snowflake-ml-python 1.5.3__py3-none-any.whl → 1.6.0__py3-none-any.whl

snowflake/ml/model/_packager/model_runtime/model_runtime.py

@@ -35,7 +35,7 @@ class ModelRuntime:
         self,
         name: str,
         env: model_env.ModelEnv,
-        imports: Optional[List[pathlib.PurePosixPath]] = None,
+        imports: Optional[List[str]] = None,
         is_gpu: bool = False,
         loading_from_file: bool = False,
     ) -> None:
@@ -75,7 +75,7 @@ class ModelRuntime:
             snowpark_ml_lib_path = runtime_base_path / "snowflake-ml-python.zip"
             file_utils.zip_python_package(str(snowpark_ml_lib_path), "snowflake.ml")
             snowpark_ml_lib_rel_path = pathlib.PurePosixPath(snowpark_ml_lib_path.relative_to(packager_path).as_posix())
-            self.imports.append(snowpark_ml_lib_rel_path)
+            self.imports.append(str(snowpark_ml_lib_rel_path))
 
         self.runtime_env.conda_env_rel_path = self.runtime_rel_path / self.runtime_env.conda_env_rel_path
         self.runtime_env.pip_requirements_rel_path = self.runtime_rel_path / self.runtime_env.pip_requirements_rel_path
@@ -108,6 +108,4 @@ class ModelRuntime:
             warnings.simplefilter("ignore")
             env.load_from_conda_file(packager_path / conda_env_rel_path)
             env.load_from_pip_file(packager_path / pip_requirements_rel_path)
-        return ModelRuntime(
-            name=name, env=env, imports=list(map(pathlib.PurePosixPath, loaded_dict["imports"])), loading_from_file=True
-        )
+        return ModelRuntime(name=name, env=env, imports=loaded_dict["imports"], loading_from_file=True)

snowflake/ml/model/custom_model.py

@@ -1,6 +1,6 @@
 import functools
 import inspect
-from typing import Any, Callable, Coroutine, Dict, Generator, Optional
+from typing import Any, Callable, Coroutine, Dict, Generator, List, Optional
 
 import anyio
 import pandas as pd
@@ -168,7 +168,7 @@ class CustomModel:
     def _get_infer_methods(
         self,
     ) -> Generator[Callable[[model_types.CustomModelType, pd.DataFrame], pd.DataFrame], None, None]:
-        """Returns all methods in CLS with DECORATOR as the outermost decorator."""
+        """Returns all methods in CLS with `inference_api` decorator as the outermost decorator."""
         for cls_method_str in dir(self):
             cls_method = getattr(self, cls_method_str)
             if getattr(cls_method, "_is_inference_api", False):
@@ -177,6 +177,18 @@ class CustomModel:
                 else:
                     raise TypeError("A non-method inference API function is not supported.")
 
+    def _get_partitioned_infer_methods(self) -> List[str]:
+        """Returns all methods in CLS with `partitioned_inference_api` as the outermost decorator."""
+        rv = []
+        for cls_method_str in dir(self):
+            cls_method = getattr(self, cls_method_str)
+            if getattr(cls_method, "_is_partitioned_inference_api", False):
+                if inspect.ismethod(cls_method):
+                    rv.append(cls_method_str)
+                else:
+                    raise TypeError("A non-method inference API function is not supported.")
+        return rv
+
 
 def _validate_predict_function(func: Callable[[model_types.CustomModelType, pd.DataFrame], pd.DataFrame]) -> None:
     """Validate the user provided predict method.
@@ -219,3 +231,11 @@ def inference_api(
 ) -> Callable[[model_types.CustomModelType, pd.DataFrame], pd.DataFrame]:
     func.__dict__["_is_inference_api"] = True
     return func
+
+
+def partitioned_inference_api(
+    func: Callable[[model_types.CustomModelType, pd.DataFrame], pd.DataFrame]
+) -> Callable[[model_types.CustomModelType, pd.DataFrame], pd.DataFrame]:
+    func.__dict__["_is_inference_api"] = True
+    func.__dict__["_is_partitioned_inference_api"] = True
+    return func

snowflake/ml/model/model_signature.py

@@ -232,7 +232,7 @@ def _validate_pandas_df(data: pd.DataFrame, features: Sequence[core.BaseFeatureS
                     ),
                 )
         else:
-            if isinstance(data_col[0], list):
+            if isinstance(data_col.iloc[0], list):
                 if not ft_shape:
                     raise snowml_exceptions.SnowflakeMLException(
                         error_code=error_codes.INVALID_DATA,
@@ -266,7 +266,7 @@ def _validate_pandas_df(data: pd.DataFrame, features: Sequence[core.BaseFeatureS
                             ),
                         )
 
