autogluon.tabular 1.4.1b20251207__tar.gz → 1.4.1b20251216__tar.gz

{autogluon_tabular-1.4.1b20251207/src/autogluon.tabular.egg-info → autogluon_tabular-1.4.1b20251216}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: autogluon.tabular
-Version: 1.4.1b20251207
+Version: 1.4.1b20251216
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community
@@ -40,8 +40,8 @@ Requires-Dist: scipy<1.17,>=1.5.4
 Requires-Dist: pandas<2.4.0,>=2.0.0
 Requires-Dist: scikit-learn<1.8.0,>=1.4.0
 Requires-Dist: networkx<4,>=3.0
-Requires-Dist: autogluon.core==1.4.1b20251207
-Requires-Dist: autogluon.features==1.4.1b20251207
+Requires-Dist: autogluon.core==1.4.1b20251216
+Requires-Dist: autogluon.features==1.4.1b20251216
 Provides-Extra: lightgbm
 Requires-Dist: lightgbm<4.7,>=4.0; extra == "lightgbm"
 Provides-Extra: catboost
@@ -76,7 +76,7 @@ Requires-Dist: einops<0.9,>=0.7; extra == "mitra"
 Provides-Extra: tabicl
 Requires-Dist: tabicl<0.2,>=0.1.3; extra == "tabicl"
 Provides-Extra: ray
-Requires-Dist: autogluon.core[all]==1.4.1b20251207; extra == "ray"
+Requires-Dist: autogluon.core[all]==1.4.1b20251216; extra == "ray"
 Provides-Extra: skex
 Requires-Dist: scikit-learn-intelex<2025.5,>=2024.0; extra == "skex"
 Provides-Extra: imodels
@@ -88,38 +88,38 @@ Requires-Dist: onnx<1.21.0,>=1.13.0; platform_system != "Windows" and extra == "
 Requires-Dist: onnxruntime<1.24.0,>=1.17.0; extra == "skl2onnx"
 Requires-Dist: onnxruntime-gpu<1.24.0,>=1.17.0; (platform_system != "Darwin" and platform_machine != "aarch64") and extra == "skl2onnx"
 Provides-Extra: all
-Requires-Dist: loguru; extra == "all"
-Requires-Dist: torch<2.10,>=2.6; extra == "all"
-Requires-Dist: huggingface_hub[torch]<1.0; extra == "all"
-Requires-Dist: transformers; extra == "all"
 Requires-Dist: fastai<2.9,>=2.3.1; extra == "all"
-Requires-Dist: catboost<1.3,>=1.2; extra == "all"
+Requires-Dist: huggingface_hub[torch]<1.0; extra == "all"
+Requires-Dist: torch<2.10,>=2.6; extra == "all"
+Requires-Dist: omegaconf; extra == "all"
 Requires-Dist: numpy<2.3.0,>=1.25; extra == "all"
-Requires-Dist: einops<0.9,>=0.7; extra == "all"
-Requires-Dist: spacy<3.9; extra == "all"
+Requires-Dist: autogluon.core[all]==1.4.1b20251216; extra == "all"
+Requires-Dist: loguru; extra == "all"
+Requires-Dist: transformers; extra == "all"
+Requires-Dist: xgboost<3.1,>=2.0; extra == "all"
 Requires-Dist: lightgbm<4.7,>=4.0; extra == "all"
+Requires-Dist: catboost<1.3,>=1.2; extra == "all"
 Requires-Dist: einx; extra == "all"
-Requires-Dist: autogluon.core[all]==1.4.1b20251207; extra == "all"
-Requires-Dist: xgboost<3.1,>=2.0; extra == "all"
-Requires-Dist: omegaconf; extra == "all"
+Requires-Dist: spacy<3.9; extra == "all"
+Requires-Dist: einops<0.9,>=0.7; extra == "all"
 Provides-Extra: tabarena
-Requires-Dist: loguru; extra == "tabarena"
-Requires-Dist: torch<2.10,>=2.6; extra == "tabarena"
-Requires-Dist: huggingface_hub[torch]<1.0; extra == "tabarena"
-Requires-Dist: tabicl<0.2,>=0.1.3; extra == "tabarena"
-Requires-Dist: transformers; extra == "tabarena"
 Requires-Dist: fastai<2.9,>=2.3.1; extra == "tabarena"
-Requires-Dist: tabpfn<2.2,>=2.0.9; extra == "tabarena"
+Requires-Dist: huggingface_hub[torch]<1.0; extra == "tabarena"
+Requires-Dist: torch<2.10,>=2.6; extra == "tabarena"
 Requires-Dist: omegaconf; extra == "tabarena"
-Requires-Dist: pytabkit<1.7,>=1.6; extra == "tabarena"
-Requires-Dist: catboost<1.3,>=1.2; extra == "tabarena"
 Requires-Dist: numpy<2.3.0,>=1.25; extra == "tabarena"
-Requires-Dist: autogluon.core[all]==1.4.1b20251207; extra == "tabarena"
-Requires-Dist: spacy<3.9; extra == "tabarena"
+Requires-Dist: autogluon.core[all]==1.4.1b20251216; extra == "tabarena"
+Requires-Dist: pytabkit<1.7,>=1.6; extra == "tabarena"
+Requires-Dist: loguru; extra == "tabarena"
+Requires-Dist: transformers; extra == "tabarena"
+Requires-Dist: xgboost<3.1,>=2.0; extra == "tabarena"
 Requires-Dist: lightgbm<4.7,>=4.0; extra == "tabarena"
+Requires-Dist: catboost<1.3,>=1.2; extra == "tabarena"
 Requires-Dist: einx; extra == "tabarena"
-Requires-Dist: xgboost<3.1,>=2.0; extra == "tabarena"
+Requires-Dist: spacy<3.9; extra == "tabarena"
 Requires-Dist: einops<0.9,>=0.7; extra == "tabarena"
+Requires-Dist: tabicl<0.2,>=0.1.3; extra == "tabarena"
+Requires-Dist: tabpfn<2.2,>=2.0.9; extra == "tabarena"
 Requires-Dist: interpret-core<0.8,>=0.7.2; extra == "tabarena"
 Provides-Extra: tests
 Requires-Dist: interpret-core<0.8,>=0.7.2; extra == "tests"

