snowflake-ml-python 1.2.0__py3-none-any.whl → 1.2.2__py3-none-any.whl

snowflake/ml/modeling/ensemble/gradient_boosting_classifier.py

@@ -26,7 +26,7 @@ from snowflake.ml._internal.env_utils import SNOWML_SPROC_ENV
 from snowflake.ml._internal.utils import pkg_version_utils, identifier
 from snowflake.snowpark import DataFrame, Session
 from snowflake.snowpark._internal.type_utils import convert_sp_to_sf_type
-from snowflake.ml.modeling._internal.snowpark_handlers import SnowparkHandlers as HandlersImpl
+from snowflake.ml.modeling._internal.snowpark_implementations.snowpark_handlers import SnowparkHandlers as HandlersImpl
 from snowflake.ml.modeling._internal.model_trainer_builder import ModelTrainerBuilder
 from snowflake.ml.modeling._internal.model_trainer import ModelTrainer
 from snowflake.ml.modeling._internal.estimator_utils import (
@@ -35,7 +35,7 @@ from snowflake.ml.modeling._internal.estimator_utils import (
     transform_snowml_obj_to_sklearn_obj,
     validate_sklearn_args,
 )
-from snowflake.ml.modeling._internal.estimator_protocols import FitPredictHandlers
+from snowflake.ml.modeling._internal.estimator_protocols import TransformerHandlers
 
 from snowflake.ml.model.model_signature import (
     DataType,
@@ -353,7 +353,7 @@ class GradientBoostingClassifier(BaseTransformer):
         self._model_signature_dict: Optional[Dict[str, ModelSignature]] = None
         # If user used snowpark dataframe during fit, here it stores the snowpark input_cols, otherwise the processed input_cols
         self._snowpark_cols: Optional[List[str]] = self.input_cols
-        self._handlers: FitPredictHandlers = HandlersImpl(class_name=GradientBoostingClassifier.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=GradientBoostingClassifier.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -713,6 +713,22 @@ class GradientBoostingClassifier(BaseTransformer):
                 # each row containing a list of values.
                 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 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"
+                elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
+                    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:
+                    # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
+                    # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
+                    if all(x == output_types[0] for x in output_types) and len(output_types) == len(self.output_cols):
+                        expected_dtype = convert_sp_to_sf_type(output_types[0])
+            
             output_df = self._batch_inference(
                 dataset=dataset,
                 inference_method="transform",

snowflake/ml/modeling/ensemble/gradient_boosting_regressor.py

@@ -26,7 +26,7 @@ from snowflake.ml._internal.env_utils import SNOWML_SPROC_ENV
 from snowflake.ml._internal.utils import pkg_version_utils, identifier
 from snowflake.snowpark import DataFrame, Session
 from snowflake.snowpark._internal.type_utils import convert_sp_to_sf_type
-from snowflake.ml.modeling._internal.snowpark_handlers import SnowparkHandlers as HandlersImpl
+from snowflake.ml.modeling._internal.snowpark_implementations.snowpark_handlers import SnowparkHandlers as HandlersImpl
 from snowflake.ml.modeling._internal.model_trainer_builder import ModelTrainerBuilder
 from snowflake.ml.modeling._internal.model_trainer import ModelTrainer
 from snowflake.ml.modeling._internal.estimator_utils import (
@@ -35,7 +35,7 @@ from snowflake.ml.modeling._internal.estimator_utils import (
     transform_snowml_obj_to_sklearn_obj,
     validate_sklearn_args,
 )
-from snowflake.ml.modeling._internal.estimator_protocols import FitPredictHandlers
+from snowflake.ml.modeling._internal.estimator_protocols import TransformerHandlers
 
 from snowflake.ml.model.model_signature import (
     DataType,
@@ -362,7 +362,7 @@ class GradientBoostingRegressor(BaseTransformer):
         self._model_signature_dict: Optional[Dict[str, ModelSignature]] = None
         # If user used snowpark dataframe during fit, here it stores the snowpark input_cols, otherwise the processed input_cols
         self._snowpark_cols: Optional[List[str]] = self.input_cols
-        self._handlers: FitPredictHandlers = HandlersImpl(class_name=GradientBoostingRegressor.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=GradientBoostingRegressor.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -722,6 +722,22 @@ class GradientBoostingRegressor(BaseTransformer):
                 # each row containing a list of values.
                 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 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"
+                elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
+                    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:
+                    # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
+                    # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
+                    if all(x == output_types[0] for x in output_types) and len(output_types) == len(self.output_cols):
+                        expected_dtype = convert_sp_to_sf_type(output_types[0])
+            
             output_df = self._batch_inference(
                 dataset=dataset,
                 inference_method="transform",

