autogluon.tabular 1.2.1b20250225__tar.gz → 1.2.1b20250227__tar.gz

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: autogluon.tabular
-Version: 1.2.1b20250225
+Version: 1.2.1b20250227
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/learner/abstract_learner.py

@@ -39,19 +39,19 @@ class AbstractTabularLearner(AbstractLearner):
         self,
         path_context: str,
         label: str,
-        feature_generator: PipelineFeatureGenerator,
+        feature_generator: PipelineFeatureGenerator | None = None,
         ignored_columns: list = None,
-        label_count_threshold=10,
-        problem_type=None,
-        quantile_levels=None,
-        eval_metric=None,
-        positive_class=None,
-        cache_data=True,
-        is_trainer_present=False,
-        random_state=0,
-        sample_weight=None,
-        weight_evaluation=False,
-        groups=None,
+        label_count_threshold: int = 10,
+        problem_type: str | None = None,
+        quantile_levels: list[float] | None = None,
+        eval_metric: Scorer | None = None,
+        positive_class: str | None = None,
+        cache_data: bool = True,
+        is_trainer_present: bool = False,
+        random_state: int = 0,
+        sample_weight: str | None = None,
+        weight_evaluation: bool = False,
+        groups: str | None = None,
     ):
         super().__init__(path_context=path_context, random_state=random_state)
         self.label = label

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/learner/default_learner.py

@@ -43,16 +43,17 @@ class DefaultLearner(AbstractTabularLearner):
     def _fit(
         self,
         X: DataFrame,
-        X_val: DataFrame = None,
-        X_test: DataFrame = None,
-        X_unlabeled: DataFrame = None,
-        holdout_frac=0.1,
-        num_bag_folds=0,
-        num_bag_sets=1,
-        time_limit=None,
-        infer_limit=None,
-        infer_limit_batch_size=None,
-        verbosity=2,
+        X_val: DataFrame | None = None,
+        X_test: DataFrame | None = None,
+        X_unlabeled: DataFrame | None = None,
+        holdout_frac: float = 0.1,
+        num_bag_folds: int = 0,
+        num_bag_sets: int = 1,
+        time_limit: float | None = None,
+        infer_limit: float | None = None,
+        infer_limit_batch_size: int | None = None,
+        verbosity: int = 2,
+        raise_on_model_failure: bool = False,
         **trainer_fit_kwargs,
     ):
         """Arguments:
@@ -121,6 +122,7 @@ class DefaultLearner(AbstractTabularLearner):
             save_data=self.cache_data,
             random_state=self.random_state,
             verbosity=verbosity,
+            raise_on_model_failure=raise_on_model_failure,
         )
 
         self.trainer_path = trainer.path

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/automm/automm_model.py

@@ -26,6 +26,8 @@ logger = logging.getLogger(__name__)
 
 
 class MultiModalPredictorModel(AbstractModel):
+    ag_key = "AG_AUTOMM"
+    ag_name = "MultiModalPredictor"
     _NN_MODEL_NAME = "automm_model"
 
     def __init__(self, **kwargs):

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/automm/ft_transformer.py

@@ -12,6 +12,9 @@ logger = logging.getLogger(__name__)
 
 # TODO: Add unit tests
 class FTTransformerModel(MultiModalPredictorModel):
+    ag_key = "FT_TRANSFORMER"
+    ag_name = "FTTransformer"
+
     def __init__(self, **kwargs):
         """Wrapper of autogluon.multimodal.MultiModalPredictor.
 

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/catboost/catboost_model.py

@@ -2,6 +2,7 @@ import logging
 import math
 import os
 import time
+from types import MappingProxyType
 
 import numpy as np
 import pandas as pd
@@ -30,6 +31,12 @@ class CatBoostModel(AbstractModel):
 
     Hyperparameter options: https://catboost.ai/en/docs/references/training-parameters
     """
+    ag_key = "CAT"
+    ag_name = "CatBoost"
+    ag_priority = 70
+    ag_priority_by_problem_type = MappingProxyType({
+        SOFTCLASS: 60
+    })
 
     def __init__(self, **kwargs):
         super().__init__(**kwargs)

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/fastainn/tabular_nn_fastai.py

