autogluon.tabular 1.5.1b20260105__py3-none-any.whl → 1.5.1b20260116__py3-none-any.whl

autogluon/tabular/trainer/auto_trainer.py

@@ -4,10 +4,10 @@ from autogluon.core.models import AbstractModel
 from autogluon.core.utils import generate_train_test_split
 
 from ..models.lgb.lgb_model import LGBModel
+from ..registry import ag_model_registry
 from .abstract_trainer import AbstractTabularTrainer
 from .model_presets.presets import get_preset_models
 from .model_presets.presets_distill import get_preset_models_distillation
-from ..registry import ag_model_registry
 
 logger = logging.getLogger(__name__)
 
@@ -67,14 +67,21 @@ class AutoTrainer(AbstractTabularTrainer):
 
         if use_bag_holdout:
             if self.bagged_mode:
-                logger.log(20, f"use_bag_holdout={use_bag_holdout}, will use tuning_data as holdout (will not be used for early stopping).")
+                logger.log(
+                    20,
+                    f"use_bag_holdout={use_bag_holdout}, will use tuning_data as holdout (will not be used for early stopping).",
+                )
             else:
-                logger.warning(f"Warning: use_bag_holdout={use_bag_holdout}, but bagged mode is not enabled. use_bag_holdout will be ignored.")
+                logger.warning(
+                    f"Warning: use_bag_holdout={use_bag_holdout}, but bagged mode is not enabled. use_bag_holdout will be ignored."
+                )
 
         if (y_val is None) or (X_val is None):
             if not self.bagged_mode or use_bag_holdout:
                 if groups is not None:
-                    raise AssertionError(f"Validation data must be manually specified if use_bag_holdout and groups are both specified.")
+                    raise AssertionError(
+                        f"Validation data must be manually specified if use_bag_holdout and groups are both specified."
+                    )
                 if self.bagged_mode:
                     # Need at least 2 samples of each class in train data after split for downstream k-fold splits
                     # to ensure each k-fold has at least 1 sample of each class in training data
@@ -90,7 +97,8 @@ class AutoTrainer(AbstractTabularTrainer):
                     min_cls_count_train=min_cls_count_train,
                 )
                 logger.log(
-                    20, f"Automatically generating train/validation split with holdout_frac={holdout_frac}, Train Rows: {len(X)}, Val Rows: {len(X_val)}"
+                    20,
+                    f"Automatically generating train/validation split with holdout_frac={holdout_frac}, Train Rows: {len(X)}, Val Rows: {len(X_val)}",
                 )
         elif self.bagged_mode:
             if not use_bag_holdout:
@@ -115,9 +123,10 @@ class AutoTrainer(AbstractTabularTrainer):
         if not display_all:
             # FIXME: This isn't correct
             extra_log_str = (
-                f"Large model count detected ({n_configs} configs) ... " f"Only displaying the first 3 models of each family. To see all, set `verbosity=3`.\n"
+                f"Large model count detected ({n_configs} configs) ... "
+                f"Only displaying the first 3 models of each family. To see all, set `verbosity=3`.\n"
             )
-        log_str = f"{extra_log_str}User-specified model hyperparameters to be fit:\n" "{\n"
+        log_str = f"{extra_log_str}User-specified model hyperparameters to be fit:\n{{\n"
         if display_all:
             for k in hyperparameters.keys():
                 # TODO: Make hyperparameters[k] be a list upstream to avoid needing these edge-cases
@@ -189,7 +198,9 @@ class AutoTrainer(AbstractTabularTrainer):
                 else:
                     compiler_configs_new[k] = compiler_configs[k]
             compiler_configs = compiler_configs_new
-        return super().compile(model_names=model_names, with_ancestors=with_ancestors, compiler_configs=compiler_configs)
+        return super().compile(
+            model_names=model_names, with_ancestors=with_ancestors, compiler_configs=compiler_configs
+        )
 
     def _get_model_types_map(self) -> dict[str, AbstractModel]:
         return ag_model_registry.key_to_cls_map()