snowflake/ml/modeling/ensemble/hist_gradient_boosting_classifier.py

@@ -26,7 +26,7 @@ from snowflake.ml._internal.env_utils import SNOWML_SPROC_ENV
 from snowflake.ml._internal.utils import pkg_version_utils, identifier
 from snowflake.snowpark import DataFrame, Session
 from snowflake.snowpark._internal.type_utils import convert_sp_to_sf_type
-from snowflake.ml.modeling._internal.snowpark_handlers import SnowparkHandlers as HandlersImpl
+from snowflake.ml.modeling._internal.snowpark_implementations.snowpark_handlers import SnowparkHandlers as HandlersImpl
 from snowflake.ml.modeling._internal.model_trainer_builder import ModelTrainerBuilder
 from snowflake.ml.modeling._internal.model_trainer import ModelTrainer
 from snowflake.ml.modeling._internal.estimator_utils import (
@@ -35,7 +35,7 @@ from snowflake.ml.modeling._internal.estimator_utils import (
     transform_snowml_obj_to_sklearn_obj,
     validate_sklearn_args,
 )
-from snowflake.ml.modeling._internal.estimator_protocols import FitPredictHandlers
+from snowflake.ml.modeling._internal.estimator_protocols import TransformerHandlers
 
 from snowflake.ml.model.model_signature import (
     DataType,
@@ -334,7 +334,7 @@ class HistGradientBoostingClassifier(BaseTransformer):
         self._model_signature_dict: Optional[Dict[str, ModelSignature]] = None
         # If user used snowpark dataframe during fit, here it stores the snowpark input_cols, otherwise the processed input_cols
         self._snowpark_cols: Optional[List[str]] = self.input_cols
-        self._handlers: FitPredictHandlers = HandlersImpl(class_name=HistGradientBoostingClassifier.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=HistGradientBoostingClassifier.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -694,6 +694,22 @@ class HistGradientBoostingClassifier(BaseTransformer):
                 # each row containing a list of values.
                 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 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"
+                elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
+                    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:
+                    # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
+                    # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
+                    if all(x == output_types[0] for x in output_types) and len(output_types) == len(self.output_cols):
+                        expected_dtype = convert_sp_to_sf_type(output_types[0])
+            
             output_df = self._batch_inference(
                 dataset=dataset,
                 inference_method="transform",

snowflake/ml/modeling/ensemble/hist_gradient_boosting_regressor.py

@@ -26,7 +26,7 @@ from snowflake.ml._internal.env_utils import SNOWML_SPROC_ENV
 from snowflake.ml._internal.utils import pkg_version_utils, identifier
 from snowflake.snowpark import DataFrame, Session
 from snowflake.snowpark._internal.type_utils import convert_sp_to_sf_type
-from snowflake.ml.modeling._internal.snowpark_handlers import SnowparkHandlers as HandlersImpl
+from snowflake.ml.modeling._internal.snowpark_implementations.snowpark_handlers import SnowparkHandlers as HandlersImpl
 from snowflake.ml.modeling._internal.model_trainer_builder import ModelTrainerBuilder
 from snowflake.ml.modeling._internal.model_trainer import ModelTrainer
 from snowflake.ml.modeling._internal.estimator_utils import (
@@ -35,7 +35,7 @@ from snowflake.ml.modeling._internal.estimator_utils import (
     transform_snowml_obj_to_sklearn_obj,
     validate_sklearn_args,
 )
-from snowflake.ml.modeling._internal.estimator_protocols import FitPredictHandlers
+from snowflake.ml.modeling._internal.estimator_protocols import TransformerHandlers
 
 from snowflake.ml.model.model_signature import (
     DataType,
@@ -325,7 +325,7 @@ class HistGradientBoostingRegressor(BaseTransformer):
         self._model_signature_dict: Optional[Dict[str, ModelSignature]] = None
         # If user used snowpark dataframe during fit, here it stores the snowpark input_cols, otherwise the processed input_cols
         self._snowpark_cols: Optional[List[str]] = self.input_cols
-        self._handlers: FitPredictHandlers = HandlersImpl(class_name=HistGradientBoostingRegressor.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=HistGradientBoostingRegressor.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -685,6 +685,22 @@ class HistGradientBoostingRegressor(BaseTransformer):
                 # each row containing a list of values.
                 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 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"
+                elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
+                    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:
+                    # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
+                    # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
+                    if all(x == output_types[0] for x in output_types) and len(output_types) == len(self.output_cols):
+                        expected_dtype = convert_sp_to_sf_type(output_types[0])
+            
             output_df = self._batch_inference(
                 dataset=dataset,
                 inference_method="transform",

snowflake/ml/modeling/ensemble/isolation_forest.py

@@ -26,7 +26,7 @@ from snowflake.ml._internal.env_utils import SNOWML_SPROC_ENV
 from snowflake.ml._internal.utils import pkg_version_utils, identifier
 from snowflake.snowpark import DataFrame, Session
 from snowflake.snowpark._internal.type_utils import convert_sp_to_sf_type
-from snowflake.ml.modeling._internal.snowpark_handlers import SnowparkHandlers as HandlersImpl
+from snowflake.ml.modeling._internal.snowpark_implementations.snowpark_handlers import SnowparkHandlers as HandlersImpl
 from snowflake.ml.modeling._internal.model_trainer_builder import ModelTrainerBuilder
 from snowflake.ml.modeling._internal.model_trainer import ModelTrainer
 from snowflake.ml.modeling._internal.estimator_utils import (
@@ -35,7 +35,7 @@ from snowflake.ml.modeling._internal.estimator_utils import (
     transform_snowml_obj_to_sklearn_obj,
     validate_sklearn_args,
 )
-from snowflake.ml.modeling._internal.estimator_protocols import FitPredictHandlers
+from snowflake.ml.modeling._internal.estimator_protocols import TransformerHandlers
 
 from snowflake.ml.model.model_signature import (
     DataType,
@@ -225,7 +225,7 @@ class IsolationForest(BaseTransformer):
         self._model_signature_dict: Optional[Dict[str, ModelSignature]] = None
         # If user used snowpark dataframe during fit, here it stores the snowpark input_cols, otherwise the processed input_cols
         self._snowpark_cols: Optional[List[str]] = self.input_cols
-        self._handlers: FitPredictHandlers = HandlersImpl(class_name=IsolationForest.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=IsolationForest.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -585,6 +585,22 @@ class IsolationForest(BaseTransformer):
                 # each row containing a list of values.
                 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 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"
+                elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
+                    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:
+                    # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
+                    # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
+                    if all(x == output_types[0] for x in output_types) and len(output_types) == len(self.output_cols):
+                        expected_dtype = convert_sp_to_sf_type(output_types[0])
+            
             output_df = self._batch_inference(
                 dataset=dataset,
                 inference_method="transform",

snowflake/ml/modeling/ensemble/random_forest_classifier.py

@@ -26,7 +26,7 @@ from snowflake.ml._internal.env_utils import SNOWML_SPROC_ENV
 from snowflake.ml._internal.utils import pkg_version_utils, identifier
 from snowflake.snowpark import DataFrame, Session
 from snowflake.snowpark._internal.type_utils import convert_sp_to_sf_type
-from snowflake.ml.modeling._internal.snowpark_handlers import SnowparkHandlers as HandlersImpl
+from snowflake.ml.modeling._internal.snowpark_implementations.snowpark_handlers import SnowparkHandlers as HandlersImpl
 from snowflake.ml.modeling._internal.model_trainer_builder import ModelTrainerBuilder
 from snowflake.ml.modeling._internal.model_trainer import ModelTrainer
 from snowflake.ml.modeling._internal.estimator_utils import (
@@ -35,7 +35,7 @@ from snowflake.ml.modeling._internal.estimator_utils import (
     transform_snowml_obj_to_sklearn_obj,
     validate_sklearn_args,
 )
-from snowflake.ml.modeling._internal.estimator_protocols import FitPredictHandlers
+from snowflake.ml.modeling._internal.estimator_protocols import TransformerHandlers
 
 from snowflake.ml.model.model_signature import (
     DataType,
@@ -337,7 +337,7 @@ class RandomForestClassifier(BaseTransformer):
         self._model_signature_dict: Optional[Dict[str, ModelSignature]] = None
         # If user used snowpark dataframe during fit, here it stores the snowpark input_cols, otherwise the processed input_cols
         self._snowpark_cols: Optional[List[str]] = self.input_cols
-        self._handlers: FitPredictHandlers = HandlersImpl(class_name=RandomForestClassifier.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=RandomForestClassifier.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -697,6 +697,22 @@ class RandomForestClassifier(BaseTransformer):
                 # each row containing a list of values.
                 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 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"
+                elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
+                    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:
+                    # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
+                    # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
+                    if all(x == output_types[0] for x in output_types) and len(output_types) == len(self.output_cols):
+                        expected_dtype = convert_sp_to_sf_type(output_types[0])
+            
             output_df = self._batch_inference(
                 dataset=dataset,
                 inference_method="transform",

