autogluon.tabular 1.3.2b20250722__py3-none-any.whl → 1.4.0__py3-none-any.whl

autogluon/tabular/configs/config_helper.py

@@ -326,7 +326,7 @@ class ConfigBuilder:
         """
         If True, only the best model and its ancestor models are saved in the outputted `predictor`. All other models are deleted.
             If you only care about deploying the most accurate predictor with the smallest file-size and no longer need any of the other trained models or functionality beyond prediction on new data, then set: `keep_only_best=True`, `save_space=True`.
-            This is equivalent to calling `predictor.delete_models(models_to_keep='best', dry_run=False)` directly after `fit()`.
+            This is equivalent to calling `predictor.delete_models(models_to_keep='best')` directly after `fit()`.
         If used with `refit_full` and `set_best_to_refit_full`, the best model will be the refit_full model, and the original bagged best model will be deleted.
             `refit_full` will be automatically set to 'best' in this case to avoid training models which will be later deleted.
         """

autogluon/tabular/configs/hyperparameter_configs.py

@@ -1,6 +1,7 @@
 import copy
 
 from .zeroshot.zeroshot_portfolio_2023 import hyperparameter_portfolio_zeroshot_2023
+from .zeroshot.zeroshot_portfolio_2025 import hyperparameter_portfolio_zeroshot_2025_small
 