{autogluon_tabular-1.4.1b20251207 → autogluon_tabular-1.4.1b20251216}/src/autogluon/tabular/learner/default_learner.py

@@ -143,6 +143,7 @@ class DefaultLearner(AbstractTabularLearner):
             infer_limit=infer_limit,
             infer_limit_batch_size=infer_limit_batch_size,
             groups=groups,
+            label_cleaner=copy.deepcopy(self.label_cleaner),
             **trainer_fit_kwargs,
         )
         self.save_trainer(trainer=trainer)

{autogluon_tabular-1.4.1b20251207 → autogluon_tabular-1.4.1b20251216}/src/autogluon/tabular/models/rf/rf_model.py

@@ -151,13 +151,13 @@ class RFModel(AbstractModel):
             hyperparameters = {}
         n_estimators_final = hyperparameters.get("n_estimators", 300)
         if isinstance(n_estimators_final, int):
-            n_estimators_minimum = min(40, n_estimators_final)
+            n_estimators = n_estimators_final
         else:  # if search space
-            n_estimators_minimum = 40
+            n_estimators = 40
         num_trees_per_estimator = cls._get_num_trees_per_estimator_static(problem_type=problem_type, num_classes=num_classes)
         bytes_per_estimator = num_trees_per_estimator * len(X) / 60000 * 1e6  # Underestimates by 3x on ExtraTrees
-        expected_min_memory_usage = int(bytes_per_estimator * n_estimators_minimum)
-        return expected_min_memory_usage
+        expected_memory_usage = int(bytes_per_estimator * n_estimators)
+        return expected_memory_usage
 
     def _validate_fit_memory_usage(self, mem_error_threshold: float = 0.5, mem_warning_threshold: float = 0.4, mem_size_threshold: int = 1e7, **kwargs):
         return super()._validate_fit_memory_usage(

{autogluon_tabular-1.4.1b20251207 → autogluon_tabular-1.4.1b20251216}/src/autogluon/tabular/models/tabular_nn/torch/tabular_nn_torch.py

@@ -371,7 +371,6 @@ class TabularNeuralNetTorchModel(AbstractNeuralNetworkModel):
         best_epoch = 0
         best_val_metric = -np.inf  # higher = better
         best_val_update = 0
-        val_improve_epoch = 0  # most recent epoch where validation-score strictly improved
         start_fit_time = time.time()
         if time_limit is not None:
             time_limit = time_limit - (start_fit_time - start_time)

{autogluon_tabular-1.4.1b20251207 → autogluon_tabular-1.4.1b20251216}/src/autogluon/tabular/trainer/abstract_trainer.py