-            elif isinstance(data_col[0], np.ndarray):
+            elif isinstance(data_col.iloc[0], np.ndarray):
                 if not ft_shape:
                     raise snowml_exceptions.SnowflakeMLException(
                         error_code=error_codes.INVALID_DATA,
@@ -297,7 +297,7 @@ def _validate_pandas_df(data: pd.DataFrame, features: Sequence[core.BaseFeatureS
                             ),
                         )
 
-            elif isinstance(data_col[0], str):
+            elif isinstance(data_col.iloc[0], str):
                 if ft_shape is not None:
                     raise snowml_exceptions.SnowflakeMLException(
                         error_code=error_codes.INVALID_DATA,
@@ -316,7 +316,7 @@ def _validate_pandas_df(data: pd.DataFrame, features: Sequence[core.BaseFeatureS
                         ),
                     )
 
-            elif isinstance(data_col[0], bytes):
+            elif isinstance(data_col.iloc[0], bytes):
                 if ft_shape is not None:
                     raise snowml_exceptions.SnowflakeMLException(
                         error_code=error_codes.INVALID_DATA,

snowflake/ml/model/type_hints.py

@@ -232,11 +232,13 @@ class BaseModelSaveOption(TypedDict):
     _legacy_save: NotRequired[bool]
     function_type: NotRequired[Literal["FUNCTION", "TABLE_FUNCTION"]]
     method_options: NotRequired[Dict[str, ModelMethodSaveOptions]]
+    include_pip_dependencies: NotRequired[bool]
 
 
 class CatBoostModelSaveOptions(BaseModelSaveOption):
     target_methods: NotRequired[Sequence[str]]
     cuda_version: NotRequired[str]
+    enable_explainability: NotRequired[bool]
 
 
 class CustomModelSaveOption(BaseModelSaveOption):
@@ -250,10 +252,12 @@ class SKLModelSaveOptions(BaseModelSaveOption):
 class XGBModelSaveOptions(BaseModelSaveOption):
     target_methods: NotRequired[Sequence[str]]
     cuda_version: NotRequired[str]
+    enable_explainability: NotRequired[bool]
 
 
 class LGBMModelSaveOptions(BaseModelSaveOption):
     target_methods: NotRequired[Sequence[str]]
+    enable_explainability: NotRequired[bool]
 
 
 class SNOWModelSaveOptions(BaseModelSaveOption):
@@ -313,15 +317,84 @@ ModelSaveOption = Union[
 ]
 
 
-class ModelLoadOption(TypedDict):
-    """Options for loading the model.
+class BaseModelLoadOption(TypedDict):
+    """Options for loading the model."""
+
+    ...
+
+
+class CatBoostModelLoadOptions(BaseModelLoadOption):
+    use_gpu: NotRequired[bool]
+
+
+class CustomModelLoadOption(BaseModelLoadOption):
+    ...
+
+
+class SKLModelLoadOptions(BaseModelLoadOption):
+    ...
+
+
+class XGBModelLoadOptions(BaseModelLoadOption):
+    use_gpu: NotRequired[bool]
+
+
+class LGBMModelLoadOptions(BaseModelLoadOption):
+    ...
+
+
+class SNOWModelLoadOptions(BaseModelLoadOption):
+    ...
 