autogluon/tabular/trainer/model_presets/presets.py

@@ -108,7 +108,9 @@ def get_preset_models(
     if level_key not in hyperparameters.keys() and level_key == "default":
         hyperparameters = {"default": hyperparameters}
     hp_level = hyperparameters[level_key]
-    hp_level = ModelFilter.filter_models(models=hp_level, included_model_types=included_model_types, excluded_model_types=excluded_model_types)
+    hp_level = ModelFilter.filter_models(
+        models=hp_level, included_model_types=included_model_types, excluded_model_types=excluded_model_types
+    )
     model_cfg_priority_dict = defaultdict(list)
     model_type_list = list(hp_level.keys())
     for model_type in model_type_list:
@@ -127,7 +129,9 @@ def get_preset_models(
                 ag_args_fit=ag_args_fit,
                 problem_type=problem_type,
             )
-            model_cfg[AG_ARGS]["priority"] = model_cfg[AG_ARGS].get("priority", default_priorities.get(model_type, DEFAULT_CUSTOM_MODEL_PRIORITY))
+            model_cfg[AG_ARGS]["priority"] = model_cfg[AG_ARGS].get(
+                "priority", default_priorities.get(model_type, DEFAULT_CUSTOM_MODEL_PRIORITY)
+            )
             model_priority = model_cfg[AG_ARGS]["priority"]
             # Check if model_cfg is valid
             is_valid = is_model_cfg_valid(model_cfg, level=level, problem_type=problem_type)
@@ -136,7 +140,11 @@ def get_preset_models(
             if is_valid:
                 model_cfg_priority_dict[model_priority].append(model_cfg)
 
-    model_cfg_priority_list = [model for priority in sorted(model_cfg_priority_dict.keys(), reverse=True) for model in model_cfg_priority_dict[priority]]
+    model_cfg_priority_list = [
+        model
+        for priority in sorted(model_cfg_priority_dict.keys(), reverse=True)
+        for model in model_cfg_priority_dict[priority]
+    ]
 
     if not silent:
         logger.log(20, "Model configs that will be trained (in order):")
@@ -156,7 +164,9 @@ def get_preset_models(
         )
         invalid_name_set.add(model.name)
         if "hyperparameter_tune_kwargs" in model_cfg[AG_ARGS]:
-            model_args_fit[model.name] = {"hyperparameter_tune_kwargs": model_cfg[AG_ARGS]["hyperparameter_tune_kwargs"]}
+            model_args_fit[model.name] = {
+                "hyperparameter_tune_kwargs": model_cfg[AG_ARGS]["hyperparameter_tune_kwargs"]
+            }
         if "ag_args_ensemble" in model_cfg and not model_cfg["ag_args_ensemble"]:
             model_cfg.pop("ag_args_ensemble")
         if not silent:
@@ -165,7 +175,9 @@ def get_preset_models(
     return models, model_args_fit
 
 
-def clean_model_cfg(model_cfg: dict, model_type=None, ag_args=None, ag_args_ensemble=None, ag_args_fit=None, problem_type=None):
+def clean_model_cfg(
+    model_cfg: dict, model_type=None, ag_args=None, ag_args_ensemble=None, ag_args_fit=None, problem_type=None
+):
     model_cfg = _verify_model_cfg(model_cfg=model_cfg, model_type=model_type)
     model_cfg = copy.deepcopy(model_cfg)
     if AG_ARGS not in model_cfg:
@@ -178,7 +190,9 @@ def clean_model_cfg(model_cfg: dict, model_type=None, ag_args=None, ag_args_ense
     model_types = ag_model_registry.key_to_cls_map()
     if not inspect.isclass(model_type):
         if model_type not in model_types:
-            raise AssertionError(f"Unknown model type specified in hyperparameters: '{model_type}'. Valid model types: {list(model_types.keys())}")
+            raise AssertionError(
+                f"Unknown model type specified in hyperparameters: '{model_type}'. Valid model types: {list(model_types.keys())}"
+            )
         model_type = model_types[model_type]
     elif not issubclass(model_type, AbstractModel):
         logger.warning(
@@ -254,7 +268,9 @@ def is_model_cfg_valid(model_cfg, level=1, problem_type=None):
         is_valid = False  # AG_ARGS is required
     elif model_cfg[AG_ARGS].get("model_type", None) is None:
         is_valid = False  # model_type is required
-    elif model_cfg[AG_ARGS].get("hyperparameter_tune_kwargs", None) and model_cfg[AG_ARGS].get("disable_in_hpo", False):
+    elif model_cfg[AG_ARGS].get("hyperparameter_tune_kwargs", None) and model_cfg[AG_ARGS].get(
+        "disable_in_hpo", False
+    ):
         is_valid = False
     elif not model_cfg[AG_ARGS].get("valid_stacker", True) and level > 1:
         is_valid = False  # Not valid as a stacker model
@@ -335,7 +351,13 @@ def model_factory(
         if ensemble_kwargs_model["hyperparameters"] is None:
             ensemble_kwargs_model["hyperparameters"] = {}
         ensemble_kwargs_model["hyperparameters"].update(extra_ensemble_hyperparameters)
-        model_init = ensemble_type(path=path, name=name_stacker, model_base=model_type, model_base_kwargs=model_init_kwargs, **ensemble_kwargs_model)
+        model_init = ensemble_type(
+            path=path,
+            name=name_stacker,
+            model_base=model_type,
+            model_base_kwargs=model_init_kwargs,
+            **ensemble_kwargs_model,
+        )
     else:
         model_init = model_type(**model_init_kwargs)
 
