autogluon.tabular 1.2.1b20250417__py3-none-any.whl → 1.2.1b20250418__py3-none-any.whl

autogluon/tabular/configs/config_helper.py

@@ -9,7 +9,7 @@ from autogluon.core.scheduler import scheduler_factory
 from autogluon.features import AutoMLPipelineFeatureGenerator
 from autogluon.tabular.configs.hyperparameter_configs import hyperparameter_config_dict
 from autogluon.tabular.configs.presets_configs import tabular_presets_dict
-from autogluon.tabular.trainer.model_presets.presets import MODEL_TYPES
+from autogluon.tabular.register import ag_model_register
 
 
 class FeatureGeneratorBuilder:
@@ -107,6 +107,10 @@ class ConfigBuilder:
     def __init__(self):
         self.config = {}
 
+    def _valid_keys(self):
+        valid_keys = [m for m in ag_model_register.keys if m not in ["ENS_WEIGHTED", "SIMPLE_ENS_WEIGHTED"]]
+        return valid_keys
+
     def presets(self, presets: Union[str, list, dict]) -> ConfigBuilder:
         """
         List of preset configurations for various arguments in `fit()`. Can significantly impact predictive accuracy, memory-footprint, and inference latency of trained models, and various other properties of the returned `predictor`.
@@ -137,7 +141,7 @@ class ConfigBuilder:
         return self
 
     def hyperparameters(self, hyperparameters: Union[str, dict]) -> ConfigBuilder:
-        valid_keys = [m for m in MODEL_TYPES.keys() if m not in ["ENS_WEIGHTED", "SIMPLE_ENS_WEIGHTED"]]
+        valid_keys = self._valid_keys()
         valid_str_values = list(hyperparameter_config_dict.keys())
         if isinstance(hyperparameters, str):
             assert hyperparameters in hyperparameter_config_dict, f"{hyperparameters} is not one of the valid presets {valid_str_values}"
@@ -270,7 +274,7 @@ class ConfigBuilder:
         Useful when a particular model type such as 'KNN' or 'custom' is not desired but altering the `hyperparameters` dictionary is difficult or time-consuming.
             Example: To exclude both 'KNN' and 'custom' models, specify `excluded_model_types=['KNN', 'custom']`.
         """
-        valid_keys = [m for m in MODEL_TYPES.keys() if m not in ["ENS_WEIGHTED", "SIMPLE_ENS_WEIGHTED"]]
+        valid_keys = self._valid_keys()
         if not isinstance(models, list):
             models = [models]
         for model in models:
@@ -285,7 +289,7 @@ class ConfigBuilder:
         Useful when only the particular models should be trained such as 'KNN' or 'custom', but altering the `hyperparameters` dictionary is difficult or time-consuming.
             Example: To keep only 'KNN' and 'custom' models, specify `included_model_types=['KNN', 'custom']`.
         """
-        valid_keys = [m for m in MODEL_TYPES.keys() if m not in ["ENS_WEIGHTED", "SIMPLE_ENS_WEIGHTED"]]
+        valid_keys = self._valid_keys()
         if not isinstance(models, list):
             models = [models]
 

autogluon/tabular/predictor/predictor.py

@@ -55,7 +55,7 @@ from ..configs.hyperparameter_configs import get_hyperparameter_config
 from ..configs.presets_configs import tabular_presets_alias, tabular_presets_dict
 from ..learner import AbstractTabularLearner, DefaultLearner
 from ..trainer.abstract_trainer import AbstractTabularTrainer
-from ..trainer.model_presets.presets import MODEL_TYPES
+from ..register import ag_model_register
 from ..version import __version__
 