-    use_gpu: Enable GPU-specific loading logic.
-    """
 
+class PyTorchLoadOptions(BaseModelLoadOption):
     use_gpu: NotRequired[bool]
 
 
+class TorchScriptLoadOptions(BaseModelLoadOption):
+    use_gpu: NotRequired[bool]
+
+
+class TensorflowLoadOptions(BaseModelLoadOption):
+    ...
+
+
+class MLFlowLoadOptions(BaseModelLoadOption):
+    ...
+
+
+class HuggingFaceLoadOptions(BaseModelLoadOption):
+    use_gpu: NotRequired[bool]
+    device_map: NotRequired[str]
+    device: NotRequired[Union[str, int]]
+
+
+class SentenceTransformersLoadOptions(BaseModelLoadOption):
+    use_gpu: NotRequired[bool]
+
+
+class LLMLoadOptions(BaseModelLoadOption):
+    ...
+
+
+ModelLoadOption = Union[
+    BaseModelLoadOption,
+    CatBoostModelLoadOptions,
+    CustomModelLoadOption,
+    LGBMModelLoadOptions,
+    SKLModelLoadOptions,
+    XGBModelLoadOptions,
+    SNOWModelLoadOptions,
+    PyTorchLoadOptions,
+    TorchScriptLoadOptions,
+    TensorflowLoadOptions,
+    MLFlowLoadOptions,
+    HuggingFaceLoadOptions,
+    SentenceTransformersLoadOptions,
+    LLMLoadOptions,
+]
+
+
 class SnowparkContainerServiceDeployDetails(TypedDict):
     """
     Attributes:

snowflake/ml/modeling/_internal/snowpark_implementations/distributed_hpo_trainer.py

@@ -41,7 +41,7 @@ cp.register_pickle_by_value(inspect.getmodule(snowpark_dataframe_utils.cast_snow
 
 _PROJECT = "ModelDevelopment"
 DEFAULT_UDTF_NJOBS = 3
-ENABLE_EFFICIENT_MEMORY_USAGE = False
+ENABLE_EFFICIENT_MEMORY_USAGE = True
 _UDTF_STAGE_NAME = f"MEMORY_EFFICIENT_UDTF_{str(uuid.uuid4()).replace('-', '_')}"
 
 
@@ -377,6 +377,7 @@ class DistributedHPOTrainer(SnowparkModelTrainer):
             anonymous=True,
             imports=imports,  # type: ignore[arg-type]
             statement_params=sproc_statement_params,
+            execute_as="caller",
         )
         def _distributed_search(
             session: Session,
@@ -782,6 +783,7 @@ class DistributedHPOTrainer(SnowparkModelTrainer):
             anonymous=True,
             imports=imports,  # type: ignore[arg-type]
             statement_params=sproc_statement_params,
+            execute_as="caller",
         )
         def _distributed_search(
             session: Session,

snowflake/ml/modeling/_internal/snowpark_implementations/distributed_search_udf_file.py

@@ -83,7 +83,19 @@ def _load_data_into_udf() -> Tuple[
     with open(local_fit_and_score_kwargs_file_path, mode="rb") as local_fit_and_score_kwargs_file_obj:
         fit_and_score_kwargs = cp.load(local_fit_and_score_kwargs_file_obj)
 
-    # convert dataframe to numpy would save memory consumption
+    # Convert dataframe to numpy would save memory consumption
+    # Except for Pipeline, we need to keep the dataframe for the column names
+    from sklearn.pipeline import Pipeline
+    if isinstance(base_estimator, Pipeline):
+        return (
+            df[CONSTANTS['input_cols']],
+            df[CONSTANTS['label_cols']].squeeze(),
+            indices,
+            params_to_evaluate,
+            base_estimator,
+            fit_and_score_kwargs,
+            CONSTANTS
+        )
     return (
         df[CONSTANTS['input_cols']].to_numpy(),
         df[CONSTANTS['label_cols']].squeeze().to_numpy(),

snowflake/ml/modeling/_internal/snowpark_implementations/snowpark_handlers.py

@@ -286,6 +286,7 @@ class SnowparkTransformHandlers:
             session=session,
             statement_params=statement_params,
             anonymous=True,
+            execute_as="caller",
         )
         def score_wrapper_sproc(
             session: Session,