@@ -358,7 +380,9 @@ def get_preset_models_softclass(hyperparameters, invalid_model_names: list = Non
         rf_newparams = {"criterion": "squared_error", "ag_args": {"name_suffix": "MSE"}}
         for i in range(len(rf_params)):
             rf_params[i].update(rf_newparams)
-        rf_params = [j for n, j in enumerate(rf_params) if j not in rf_params[(n + 1) :]]  # Remove duplicates which may arise after overwriting criterion
+        rf_params = [
+            j for n, j in enumerate(rf_params) if j not in rf_params[(n + 1) :]
+        ]  # Remove duplicates which may arise after overwriting criterion
         hyperparameters_standard["RF"] = rf_params
     models, model_args_fit = get_preset_models(
         problem_type=SOFTCLASS,

autogluon/tabular/trainer/model_presets/presets_distill.py

@@ -17,7 +17,16 @@ DEFAULT_DISTILL_PRIORITY = dict(
 )
 
 
-def get_preset_models_distillation(path, problem_type, eval_metric, hyperparameters, level=1, name_suffix="_DSTL", invalid_model_names: list = None, **kwargs):
+def get_preset_models_distillation(
+    path,
+    problem_type,
+    eval_metric,
+    hyperparameters,
+    level=1,
+    name_suffix="_DSTL",
+    invalid_model_names: list = None,
+    **kwargs,
+):
     hyperparameters = process_hyperparameters(hyperparameters)
     level_key = level if level in hyperparameters.keys() else "default"
     if level_key not in hyperparameters.keys() and level_key == "default":
@@ -52,7 +61,12 @@ def get_preset_models_distillation(path, problem_type, eval_metric, hyperparamet
 
     if problem_type == MULTICLASS:
         models, model_args_fit = get_preset_models_softclass(
-            path=path, hyperparameters=hyperparameters, level=level, name_suffix=name_suffix, invalid_model_names=invalid_model_names, **kwargs
+            path=path,
+            hyperparameters=hyperparameters,
+            level=level,
+            name_suffix=name_suffix,
+            invalid_model_names=invalid_model_names,
+            **kwargs,
         )
     else:  # BINARY or REGRESSION
         models, model_args_fit = get_preset_models(

autogluon/tabular/version.py

@@ -1,4 +1,4 @@
 """This is the autogluon version file."""
 
-__version__ = "1.5.1b20260105"
+__version__ = "1.5.1b20260116"
 __lite__ = False