@@ -8,6 +8,7 @@ import warnings
 from builtins import classmethod
 from functools import partial
 from pathlib import Path
+from types import MappingProxyType
 from typing import Union
 
 import numpy as np
@@ -28,7 +29,7 @@ from autogluon.common.features.types import (
 from autogluon.common.utils.pandas_utils import get_approximate_df_mem_usage
 from autogluon.common.utils.resource_utils import ResourceManager
 from autogluon.common.utils.try_import import try_import_fastai
-from autogluon.core.constants import BINARY, QUANTILE, REGRESSION
+from autogluon.core.constants import BINARY, MULTICLASS, QUANTILE, REGRESSION
 from autogluon.core.hpo.constants import RAY_BACKEND
 from autogluon.core.models import AbstractModel
 from autogluon.core.utils.exceptions import TimeLimitExceeded
@@ -92,6 +93,14 @@ class NNFastAiTabularModel(AbstractModel):
         'early.stopping.min_delta': 0.0001,
         'early.stopping.patience': 10,
     """
+    ag_key = "FASTAI"
+    ag_name = "NeuralNetFastAI"
+    ag_priority = 50
+    # Increase priority for multiclass since neural networks
+    # scale better than trees as a function of n_classes.
+    ag_priority_by_problem_type = MappingProxyType({
+        MULTICLASS: 95,
+    })
 
     model_internals_file_name = "model-internals.pkl"
 

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/fasttext/fasttext_model.py

@@ -21,6 +21,9 @@ logger = logging.getLogger(__name__)
 
 
 class FastTextModel(AbstractModel):
+    ag_key = "FASTTEXT"
+    ag_name = "FastText"
+
     model_bin_file_name = "fasttext.ftz"
 
     def __init__(self, **kwargs):

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/image_prediction/image_predictor.py

@@ -22,6 +22,8 @@ class ImagePredictorModel(MultiModalPredictorModel):
     Additionally has special null image handling to improve performance in the presence of null images (aka image path of '')
         Note: null handling has not been compared to the built-in null handling of MultimodalPredictor yet.
     """
+    ag_key = "AG_IMAGE_NN"
+    ag_name = "ImagePredictor"
 
     def __init__(self, **kwargs):
         super().__init__(**kwargs)

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/imodels/imodels_models.py

@@ -75,6 +75,9 @@ class _IModelsModel(AbstractModel):
 
 
 class RuleFitModel(_IModelsModel):
+    ag_key = "IM_RULEFIT"
+    ag_name = "RuleFit"
+
     def get_model(self):
         try_import_imodels()
         from imodels import RuleFitClassifier, RuleFitRegressor
@@ -86,6 +89,9 @@ class RuleFitModel(_IModelsModel):
 
 
 class GreedyTreeModel(_IModelsModel):
+    ag_key = "IM_GREEDYTREE"
+    ag_name = "GreedyTree"
+
     def get_model(self):
         try_import_imodels()
         from imodels import GreedyTreeClassifier
@@ -98,6 +104,9 @@ class GreedyTreeModel(_IModelsModel):
 
 
 class BoostedRulesModel(_IModelsModel):
+    ag_key = "IM_BOOSTEDRULES"
+    ag_name = "BoostedRules"
+
     def get_model(self):
         try_import_imodels()
         from imodels import BoostedRulesClassifier
@@ -109,6 +118,9 @@ class BoostedRulesModel(_IModelsModel):
 
 
 class HSTreeModel(_IModelsModel):
+    ag_key = "IM_HSTREE"
+    ag_name = "HierarchicalShrinkageTree"
+
     def get_model(self):
         try_import_imodels()
         from imodels import HSTreeClassifierCV, HSTreeRegressorCV
@@ -120,6 +132,9 @@ class HSTreeModel(_IModelsModel):
 
 
 class FigsModel(_IModelsModel):
+    ag_key = "IM_FIGS"
+    ag_name = "Figs"
+
     def get_model(self):
         try_import_imodels()
         from imodels import FIGSClassifier, FIGSRegressor