@@ -27,7 +27,7 @@ from autogluon.core.calibrate.conformity_score import compute_conformity_score
 from autogluon.core.calibrate.temperature_scaling import apply_temperature_scaling, tune_temperature_scaling
 from autogluon.core.callbacks import AbstractCallback
 from autogluon.core.constants import BINARY, MULTICLASS, QUANTILE, REFIT_FULL_NAME, REGRESSION, SOFTCLASS
-from autogluon.core.data.label_cleaner import LabelCleanerMulticlassToBinary
+from autogluon.core.data.label_cleaner import LabelCleanerMulticlassToBinary, LabelCleaner
 from autogluon.core.metrics import Scorer, compute_metric, get_metric
 from autogluon.core.models import (
     AbstractModel,
@@ -2493,6 +2493,7 @@ class AbstractTabularTrainer(AbstractTrainer[AbstractModel]):
         errors_ignore: list | None = None,
         errors_raise: list | None = None,
         is_ray_worker: bool = False,
+        label_cleaner: None | LabelCleaner = None,
         **kwargs,
     ) -> list[str]:
         """
@@ -2527,7 +2528,8 @@ class AbstractTabularTrainer(AbstractTrainer[AbstractModel]):
             return []
 
         model_fit_kwargs = self._get_model_fit_kwargs(
-            X=X, X_val=X_val, time_limit=time_limit, k_fold=k_fold, fit_kwargs=fit_kwargs, ens_sample_weight=kwargs.get("ens_sample_weight", None)
+            X=X, X_val=X_val, time_limit=time_limit, k_fold=k_fold, fit_kwargs=fit_kwargs,
+            ens_sample_weight=kwargs.get("ens_sample_weight", None), label_cleaner=label_cleaner,
         )
         exception = None
         if hyperparameter_tune_kwargs:
@@ -4294,7 +4296,8 @@ class AbstractTabularTrainer(AbstractTrainer[AbstractModel]):
         return distilled_model_names
 
     def _get_model_fit_kwargs(
-        self, X: pd.DataFrame, X_val: pd.DataFrame, time_limit: float, k_fold: int, fit_kwargs: dict, ens_sample_weight: list | None = None
+        self, X: pd.DataFrame, X_val: pd.DataFrame, time_limit: float, k_fold: int,
+        fit_kwargs: dict, ens_sample_weight: list | None = None, label_cleaner: None | LabelCleaner = None
     ) -> dict:
         # Returns kwargs to be passed to AbstractModel's fit function
         if fit_kwargs is None:
@@ -4316,6 +4319,9 @@ class AbstractTabularTrainer(AbstractTrainer[AbstractModel]):
             if k_fold == self.k_fold:  # don't do this on refit full
                 model_fit_kwargs["groups"] = self._groups
 
+        if label_cleaner is not None:
+            model_fit_kwargs["label_cleaner"] = label_cleaner
+
         # FIXME: Sample weight `extract_column` is a hack, have to compute feature_metadata here because sample weight column could be in X upstream, extract sample weight column upstream instead.
         if "feature_metadata" not in model_fit_kwargs:
             raise AssertionError(f"Missing expected parameter 'feature_metadata'.")

{autogluon_tabular-1.4.1b20251207 → autogluon_tabular-1.4.1b20251216}/src/autogluon/tabular/trainer/auto_trainer.py

@@ -59,6 +59,7 @@ class AutoTrainer(AbstractTabularTrainer):
         use_bag_holdout=False,
         groups=None,
         callbacks: list[callable] = None,
+        label_cleaner=None,
         **kwargs,
     ):
         for key in kwargs:
@@ -132,6 +133,9 @@ class AutoTrainer(AbstractTabularTrainer):
         log_str += "}"
         logger.log(20, log_str)
 
+        if label_cleaner is not None:
+            core_kwargs["label_cleaner"] = label_cleaner
+
         self._train_multi_and_ensemble(
             X=X,
             y=y,

{autogluon_tabular-1.4.1b20251207 → autogluon_tabular-1.4.1b20251216}/src/autogluon/tabular/version.py

@@ -1,4 +1,4 @@
 """This is the autogluon version file."""
 