 # Dictionary of preset hyperparameter configurations.
 hyperparameter_config_dict = dict(
@@ -31,10 +32,6 @@ hyperparameter_config_dict = dict(
             {"criterion": "entropy", "ag_args": {"name_suffix": "Entr", "problem_types": ["binary", "multiclass"]}},
             {"criterion": "squared_error", "ag_args": {"name_suffix": "MSE", "problem_types": ["regression", "quantile"]}},
         ],
-        "KNN": [
-            {"weights": "uniform", "ag_args": {"name_suffix": "Unif"}},
-            {"weights": "distance", "ag_args": {"name_suffix": "Dist"}},
-        ],
     },
     # Results in smaller models. Generally will make inference speed much faster and disk usage much lower, but with worse accuracy.
     light={
@@ -117,269 +114,9 @@ hyperparameter_config_dict = dict(
         # 'IM_BOOSTEDRULES': [{'n_estimators': 5}, {'n_estimators': 10}],
         # 'IM_HSTREE': [{'max_rules': 6}, {'max_rules': 12}, {'max_rules': 18}],
     },
-    zeroshot_hpo={
-        "XT": [{"min_samples_leaf": 1, "max_leaf_nodes": 15000, "max_features": 0.5, "ag_args": {"name_suffix": "_r19", "priority": 20}}],
-        "RF": [{"min_samples_leaf": 5, "max_leaf_nodes": 50000, "max_features": 0.5, "ag_args": {"name_suffix": "_r5", "priority": 19}}],
-        "GBM": [
-            {
-                "extra_trees": False,
-                "feature_fraction": 0.7248284762542815,
-                "learning_rate": 0.07947286942946127,
-                "min_data_in_leaf": 50,
-                "num_leaves": 89,
-                "ag_args": {"name_suffix": "_r158", "priority": 18},
-            },
-            {
-                "extra_trees": True,
-                "feature_fraction": 0.7832570544199176,
-                "learning_rate": 0.021720607471727896,
-                "min_data_in_leaf": 3,
-                "num_leaves": 21,
-                "ag_args": {"name_suffix": "_r118", "priority": 17},
-            },
-            {
-                "extra_trees": True,
-                "feature_fraction": 0.7113010892989156,
-                "learning_rate": 0.012535427424259274,
-                "min_data_in_leaf": 16,
-                "num_leaves": 48,
-                "ag_args": {"name_suffix": "_r97", "priority": 16},
-            },
-            {
-                "extra_trees": True,
-                "feature_fraction": 0.45555769907110816,
-                "learning_rate": 0.009591347321206594,
-                "min_data_in_leaf": 50,
-                "num_leaves": 110,
-                "ag_args": {"name_suffix": "_r71", "priority": 15},
-            },
-            {
-                "extra_trees": False,
-                "feature_fraction": 0.40979710161022476,
-                "learning_rate": 0.008708890211023034,
-                "min_data_in_leaf": 3,
-                "num_leaves": 80,
-                "ag_args": {"name_suffix": "_r111", "priority": 14},
-            },
-        ],
-        "FASTAI": [
-            {
-                "bs": 1024,
-                "emb_drop": 0.6167722379778131,
-                "epochs": 44,
-                "layers": [200, 100, 50],
-                "lr": 0.053440377855629266,
-                "ps": 0.48477211305443607,
-                "ag_args": {"name_suffix": "_r25", "priority": 13},
-            },
-            {
-                "bs": 1024,
-                "emb_drop": 0.6046989241462619,
-                "epochs": 48,
-                "layers": [200, 100, 50],
-                "lr": 0.00775309042164966,
-                "ps": 0.09244767444160731,
-                "ag_args": {"name_suffix": "_r51", "priority": 12},
-            },
-            {
-                "bs": 512,
-                "emb_drop": 0.6557225316526186,
-                "epochs": 49,
-                "layers": [200, 100],
-                "lr": 0.023627682025564638,
-                "ps": 0.519566584552178,
-                "ag_args": {"name_suffix": "_r82", "priority": 11},
-            },
-            {
-                "bs": 2048,
-                "emb_drop": 0.4066210919034579,
-                "epochs": 43,
-                "layers": [400, 200],
-                "lr": 0.0029598312717673434,
-                "ps": 0.4378695797438974,