{autogluon_tabular-1.5.1b20260105.dist-info → autogluon_tabular-1.5.1b20260116.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: autogluon.tabular
-Version: 1.5.1b20260105
+Version: 1.5.1b20260116
 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==1.5.1b20260105
-Requires-Dist: autogluon.features==1.5.1b20260105
+Requires-Dist: autogluon.core==1.5.1b20260116
+Requires-Dist: autogluon.features==1.5.1b20260116
 Provides-Extra: lightgbm
 Requires-Dist: lightgbm<4.7,>=4.0; extra == "lightgbm"
 Provides-Extra: catboost
@@ -55,7 +55,7 @@ Requires-Dist: interpret-core<0.8,>=0.7.2; extra == "interpret"
 Provides-Extra: fastai
 Requires-Dist: spacy<3.9; extra == "fastai"
 Requires-Dist: torch<2.10,>=2.6; extra == "fastai"
-Requires-Dist: fastai<2.9,>=2.3.1; extra == "fastai"
+Requires-Dist: fastai<2.8.6,>=2.3.1; extra == "fastai"
 Provides-Extra: tabm
 Requires-Dist: torch<2.10,>=2.6; extra == "tabm"
 Provides-Extra: tabpfn
@@ -77,7 +77,7 @@ Requires-Dist: einops<0.9,>=0.7; extra == "mitra"
 Provides-Extra: tabicl
 Requires-Dist: tabicl<0.2,>=0.1.4; extra == "tabicl"
 Provides-Extra: ray
-Requires-Dist: autogluon.core[all]==1.5.1b20260105; extra == "ray"
+Requires-Dist: autogluon.core[all]==1.5.1b20260116; extra == "ray"
 Provides-Extra: skex
 Requires-Dist: scikit-learn-intelex<2025.10,>=2025.0; extra == "skex"
 Provides-Extra: imodels
@@ -89,38 +89,38 @@ 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: catboost<1.3,>=1.2; extra == "all"
-Requires-Dist: loguru; extra == "all"
-Requires-Dist: transformers; extra == "all"
-Requires-Dist: torch<2.10,>=2.6; extra == "all"
 Requires-Dist: lightgbm<4.7,>=4.0; extra == "all"
+Requires-Dist: loguru; extra == "all"
 Requires-Dist: omegaconf; extra == "all"
-Requires-Dist: huggingface_hub[torch]<1.0; extra == "all"
-Requires-Dist: autogluon.core[all]==1.5.1b20260105; extra == "all"
 Requires-Dist: spacy<3.9; extra == "all"
-Requires-Dist: fastai<2.9,>=2.3.1; extra == "all"
+Requires-Dist: fastai<2.8.6,>=2.3.1; extra == "all"
+Requires-Dist: torch<2.10,>=2.6; extra == "all"
+Requires-Dist: einops<0.9,>=0.7; extra == "all"
+Requires-Dist: autogluon.core[all]==1.5.1b20260116; extra == "all"
 Requires-Dist: einx; extra == "all"
+Requires-Dist: catboost<1.3,>=1.2; extra == "all"
+Requires-Dist: huggingface_hub[torch]<1.0; extra == "all"
 Requires-Dist: xgboost<3.2,>=2.0; extra == "all"
-Requires-Dist: einops<0.9,>=0.7; extra == "all"
+Requires-Dist: transformers; extra == "all"
 Provides-Extra: tabarena
-Requires-Dist: interpret-core<0.8,>=0.7.2; extra == "tabarena"
-Requires-Dist: catboost<1.3,>=1.2; extra == "tabarena"
-Requires-Dist: tabicl<0.2,>=0.1.4; extra == "tabarena"
-Requires-Dist: loguru; extra == "tabarena"
-Requires-Dist: transformers; extra == "tabarena"
-Requires-Dist: torch<2.10,>=2.6; extra == "tabarena"
 Requires-Dist: lightgbm<4.7,>=4.0; extra == "tabarena"
+Requires-Dist: loguru; extra == "tabarena"
+Requires-Dist: tabdpt<1.2,>=1.1.11; extra == "tabarena"
+Requires-Dist: interpret-core<0.8,>=0.7.2; extra == "tabarena"
+Requires-Dist: pytabkit<1.8,>=1.7.2; extra == "tabarena"
 Requires-Dist: omegaconf; extra == "tabarena"
-Requires-Dist: huggingface_hub[torch]<1.0; extra == "tabarena"
-Requires-Dist: autogluon.core[all]==1.5.1b20260105; extra == "tabarena"
+Requires-Dist: fastai<2.8.6,>=2.3.1; extra == "tabarena"
 Requires-Dist: spacy<3.9; extra == "tabarena"
-Requires-Dist: fastai<2.9,>=2.3.1; extra == "tabarena"
-Requires-Dist: tabdpt<1.2,>=1.1.11; extra == "tabarena"
+Requires-Dist: torch<2.10,>=2.6; extra == "tabarena"
+Requires-Dist: einops<0.9,>=0.7; extra == "tabarena"
+Requires-Dist: autogluon.core[all]==1.5.1b20260116; extra == "tabarena"
 Requires-Dist: einx; extra == "tabarena"
-Requires-Dist: xgboost<3.2,>=2.0; extra == "tabarena"
 Requires-Dist: tabpfn<6.2.1,>=6.2.0; extra == "tabarena"
-Requires-Dist: pytabkit<1.8,>=1.7.2; extra == "tabarena"
-Requires-Dist: einops<0.9,>=0.7; extra == "tabarena"
+Requires-Dist: tabicl<0.2,>=0.1.4; extra == "tabarena"
+Requires-Dist: catboost<1.3,>=1.2; extra == "tabarena"
+Requires-Dist: huggingface_hub[torch]<1.0; extra == "tabarena"
+Requires-Dist: xgboost<3.2,>=2.0; extra == "tabarena"
+Requires-Dist: transformers; extra == "tabarena"
 Provides-Extra: tests
 Requires-Dist: interpret-core<0.8,>=0.7.2; extra == "tests"
 Requires-Dist: tabdpt<1.2,>=1.1.11; extra == "tests"