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/knn/knn_model.py

@@ -22,6 +22,9 @@ class KNNModel(AbstractModel):
     """
     KNearestNeighbors model (scikit-learn): https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsClassifier.html
     """
+    ag_key = "KNN"
+    ag_name = "KNeighbors"
+    ag_priority = 100
 
     def __init__(self, **kwargs):
         super().__init__(**kwargs)

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/lgb/lgb_model.py

@@ -7,6 +7,7 @@ import random
 import re
 import time
 import warnings
+from types import MappingProxyType
 
 import numpy as np
 import pandas as pd
@@ -40,6 +41,12 @@ class LGBModel(AbstractModel):
     Extra hyperparameter options:
         ag.early_stop : int, specifies the early stopping rounds. Defaults to an adaptive strategy. Recommended to keep default.
     """
+    ag_key = "GBM"
+    ag_name = "LightGBM"
+    ag_priority = 90
+    ag_priority_by_problem_type = MappingProxyType({
+        SOFTCLASS: 100
+    })
 
     def __init__(self, **kwargs):
         super().__init__(**kwargs)

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/lr/lr_model.py

@@ -38,6 +38,9 @@ class LinearModel(AbstractModel):
 
         'regression': https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Ridge.html#sklearn.linear_model.Ridge
     """
+    ag_key = "LR"
+    ag_name = "LinearModel"
+    ag_priority = 30
 
     def __init__(self, **kwargs):
         super().__init__(**kwargs)

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/rf/rf_model.py

@@ -27,6 +27,9 @@ class RFModel(AbstractModel):
     """
     Random Forest model (scikit-learn): https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html
     """
+    ag_key = "RF"
+    ag_name = "RandomForest"
+    ag_priority = 80
 
     def __init__(self, **kwargs):
         super().__init__(**kwargs)

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/tab_transformer/tab_transformer_model.py

@@ -40,6 +40,8 @@ class TabTransformerModel(AbstractNeuralNetworkModel):
     and applies them to the use case of tabular data. Specifically, this makes TabTransformer suitable for unsupervised
     training of Tabular data with a subsequent fine-tuning step on labeled data.
     """
+    ag_key = "TRANSF"
+    ag_name = "Transformer"
 
     params_file_name = "tab_trans_params.pth"
 

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/tabpfn/tabpfn_model.py

@@ -22,6 +22,9 @@ class TabPFNModel(AbstractModel):
     To use this model, `tabpfn` must be installed.
     To install TabPFN, you can run `pip install autogluon.tabular[tabpfn]` or `pip install tabpfn`.
     """
+    ag_key = "TABPFN"
+    ag_name = "TabPFN"
+    ag_priority = 110
 
     def __init__(self, **kwargs):
         super().__init__(**kwargs)

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/tabpfnmix/tabpfnmix_model.py

@@ -35,6 +35,10 @@ class TabPFNMixModel(AbstractModel):
 
     For more information, refer to the `./_internals/README.md` file.
     """
+    ag_key = "TABPFNMIX"
+    ag_name = "TabPFNMix"
+    ag_priority = 45
+
     weights_file_name = "model.pt"
 
     def __init__(self, **kwargs):

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/tabular_nn/torch/tabular_nn_torch.py

@@ -47,6 +47,9 @@ class TabularNeuralNetTorchModel(AbstractNeuralNetworkModel):
         ag.early_stop : int | str, default = "default"
             Specifies the early stopping rounds. Defaults to an adaptive strategy. Recommended to keep default.
     """
+    ag_key = "NN_TORCH"
+    ag_name = "NeuralNetTorch"
+    ag_priority = 25
 
     # Constants used throughout this class:
     unique_category_str = np.nan  # string used to represent missing values and unknown categories for categorical features.