-                "ag_args": {"name_suffix": "_r121", "priority": 10},
-            },
-            {
-                "bs": 128,
-                "emb_drop": 0.44339037504795686,
-                "epochs": 31,
-                "layers": [400, 200, 100],
-                "lr": 0.008615195908919904,
-                "ps": 0.19220253419114286,
-                "ag_args": {"name_suffix": "_r145", "priority": 9},
-            },
-            {
-                "bs": 128,
-                "emb_drop": 0.12106594798980945,
-                "epochs": 38,
-                "layers": [200, 100, 50],
-                "lr": 0.037991970245029975,
-                "ps": 0.33120008492595093,
-                "ag_args": {"name_suffix": "_r173", "priority": 8},
-            },
-            {
-                "bs": 128,
-                "emb_drop": 0.4599138419358,
-                "epochs": 47,
-                "layers": [200, 100],
-                "lr": 0.03888383281136287,
-                "ps": 0.28193673177122863,
-                "ag_args": {"name_suffix": "_r128", "priority": 7},
-            },
-        ],
-        "CAT": [
-            {"depth": 5, "l2_leaf_reg": 4.774992314058497, "learning_rate": 0.038551267822920274, "ag_args": {"name_suffix": "_r16", "priority": 6}},
-            {"depth": 4, "l2_leaf_reg": 1.9950125740798321, "learning_rate": 0.028091050379971633, "ag_args": {"name_suffix": "_r42", "priority": 5}},
-            {"depth": 6, "l2_leaf_reg": 1.8298803017644376, "learning_rate": 0.017844259810823604, "ag_args": {"name_suffix": "_r93", "priority": 4}},
-            {"depth": 7, "l2_leaf_reg": 4.81099604606794, "learning_rate": 0.019085060180573103, "ag_args": {"name_suffix": "_r44", "priority": 3}},
-        ],
-    },
-    zeroshot_hpo_hybrid={
-        "NN_TORCH": {},
-        "XT": [
-            {"criterion": "gini", "ag_args": {"name_suffix": "Gini", "problem_types": ["binary", "multiclass"]}},
-            {"criterion": "entropy", "ag_args": {"name_suffix": "Entr", "problem_types": ["binary", "multiclass"]}},
-            {"criterion": "squared_error", "ag_args": {"name_suffix": "MSE", "problem_types": ["regression", "quantile"]}},
-            {"min_samples_leaf": 1, "max_leaf_nodes": 15000, "max_features": 0.5, "ag_args": {"name_suffix": "_r19", "priority": 20}},
-        ],
-        "RF": [
-            {"criterion": "gini", "ag_args": {"name_suffix": "Gini", "problem_types": ["binary", "multiclass"]}},
-            {"criterion": "entropy", "ag_args": {"name_suffix": "Entr", "problem_types": ["binary", "multiclass"]}},
-            {"criterion": "squared_error", "ag_args": {"name_suffix": "MSE", "problem_types": ["regression", "quantile"]}},
-            {"min_samples_leaf": 5, "max_leaf_nodes": 50000, "max_features": 0.5, "ag_args": {"name_suffix": "_r5", "priority": 19}},
-        ],
-        "GBM": [
-            {"extra_trees": True, "ag_args": {"name_suffix": "XT"}},
-            {},
-            {
-                "learning_rate": 0.03,
-                "num_leaves": 128,
-                "feature_fraction": 0.9,
-                "min_data_in_leaf": 3,
-                "ag_args": {"name_suffix": "Large", "priority": 0, "hyperparameter_tune_kwargs": None},
-            },
-            {
-                "extra_trees": False,
-                "feature_fraction": 0.7248284762542815,
-                "learning_rate": 0.07947286942946127,
-                "min_data_in_leaf": 50,
-                "num_leaves": 89,
-                "ag_args": {"name_suffix": "_r158", "priority": 18},
-            },
-            {
-                "extra_trees": True,
-                "feature_fraction": 0.7832570544199176,
-                "learning_rate": 0.021720607471727896,
-                "min_data_in_leaf": 3,
-                "num_leaves": 21,
-                "ag_args": {"name_suffix": "_r118", "priority": 17},
-            },
-            {
-                "extra_trees": True,
-                "feature_fraction": 0.7113010892989156,
-                "learning_rate": 0.012535427424259274,
-                "min_data_in_leaf": 16,
-                "num_leaves": 48,
