autogluon.core 1.2.1b20250211__py3-none-any.whl → 1.2.1b20250213__py3-none-any.whl

autogluon/core/models/abstract/abstract_model.py

@@ -823,8 +823,8 @@ class AbstractModel:
             self._fit_metadata = self._compute_fit_metadata(**kwargs)
             self._is_fit_metadata_registered = True
 
-    def _compute_fit_metadata(self, X_val: pd.DataFrame = None, X_unlabeled: pd.DataFrame = None, num_cpus: int = None, num_gpus: int = None, **kwargs) -> dict:
-        fit_metadata = dict(val_in_fit=X_val is not None, unlabeled_in_fit=X_unlabeled is not None, num_cpus=num_cpus, num_gpus=num_gpus)
+    def _compute_fit_metadata(self, X: pd.DataFrame = None, X_val: pd.DataFrame = None, X_unlabeled: pd.DataFrame = None, num_cpus: int = None, num_gpus: int = None, **kwargs) -> dict:
+        fit_metadata = dict(num_samples=len(X) if X is not None else None, val_in_fit=X_val is not None, unlabeled_in_fit=X_unlabeled is not None, num_cpus=num_cpus, num_gpus=num_gpus)
         return fit_metadata
 
     def get_fit_metadata(self) -> dict:

autogluon/core/models/ensemble/bagged_ensemble_model.py

@@ -240,6 +240,66 @@ class BaggedEnsembleModel(AbstractModel):
         _skip_oof: bool = False,
         **kwargs,
     ):
+        """
+
+        Parameters
+        ----------
+        X : pd.DataFrame
+            The training data features.
+        y : pd.Series
+            The training data ground truth labels.
+        X_val : pd.DataFrame, default None
+            The validation data features.
+            Ignored by BaggedEnsembleModel.
+        y_val : pd.Series, default None
+            The validation data ground truth labels.
+            Ignored by BaggedEnsembleModel.
+        X_pseudo : pd.DataFrame, default None
+            Pseudo data features.
+            If specified, this data is added to each fold model's training data.
+        y_pseudo : pd.Series, default None
+            Pseudo data ground truth labels.
+            If specified, this data is added to each fold model's training data.
+        k_fold : int | None, default None
+            If int, must be a value >=1. Passing 0 will result in an exception.
+            If >1, will fit with `k_fold` folds per n_repeat.
+                This splits X and y into `k_fold` chunks to fit `k_fold` models, each with `k-1` chunks used for training and the remaining used for validation.
+            If 1, will only fit 1 model using all the training data.
+                This is generally reserved for models which are refits of previously trained bags (along with specifying `_skip_oof=True`).
+                This can also be used for models which support child oof generation (Random Forest, Extra Trees, KNN).
+            If None, defaults to 5 if `groups` is None. Else it will be set based on `groups`.
+        k_fold_start : int, default 0
+            The fold to start fitting on.
+            This allows for fitting only a subset of the bagged ensemble's folds per fit call, if desired.
+        k_fold_end : int, default None
+            The fold to stop fitting on.
+            This allows for fitting only a subset of the bagged ensemble's folds per fit call, if desired.
+            If None, will be set to `k_fold`.
+        n_repeats : int, default 1
+            The number of bagging sets (aka repeats).
+            If 1, will only fit `k_fold` models.
+            If >1, will fit `n_repeats * k_fold` models.
+            For each repeat, will split X and y with an incrementing random seed.
+        n_repeat_start : int, default 0
+            The repeat to start on.
+            This allows for fitting only a subset of the bagged ensemble's repeats per fit call, if desired.
+        groups : pd.Series, default None
+            If specified, will split X and y based on `groups`, with each sample going to a specific group.
+            Overrides `k_fold` and disables `n_repeats>1` if specified.
+        _skip_oof : bool, default False
+            If True, will not calculate the out-of-fold predictions from the fold models.
+            This should be set to True when performing a bagged refit.
+        kwargs : dict,
+            Arguments passed downstream to the fold models.
+
+        Returns
+        -------
+        BaggedEnsembleModel
+            The fitted bagged ensemble model.
+            In most cases this is `self`.
+            If `refit_folds=True`, then instead the refit version of the bagged ensemble is returned.
+
+        """
         use_child_oof = self.params.get("use_child_oof", False)
         if use_child_oof and groups is not None:
             logger.log(20, f"\tForcing `use_child_oof=False` because `groups` is specified")
@@ -269,6 +329,7 @@ class BaggedEnsembleModel(AbstractModel):
             n_repeat_start=n_repeat_start,
             groups=groups,
             use_child_oof=use_child_oof,
+            skip_oof=_skip_oof,
         )
         if k_fold_end is None:
             k_fold_end = k_fold
@@ -384,6 +445,7 @@ class BaggedEnsembleModel(AbstractModel):
         n_repeat_start: int,
         groups: pd.Series | None,
         use_child_oof: bool,
+        skip_oof: bool,
     ):
         if groups is not None:
             if self._n_repeats_finished != 0:
@@ -419,7 +481,7 @@ class BaggedEnsembleModel(AbstractModel):
                 f"\tTo enable this logic, `{self._child_type.__name__}._predict_proba_oof` must be implemented "
                 f"and `tags['valid_oof'] = True` must be set in `{self._child_type.__name__}._more_tags`."
             )
-        if k_fold == 1 and not use_child_oof and not self._get_tags().get("can_get_oof_from_train", False):
+        if k_fold == 1 and not skip_oof and not use_child_oof and not self._get_tags().get("can_get_oof_from_train", False):
             logger.log(
                 30,
                 f"\tWARNING: Fitting bagged model with `k_fold=1`, "

