snowflake-ml-python 1.3.0__py3-none-any.whl → 1.4.0__py3-none-any.whl

snowflake/ml/modeling/feature_selection/sequential_feature_selector.py

@@ -324,18 +324,24 @@ class SequentialFeatureSelector(BaseTransformer):
         self._get_model_signatures(dataset)
         return self
 
-    def _get_pass_through_columns(self, dataset: DataFrame) -> List[str]:
-        if self._drop_input_cols:
-            return []
-        else:
-            return list(set(dataset.columns) - set(self.output_cols))
-
     def _batch_inference_validate_snowpark(
         self,
         dataset: DataFrame,
         inference_method: str,
     ) -> List[str]:
-        """Util method to run validate that batch inference can be run on a snowpark dataframe.
+        """Util method to run validate that batch inference can be run on a snowpark dataframe and
+        return the available package that exists in the snowflake anaconda channel
+
+        Args:
+            dataset: snowpark dataframe
+            inference_method: the inference method such as predict, score...
+
+        Raises:
+            SnowflakeMLException: If the estimator is not fitted, raise error
+            SnowflakeMLException: If the session is None, raise error
+
+        Returns:
+            A list of available package that exists in the snowflake anaconda channel
         """
         if not self._is_fitted:
             raise exceptions.SnowflakeMLException(
@@ -407,7 +413,7 @@ class SequentialFeatureSelector(BaseTransformer):
             transform_kwargs = dict(
                 session = dataset._session,
                 dependencies = self._deps,
-                pass_through_cols = self._get_pass_through_columns(dataset),
+                drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type = expected_type_inferred,
             )
 
@@ -469,16 +475,16 @@ class SequentialFeatureSelector(BaseTransformer):
                 # from (n_samples, n_estimators) to (n_samples, n_estimators * n_classes) (and everything in between)
                 # based on init param values. We will convert that to pandas dataframe of shape (n_samples, 1) with
                 # each row containing a list of values.
-                expected_dtype = "ARRAY"
+                expected_dtype = "array"
 
             # If we were unable to assign a type to this transform in the factory, infer the type here.
             if expected_dtype == "":
-                # If this is a clustering transformer, if the number of output columns does not equal the number of clusters the response will be an "ARRAY"
+                # If this is a clustering transformer, if the number of output columns does not equal the number of clusters the response will be an "array"
                 if hasattr(self._sklearn_object, "n_clusters") and getattr(self._sklearn_object, "n_clusters") != len(self.output_cols):
-                    expected_dtype = "ARRAY"
-                # If this is a decomposition transformer, if the number of output columns does not equal the number of components the response will be an "ARRAY"
+                    expected_dtype = "array"
+                # If this is a decomposition transformer, if the number of output columns does not equal the number of components the response will be an "array"
                 elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
-                    expected_dtype = "ARRAY"
+                    expected_dtype = "array"
                 else:
                     output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
                     # We can only infer the output types from the input types if the following two statemetns are true:
@@ -496,7 +502,7 @@ class SequentialFeatureSelector(BaseTransformer):
             transform_kwargs = dict(
                 session = dataset._session,
                 dependencies = self._deps,
-                pass_through_cols = self._get_pass_through_columns(dataset),
+                drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type = expected_dtype,
             )
 
@@ -547,7 +553,7 @@ class SequentialFeatureSelector(BaseTransformer):
             subproject=_SUBPROJECT,
         )
         output_result, fitted_estimator = model_trainer.train_fit_predict(
-            pass_through_columns=self._get_pass_through_columns(dataset),
+            drop_input_cols=self._drop_input_cols,
             expected_output_cols_list=self.output_cols if self.output_cols else self._get_output_column_names(output_cols_prefix),
         )
         self._sklearn_object = fitted_estimator
@@ -565,44 +571,6 @@ class SequentialFeatureSelector(BaseTransformer):
         assert self._sklearn_object is not None
         return self._sklearn_object.embedding_
 
-
-    def _get_output_column_names(self, output_cols_prefix: str, output_cols: Optional[List[str]] = None) -> List[str]:
-        """ Returns the list of output columns for predict_proba(), decision_function(), etc.. functions.
-        Returns a list with output_cols_prefix as the only element if the estimator is not a classifier.
-        """
-        output_cols_prefix = identifier.resolve_identifier(output_cols_prefix)
-        if output_cols:
-            output_cols = [
-                identifier.concat_names([output_cols_prefix, identifier.resolve_identifier(c)])
-                for c in output_cols
-            ]
-        elif getattr(self._sklearn_object, "classes_", None) is None:
-            output_cols = [output_cols_prefix]
-        elif self._sklearn_object is not None:
-            classes = self._sklearn_object.classes_
-            if isinstance(classes, numpy.ndarray):
-                output_cols = [f'{output_cols_prefix}{str(c)}' for c in classes.tolist()]
-            elif isinstance(classes, list) and len(classes) > 0 and isinstance(classes[0], numpy.ndarray):
-                # If the estimator is a multioutput estimator, classes_ will be a list of ndarrays.
-                output_cols = []
-                for i, cl in enumerate(classes):
-                    # For binary classification, there is only one output column for each class
-                    # ndarray as the two classes are complementary.
-                    if len(cl) == 2:
-                        output_cols.append(f'{output_cols_prefix}{i}_{cl[0]}')
-                    else:
-                        output_cols.extend([
-                            f'{output_cols_prefix}{i}_{c}' for c in cl.tolist()
-                        ])
-        else:
-            output_cols = []
-
-        # Make sure column names are valid snowflake identifiers.
-        assert output_cols is not None  # Make MyPy happy
-        rv = [identifier.rename_to_valid_snowflake_identifier(c) for c in output_cols]
-
-        return rv
-
     @available_if(original_estimator_has_callable("predict_proba"))  # type: ignore[misc]
     @telemetry.send_api_usage_telemetry(
         project=_PROJECT,
@@ -642,7 +610,7 @@ class SequentialFeatureSelector(BaseTransformer):
             transform_kwargs = dict(
                 session=dataset._session,
                 dependencies=self._deps,
-                pass_through_cols=self._get_pass_through_columns(dataset),
+                drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type="float",
             )
 
@@ -707,7 +675,7 @@ class SequentialFeatureSelector(BaseTransformer):
             transform_kwargs = dict(
                 session=dataset._session,
                 dependencies=self._deps,
-                pass_through_cols=self._get_pass_through_columns(dataset),
+                drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type="float",
             )
         elif isinstance(dataset, pd.DataFrame):
@@ -768,7 +736,7 @@ class SequentialFeatureSelector(BaseTransformer):
             transform_kwargs = dict(
                 session=dataset._session,
                 dependencies=self._deps,
-                pass_through_cols=self._get_pass_through_columns(dataset),
+                drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type="float",
             )
 
@@ -833,7 +801,7 @@ class SequentialFeatureSelector(BaseTransformer):
             transform_kwargs = dict(
                 session=dataset._session,
                 dependencies=self._deps,
-                pass_through_cols=self._get_pass_through_columns(dataset),
+                drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type="float",
             )
 
@@ -887,13 +855,17 @@ class SequentialFeatureSelector(BaseTransformer):
         transform_kwargs: ScoreKwargsTypedDict = dict()  
 
         if isinstance(dataset, DataFrame):
+            self._deps = self._batch_inference_validate_snowpark(
+                dataset=dataset,
+                inference_method="score",
+            )
             selected_cols = self._get_active_columns()
             if len(selected_cols) > 0:
                 dataset = dataset.select(selected_cols)
             assert isinstance(dataset._session, Session) # keep mypy happy
             transform_kwargs = dict(
                 session=dataset._session,
-                dependencies=["snowflake-snowpark-python"] + self._get_dependencies(),
+                dependencies=["snowflake-snowpark-python"] + self._deps,
                 score_sproc_imports=['sklearn'],
             )
         elif isinstance(dataset, pd.DataFrame):
@@ -967,9 +939,9 @@ class SequentialFeatureSelector(BaseTransformer):
             transform_kwargs = dict(
                 session = dataset._session,
                 dependencies = self._deps,
-                pass_through_cols = self._get_pass_through_columns(dataset),
-                expected_output_cols_type =  "array",
-                n_neighbors =  n_neighbors,
+                drop_input_cols = self._drop_input_cols,
+                expected_output_cols_type="array",
+                n_neighbors = n_neighbors,
                 return_distance =  return_distance
             )
         elif isinstance(dataset, pd.DataFrame):

snowflake/ml/modeling/feature_selection/variance_threshold.py

@@ -257,18 +257,24 @@ class VarianceThreshold(BaseTransformer):
         self._get_model_signatures(dataset)
         return self
 
-    def _get_pass_through_columns(self, dataset: DataFrame) -> List[str]:
-        if self._drop_input_cols:
-            return []
-        else:
-            return list(set(dataset.columns) - set(self.output_cols))
-
     def _batch_inference_validate_snowpark(
         self,
         dataset: DataFrame,
         inference_method: str,
     ) -> List[str]:
-        """Util method to run validate that batch inference can be run on a snowpark dataframe.
+        """Util method to run validate that batch inference can be run on a snowpark dataframe and
+        return the available package that exists in the snowflake anaconda channel
+
+        Args:
+            dataset: snowpark dataframe
+            inference_method: the inference method such as predict, score...
+
+        Raises:
+            SnowflakeMLException: If the estimator is not fitted, raise error
+            SnowflakeMLException: If the session is None, raise error
+
+        Returns:
+            A list of available package that exists in the snowflake anaconda channel
         """
         if not self._is_fitted:
             raise exceptions.SnowflakeMLException(
@@ -340,7 +346,7 @@ class VarianceThreshold(BaseTransformer):
             transform_kwargs = dict(
                 session = dataset._session,
                 dependencies = self._deps,
-                pass_through_cols = self._get_pass_through_columns(dataset),
+                drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type = expected_type_inferred,
             )
 
@@ -402,16 +408,16 @@ class VarianceThreshold(BaseTransformer):
                 # from (n_samples, n_estimators) to (n_samples, n_estimators * n_classes) (and everything in between)
                 # based on init param values. We will convert that to pandas dataframe of shape (n_samples, 1) with
                 # each row containing a list of values.
-                expected_dtype = "ARRAY"
+                expected_dtype = "array"
 
             # If we were unable to assign a type to this transform in the factory, infer the type here.
             if expected_dtype == "":
-                # If this is a clustering transformer, if the number of output columns does not equal the number of clusters the response will be an "ARRAY"
+                # If this is a clustering transformer, if the number of output columns does not equal the number of clusters the response will be an "array"
                 if hasattr(self._sklearn_object, "n_clusters") and getattr(self._sklearn_object, "n_clusters") != len(self.output_cols):
-                    expected_dtype = "ARRAY"
-                # If this is a decomposition transformer, if the number of output columns does not equal the number of components the response will be an "ARRAY"
+                    expected_dtype = "array"
+                # If this is a decomposition transformer, if the number of output columns does not equal the number of components the response will be an "array"
                 elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
-                    expected_dtype = "ARRAY"
+                    expected_dtype = "array"
                 else:
                     output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
                     # We can only infer the output types from the input types if the following two statemetns are true:
@@ -429,7 +435,7 @@ class VarianceThreshold(BaseTransformer):
             transform_kwargs = dict(
                 session = dataset._session,
                 dependencies = self._deps,
-                pass_through_cols = self._get_pass_through_columns(dataset),
+                drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type = expected_dtype,
             )
 
@@ -480,7 +486,7 @@ class VarianceThreshold(BaseTransformer):
             subproject=_SUBPROJECT,
         )
         output_result, fitted_estimator = model_trainer.train_fit_predict(
-            pass_through_columns=self._get_pass_through_columns(dataset),
+            drop_input_cols=self._drop_input_cols,
             expected_output_cols_list=self.output_cols if self.output_cols else self._get_output_column_names(output_cols_prefix),
         )
         self._sklearn_object = fitted_estimator
@@ -498,44 +504,6 @@ class VarianceThreshold(BaseTransformer):
         assert self._sklearn_object is not None
         return self._sklearn_object.embedding_
 
-
-    def _get_output_column_names(self, output_cols_prefix: str, output_cols: Optional[List[str]] = None) -> List[str]:
-        """ Returns the list of output columns for predict_proba(), decision_function(), etc.. functions.
-        Returns a list with output_cols_prefix as the only element if the estimator is not a classifier.
-        """
-        output_cols_prefix = identifier.resolve_identifier(output_cols_prefix)
-        if output_cols:
-            output_cols = [
-                identifier.concat_names([output_cols_prefix, identifier.resolve_identifier(c)])
-                for c in output_cols
-            ]
-        elif getattr(self._sklearn_object, "classes_", None) is None:
-            output_cols = [output_cols_prefix]
-        elif self._sklearn_object is not None:
-            classes = self._sklearn_object.classes_
-            if isinstance(classes, numpy.ndarray):
-                output_cols = [f'{output_cols_prefix}{str(c)}' for c in classes.tolist()]
-            elif isinstance(classes, list) and len(classes) > 0 and isinstance(classes[0], numpy.ndarray):
-                # If the estimator is a multioutput estimator, classes_ will be a list of ndarrays.
-                output_cols = []
-                for i, cl in enumerate(classes):
-                    # For binary classification, there is only one output column for each class
-                    # ndarray as the two classes are complementary.
-                    if len(cl) == 2:
-                        output_cols.append(f'{output_cols_prefix}{i}_{cl[0]}')
-                    else:
-                        output_cols.extend([
-                            f'{output_cols_prefix}{i}_{c}' for c in cl.tolist()
-                        ])
-        else:
-            output_cols = []
-
-        # Make sure column names are valid snowflake identifiers.
-        assert output_cols is not None  # Make MyPy happy
-        rv = [identifier.rename_to_valid_snowflake_identifier(c) for c in output_cols]
-
-        return rv
-
     @available_if(original_estimator_has_callable("predict_proba"))  # type: ignore[misc]
     @telemetry.send_api_usage_telemetry(
         project=_PROJECT,
@@ -575,7 +543,7 @@ class VarianceThreshold(BaseTransformer):
             transform_kwargs = dict(
                 session=dataset._session,
                 dependencies=self._deps,
-                pass_through_cols=self._get_pass_through_columns(dataset),
+                drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type="float",
             )
 
@@ -640,7 +608,7 @@ class VarianceThreshold(BaseTransformer):
             transform_kwargs = dict(
                 session=dataset._session,
                 dependencies=self._deps,
-                pass_through_cols=self._get_pass_through_columns(dataset),
+                drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type="float",
             )
         elif isinstance(dataset, pd.DataFrame):
@@ -701,7 +669,7 @@ class VarianceThreshold(BaseTransformer):
             transform_kwargs = dict(
                 session=dataset._session,
                 dependencies=self._deps,
-                pass_through_cols=self._get_pass_through_columns(dataset),
+                drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type="float",
             )
 
@@ -766,7 +734,7 @@ class VarianceThreshold(BaseTransformer):
             transform_kwargs = dict(
                 session=dataset._session,
                 dependencies=self._deps,
-                pass_through_cols=self._get_pass_through_columns(dataset),
+                drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type="float",
             )
 
@@ -820,13 +788,17 @@ class VarianceThreshold(BaseTransformer):
         transform_kwargs: ScoreKwargsTypedDict = dict()  
 
         if isinstance(dataset, DataFrame):
+            self._deps = self._batch_inference_validate_snowpark(
+                dataset=dataset,
+                inference_method="score",
+            )
             selected_cols = self._get_active_columns()
             if len(selected_cols) > 0:
                 dataset = dataset.select(selected_cols)
             assert isinstance(dataset._session, Session) # keep mypy happy
             transform_kwargs = dict(
                 session=dataset._session,
-                dependencies=["snowflake-snowpark-python"] + self._get_dependencies(),
+                dependencies=["snowflake-snowpark-python"] + self._deps,
                 score_sproc_imports=['sklearn'],
             )
         elif isinstance(dataset, pd.DataFrame):
@@ -900,9 +872,9 @@ class VarianceThreshold(BaseTransformer):
             transform_kwargs = dict(
                 session = dataset._session,
                 dependencies = self._deps,
-                pass_through_cols = self._get_pass_through_columns(dataset),
-                expected_output_cols_type =  "array",
-                n_neighbors =  n_neighbors,
+                drop_input_cols = self._drop_input_cols,
+                expected_output_cols_type="array",
+                n_neighbors = n_neighbors,
                 return_distance =  return_distance
             )
         elif isinstance(dataset, pd.DataFrame):

snowflake/ml/modeling/framework/base.py

@@ -51,8 +51,8 @@ class Base:
             input_cols: Input columns.
             output_cols: Output columns.
             label_cols: Label column(s).
-            passthrough_cols: List columns not to be used or modified by the estimator/trasformers.
-                These columns will be passed through all the estimator/trasformer operations without any modifications.
+            passthrough_cols: List columns not to be used or modified by the estimator/transformers.
+                These columns will be passed through all the estimator/transformer operations without any modifications.
         """
         self.input_cols: List[str] = []
         self.output_cols: List[str] = []
@@ -185,7 +185,10 @@ class Base:
                 error_code=error_codes.INVALID_ATTRIBUTE,
                 original_exception=RuntimeError(
                     modeling_error_messages.SIZE_MISMATCH.format(
-                        "input_cols", len(self.input_cols), "output_cols", len(self.output_cols)
+                        "input_cols",
+                        len(self.input_cols),
+                        "output_cols",
+                        len(self.output_cols),
                     )
                 ),
             )
@@ -498,7 +501,11 @@ class BaseTransformer(BaseEstimator):
         sample_weight_col: Optional[str] = None,
     ) -> None:
         """Base class for all transformers."""
-        super().__init__(file_names=file_names, custom_states=custom_states, sample_weight_col=sample_weight_col)
+        super().__init__(
+            file_names=file_names,
+            custom_states=custom_states,
+            sample_weight_col=sample_weight_col,
+        )
         self._sklearn_object = None
         self._is_fitted = False
         self._drop_input_cols = drop_input_cols
@@ -577,6 +584,46 @@ class BaseTransformer(BaseEstimator):
                     ),
                 )
 
+    def _get_output_column_names(self, output_cols_prefix: str, output_cols: Optional[List[str]] = None) -> List[str]:
+        """Returns the list of output columns for predict_proba(), decision_function(), etc.. functions.
+        Returns a list with output_cols_prefix as the only element if the estimator is not a classifier.
+
+        Args:
+            output_cols_prefix: the prefix for output cols, such as its inference method.
+            output_cols: The output cols. Defaults to None. This is introduced by kneighbors methods
+
+        Returns:
+            inferred output column names
+        """
+        output_cols_prefix = identifier.resolve_identifier(output_cols_prefix)
+        if output_cols:
+            output_cols = [
+                identifier.concat_names([output_cols_prefix, identifier.resolve_identifier(c)]) for c in output_cols
+            ]
+        elif getattr(self._sklearn_object, "classes_", None) is None:
+            output_cols = [output_cols_prefix]
+        elif self._sklearn_object is not None:
+            classes = self._sklearn_object.classes_
+            if isinstance(classes, np.ndarray):
+                output_cols = [f"{output_cols_prefix}{str(c)}" for c in classes.tolist()]
+            elif isinstance(classes, list) and len(classes) > 0 and isinstance(classes[0], np.ndarray):
+                # If the estimator is a multioutput estimator, classes_ will be a list of ndarrays.
+                output_cols = []
+                for i, cl in enumerate(classes):
+                    # For binary classification, there is only one output column for each class
+                    # ndarray as the two classes are complementary.
+                    if len(cl) == 2:
+                        output_cols.append(f"{output_cols_prefix}{i}_{cl[0]}")
+                    else:
+                        output_cols.extend([f"{output_cols_prefix}{i}_{c}" for c in cl.tolist()])
+        else:
+            output_cols = []
+
+        # Make sure column names are valid snowflake identifiers.
+        assert output_cols is not None  # Make MyPy happy
+        rv = [identifier.rename_to_valid_snowflake_identifier(c) for c in output_cols]
+        return rv
+
     def set_drop_input_cols(self, drop_input_cols: Optional[bool] = False) -> None:
         self._drop_input_cols = drop_input_cols
 
@@ -665,7 +712,10 @@ class BaseTransformer(BaseEstimator):
                 error_code=error_codes.INVALID_ATTRIBUTE,
                 original_exception=RuntimeError(
                     modeling_error_messages.SIZE_MISMATCH.format(
-                        "output_cols", len(self.output_cols), "transformed array shape", shape
+                        "output_cols",
+                        len(self.output_cols),
+                        "transformed array shape",
+                        shape,
                     )
                 ),
             )

snowflake/ml/modeling/gaussian_process/gaussian_process_classifier.py

@@ -352,18 +352,24 @@ class GaussianProcessClassifier(BaseTransformer):
         self._get_model_signatures(dataset)
         return self
 
-    def _get_pass_through_columns(self, dataset: DataFrame) -> List[str]:
-        if self._drop_input_cols:
-            return []
-        else:
-            return list(set(dataset.columns) - set(self.output_cols))
-
     def _batch_inference_validate_snowpark(
         self,
         dataset: DataFrame,
         inference_method: str,
     ) -> List[str]:
-        """Util method to run validate that batch inference can be run on a snowpark dataframe.
+        """Util method to run validate that batch inference can be run on a snowpark dataframe and
+        return the available package that exists in the snowflake anaconda channel
+
+        Args:
+            dataset: snowpark dataframe
+            inference_method: the inference method such as predict, score...
+
+        Raises:
+            SnowflakeMLException: If the estimator is not fitted, raise error
+            SnowflakeMLException: If the session is None, raise error
+
+        Returns:
+            A list of available package that exists in the snowflake anaconda channel
         """
         if not self._is_fitted:
             raise exceptions.SnowflakeMLException(
@@ -437,7 +443,7 @@ class GaussianProcessClassifier(BaseTransformer):
             transform_kwargs = dict(
                 session = dataset._session,
                 dependencies = self._deps,
-                pass_through_cols = self._get_pass_through_columns(dataset),
+                drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type = expected_type_inferred,
             )
 
@@ -497,16 +503,16 @@ class GaussianProcessClassifier(BaseTransformer):
                 # from (n_samples, n_estimators) to (n_samples, n_estimators * n_classes) (and everything in between)
                 # based on init param values. We will convert that to pandas dataframe of shape (n_samples, 1) with
                 # each row containing a list of values.
-                expected_dtype = "ARRAY"
+                expected_dtype = "array"
 
             # If we were unable to assign a type to this transform in the factory, infer the type here.
             if expected_dtype == "":
-                # If this is a clustering transformer, if the number of output columns does not equal the number of clusters the response will be an "ARRAY"
+                # If this is a clustering transformer, if the number of output columns does not equal the number of clusters the response will be an "array"
                 if hasattr(self._sklearn_object, "n_clusters") and getattr(self._sklearn_object, "n_clusters") != len(self.output_cols):
-                    expected_dtype = "ARRAY"
-                # If this is a decomposition transformer, if the number of output columns does not equal the number of components the response will be an "ARRAY"
+                    expected_dtype = "array"
+                # If this is a decomposition transformer, if the number of output columns does not equal the number of components the response will be an "array"
                 elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
-                    expected_dtype = "ARRAY"
+                    expected_dtype = "array"
                 else:
                     output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
                     # We can only infer the output types from the input types if the following two statemetns are true:
@@ -524,7 +530,7 @@ class GaussianProcessClassifier(BaseTransformer):
             transform_kwargs = dict(
                 session = dataset._session,
                 dependencies = self._deps,
-                pass_through_cols = self._get_pass_through_columns(dataset),
+                drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type = expected_dtype,
             )
 
@@ -575,7 +581,7 @@ class GaussianProcessClassifier(BaseTransformer):
             subproject=_SUBPROJECT,
         )
         output_result, fitted_estimator = model_trainer.train_fit_predict(
-            pass_through_columns=self._get_pass_through_columns(dataset),
+            drop_input_cols=self._drop_input_cols,
             expected_output_cols_list=self.output_cols if self.output_cols else self._get_output_column_names(output_cols_prefix),
         )
         self._sklearn_object = fitted_estimator
@@ -593,44 +599,6 @@ class GaussianProcessClassifier(BaseTransformer):
         assert self._sklearn_object is not None
         return self._sklearn_object.embedding_
 