snowflake/ml/modeling/_internal/snowpark_implementations/snowpark_trainer.py

@@ -207,6 +207,7 @@ class SnowparkModelTrainer:
             session=self.session,
             statement_params=statement_params,
             anonymous=True,
+            execute_as="caller",
         )
 
         return fit_wrapper_sproc
@@ -236,6 +237,7 @@ class SnowparkModelTrainer:
             replace=True,
             session=self.session,
             statement_params=statement_params,
+            execute_as="caller",
         )
 
         self.session._FIT_WRAPPER_SPROCS[fit_sproc_key] = fit_wrapper_sproc  # type: ignore[attr-defined]
@@ -493,6 +495,7 @@ class SnowparkModelTrainer:
             session=self.session,
             statement_params=statement_params,
             anonymous=True,
+            execute_as="caller",
         )
 
         return fit_predict_wrapper_sproc
@@ -524,6 +527,7 @@ class SnowparkModelTrainer:
             replace=True,
             session=self.session,
             statement_params=statement_params,
+            execute_as="caller",
         )
 
         self.session._FIT_WRAPPER_SPROCS[  # type: ignore[attr-defined]
@@ -550,6 +554,7 @@ class SnowparkModelTrainer:
             session=self.session,
             statement_params=statement_params,
             anonymous=True,
+            execute_as="caller",
         )
         return fit_transform_wrapper_sproc
 
@@ -580,6 +585,7 @@ class SnowparkModelTrainer:
             replace=True,
             session=self.session,
             statement_params=statement_params,
+            execute_as="caller",
         )
 
         self.session._FIT_WRAPPER_SPROCS[  # type: ignore[attr-defined]

snowflake/ml/modeling/_internal/snowpark_implementations/xgboost_external_memory_trainer.py

@@ -303,6 +303,7 @@ class XGBoostExternalMemoryTrainer(SnowparkModelTrainer):
             statement_params=statement_params,
             anonymous=True,
             imports=list(import_file_paths),
+            execute_as="caller",
         )  # type: ignore[misc]
         def fit_wrapper_sproc(
             session: Session,

snowflake/ml/modeling/cluster/affinity_propagation.py

@@ -76,8 +76,10 @@ class AffinityPropagation(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/cluster/agglomerative_clustering.py

@@ -76,8 +76,10 @@ class AgglomerativeClustering(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/cluster/birch.py

@@ -76,8 +76,10 @@ class Birch(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/cluster/bisecting_k_means.py

@@ -76,8 +76,10 @@ class BisectingKMeans(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/cluster/dbscan.py

@@ -76,8 +76,10 @@ class DBSCAN(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/cluster/feature_agglomeration.py

@@ -76,8 +76,10 @@ class FeatureAgglomeration(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/cluster/k_means.py

@@ -76,8 +76,10 @@ class KMeans(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/cluster/mean_shift.py

@@ -76,8 +76,10 @@ class MeanShift(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/cluster/mini_batch_k_means.py

@@ -76,8 +76,10 @@ class MiniBatchKMeans(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/cluster/optics.py

@@ -76,8 +76,10 @@ class OPTICS(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/cluster/spectral_biclustering.py

@@ -76,8 +76,10 @@ class SpectralBiclustering(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/cluster/spectral_clustering.py

@@ -76,8 +76,10 @@ class SpectralClustering(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/cluster/spectral_coclustering.py

@@ -76,8 +76,10 @@ class SpectralCoclustering(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/compose/column_transformer.py

@@ -76,8 +76,10 @@ class ColumnTransformer(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/covariance/elliptic_envelope.py

@@ -76,8 +76,10 @@ class EllipticEnvelope(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/covariance/empirical_covariance.py

@@ -76,8 +76,10 @@ class EmpiricalCovariance(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/covariance/graphical_lasso.py

@@ -76,8 +76,10 @@ class GraphicalLasso(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/covariance/graphical_lasso_cv.py

@@ -76,8 +76,10 @@ class GraphicalLassoCV(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/covariance/ledoit_wolf.py

@@ -76,8 +76,10 @@ class LedoitWolf(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/covariance/min_cov_det.py

@@ -76,8 +76,10 @@ class MinCovDet(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/covariance/oas.py

@@ -76,8 +76,10 @@ class OAS(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must