags = _make_lags_for_week(offset.n)
@@ -110,21 +111,21 @@ def get_lags_for_frequency(
         lags = _make_lags_for_day(offset.n) + _make_lags_for_week(offset.n / 7.0)
     elif offset_name == "B":
         lags = _make_lags_for_day(offset.n, days_in_week=5, days_in_month=22) + _make_lags_for_week(offset.n / 5.0)
-    elif offset_name == "H":
+    elif offset_name == "h":
         lags = (
             _make_lags_for_hour(offset.n)
             + _make_lags_for_day(offset.n / 24)
             + _make_lags_for_week(offset.n / (24 * 7))
         )
     # business hour
-    elif offset_name == "BH":
+    elif offset_name == "bh":
         lags = (
             _make_lags_for_business_hour(offset.n)
             + _make_lags_for_day(offset.n / 9)
             + _make_lags_for_week(offset.n / (9 * 7))
         )
     # minutes
-    elif offset_name == "T":
+    elif offset_name == "min":
         lags = (
             _make_lags_for_minute(offset.n)
             + _make_lags_for_hour(offset.n / 60)
@@ -132,32 +133,32 @@ def get_lags_for_frequency(
             + _make_lags_for_week(offset.n / (60 * 24 * 7))
         )
     # second
-    elif offset_name == "S":
+    elif offset_name == "s":
         lags = (
             _make_lags_for_second(offset.n)
             + _make_lags_for_minute(offset.n / 60)
             + _make_lags_for_hour(offset.n / (60 * 60))
         )
-    elif offset_name == "L":
+    elif offset_name == "ms":
         lags = (
             _make_lags_for_second(offset.n / 1e3)
             + _make_lags_for_minute(offset.n / (60 * 1e3))
             + _make_lags_for_hour(offset.n / (60 * 60 * 1e3))
         )
-    elif offset_name == "U":
+    elif offset_name == "us":
         lags = (
             _make_lags_for_second(offset.n / 1e6)
             + _make_lags_for_minute(offset.n / (60 * 1e6))
             + _make_lags_for_hour(offset.n / (60 * 60 * 1e6))
         )
-    elif offset_name == "N":
+    elif offset_name == "ns":
         lags = (
             _make_lags_for_second(offset.n / 1e9)
             + _make_lags_for_minute(offset.n / (60 * 1e9))
             + _make_lags_for_hour(offset.n / (60 * 60 * 1e9))
         )
     else:
-        raise Exception(f"invalid frequency {freq}")
+        raise Exception(f"Cannot get lags for unsupported frequency {freq}")
 
     # flatten lags list and filter
     lags = [int(lag) for sub_list in lags for lag in sub_list if 7 < lag <= lag_ub]

{autogluon.timeseries-1.1.0b20240411 → autogluon.timeseries-1.1.0b20240413}/src/autogluon/timeseries/utils/datetime/seasonality.py

@@ -5,20 +5,20 @@ import pandas as pd
 from .base import norm_freq_str
 
 DEFAULT_SEASONALITIES = {
-    "A": 1,
-    "Q": 4,
-    "M": 12,
-    "SM": 24,
+    "YE": 1,
+    "QE": 4,
+    "ME": 12,
+    "SME": 24,
     "W": 1,
     "D": 7,
     "B": 5,
-    "BH": 9,
-    "H": 24,
-    "T": 60 * 24,
-    "S": 1,
-    "L": 1,
-    "U": 1,
-    "N": 1,
+    "bh": 9,
+    "h": 24,
+    "min": 60 * 24,
+    "s": 1,
+    "ms": 1,
+    "us": 1,
+    "ns": 1,
 }
 
 

{autogluon.timeseries-1.1.0b20240411 → autogluon.timeseries-1.1.0b20240413}/src/autogluon/timeseries/utils/datetime/time_features.py

@@ -1,6 +1,7 @@
 """
 Generate time features based on frequency string. Adapted from gluonts.time_feature.time_feature.
 """
+
 from typing import Callable, List
 
 import numpy as np
@@ -57,20 +58,20 @@ def second_of_minute(index: pd.DatetimeIndex) -> np.ndarray:
 
 def get_time_features_for_frequency(freq) -> List[Callable]:
     features_by_offset_name = {
-        "A": [],
-        "Q": [quarter_of_year],
-        "M": [month_of_year],
-        "SM": [day_of_month, month_of_year],
+        "YE": [],
+        "QE": [quarter_of_year],
+        "ME": [month_of_year],
+        "SME": [day_of_month, month_of_year],
         "W": [day_of_month, week_of_year],
         "D": [day_of_week, day_of_month, day_of_year],
         "B": [day_of_week, day_of_month, day_of_year],
-        "BH": [hour_of_day, day_of_week, day_of_month, day_of_year],
-        "H": [hour_of_day, day_of_week, day_of_month, day_of_year],
-        "T": [minute_of_hour, hour_of_day, day_of_week, day_of_month, day_of_year],
-        "S": [second_of_minute, minute_of_hour, hour_of_day, day_of_week, day_of_month, day_of_year],
-        "L": [second_of_minute, minute_of_hour, hour_of_day, day_of_week, day_of_month, day_of_year],
-        "U": [second_of_minute, minute_of_hour, hour_of_day, day_of_week, day_of_month, day_of_year],
-        "N": [second_of_minute, minute_of_hour, hour_of_day, day_of_week, day_of_month, day_of_year],
+        "bh": [hour_of_day, day_of_week, day_of_month, day_of_year],
+        "h": [hour_of_day, day_of_week, day_of_month, day_of_year],
+        "min": [minute_of_hour, hour_of_day, day_of_week, day_of_month, day_of_year],
+        "s": [second_of_minute, minute_of_hour, hour_of_day, day_of_week, day_of_month, day_of_year],
+        "ms": [second_of_minute, minute_of_hour, hour_of_day, day_of_week, day_of_month, day_of_year],
+        "us": [second_of_minute, minute_of_hour, hour_of_day, day_of_week, day_of_month, day_of_year],
+        "ns": [second_of_minute, minute_of_hour, hour_of_day, day_of_week, day_of_month, day_of_year],
     }
     offset = pd.tseries.frequencies.to_offset(freq)
     offset_name = norm_freq_str(offset)

