snowflake-ml-python 1.5.2__py3-none-any.whl → 1.5.4__py3-none-any.whl

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

@@ -13,12 +13,12 @@ from snowflake.ml._internal.exceptions import (
     exceptions,
     modeling_error_messages,
 )
-from snowflake.ml._internal.utils import pkg_version_utils
+from snowflake.ml._internal.utils import pkg_version_utils, temp_file_utils
 from snowflake.ml._internal.utils.query_result_checker import ResultValidator
 from snowflake.ml._internal.utils.snowpark_dataframe_utils import (
     cast_snowpark_dataframe,
 )
-from snowflake.ml._internal.utils.temp_file_utils import get_temp_file_path
+from snowflake.ml.modeling._internal import estimator_utils
 from snowflake.ml.modeling._internal.model_specifications import (
     ModelSpecifications,
     ModelSpecificationsBuilder,
@@ -303,11 +303,10 @@ 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,
-            stage_transform_file_name: str,
-            stage_result_file_name: str,
             dataset_stage_name: str,
             batch_size: int,
             input_cols: List[str],
@@ -320,9 +319,13 @@ class XGBoostExternalMemoryTrainer(SnowparkModelTrainer):
 
             import cloudpickle as cp
 
-            local_transform_file_name = get_temp_file_path()
+            local_transform_file_name = temp_file_utils.get_temp_file_path()
 
-            session.file.get(stage_transform_file_name, local_transform_file_name, statement_params=statement_params)
+            session.file.get(
+                stage_location=dataset_stage_name,
+                target_directory=local_transform_file_name,
+                statement_params=statement_params,
+            )
 
             local_transform_file_path = os.path.join(
                 local_transform_file_name, os.listdir(local_transform_file_name)[0]
@@ -345,13 +348,13 @@ class XGBoostExternalMemoryTrainer(SnowparkModelTrainer):
                 sample_weight_col=sample_weight_col,
             )
 
-            local_result_file_name = get_temp_file_path()
+            local_result_file_name = temp_file_utils.get_temp_file_path()
             with open(local_result_file_name, mode="w+b") as local_result_file_obj:
                 cp.dump(estimator, local_result_file_obj)
 
             session.file.put(
-                local_result_file_name,
-                stage_result_file_name,
+                local_file_name=local_result_file_name,
+                stage_location=dataset_stage_name,
                 auto_compress=False,
                 overwrite=True,
                 statement_params=statement_params,
@@ -394,11 +397,6 @@ class XGBoostExternalMemoryTrainer(SnowparkModelTrainer):
             SnowflakeMLException: For known types of user and system errors.
             e: For every unexpected exception from SnowflakeClient.
         """
-        temp_stage_name = self._create_temp_stage()
-        (stage_transform_file_name, stage_result_file_name) = self._upload_model_to_stage(stage_name=temp_stage_name)
-        data_file_paths = self._write_training_data_to_stage(dataset_stage_name=temp_stage_name)
-
-        # Call fit sproc
         statement_params = telemetry.get_function_usage_statement_params(
             project=_PROJECT,
             subproject=self._subproject,
@@ -406,7 +404,16 @@ class XGBoostExternalMemoryTrainer(SnowparkModelTrainer):
             api_calls=[Session.call],
             custom_tags=None,
         )
+        temp_stage_name = estimator_utils.create_temp_stage(self.session)
+        estimator_utils.upload_model_to_stage(
+            stage_name=temp_stage_name,
+            estimator=self.estimator,
+            session=self.session,
+            statement_params=statement_params,
+        )
+        data_file_paths = self._write_training_data_to_stage(dataset_stage_name=temp_stage_name)
 