-__version__ = "1.4.1b20251207"
+__version__ = "1.4.1b20251216"
 __lite__ = False

{autogluon_tabular-1.4.1b20251207 → autogluon_tabular-1.4.1b20251216/src/autogluon.tabular.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: autogluon.tabular
-Version: 1.4.1b20251207
+Version: 1.4.1b20251216
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community
@@ -40,8 +40,8 @@ Requires-Dist: scipy<1.17,>=1.5.4
 Requires-Dist: pandas<2.4.0,>=2.0.0
 Requires-Dist: scikit-learn<1.8.0,>=1.4.0
 Requires-Dist: networkx<4,>=3.0
-Requires-Dist: autogluon.core==1.4.1b20251207
-Requires-Dist: autogluon.features==1.4.1b20251207
+Requires-Dist: autogluon.core==1.4.1b20251216
+Requires-Dist: autogluon.features==1.4.1b20251216
 Provides-Extra: lightgbm
 Requires-Dist: lightgbm<4.7,>=4.0; extra == "lightgbm"
 Provides-Extra: catboost
@@ -76,7 +76,7 @@ Requires-Dist: einops<0.9,>=0.7; extra == "mitra"
 Provides-Extra: tabicl
 Requires-Dist: tabicl<0.2,>=0.1.3; extra == "tabicl"
 Provides-Extra: ray
-Requires-Dist: autogluon.core[all]==1.4.1b20251207; extra == "ray"
+Requires-Dist: autogluon.core[all]==1.4.1b20251216; extra == "ray"
 Provides-Extra: skex
 Requires-Dist: scikit-learn-intelex<2025.5,>=2024.0; extra == "skex"
 Provides-Extra: imodels
@@ -88,38 +88,38 @@ Requires-Dist: onnx<1.21.0,>=1.13.0; platform_system != "Windows" and extra == "
 Requires-Dist: onnxruntime<1.24.0,>=1.17.0; extra == "skl2onnx"
 Requires-Dist: onnxruntime-gpu<1.24.0,>=1.17.0; (platform_system != "Darwin" and platform_machine != "aarch64") and extra == "skl2onnx"
 Provides-Extra: all
-Requires-Dist: loguru; extra == "all"
-Requires-Dist: torch<2.10,>=2.6; extra == "all"
-Requires-Dist: huggingface_hub[torch]<1.0; extra == "all"
-Requires-Dist: transformers; extra == "all"
 Requires-Dist: fastai<2.9,>=2.3.1; extra == "all"
-Requires-Dist: catboost<1.3,>=1.2; extra == "all"
+Requires-Dist: huggingface_hub[torch]<1.0; extra == "all"
+Requires-Dist: torch<2.10,>=2.6; extra == "all"
+Requires-Dist: omegaconf; extra == "all"
 Requires-Dist: numpy<2.3.0,>=1.25; extra == "all"
-Requires-Dist: einops<0.9,>=0.7; extra == "all"
-Requires-Dist: spacy<3.9; extra == "all"
+Requires-Dist: autogluon.core[all]==1.4.1b20251216; extra == "all"
+Requires-Dist: loguru; extra == "all"
+Requires-Dist: transformers; extra == "all"
+Requires-Dist: xgboost<3.1,>=2.0; extra == "all"
 Requires-Dist: lightgbm<4.7,>=4.0; extra == "all"
+Requires-Dist: catboost<1.3,>=1.2; extra == "all"
 Requires-Dist: einx; extra == "all"
-Requires-Dist: autogluon.core[all]==1.4.1b20251207; extra == "all"
-Requires-Dist: xgboost<3.1,>=2.0; extra == "all"
-Requires-Dist: omegaconf; extra == "all"
+Requires-Dist: spacy<3.9; extra == "all"
+Requires-Dist: einops<0.9,>=0.7; extra == "all"
 Provides-Extra: tabarena
-Requires-Dist: loguru; extra == "tabarena"
-Requires-Dist: torch<2.10,>=2.6; extra == "tabarena"
-Requires-Dist: huggingface_hub[torch]<1.0; extra == "tabarena"
-Requires-Dist: tabicl<0.2,>=0.1.3; extra == "tabarena"
-Requires-Dist: transformers; extra == "tabarena"
 Requires-Dist: fastai<2.9,>=2.3.1; extra == "tabarena"
-Requires-Dist: tabpfn<2.2,>=2.0.9; extra == "tabarena"
+Requires-Dist: huggingface_hub[torch]<1.0; extra == "tabarena"
+Requires-Dist: torch<2.10,>=2.6; extra == "tabarena"
 Requires-Dist: omegaconf; extra == "tabarena"
-Requires-Dist: pytabkit<1.7,>=1.6; extra == "tabarena"
-Requires-Dist: catboost<1.3,>=1.2; extra == "tabarena"
 Requires-Dist: numpy<2.3.0,>=1.25; extra == "tabarena"
-Requires-Dist: autogluon.core[all]==1.4.1b20251207; extra == "tabarena"
-Requires-Dist: spacy<3.9; extra == "tabarena"
+Requires-Dist: autogluon.core[all]==1.4.1b20251216; extra == "tabarena"
+Requires-Dist: pytabkit<1.7,>=1.6; extra == "tabarena"
+Requires-Dist: loguru; extra == "tabarena"
+Requires-Dist: transformers; extra == "tabarena"
+Requires-Dist: xgboost<3.1,>=2.0; extra == "tabarena"
 Requires-Dist: lightgbm<4.7,>=4.0; extra == "tabarena"
+Requires-Dist: catboost<1.3,>=1.2; extra == "tabarena"
 Requires-Dist: einx; extra == "tabarena"
-Requires-Dist: xgboost<3.1,>=2.0; extra == "tabarena"
+Requires-Dist: spacy<3.9; extra == "tabarena"
 Requires-Dist: einops<0.9,>=0.7; extra == "tabarena"
+Requires-Dist: tabicl<0.2,>=0.1.3; extra == "tabarena"
+Requires-Dist: tabpfn<2.2,>=2.0.9; extra == "tabarena"
 Requires-Dist: interpret-core<0.8,>=0.7.2; extra == "tabarena"
 Provides-Extra: tests
 Requires-Dist: interpret-core<0.8,>=0.7.2; extra == "tests"