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/text_prediction/text_prediction_v1_model.py

@@ -19,6 +19,9 @@ logger = logging.getLogger(__name__)
 class TextPredictorModel(MultiModalPredictorModel):
     """MultimodalPredictor that doesn't use image features"""
 
+    ag_key = "AG_TEXT_NN"
+    ag_name = "TextPredictor"
+
     def _get_default_auxiliary_params(self) -> dict:
         default_auxiliary_params = super()._get_default_auxiliary_params()
         extra_auxiliary_params = dict(

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/vowpalwabbit/vowpalwabbit_model.py

@@ -38,6 +38,9 @@ class VowpalWabbitModel(AbstractModel):
     VowpalWabbit Command Line args: https://github.com/VowpalWabbit/vowpal_wabbit/wiki/Command-line-arguments
 
     """
+    ag_key = "VW"
+    ag_name = "VowpalWabbit"
+    ag_priority = 10
 
     model_internals_file_name = "model-internals.pkl"
 

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/xgboost/xgboost_model.py

@@ -27,6 +27,9 @@ class XGBoostModel(AbstractModel):
 
     Hyperparameter options: https://xgboost.readthedocs.io/en/latest/parameter.html
     """
+    ag_key = "XGB"
+    ag_name = "XGBoost"
+    ag_priority = 40
 
     def __init__(self, **kwargs):
         super().__init__(**kwargs)

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/models/xt/xt_model.py

@@ -7,6 +7,9 @@ class XTModel(RFModel):
     """
     Extra Trees model (scikit-learn): https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.ExtraTreesClassifier.html#sklearn.ensemble.ExtraTreesClassifier
     """
+    ag_key = "XT"
+    ag_name = "ExtraTrees"
+    ag_priority = 60
 
     def _get_model_type(self):
         if self.problem_type == REGRESSION:

{autogluon.tabular-1.2.1b20250225 → autogluon.tabular-1.2.1b20250227}/src/autogluon/tabular/predictor/predictor.py

@@ -990,6 +990,14 @@ class TabularPredictor:
                 to any amount of labeled data.
             verbosity : int
                 If specified, overrides the existing `predictor.verbosity` value.
+            raise_on_model_failure: bool, default = False
+                If True, will raise on any exception during model training.
+                    This is useful when using a debugger during development to identify the cause of model failures.
+                    This should only be used for debugging.
+                If False, will try to skip to the next model if an exception occurred during model training.
+                    This is the default logic and is a core principle of AutoGluon's design.
+
+                .. versionadded:: 1.3.0
             raise_on_no_models_fitted: bool, default = True
                 If True, will raise a RuntimeError if no models were successfully fit during `fit()`.
             calibrate: bool or str, default = 'auto'
@@ -1109,6 +1117,7 @@ class TabularPredictor:
         delay_bag_sets: bool = kwargs["delay_bag_sets"]
         test_data = kwargs["test_data"]
         learning_curves = kwargs["learning_curves"]
+        raise_on_model_failure = kwargs["raise_on_model_failure"]
 
         if ag_args is None:
             ag_args = {}
@@ -1256,6 +1265,7 @@ class TabularPredictor:
             verbosity=verbosity,
             use_bag_holdout=use_bag_holdout,
             callbacks=callbacks,
+            raise_on_model_failure=raise_on_model_failure,
         )
         ag_post_fit_kwargs = dict(
             keep_only_best=kwargs["keep_only_best"],
@@ -4330,7 +4340,14 @@ class TabularPredictor:
             reduce_children=reduce_children,
         )
 
-    def delete_models(self, models_to_keep=None, models_to_delete=None, allow_delete_cascade=False, delete_from_disk=True, dry_run=True):
+    def delete_models(
+        self,
+        models_to_keep: str | list[str] | None = None,
+        models_to_delete: str | list[str] | None = None,
+        allow_delete_cascade: bool = False,
+        delete_from_disk: bool = True,
+        dry_run: bool | None = None,
+    ):
         """
         Deletes models from `predictor`.
         This can be helpful to minimize memory usage and disk usage, particularly for model deployment.
@@ -4341,13 +4358,13 @@ class TabularPredictor:
 