-                "ag_args": {"name_suffix": "_r97", "priority": 16},
-            },
-            {
-                "extra_trees": True,
-                "feature_fraction": 0.45555769907110816,
-                "learning_rate": 0.009591347321206594,
-                "min_data_in_leaf": 50,
-                "num_leaves": 110,
-                "ag_args": {"name_suffix": "_r71", "priority": 15},
-            },
-            {
-                "extra_trees": False,
-                "feature_fraction": 0.40979710161022476,
-                "learning_rate": 0.008708890211023034,
-                "min_data_in_leaf": 3,
-                "num_leaves": 80,
-                "ag_args": {"name_suffix": "_r111", "priority": 14},
-            },
-        ],
-        "XGB": {},
-        "FASTAI": [
-            {},
-            {
-                "bs": 1024,
-                "emb_drop": 0.6167722379778131,
-                "epochs": 44,
-                "layers": [200, 100, 50],
-                "lr": 0.053440377855629266,
-                "ps": 0.48477211305443607,
-                "ag_args": {"name_suffix": "_r25", "priority": 13},
-            },
-            {
-                "bs": 1024,
-                "emb_drop": 0.6046989241462619,
-                "epochs": 48,
-                "layers": [200, 100, 50],
-                "lr": 0.00775309042164966,
-                "ps": 0.09244767444160731,
-                "ag_args": {"name_suffix": "_r51", "priority": 12},
-            },
-            {
-                "bs": 512,
-                "emb_drop": 0.6557225316526186,
-                "epochs": 49,
-                "layers": [200, 100],
-                "lr": 0.023627682025564638,
-                "ps": 0.519566584552178,
-                "ag_args": {"name_suffix": "_r82", "priority": 11},
-            },
-            {
-                "bs": 2048,
-                "emb_drop": 0.4066210919034579,
-                "epochs": 43,
-                "layers": [400, 200],
-                "lr": 0.0029598312717673434,
-                "ps": 0.4378695797438974,
-                "ag_args": {"name_suffix": "_r121", "priority": 10},
-            },
-            {
-                "bs": 128,
-                "emb_drop": 0.44339037504795686,
-                "epochs": 31,
-                "layers": [400, 200, 100],
-                "lr": 0.008615195908919904,
-                "ps": 0.19220253419114286,
-                "ag_args": {"name_suffix": "_r145", "priority": 9},
-            },
-            {
-                "bs": 128,
-                "emb_drop": 0.12106594798980945,
-                "epochs": 38,
-                "layers": [200, 100, 50],
-                "lr": 0.037991970245029975,
-                "ps": 0.33120008492595093,
-                "ag_args": {"name_suffix": "_r173", "priority": 8},
-            },
-            {
-                "bs": 128,
-                "emb_drop": 0.4599138419358,
-                "epochs": 47,
-                "layers": [200, 100],
-                "lr": 0.03888383281136287,
-                "ps": 0.28193673177122863,
-                "ag_args": {"name_suffix": "_r128", "priority": 7},
-            },
-        ],
-        "CAT": [
-            {},
-            {"depth": 5, "l2_leaf_reg": 4.774992314058497, "learning_rate": 0.038551267822920274, "ag_args": {"name_suffix": "_r16", "priority": 6}},
-            {"depth": 4, "l2_leaf_reg": 1.9950125740798321, "learning_rate": 0.028091050379971633, "ag_args": {"name_suffix": "_r42", "priority": 5}},
-            {"depth": 6, "l2_leaf_reg": 1.8298803017644376, "learning_rate": 0.017844259810823604, "ag_args": {"name_suffix": "_r93", "priority": 4}},
-            {"depth": 7, "l2_leaf_reg": 4.81099604606794, "learning_rate": 0.019085060180573103, "ag_args": {"name_suffix": "_r44", "priority": 3}},
-        ],
-        "KNN": [
-            {"weights": "uniform", "ag_args": {"name_suffix": "Unif"}},
-            {"weights": "distance", "ag_args": {"name_suffix": "Dist"}},
-        ],
-    },
     zeroshot=hyperparameter_portfolio_zeroshot_2023,
     zeroshot_2023=hyperparameter_portfolio_zeroshot_2023,
+    zeroshot_2025_tabfm=hyperparameter_portfolio_zeroshot_2025_small,
 )
 