 logger = logging.getLogger(__name__)  # return autogluon root logger
@@ -516,7 +516,6 @@ class TabularPredictor:
                     'FT_TRANSFORMER' (Tabular Transformer, GPU is recommended. Does not scale well to >100 features.)
                     'FASTTEXT' (FastText. Note: Has not been tested for a long time.)
                     'TABPFN' (TabPFN. Does not scale well to >100 features or >1000 rows, and does not support regression. Extremely slow inference speed.)
-                    'VW' (VowpalWabbit. Note: Has not been tested for a long time.)
                     'AG_TEXT_NN' (Multimodal Text+Tabular model, GPU is required. Recommended to instead use its successor, 'AG_AUTOMM'.)
                     'AG_IMAGE_NN' (Image model, GPU is required. Recommended to instead use its successor, 'AG_AUTOMM'.)
                 If a certain key is missing from hyperparameters, then `fit()` will not train any models of that type. Omitting a model key from hyperparameters is equivalent to including this model key in `excluded_model_types`.
@@ -977,17 +976,10 @@ class TabularPredictor:
                         sklearn CountVectorizer object to use in TextNgramFeatureGenerator.
                         Only used if `enable_text_ngram_features=True`.
             unlabeled_data : pd.DataFrame, default = None
-                [Experimental Parameter]
-                Collection of data without labels that we can use to pretrain on. This is the same schema as train_data, except
-                without the labels. Currently, unlabeled_data is only used for pretraining a TabTransformer model.
-                If you do not specify 'TRANSF' with unlabeled_data, then no pretraining will occur and unlabeled_data will be ignored!
-                After the pretraining step, we will finetune using the TabTransformer model as well. If TabTransformer is ensembled
-                with other models, like in typical AutoGluon fashion, then the output of this "pretrain/finetune" will be ensembled
-                with other models, which will not used the unlabeled_data. The "pretrain/finetune flow" is also known as semi-supervised learning.
-                The typical use case for unlabeled_data is to add signal to your model where you may not have sufficient training
-                data. e.g. 500 hand-labeled samples (perhaps a hard human task), whole data set (unlabeled) is thousands/millions.
-                However, this isn't the only use case. Given enough unlabeled data(millions of rows), you may see improvements
-                to any amount of labeled data.
+                [Experimental Parameter] UNUSED.
+                Collection of data without labels that we can use to pretrain on.
+                This is the same schema as train_data, except without the labels.
+                Currently, unlabeled_data is not used by any model.
             verbosity : int
                 If specified, overrides the existing `predictor.verbosity` value.
             raise_on_model_failure: bool, default = False
@@ -5680,12 +5672,13 @@ class TabularPredictor:
             for key in hyperparameters:
                 models_in_hyperparameters.add(key)
         models_in_hyperparameters_raw_text_compatible = []
+        model_key_to_cls_map = ag_model_register.key_to_cls_map()
         for m in models_in_hyperparameters:
             if isinstance(m, str):
                 # TODO: Technically the use of MODEL_TYPES here is a hack since we should derive valid types from trainer,
                 #  but this is required prior to trainer existing.
-                if m in MODEL_TYPES:
-                    m = MODEL_TYPES[m]
+                if m in model_key_to_cls_map:
+                    m = model_key_to_cls_map[m]
                 else:
                     continue
             if m._get_class_tags().get("handles_text", False):

autogluon/tabular/trainer/auto_trainer.py

@@ -5,8 +5,9 @@ from autogluon.core.utils import generate_train_test_split
 
 from ..models.lgb.lgb_model import LGBModel
 from .abstract_trainer import AbstractTabularTrainer
-from .model_presets.presets import MODEL_TYPES, get_preset_models
+from .model_presets.presets import get_preset_models
 from .model_presets.presets_distill import get_preset_models_distillation
+from ..register import ag_model_register
 
 logger = logging.getLogger(__name__)
 
@@ -186,4 +187,4 @@ class AutoTrainer(AbstractTabularTrainer):
         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 MODEL_TYPES
+        return ag_model_register.key_to_cls_map()

autogluon/tabular/trainer/model_presets/presets.py

@@ -33,31 +33,8 @@ from ...version import __version__
 
 logger = logging.getLogger(__name__)
 
-# TODO: Replace with ag_model_register
-# Problem type specific model priority overrides (will update default values in DEFAULT_MODEL_PRIORITY)
-PROBLEM_TYPE_MODEL_PRIORITY = {
-    MULTICLASS: dict(
-        FASTAI=95,
-    ),
-}
-
-# TODO: Replace with ag_model_register
-DEFAULT_SOFTCLASS_PRIORITY = dict(
-    GBM=100,
-    RF=80,
-    CAT=60,
-    custom=0,
-)
-
 DEFAULT_CUSTOM_MODEL_PRIORITY = 0
 
-# FIXME: Don't do this, use ag_model_register lazily so users can register custom models before calling fit
-DEFAULT_MODEL_PRIORITY = {ag_model_register.key(model_cls): ag_model_register.priority(model_cls) for model_cls in ag_model_register.model_cls_list}
-DEFAULT_MODEL_NAMES = ag_model_register.name_map()
-REGISTERED_MODEL_CLS_LST = ag_model_register.model_cls_list
-MODEL_TYPES = ag_model_register.key_to_cls_map()
-
-
 VALID_AG_ARGS_KEYS = {
     "name",
     "name_main",
@@ -122,9 +99,10 @@ def get_preset_models(
         invalid_name_set.update(invalid_model_names)
 
     if default_priorities is None:
-        default_priorities = copy.deepcopy(DEFAULT_MODEL_PRIORITY)
-        if problem_type in PROBLEM_TYPE_MODEL_PRIORITY:
-            default_priorities.update(PROBLEM_TYPE_MODEL_PRIORITY[problem_type])
+        priority_cls_map = ag_model_register.priority_map(problem_type=problem_type)
+        default_priorities = {
+            ag_model_register.key(model_cls): priority for model_cls, priority in priority_cls_map.items()
+        }
 
     level_key = level if level in hyperparameters.keys() else "default"
     if level_key not in hyperparameters.keys() and level_key == "default":
@@ -197,20 +175,22 @@ def clean_model_cfg(model_cfg: dict, model_type=None, ag_args=None, ag_args_ense
     if model_cfg[AG_ARGS]["model_type"] is None:
         raise AssertionError(f"model_type was not specified for model! Model: {model_cfg}")
     model_type = model_cfg[AG_ARGS]["model_type"]
+    model_types = ag_model_register.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())}")
-        model_type = MODEL_TYPES[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())}")
+        model_type = model_types[model_type]
     elif not issubclass(model_type, AbstractModel):
         logger.warning(
             f"Warning: Custom model type {model_type} does not inherit from {AbstractModel}. This may lead to instability. Consider wrapping {model_type} with an implementation of {AbstractModel}!"
         )
     else:
-        logger.log(20, f"Custom Model Type Detected: {model_type}")
+        if not ag_model_register.exists(model_type):
+            logger.log(20, f"Custom Model Type Detected: {model_type}")
     model_cfg[AG_ARGS]["model_type"] = model_type
     model_type_real = model_cfg[AG_ARGS]["model_type"]
     if not inspect.isclass(model_type_real):
-        model_type_real = MODEL_TYPES[model_type_real]
+        model_type_real = model_types[model_type_real]
     default_ag_args = model_type_real._get_default_ag_args()
     if ag_args is not None:
         model_extra_ag_args = ag_args.copy()
@@ -300,10 +280,13 @@ def model_factory(
         invalid_name_set = set()
     model_type = model[AG_ARGS]["model_type"]
     if not inspect.isclass(model_type):
-        model_type = MODEL_TYPES[model_type]
+        model_type = ag_model_register.key_to_cls(model_type)
     name_orig = model[AG_ARGS].get("name", None)
     if name_orig is None:
-        name_main = model[AG_ARGS].get("name_main", DEFAULT_MODEL_NAMES.get(model_type, model_type.__name__))
+        ag_name = model_type.ag_name
+        if ag_name is None:
+            ag_name = model_type.__name__
+        name_main = model[AG_ARGS].get("name_main", ag_name)
         name_prefix = model[AG_ARGS].get("name_prefix", "")
         name_suff = model[AG_ARGS].get("name_suffix", "")
         name_orig = name_prefix + name_main + name_suff
@@ -372,7 +355,6 @@ def get_preset_models_softclass(hyperparameters, invalid_model_names: list = Non
         problem_type=SOFTCLASS,
         eval_metric=soft_log_loss,
         hyperparameters=hyperparameters_standard,
-        default_priorities=DEFAULT_SOFTCLASS_PRIORITY,
         invalid_model_names=invalid_model_names,
         **kwargs,
     )

autogluon/tabular/version.py

@@ -1,4 +1,4 @@
 """This is the autogluon version file."""
 
-__version__ = "1.2.1b20250417"
+__version__ = "1.2.1b20250418"
 __lite__ = False