{autogluon.timeseries-1.1.0b20240411 → autogluon.timeseries-1.1.0b20240413}/src/autogluon/timeseries/utils/features.py

@@ -14,6 +14,7 @@ from autogluon.features.generators import (
     PipelineFeatureGenerator,
 )
 from autogluon.timeseries.dataset.ts_dataframe import ITEMID, TimeSeriesDataFrame
+from autogluon.timeseries.utils.warning_filters import warning_filter
 
 logger = logging.getLogger(__name__)
 
@@ -335,7 +336,9 @@ class AbstractFeatureImportanceTransform:
             # we'll have to work on the history of the data alone
             data[feature_name] = data[feature_name].copy()
             feature_data = data[feature_name].groupby(level=ITEMID, sort=False).head(-self.prediction_length)
-            data[feature_name].update(self._transform_series(feature_data, is_categorical=is_categorical))
+            # Silence spurious FutureWarning raised by DataFrame.update https://github.com/pandas-dev/pandas/issues/57124
+            with warning_filter():
+                data[feature_name].update(self._transform_series(feature_data, is_categorical=is_categorical))
         elif feature_name in self.covariate_metadata.static_features:
             feature_data = data.static_features[feature_name].copy()
             feature_data.reset_index(drop=True, inplace=True)

{autogluon.timeseries-1.1.0b20240411 → autogluon.timeseries-1.1.0b20240413}/src/autogluon/timeseries/version.py

@@ -1,3 +1,3 @@
 """This is the autogluon version file."""
-__version__ = '1.1.0b20240411'
+__version__ = '1.1.0b20240413'
 __lite__ = False

{autogluon.timeseries-1.1.0b20240411 → autogluon.timeseries-1.1.0b20240413}/src/autogluon.timeseries.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: autogluon.timeseries
-Version: 1.1.0b20240411
+Version: 1.1.0b20240413
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community

{autogluon.timeseries-1.1.0b20240411 → autogluon.timeseries-1.1.0b20240413}/src/autogluon.timeseries.egg-info/requires.txt

@@ -1,14 +1,14 @@
 joblib<2,>=1.1
 numpy<1.29,>=1.21
 scipy<1.13,>=1.5.4
-pandas<2.2.0,>=2.0.0
+pandas<2.3.0,>=2.0.0
 torch<2.2,>=2.1
 lightning<2.2,>=2.1
 pytorch_lightning<2.2,>=2.1
 transformers[sentencepiece]<4.39.0,>=4.38.0
 accelerate<0.22.0,>=0.21.0
 statsmodels<0.15,>=0.13.0
-gluonts<0.15,>=0.14.0
+gluonts<0.14.4,>=0.14.0
 networkx<4,>=3.0
 statsforecast<1.5,>=1.4.0
 mlforecast<0.10.1,>=0.10.0
@@ -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]==1.1.0b20240411
-autogluon.common==1.1.0b20240411
-autogluon.tabular[catboost,lightgbm,xgboost]==1.1.0b20240411
+autogluon.core[raytune]==1.1.0b20240413
+autogluon.common==1.1.0b20240413
+autogluon.tabular[catboost,lightgbm,xgboost]==1.1.0b20240413
 
 [all]
 optimum[onnxruntime]<1.19,>=1.17

autogluon.timeseries-1.1.0b20240411/src/autogluon/timeseries/utils/datetime/base.py

@@ -1,39 +0,0 @@
-import pandas as pd
-
-TO_MAJOR_FREQ = {
-    "min": "T",
-    "ms": "L",
-    "us": "U",
-    # business day
-    "C": "B",
-    # month
-    "BM": "M",
-    "CBM": "M",
-    "MS": "M",
-    "BMS": "M",
-    "CBMS": "M",
-    # semi-month
-    "SMS": "SM",
-    # quarter
-    "BQ": "Q",
-    "QS": "Q",
-    "BQS": "Q",
-    # annual
-    "Y": "A",
-    "BA": "A",
-    "BY": "A",
-    "AS": "A",
-    "YS": "A",
-    "BAS": "A",
-    "BYS": "A",
-}
-
-
-def norm_freq_str(offset: pd.DateOffset) -> str:
-    """Obtain frequency string from a pandas.DateOffset object.
-
-    "Non-standard" frequencies are converted to their "standard" counterparts. For example, MS (month start) is mapped
-    to M (month) since both correspond to the same seasonality, lags and time features.
-    """
-    base_freq = offset.name.split("-")[0]
-    return TO_MAJOR_FREQ.get(base_freq, base_freq)