{autogluon_tabular-1.4.1b20251207 → autogluon_tabular-1.4.1b20251216}/src/autogluon.tabular.egg-info/requires.txt

@@ -3,24 +3,24 @@ scipy<1.17,>=1.5.4
 pandas<2.4.0,>=2.0.0
 scikit-learn<1.8.0,>=1.4.0
 networkx<4,>=3.0
-autogluon.core==1.4.1b20251207
-autogluon.features==1.4.1b20251207
+autogluon.core==1.4.1b20251216
+autogluon.features==1.4.1b20251216
 
 [all]
-loguru
-torch<2.10,>=2.6
-huggingface_hub[torch]<1.0
-transformers
 fastai<2.9,>=2.3.1
-catboost<1.3,>=1.2
+huggingface_hub[torch]<1.0
+torch<2.10,>=2.6
+omegaconf
 numpy<2.3.0,>=1.25
-einops<0.9,>=0.7
-spacy<3.9
+autogluon.core[all]==1.4.1b20251216
+loguru
+transformers
+xgboost<3.1,>=2.0
 lightgbm<4.7,>=4.0
+catboost<1.3,>=1.2
 einx
-autogluon.core[all]==1.4.1b20251207
-xgboost<3.1,>=2.0
-omegaconf
+spacy<3.9
+einops<0.9,>=0.7
 
 [catboost]
 numpy<2.3.0,>=1.25
@@ -50,7 +50,7 @@ huggingface_hub[torch]<1.0
 einops<0.9,>=0.7
 
 [ray]
-autogluon.core[all]==1.4.1b20251207
+autogluon.core[all]==1.4.1b20251216
 
 [realmlp]
 pytabkit<1.7,>=1.6
@@ -72,23 +72,23 @@ onnx<1.21.0,>=1.13.0
 onnx!=1.16.2,<1.21.0,>=1.13.0
 
 [tabarena]
-loguru
-torch<2.10,>=2.6
-huggingface_hub[torch]<1.0
-tabicl<0.2,>=0.1.3
-transformers
 fastai<2.9,>=2.3.1
-tabpfn<2.2,>=2.0.9
+huggingface_hub[torch]<1.0
+torch<2.10,>=2.6
 omegaconf
-pytabkit<1.7,>=1.6
-catboost<1.3,>=1.2
 numpy<2.3.0,>=1.25
-autogluon.core[all]==1.4.1b20251207
-spacy<3.9
+autogluon.core[all]==1.4.1b20251216
+pytabkit<1.7,>=1.6
+loguru
+transformers
+xgboost<3.1,>=2.0
 lightgbm<4.7,>=4.0
+catboost<1.3,>=1.2
 einx
-xgboost<3.1,>=2.0
+spacy<3.9
 einops<0.9,>=0.7
+tabicl<0.2,>=0.1.3
+tabpfn<2.2,>=2.0.9
 interpret-core<0.8,>=0.7.2
 
 [tabicl]