{autogluon.tabular-1.2.1b20250417.dist-info → autogluon.tabular-1.2.1b20250418.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: autogluon.tabular
-Version: 1.2.1b20250417
+Version: 1.2.1b20250418
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community
@@ -41,19 +41,19 @@ Requires-Dist: scipy<1.16,>=1.5.4
 Requires-Dist: pandas<2.3.0,>=2.0.0
 Requires-Dist: scikit-learn<1.7.0,>=1.4.0
 Requires-Dist: networkx<4,>=3.0
-Requires-Dist: autogluon.core==1.2.1b20250417
-Requires-Dist: autogluon.features==1.2.1b20250417
+Requires-Dist: autogluon.core==1.2.1b20250418
+Requires-Dist: autogluon.features==1.2.1b20250418
 Provides-Extra: all
-Requires-Dist: xgboost<3.1,>=2.0; extra == "all"
-Requires-Dist: numpy<2.0.0,>=1.25; extra == "all"
 Requires-Dist: einops<0.9,>=0.7; extra == "all"
+Requires-Dist: catboost<1.3,>=1.2; extra == "all"
+Requires-Dist: xgboost<3.1,>=2.0; extra == "all"
 Requires-Dist: torch<2.7,>=2.2; extra == "all"
-Requires-Dist: autogluon.core[all]==1.2.1b20250417; extra == "all"
-Requires-Dist: fastai<2.9,>=2.3.1; extra == "all"
+Requires-Dist: autogluon.core[all]==1.2.1b20250418; extra == "all"
 Requires-Dist: huggingface-hub[torch]; extra == "all"
-Requires-Dist: catboost<1.3,>=1.2; extra == "all"
-Requires-Dist: lightgbm<4.7,>=4.0; extra == "all"
 Requires-Dist: spacy<3.8; extra == "all"
+Requires-Dist: fastai<2.9,>=2.3.1; extra == "all"
+Requires-Dist: numpy<2.0.0,>=1.25; extra == "all"
+Requires-Dist: lightgbm<4.7,>=4.0; extra == "all"
 Provides-Extra: catboost
 Requires-Dist: numpy<2.0.0,>=1.25; extra == "catboost"
 Requires-Dist: catboost<1.3,>=1.2; extra == "catboost"
@@ -66,7 +66,7 @@ Requires-Dist: imodels<2.1.0,>=1.3.10; extra == "imodels"
 Provides-Extra: lightgbm
 Requires-Dist: lightgbm<4.7,>=4.0; extra == "lightgbm"
 Provides-Extra: ray
-Requires-Dist: autogluon.core[all]==1.2.1b20250417; extra == "ray"
+Requires-Dist: autogluon.core[all]==1.2.1b20250418; extra == "ray"
 Provides-Extra: skex
 Requires-Dist: scikit-learn-intelex<2025.5,>=2024.0; extra == "skex"
 Provides-Extra: skl2onnx

{autogluon.tabular-1.2.1b20250417.dist-info → autogluon.tabular-1.2.1b20250418.dist-info}/RECORD