autogluon/core/version.py

@@ -1,4 +1,4 @@
 """This is the autogluon version file."""
 
-__version__ = "1.2.1b20250211"
+__version__ = "1.2.1b20250213"
 __lite__ = False

{autogluon.core-1.2.1b20250211.dist-info → autogluon.core-1.2.1b20250213.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: autogluon.core
-Version: 1.2.1b20250211
+Version: 1.2.1b20250213
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community
@@ -45,12 +45,12 @@ Requires-Dist: tqdm<5,>=4.38
 Requires-Dist: requests
 Requires-Dist: matplotlib<3.11,>=3.7.0
 Requires-Dist: boto3<2,>=1.10
-Requires-Dist: autogluon.common==1.2.1b20250211
+Requires-Dist: autogluon.common==1.2.1b20250213
 Provides-Extra: all
+Requires-Dist: ray[default]<2.41,>=2.10.0; extra == "all"
+Requires-Dist: ray[default,tune]<2.41,>=2.10.0; extra == "all"
 Requires-Dist: pyarrow>=15.0.0; extra == "all"
 Requires-Dist: hyperopt<0.2.8,>=0.2.7; extra == "all"
-Requires-Dist: ray[default,tune]<2.41,>=2.10.0; extra == "all"
-Requires-Dist: ray[default]<2.41,>=2.10.0; extra == "all"
 Provides-Extra: ray
 Requires-Dist: ray[default]<2.41,>=2.10.0; extra == "ray"
 Provides-Extra: raytune

{autogluon.core-1.2.1b20250211.dist-info → autogluon.core-1.2.1b20250213.dist-info}/RECORD