+        # Call fit sproc
         model_spec = ModelSpecificationsBuilder.build(model=self.estimator)
         fit_wrapper = self._get_xgb_external_memory_fit_wrapper_sproc(
             model_spec=model_spec,
@@ -418,8 +425,6 @@ class XGBoostExternalMemoryTrainer(SnowparkModelTrainer):
         try:
             sproc_export_file_name = fit_wrapper(
                 self.session,
-                stage_transform_file_name,
-                stage_result_file_name,
                 temp_stage_name,
                 self._batch_size,
                 self.input_cols,
@@ -440,7 +445,7 @@ class XGBoostExternalMemoryTrainer(SnowparkModelTrainer):
             sproc_export_file_name = fields[0]
 
         return self._fetch_model_from_stage(
-            dir_path=stage_result_file_name,
+            dir_path=temp_stage_name,
             file_name=sproc_export_file_name,
             statement_params=statement_params,
         )

snowflake/ml/modeling/calibration/calibrated_classifier_cv.py

@@ -296,7 +296,7 @@ class CalibratedClassifierCV(BaseTransformer):
                         inspect.currentframe(), CalibratedClassifierCV.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -271,7 +273,7 @@ class AffinityPropagation(BaseTransformer):
                         inspect.currentframe(), AffinityPropagation.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -304,7 +306,7 @@ class AgglomerativeClustering(BaseTransformer):
                         inspect.currentframe(), AgglomerativeClustering.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -262,7 +264,7 @@ class Birch(BaseTransformer):
                         inspect.currentframe(), Birch.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -311,7 +313,7 @@ class BisectingKMeans(BaseTransformer):
                         inspect.currentframe(), BisectingKMeans.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -279,7 +281,7 @@ class DBSCAN(BaseTransformer):
                         inspect.currentframe(), DBSCAN.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -311,7 +313,7 @@ class FeatureAgglomeration(BaseTransformer):
                         inspect.currentframe(), FeatureAgglomeration.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -306,7 +308,7 @@ class KMeans(BaseTransformer):
                         inspect.currentframe(), KMeans.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -282,7 +284,7 @@ class MeanShift(BaseTransformer):
                         inspect.currentframe(), MeanShift.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -332,7 +334,7 @@ class MiniBatchKMeans(BaseTransformer):
                         inspect.currentframe(), MiniBatchKMeans.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -352,7 +354,7 @@ class OPTICS(BaseTransformer):
                         inspect.currentframe(), OPTICS.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -290,7 +292,7 @@ class SpectralBiclustering(BaseTransformer):
                         inspect.currentframe(), SpectralBiclustering.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -348,7 +350,7 @@ class SpectralClustering(BaseTransformer):
                         inspect.currentframe(), SpectralClustering.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -269,7 +271,7 @@ class SpectralCoclustering(BaseTransformer):
                         inspect.currentframe(), SpectralCoclustering.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -299,7 +301,7 @@ class ColumnTransformer(BaseTransformer):
                         inspect.currentframe(), ColumnTransformer.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

snowflake/ml/modeling/compose/transformed_target_regressor.py

@@ -260,7 +260,7 @@ class TransformedTargetRegressor(BaseTransformer):
                         inspect.currentframe(), TransformedTargetRegressor.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -255,7 +257,7 @@ class EllipticEnvelope(BaseTransformer):
                         inspect.currentframe(), EllipticEnvelope.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -231,7 +233,7 @@ class EmpiricalCovariance(BaseTransformer):
                         inspect.currentframe(), EmpiricalCovariance.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -279,7 +281,7 @@ class GraphicalLasso(BaseTransformer):
                         inspect.currentframe(), GraphicalLasso.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -305,7 +307,7 @@ class GraphicalLassoCV(BaseTransformer):
                         inspect.currentframe(), GraphicalLassoCV.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -238,7 +240,7 @@ class LedoitWolf(BaseTransformer):
                         inspect.currentframe(), LedoitWolf.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -250,7 +252,7 @@ class MinCovDet(BaseTransformer):
                         inspect.currentframe(), MinCovDet.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

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
@@ -231,7 +233,7 @@ class OAS(BaseTransformer):
                         inspect.currentframe(), OAS.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={"autogen": True} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns