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

snowflake/ml/modeling/covariance/shrunk_covariance.py

@@ -76,8 +76,10 @@ class ShrunkCovariance(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
@@ -237,7 +239,7 @@ class ShrunkCovariance(BaseTransformer):
                         inspect.currentframe(), ShrunkCovariance.__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/decomposition/dictionary_learning.py

@@ -76,8 +76,10 @@ class DictionaryLearning(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
@@ -343,7 +345,7 @@ class DictionaryLearning(BaseTransformer):
                         inspect.currentframe(), DictionaryLearning.__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/decomposition/factor_analysis.py

@@ -76,8 +76,10 @@ class FactorAnalysis(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
@@ -280,7 +282,7 @@ class FactorAnalysis(BaseTransformer):
                         inspect.currentframe(), FactorAnalysis.__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/decomposition/fast_ica.py

@@ -76,8 +76,10 @@ class FastICA(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
@@ -298,7 +300,7 @@ class FastICA(BaseTransformer):
                         inspect.currentframe(), FastICA.__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/decomposition/incremental_pca.py

@@ -76,8 +76,10 @@ class IncrementalPCA(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 IncrementalPCA(BaseTransformer):
                         inspect.currentframe(), IncrementalPCA.__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/decomposition/kernel_pca.py

@@ -76,8 +76,10 @@ class KernelPCA(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
@@ -346,7 +348,7 @@ class KernelPCA(BaseTransformer):
                         inspect.currentframe(), KernelPCA.__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/decomposition/mini_batch_dictionary_learning.py

@@ -76,8 +76,10 @@ class MiniBatchDictionaryLearning(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
@@ -368,7 +370,7 @@ class MiniBatchDictionaryLearning(BaseTransformer):
                         inspect.currentframe(), MiniBatchDictionaryLearning.__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/decomposition/mini_batch_sparse_pca.py

@@ -76,8 +76,10 @@ class MiniBatchSparsePCA(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
@@ -313,7 +315,7 @@ class MiniBatchSparsePCA(BaseTransformer):
                         inspect.currentframe(), MiniBatchSparsePCA.__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/decomposition/pca.py

@@ -76,8 +76,10 @@ class PCA(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
@@ -315,7 +317,7 @@ class PCA(BaseTransformer):
                         inspect.currentframe(), PCA.__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/decomposition/sparse_pca.py

@@ -76,8 +76,10 @@ class SparsePCA(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
@@ -288,7 +290,7 @@ class SparsePCA(BaseTransformer):
                         inspect.currentframe(), SparsePCA.__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/decomposition/truncated_svd.py

@@ -76,8 +76,10 @@ class TruncatedSVD(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 TruncatedSVD(BaseTransformer):
                         inspect.currentframe(), TruncatedSVD.__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/discriminant_analysis/linear_discriminant_analysis.py

@@ -286,7 +286,7 @@ class LinearDiscriminantAnalysis(BaseTransformer):
                         inspect.currentframe(), LinearDiscriminantAnalysis.__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/discriminant_analysis/quadratic_discriminant_analysis.py

@@ -248,7 +248,7 @@ class QuadraticDiscriminantAnalysis(BaseTransformer):
                         inspect.currentframe(), QuadraticDiscriminantAnalysis.__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/ensemble/ada_boost_classifier.py

@@ -273,7 +273,7 @@ class AdaBoostClassifier(BaseTransformer):
                         inspect.currentframe(), AdaBoostClassifier.__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/ensemble/ada_boost_regressor.py

@@ -270,7 +270,7 @@ class AdaBoostRegressor(BaseTransformer):
                         inspect.currentframe(), AdaBoostRegressor.__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/ensemble/bagging_classifier.py

@@ -305,7 +305,7 @@ class BaggingClassifier(BaseTransformer):
                         inspect.currentframe(), BaggingClassifier.__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/ensemble/bagging_regressor.py

@@ -305,7 +305,7 @@ class BaggingRegressor(BaseTransformer):
                         inspect.currentframe(), BaggingRegressor.__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/ensemble/extra_trees_classifier.py

@@ -408,7 +408,7 @@ class ExtraTreesClassifier(BaseTransformer):
                         inspect.currentframe(), ExtraTreesClassifier.__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/ensemble/extra_trees_regressor.py

@@ -387,7 +387,7 @@ class ExtraTreesRegressor(BaseTransformer):
                         inspect.currentframe(), ExtraTreesRegressor.__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/ensemble/gradient_boosting_classifier.py

@@ -420,7 +420,7 @@ class GradientBoostingClassifier(BaseTransformer):
                         inspect.currentframe(), GradientBoostingClassifier.__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/ensemble/gradient_boosting_regressor.py

@@ -429,7 +429,7 @@ class GradientBoostingRegressor(BaseTransformer):
                         inspect.currentframe(), GradientBoostingRegressor.__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/ensemble/hist_gradient_boosting_classifier.py

@@ -401,7 +401,7 @@ class HistGradientBoostingClassifier(BaseTransformer):
                         inspect.currentframe(), HistGradientBoostingClassifier.__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/ensemble/hist_gradient_boosting_regressor.py

@@ -392,7 +392,7 @@ class HistGradientBoostingRegressor(BaseTransformer):
                         inspect.currentframe(), HistGradientBoostingRegressor.__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/ensemble/isolation_forest.py

@@ -76,8 +76,10 @@ class IsolationForest(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
@@ -292,7 +294,7 @@ class IsolationForest(BaseTransformer):
                         inspect.currentframe(), IsolationForest.__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/ensemble/random_forest_classifier.py

@@ -404,7 +404,7 @@ class RandomForestClassifier(BaseTransformer):
                         inspect.currentframe(), RandomForestClassifier.__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/ensemble/random_forest_regressor.py

@@ -383,7 +383,7 @@ class RandomForestRegressor(BaseTransformer):
                         inspect.currentframe(), RandomForestRegressor.__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/ensemble/stacking_regressor.py

@@ -284,7 +284,7 @@ class StackingRegressor(BaseTransformer):
                         inspect.currentframe(), StackingRegressor.__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/ensemble/voting_classifier.py

@@ -266,7 +266,7 @@ class VotingClassifier(BaseTransformer):
                         inspect.currentframe(), VotingClassifier.__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/ensemble/voting_regressor.py

@@ -248,7 +248,7 @@ class VotingRegressor(BaseTransformer):
                         inspect.currentframe(), VotingRegressor.__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/feature_selection/generic_univariate_select.py

@@ -238,7 +238,7 @@ class GenericUnivariateSelect(BaseTransformer):
                         inspect.currentframe(), GenericUnivariateSelect.__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/feature_selection/select_fdr.py

@@ -234,7 +234,7 @@ class SelectFdr(BaseTransformer):
                         inspect.currentframe(), SelectFdr.__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/feature_selection/select_fpr.py

@@ -234,7 +234,7 @@ class SelectFpr(BaseTransformer):
                         inspect.currentframe(), SelectFpr.__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/feature_selection/select_fwe.py

@@ -234,7 +234,7 @@ class SelectFwe(BaseTransformer):
                         inspect.currentframe(), SelectFwe.__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/feature_selection/select_k_best.py

@@ -235,7 +235,7 @@ class SelectKBest(BaseTransformer):
                         inspect.currentframe(), SelectKBest.__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/feature_selection/select_percentile.py

@@ -234,7 +234,7 @@ class SelectPercentile(BaseTransformer):
                         inspect.currentframe(), SelectPercentile.__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/feature_selection/sequential_feature_selector.py

@@ -76,8 +76,10 @@ class SequentialFeatureSelector(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
@@ -292,7 +294,7 @@ class SequentialFeatureSelector(BaseTransformer):
                         inspect.currentframe(), SequentialFeatureSelector.__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/feature_selection/variance_threshold.py

@@ -76,8 +76,10 @@ class VarianceThreshold(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
@@ -225,7 +227,7 @@ class VarianceThreshold(BaseTransformer):
                         inspect.currentframe(), VarianceThreshold.__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/framework/base.py

@@ -16,7 +16,7 @@ from snowflake.ml._internal.exceptions import (
     exceptions,
     modeling_error_messages,
 )
-from snowflake.ml._internal.lineage import data_source, lineage_utils
+from snowflake.ml._internal.lineage import lineage_utils
 from snowflake.ml._internal.utils import identifier, parallelize
 from snowflake.ml.modeling.framework import _utils
 from snowflake.snowpark import functions as F
@@ -386,7 +386,6 @@ class BaseEstimator(Base):
         self.file_names = file_names
         self.custom_states = custom_states
         self.sample_weight_col = sample_weight_col
-        self._data_sources: Optional[List[data_source.DataSource]] = None
 
         self.start_time = datetime.now().strftime(_utils.DATETIME_FORMAT)[:-3]
 
@@ -421,18 +420,14 @@ class BaseEstimator(Base):
         """
         return []
 
-    def _get_data_sources(self) -> Optional[List[data_source.DataSource]]:
-        return self._data_sources
-
     @telemetry.send_api_usage_telemetry(
         project=PROJECT,
         subproject=SUBPROJECT,
     )
     def fit(self, dataset: Union[snowpark.DataFrame, pd.DataFrame]) -> "BaseEstimator":
         """Runs universal logics for all fit implementations."""
-        self._data_sources = getattr(dataset, lineage_utils.DATA_SOURCES_ATTR, None)
-        if self._data_sources:
-            assert all(isinstance(ds, data_source.DataSource) for ds in self._data_sources)
+        data_sources = lineage_utils.get_data_sources(dataset)
+        lineage_utils.set_data_sources(self, data_sources)
         return self._fit(dataset)
 
     @abstractmethod

snowflake/ml/modeling/gaussian_process/gaussian_process_classifier.py

@@ -320,7 +320,7 @@ class GaussianProcessClassifier(BaseTransformer):
                         inspect.currentframe(), GaussianProcessClassifier.__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