 tabpfnmix_default = {

autogluon/tabular/configs/presets_configs.py

@@ -1,25 +1,5 @@
 # Dictionary of preset fit() parameter configurations.
 tabular_presets_dict = dict(
-    # [EXPERIMENTAL PRESET] The `experimental_quality` preset may be changed or removed without warning.
-    # This preset acts as a testing ground for cutting edge features and models which could later be added to the `best_quality` preset in future releases.
-    # Using this preset can lead to unexpected crashes, as it hasn't been as thoroughly tested as other presets.
-    # Absolute best predictive accuracy with **zero** consideration to inference time or disk usage.
-    # Recommended for applications that benefit from the best possible model accuracy and **do not** care about inference speed.
-    # Significantly stronger than `best_quality`, but can be over 10x slower in inference.
-    # Uses pre-trained tabular foundation models, which add a minimum of 1-2 GB to the predictor artifact's size.
-    # For best results, use as large of an instance as possible with as many CPU cores as possible (ideally 64+ cores)
-    # DOES NOT SUPPORT GPU.
-    # Aliases: experimental
-    experimental_quality={
-        "auto_stack": True,
-        "dynamic_stacking": "auto",
-        "num_bag_sets": 1,
-        "hyperparameters": "experimental",
-        "fit_strategy": "parallel",
-        "num_gpus": 0,
-        "time_limit": 3600,
-    },
-
     # Best predictive accuracy with little consideration to inference time or disk usage. Achieve even better results by specifying a large time_limit value.
     # Recommended for applications that benefit from the best possible model accuracy.
     # Aliases: best
@@ -94,7 +74,52 @@ tabular_presets_dict = dict(
     # ------------------------------------------
     # Experimental presets. Only use these presets if you are ok with unstable and potentially poor performing presets.
     #  Experimental presets can be removed or changed without warning.
-    # No Experimental Presets in v1.0
+
+    # [EXPERIMENTAL PRESET] The `extreme` preset may be changed or removed without warning.
+    # This preset acts as a testing ground for cutting edge features and models which could later be added to the `best_quality` preset in future releases.
+    # Using this preset can lead to unexpected crashes, as it hasn't been as thoroughly tested as other presets.
+    # Absolute best predictive accuracy with **zero** consideration to inference time or disk usage.
+    # Recommended for applications that benefit from the best possible model accuracy and **do not** care about inference speed.
+    # Significantly stronger than `best_quality`, but can be over 10x slower in inference.
+    # Uses pre-trained tabular foundation models, which add a minimum of 1-2 GB to the predictor artifact's size.
+    # For best results, use as large of an instance as possible with a GPU and as many CPU cores as possible (ideally 64+ cores)
+    # Aliases: extreme, experimental, experimental_quality
+    # GPU STRONGLY RECOMMENDED
+    extreme_quality={
+        "auto_stack": True,
+        "dynamic_stacking": "auto",
+        "num_bag_sets": 1,
+        "_experimental_dynamic_hyperparameters": True,
+        "hyperparameters": None,
+        "time_limit": 3600,
+    },
+
+    # Preset with a portfolio learned from TabArena v0.1: https://tabarena.ai/
+    # Uses tabular foundation models: TabPFNv2, TabICL, Mitra
+    # Uses deep learning model: TabM
+    # Uses tree models: LightGBM, CatBoost, XGBoost
+    # Extremely powerful on small datasets with <= 10000 training samples.
+    # Requires a GPU for best results.
+    tabarena={
+        "auto_stack": True,
+        "dynamic_stacking": "auto",
+        "num_bag_sets": 1,
+        "num_stack_levels": 0,
+        "hyperparameters": "zeroshot_2025_tabfm",
+        "time_limit": 3600,
+    },
+
+    # DOES NOT SUPPORT GPU.
+    experimental_quality_v120={
+        "auto_stack": True,
+        "dynamic_stacking": "auto",
+        "num_bag_sets": 1,
+        "hyperparameters": "experimental",
+        "fit_strategy": "parallel",
+        "num_gpus": 0,
+        "time_limit": 3600,
+    },
+
     # ------------------------------------------
     # ------------------------------------------
     # ------------------------------------------
@@ -103,7 +128,7 @@ tabular_presets_dict = dict(
 
 # Alias preset name alternatives
 tabular_presets_alias = dict(
-    experimental="experimental_quality",
+    extreme="extreme_quality",
     best="best_quality",
     high="high_quality",
     high_quality_fast_inference_only_refit="high_quality",
@@ -111,9 +136,12 @@ tabular_presets_alias = dict(
     good_quality_faster_inference_only_refit="good_quality",
     medium="medium_quality",
     medium_quality_faster_train="medium_quality",
-    eq="experimental_quality",
+    eq="extreme_quality",
     bq="best_quality",
     hq="high_quality",
     gq="good_quality",
     mq="medium_quality",
+    experimental="extreme_quality",
+    experimental_quality="extreme_quality",
+    experimental_quality_v140="extreme_quality",
 )

autogluon/tabular/configs/zeroshot/zeroshot_portfolio_2023.py

@@ -793,5 +793,4 @@ hyperparameter_portfolio_zeroshot_2023 = {
         {"max_features": 1.0, "max_leaf_nodes": 40459, "min_samples_leaf": 1, "ag_args": {"name_suffix": "_r197", "priority": -78}},
         {"max_features": "sqrt", "max_leaf_nodes": 29702, "min_samples_leaf": 2, "ag_args": {"name_suffix": "_r126", "priority": -86}},
     ],
-    "KNN": [{"weights": "uniform", "ag_args": {"name_suffix": "Unif"}}, {"weights": "distance", "ag_args": {"name_suffix": "Dist"}}],
 }