@@ -1,8 +1,8 @@
-autogluon.tabular-1.2.1b20250417-py3.9-nspkg.pth,sha256=cQGwpuGPqg1GXscIwt-7PmME1OnSpD-7ixkikJ31WAY,554
+autogluon.tabular-1.2.1b20250418-py3.9-nspkg.pth,sha256=cQGwpuGPqg1GXscIwt-7PmME1OnSpD-7ixkikJ31WAY,554
 autogluon/tabular/__init__.py,sha256=2OXpJCvENRHubBTYNIPpHX93WWuFZzsJBtTZbNVHVas,400
-autogluon/tabular/version.py,sha256=9DNociU3CkjmMks3rFL-2UfsFfw26T7_cq6VAom-ic4,91
+autogluon/tabular/version.py,sha256=0zPPTGxy3-f1WXziWDw672VIyU_d25Uy_412DqQY6ww,91
 autogluon/tabular/configs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-autogluon/tabular/configs/config_helper.py,sha256=Pb2aW9Z9w77pYKPRVZ3nBzHY3KJaiEJSJ747zZcJIVk,21132
+autogluon/tabular/configs/config_helper.py,sha256=wLgu94NjV-l2fwZacpKqjPfvk8E_RwAl_L1hfH5xO8E,21085
 autogluon/tabular/configs/feature_generator_presets.py,sha256=EV5Ym8VW15q92MwOUpTi7wZFS2QooM51fLg3RdUsn-M,1223
 autogluon/tabular/configs/hyperparameter_configs.py,sha256=hp8J7g5GY3Couz929f1ItawobCw-isLTZJBcLoJY348,18035
 autogluon/tabular/configs/presets_configs.py,sha256=2Jlq1X9sVmVlyUxWsZpDV7ma2TncH5Y2HXDML7x2gYc,6810
@@ -130,7 +130,7 @@ autogluon/tabular/models/xt/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMp
 autogluon/tabular/models/xt/xt_model.py,sha256=qOHJ5h1lHI7uYJfbl0BWm-29R3MNp2WeZB9ptcq5Xis,1003
 autogluon/tabular/predictor/__init__.py,sha256=zCMgjxQlWpDWnr1l1xjBCiK3rWC3N3RoD8UXBnazT74,107
 autogluon/tabular/predictor/interpretable_predictor.py,sha256=5UeKgnMFsfY65tiO3kxfHBPr03lyswLrgdtjPhI0Y7Q,6934
-autogluon/tabular/predictor/predictor.py,sha256=jOkpypHAPrL2nsI4iypVkZV90TpMORK-G_Ixr3Kw3XQ,357182
+autogluon/tabular/predictor/predictor.py,sha256=tcgoqZw5WZB6ztcoqkeTYOUi_zH86tTKVt4_8f9rXMo,356183
 autogluon/tabular/register/__init__.py,sha256=7CLOTWIUho0wi4eAwhYJ5Y0PfvNCWKnRwlw3bwYoTNE,93
 autogluon/tabular/register/_ag_model_register.py,sha256=afDg51h07vImG8p2YZvzT5IT1lkpti4m2n92FhbDcfw,1414
 autogluon/tabular/register/_model_register.py,sha256=jqSg0d89dXAAcp-OT4II90ce994ByKMMzAYmpkyaRbI,6824
@@ -140,17 +140,17 @@ autogluon/tabular/testing/generate_datasets.py,sha256=UXPNfviUNZqGcx4mTYIloJxRED
 autogluon/tabular/testing/model_fit_helper.py,sha256=ZjWpw2nyeFnsrccmkfQtx3qbA8HJx282XX2rwdS-LIs,3808
 autogluon/tabular/trainer/__init__.py,sha256=PW_PGL-tWoQzx3ES2S53bQEZOtsRWTYiM9QdOqsk0dI,38
 autogluon/tabular/trainer/abstract_trainer.py,sha256=F9bT78KHyQi96FbPs6ufaswVQJBzxoK3sTXyRXXpK_g,232416
-autogluon/tabular/trainer/auto_trainer.py,sha256=FyRWM8iUJuDvw_aqV5EV_xdh_pb-nHzAvG1sbEhvs0g,8680
+autogluon/tabular/trainer/auto_trainer.py,sha256=vhDCvz3fsTFamVsx2wwMMOUhgCBUmj7vgspzwfrT4zY,8731
 autogluon/tabular/trainer/model_presets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-autogluon/tabular/trainer/model_presets/presets.py,sha256=bTPGPyz07a7GG6327yO6ryuWbNc1aq3hF1qzZL-Xe4c,16733
+autogluon/tabular/trainer/model_presets/presets.py,sha256=IMBRSBc-djd35gkb2rtXrW4Ez5Sb27Inl8B8JSpEArs,16120
 autogluon/tabular/trainer/model_presets/presets_distill.py,sha256=MnFC2GJc6RmDBNAGbsO2XMfo3PjR8cUrZoilWW8gTYQ,3295
 autogluon/tabular/tuning/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 autogluon/tabular/tuning/feature_pruner.py,sha256=9iNku8gVbYEkjuKlyITPJDicsNkoraaQOlINQq9iZlQ,6877
-autogluon.tabular-1.2.1b20250417.dist-info/LICENSE,sha256=CeipvOyAZxBGUsFoaFqwkx54aPnIKEtm9a5u2uXxEws,10142
-autogluon.tabular-1.2.1b20250417.dist-info/METADATA,sha256=KtK6Wl-kEnQ2kNajgxKGz_lQUDPD6hZqlef4klkqsrM,14069
-autogluon.tabular-1.2.1b20250417.dist-info/NOTICE,sha256=7nPQuj8Kp-uXsU0S5so3-2dNU5EctS5hDXvvzzehd7E,114
-autogluon.tabular-1.2.1b20250417.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-autogluon.tabular-1.2.1b20250417.dist-info/namespace_packages.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
-autogluon.tabular-1.2.1b20250417.dist-info/top_level.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
-autogluon.tabular-1.2.1b20250417.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-autogluon.tabular-1.2.1b20250417.dist-info/RECORD,,
+autogluon.tabular-1.2.1b20250418.dist-info/LICENSE,sha256=CeipvOyAZxBGUsFoaFqwkx54aPnIKEtm9a5u2uXxEws,10142
+autogluon.tabular-1.2.1b20250418.dist-info/METADATA,sha256=8GEi9EnAc9Zkju0dilwliJbVDqkYZf1uusuadOK4WrU,14069
+autogluon.tabular-1.2.1b20250418.dist-info/NOTICE,sha256=7nPQuj8Kp-uXsU0S5so3-2dNU5EctS5hDXvvzzehd7E,114
+autogluon.tabular-1.2.1b20250418.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+autogluon.tabular-1.2.1b20250418.dist-info/namespace_packages.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
+autogluon.tabular-1.2.1b20250418.dist-info/top_level.txt,sha256=giERA4R78OkJf2ijn5slgjURlhRPzfLr7waIcGkzYAo,10
+autogluon.tabular-1.2.1b20250418.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+autogluon.tabular-1.2.1b20250418.dist-info/RECORD,,