-
-    def _get_output_column_names(self, output_cols_prefix: str, output_cols: Optional[List[str]] = None) -> List[str]:
-        """ Returns the list of output columns for predict_proba(), decision_function(), etc.. functions.
-        Returns a list with output_cols_prefix as the only element if the estimator is not a classifier.
-        """
-        output_cols_prefix = identifier.resolve_identifier(output_cols_prefix)
-        if output_cols:
-            output_cols = [
-                identifier.concat_names([output_cols_prefix, identifier.resolve_identifier(c)])
-                for c in output_cols
-            ]
-        elif getattr(self._sklearn_object, "classes_", None) is None:
-            output_cols = [output_cols_prefix]
-        elif self._sklearn_object is not None:
-            classes = self._sklearn_object.classes_
-            if isinstance(classes, numpy.ndarray):
-                output_cols = [f'{output_cols_prefix}{str(c)}' for c in classes.tolist()]
-            elif isinstance(classes, list) and len(classes) > 0 and isinstance(classes[0], numpy.ndarray):
-                # If the estimator is a multioutput estimator, classes_ will be a list of ndarrays.
-                output_cols = []
-                for i, cl in enumerate(classes):
-                    # For binary classification, there is only one output column for each class
-                    # ndarray as the two classes are complementary.
-                    if len(cl) == 2:
-                        output_cols.append(f'{output_cols_prefix}{i}_{cl[0]}')
-                    else:
-                        output_cols.extend([
-                            f'{output_cols_prefix}{i}_{c}' for c in cl.tolist()
-                        ])
-        else:
-            output_cols = []
-
-        # Make sure column names are valid snowflake identifiers.
-        assert output_cols is not None  # Make MyPy happy
-        rv = [identifier.rename_to_valid_snowflake_identifier(c) for c in output_cols]
-
-        return rv
-
     @available_if(original_estimator_has_callable("predict_proba"))  # type: ignore[misc]
     @telemetry.send_api_usage_telemetry(
         project=_PROJECT,
@@ -672,7 +640,7 @@ class GaussianProcessClassifier(BaseTransformer):
             transform_kwargs = dict(
                 session=dataset._session,
                 dependencies=self._deps,
-                pass_through_cols=self._get_pass_through_columns(dataset),
+                drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type="float",
             )
 
@@ -739,7 +707,7 @@ class GaussianProcessClassifier(BaseTransformer):
             transform_kwargs = dict(
                 session=dataset._session,
                 dependencies=self._deps,
-                pass_through_cols=self._get_pass_through_columns(dataset),
+                drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type="float",
             )
         elif isinstance(dataset, pd.DataFrame):
@@ -800,7 +768,7 @@ class GaussianProcessClassifier(BaseTransformer):
             transform_kwargs = dict(
                 session=dataset._session,
                 dependencies=self._deps,
-                pass_through_cols=self._get_pass_through_columns(dataset),
+                drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type="float",
             )
 
@@ -865,7 +833,7 @@ class GaussianProcessClassifier(BaseTransformer):
             transform_kwargs = dict(
                 session=dataset._session,
                 dependencies=self._deps,
-                pass_through_cols=self._get_pass_through_columns(dataset),
+                drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type="float",
             )
 
@@ -921,13 +889,17 @@ class GaussianProcessClassifier(BaseTransformer):
         transform_kwargs: ScoreKwargsTypedDict = dict()  
 
         if isinstance(dataset, DataFrame):
+            self._deps = self._batch_inference_validate_snowpark(
+                dataset=dataset,
+                inference_method="score",
+            )
             selected_cols = self._get_active_columns()
             if len(selected_cols) > 0:
                 dataset = dataset.select(selected_cols)
             assert isinstance(dataset._session, Session) # keep mypy happy
             transform_kwargs = dict(
                 session=dataset._session,
-                dependencies=["snowflake-snowpark-python"] + self._get_dependencies(),
+                dependencies=["snowflake-snowpark-python"] + self._deps,
                 score_sproc_imports=['sklearn'],
             )
         elif isinstance(dataset, pd.DataFrame):
@@ -1001,9 +973,9 @@ class GaussianProcessClassifier(BaseTransformer):
             transform_kwargs = dict(
                 session = dataset._session,
                 dependencies = self._deps,
-                pass_through_cols = self._get_pass_through_columns(dataset),
-                expected_output_cols_type =  "array",
-                n_neighbors =  n_neighbors,
+                drop_input_cols = self._drop_input_cols,
+                expected_output_cols_type="array",
+                n_neighbors = n_neighbors,
                 return_distance =  return_distance
             )
         elif isinstance(dataset, pd.DataFrame):