         Parameters
         ----------
-        models_to_keep : str or list, default = None
+        models_to_keep : str or list[str], default = None
             Name of model or models to not delete.
             All models that are not specified and are also not required as a dependency of any model in `models_to_keep` will be deleted.
             Specify `models_to_keep='best'` to keep only the best model and its model dependencies.
             `models_to_delete` must be None if `models_to_keep` is set.
             To see the list of possible model names, use: `predictor.model_names()` or `predictor.leaderboard()`.
-        models_to_delete : str or list, default = None
+        models_to_delete : str or list[str], default = None
             Name of model or models to delete.
             All models that are not specified but depend on a model in `models_to_delete` will also be deleted.
             `models_to_keep` must be None if `models_to_delete` is set.
@@ -4361,10 +4378,19 @@ class TabularPredictor:
             WARNING: This deletes the entire directory for the deleted models, and ALL FILES located there.
                 It is highly recommended to first run with `dry_run=True` to understand which directories will be deleted.
         dry_run : bool, default = True
+            WARNING: Starting in v1.4.0 dry_run will default to False.
             If `True`, then deletions don't occur, and logging statements are printed describing what would have occurred.
             Set `dry_run=False` to perform the deletions.
 
         """
+        if dry_run is None:
+            warnings.warn(
+                f"dry_run was not specified for `TabularPredictor.delete_models`. dry_run prior to version 1.4.0 defaults to True. "
+                f"Starting in version 1.4, AutoGluon will default dry_run to False. "
+                f"If you want to maintain the current logic in future versions, explicitly specify `dry_run=True`.",
+                category=FutureWarning,
+            )
+            dry_run = True
         self._assert_is_fit("delete_models")
         if models_to_keep == "best":
             models_to_keep = self.model_best
@@ -5020,6 +5046,7 @@ class TabularPredictor:
             # learning curves and test data (for logging purposes only)
             learning_curves=False,
             test_data=None,
+            raise_on_model_failure=False,
         )
         kwargs, ds_valid_keys = self._sanitize_dynamic_stacking_kwargs(kwargs)
         kwargs = self._validate_fit_extra_kwargs(kwargs, extra_valid_keys=list(fit_kwargs_default.keys()) + ds_valid_keys)

autogluon.tabular-1.2.1b20250227/src/autogluon/tabular/register/__init__.py

@@ -0,0 +1,2 @@
+from ._model_register import ModelRegister
+from ._ag_model_register import ag_model_register

autogluon.tabular-1.2.1b20250227/src/autogluon/tabular/register/_ag_model_register.py

@@ -0,0 +1,66 @@
+from autogluon.core.models import (
+    DummyModel,
+    GreedyWeightedEnsembleModel,
+    SimpleWeightedEnsembleModel,
+)
+
+from . import ModelRegister
+from ..models import (
+    BoostedRulesModel,
+    CatBoostModel,
+    FastTextModel,
+    FigsModel,
+    FTTransformerModel,
+    GreedyTreeModel,
+    HSTreeModel,
+    ImagePredictorModel,
+    KNNModel,
+    LGBModel,
+    LinearModel,
+    MultiModalPredictorModel,
+    NNFastAiTabularModel,
+    RFModel,
+    RuleFitModel,
+    TabPFNMixModel,
+    TabPFNModel,
+    TabularNeuralNetTorchModel,
+    TextPredictorModel,
+    VowpalWabbitModel,
+    XGBoostModel,
+    XTModel,
+)
+from ..models.tab_transformer.tab_transformer_model import TabTransformerModel
+
+
+# When adding a new model officially to AutoGluon, the model class should be added to the bottom of this list.
+REGISTERED_MODEL_CLS_LST = [
+    RFModel,
+    XTModel,
+    KNNModel,
+    LGBModel,
+    CatBoostModel,
+    XGBoostModel,
+    TabularNeuralNetTorchModel,
+    LinearModel,
+    NNFastAiTabularModel,
+    TabTransformerModel,
+    TextPredictorModel,
+    ImagePredictorModel,
+    MultiModalPredictorModel,
+    FTTransformerModel,
+    TabPFNModel,
+    TabPFNMixModel,
+    FastTextModel,
+    VowpalWabbitModel,
+    GreedyWeightedEnsembleModel,
+    SimpleWeightedEnsembleModel,
+    RuleFitModel,
+    GreedyTreeModel,
+    FigsModel,
+    HSTreeModel,
+    BoostedRulesModel,
+    DummyModel,
+]
+
+# TODO: Replace logic in `autogluon.tabular.trainer.model_presets.presets` with `ag_model_register`
+ag_model_register = ModelRegister(model_cls_list=REGISTERED_MODEL_CLS_LST)