@@ -1,9 +1,9 @@
-autogluon.core-1.2.1b20250211-py3.9-nspkg.pth,sha256=cQGwpuGPqg1GXscIwt-7PmME1OnSpD-7ixkikJ31WAY,554
+autogluon.core-1.2.1b20250213-py3.9-nspkg.pth,sha256=cQGwpuGPqg1GXscIwt-7PmME1OnSpD-7ixkikJ31WAY,554
 autogluon/core/__init__.py,sha256=8KfvvHzXX3a4q6z43Dw1yE7VtbAoiSMaglVpKDy6Xeg,245
 autogluon/core/_setup_utils.py,sha256=ikxn4zc3PNyjJJT5SsgL0dvP-6Rbq6_dItGMiZNINv4,6958
 autogluon/core/constants.py,sha256=nEVLdSFJ-5O-tz3jUD3qPX65RMp7g8qOR38XlurbP4Y,3403
 autogluon/core/problem_type.py,sha256=XJmMgeNBgS7u43pDK-spTivatPyh_INOXveEXwQt-Rw,2993
-autogluon/core/version.py,sha256=Yxg6A266LJAF_-SqWiU5evmkHb9GvRXqM0ORyZus93M,91
+autogluon/core/version.py,sha256=-eMcoN37NqYnyDHzrKYBqqrt5oVGROjtYzQ6FocTpmU,91
 autogluon/core/augmentation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 autogluon/core/augmentation/distill_utils.py,sha256=JBlp2WOMNKoJv8aKVwJVRQSalSk8jx36HM7-k_VvkhY,9404
 autogluon/core/calibrate/__init__.py,sha256=eU6qLj7DKUhaz2HHNHDrfroRaLM-mhuSncK_v1UP4F8,62
@@ -40,14 +40,14 @@ autogluon/core/models/__init__.py,sha256=dg3onYq5wW3-sfdNurnSIGpX0rpEjG_abgzyfwD
 autogluon/core/models/_utils.py,sha256=qswE9n1ge1AJSExgstEbrZiMFmMRa4Mf5Sz8D9-XU6c,2091
 autogluon/core/models/abstract/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 autogluon/core/models/abstract/_tags.py,sha256=Qr_3an0ZMig24S3OwISa-nTFfWHQe3pwPTiXq4zlEec,3409
-autogluon/core/models/abstract/abstract_model.py,sha256=PiM7WT6clMYPdbVNQbJRg6M5Jz8ws5trY62aUnUCEx4,120461
+autogluon/core/models/abstract/abstract_model.py,sha256=SPknoRqTiRCZfTvoFrf2V3BW4h5MVbrl-2HvSHfCjOM,120532
 autogluon/core/models/abstract/abstract_nn_model.py,sha256=IId0ivO8uVvmpnK9OiM2CtPVrP1ewOaQQKtQUDtK7_k,4818
 autogluon/core/models/abstract/model_trial.py,sha256=PKEo1jfLSBCOLM42QE5VBD1u41MaVMRk31zhNhLiqTw,5035
 autogluon/core/models/dummy/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 autogluon/core/models/dummy/_dummy_quantile_regressor.py,sha256=i-ZW2flJ60jsMfMK24IP39Xwc55-UlBDvHmqanIf29Q,664
 autogluon/core/models/dummy/dummy_model.py,sha256=at2FZSM2_LuAQ78E2YrRCRt3UaKMyyOnc6p2rtZgA2w,1414
 autogluon/core/models/ensemble/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-autogluon/core/models/ensemble/bagged_ensemble_model.py,sha256=p3lkm0Cweyu_maOeboirGmQIjIaaiDHXS-XHDc-wYYw,72610
+autogluon/core/models/ensemble/bagged_ensemble_model.py,sha256=8GijtiLwFXugKWWIKY4ss_Xa_EGdASWtvJ2JUJu2avs,75887
 autogluon/core/models/ensemble/fold_fitting_strategy.py,sha256=01vzNVvE4FIFgD6YqbhK63XoUlSztnVFsrDdsoqm75U,47021
 autogluon/core/models/ensemble/ray_parallel_fold_fitting_strategy.py,sha256=8RASa-eV6n9kUgbqQHNt7k4IrvuB9NdrunIMLYOLwgA,2068
 autogluon/core/models/ensemble/stacker_ensemble_model.py,sha256=DuDXgozvG9JYYkRvGACA7EXDAtj3Tz_uAjXTfxu5tFg,18041
@@ -89,11 +89,11 @@ autogluon/core/utils/utils.py,sha256=FMa9kIUAxA3IIBbATmBnNEVObSAivehZ2_zCy3PRR-c
 autogluon/core/utils/version_utils.py,sha256=5-r8hLRKTaZbj5qo2uzE_2E4casH49Ye3WyeHlgHuz4,3252
 autogluon/core/utils/loaders/__init__.py,sha256=W5FAdQvpDcn_uisqJrlSAObWVta-YjJLKGN3NCbEgIo,109
 autogluon/core/utils/savers/__init__.py,sha256=bGWciSxAkj6u06vOC4pTvr22f_1ey0glgvmjCMEOm78,89
-autogluon.core-1.2.1b20250211.dist-info/LICENSE,sha256=CeipvOyAZxBGUsFoaFqwkx54aPnIKEtm9a5u2uXxEws,10142
-autogluon.core-1.2.1b20250211.dist-info/METADATA,sha256=BQJZOppMfQB_U55W7FdnmYvtg4bx4c098tsfRBd6TL0,12377
-autogluon.core-1.2.1b20250211.dist-info/NOTICE,sha256=7nPQuj8Kp-uXsU0S5so3-2dNU5EctS5hDXvvzzehd7E,114
-autogluon.core-1.2.1b20250211.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-autogluon.core-1.2.1b20250211.dist-info/namespace_packages.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
-autogluon.core-1.2.1b20250211.dist-info/top_level.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
-autogluon.core-1.2.1b20250211.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-autogluon.core-1.2.1b20250211.dist-info/RECORD,,
+autogluon.core-1.2.1b20250213.dist-info/LICENSE,sha256=CeipvOyAZxBGUsFoaFqwkx54aPnIKEtm9a5u2uXxEws,10142
+autogluon.core-1.2.1b20250213.dist-info/METADATA,sha256=4-NKXJvr8G2aZnpp2DnNNS0v9i6Dyclv0MbDgYbUL3M,12377
+autogluon.core-1.2.1b20250213.dist-info/NOTICE,sha256=7nPQuj8Kp-uXsU0S5so3-2dNU5EctS5hDXvvzzehd7E,114
+autogluon.core-1.2.1b20250213.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+autogluon.core-1.2.1b20250213.dist-info/namespace_packages.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
+autogluon.core-1.2.1b20250213.dist-info/top_level.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
+autogluon.core-1.2.1b20250213.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+autogluon.core-1.2.1b20250213.dist-info/RECORD,,