snowflake/ml/modeling/ensemble/random_forest_regressor.py

@@ -26,7 +26,7 @@ from snowflake.ml._internal.env_utils import SNOWML_SPROC_ENV
 from snowflake.ml._internal.utils import pkg_version_utils, identifier
 from snowflake.snowpark import DataFrame, Session
 from snowflake.snowpark._internal.type_utils import convert_sp_to_sf_type
-from snowflake.ml.modeling._internal.snowpark_handlers import SnowparkHandlers as HandlersImpl
+from snowflake.ml.modeling._internal.snowpark_implementations.snowpark_handlers import SnowparkHandlers as HandlersImpl
 from snowflake.ml.modeling._internal.model_trainer_builder import ModelTrainerBuilder
 from snowflake.ml.modeling._internal.model_trainer import ModelTrainer
 from snowflake.ml.modeling._internal.estimator_utils import (
@@ -35,7 +35,7 @@ from snowflake.ml.modeling._internal.estimator_utils import (
     transform_snowml_obj_to_sklearn_obj,
     validate_sklearn_args,
 )
-from snowflake.ml.modeling._internal.estimator_protocols import FitPredictHandlers
+from snowflake.ml.modeling._internal.estimator_protocols import TransformerHandlers
 
 from snowflake.ml.model.model_signature import (
     DataType,
@@ -316,7 +316,7 @@ class RandomForestRegressor(BaseTransformer):
         self._model_signature_dict: Optional[Dict[str, ModelSignature]] = None
         # If user used snowpark dataframe during fit, here it stores the snowpark input_cols, otherwise the processed input_cols
         self._snowpark_cols: Optional[List[str]] = self.input_cols
-        self._handlers: FitPredictHandlers = HandlersImpl(class_name=RandomForestRegressor.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=RandomForestRegressor.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -676,6 +676,22 @@ class RandomForestRegressor(BaseTransformer):
                 # each row containing a list of values.
                 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 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"
+                elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
+                    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:
+                    # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
+                    # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
+                    if all(x == output_types[0] for x in output_types) and len(output_types) == len(self.output_cols):
+                        expected_dtype = convert_sp_to_sf_type(output_types[0])
+            
             output_df = self._batch_inference(
                 dataset=dataset,
                 inference_method="transform",

snowflake/ml/modeling/ensemble/stacking_regressor.py

@@ -26,7 +26,7 @@ from snowflake.ml._internal.env_utils import SNOWML_SPROC_ENV
 from snowflake.ml._internal.utils import pkg_version_utils, identifier
 from snowflake.snowpark import DataFrame, Session
 from snowflake.snowpark._internal.type_utils import convert_sp_to_sf_type
-from snowflake.ml.modeling._internal.snowpark_handlers import SnowparkHandlers as HandlersImpl
+from snowflake.ml.modeling._internal.snowpark_implementations.snowpark_handlers import SnowparkHandlers as HandlersImpl
 from snowflake.ml.modeling._internal.model_trainer_builder import ModelTrainerBuilder
 from snowflake.ml.modeling._internal.model_trainer import ModelTrainer
 from snowflake.ml.modeling._internal.estimator_utils import (
@@ -35,7 +35,7 @@ from snowflake.ml.modeling._internal.estimator_utils import (
     transform_snowml_obj_to_sklearn_obj,
     validate_sklearn_args,
 )
-from snowflake.ml.modeling._internal.estimator_protocols import FitPredictHandlers
+from snowflake.ml.modeling._internal.estimator_protocols import TransformerHandlers
 
 from snowflake.ml.model.model_signature import (
     DataType,
@@ -217,7 +217,7 @@ class StackingRegressor(BaseTransformer):
         self._model_signature_dict: Optional[Dict[str, ModelSignature]] = None
         # If user used snowpark dataframe during fit, here it stores the snowpark input_cols, otherwise the processed input_cols
         self._snowpark_cols: Optional[List[str]] = self.input_cols
-        self._handlers: FitPredictHandlers = HandlersImpl(class_name=StackingRegressor.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=StackingRegressor.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -579,6 +579,22 @@ class StackingRegressor(BaseTransformer):
                 # each row containing a list of values.
                 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 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"
+                elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
+                    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:
+                    # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
+                    # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
+                    if all(x == output_types[0] for x in output_types) and len(output_types) == len(self.output_cols):
+                        expected_dtype = convert_sp_to_sf_type(output_types[0])
+            
             output_df = self._batch_inference(
                 dataset=dataset,
                 inference_method="transform",

snowflake/ml/modeling/ensemble/voting_classifier.py

@@ -26,7 +26,7 @@ from snowflake.ml._internal.env_utils import SNOWML_SPROC_ENV
 from snowflake.ml._internal.utils import pkg_version_utils, identifier
 from snowflake.snowpark import DataFrame, Session
 from snowflake.snowpark._internal.type_utils import convert_sp_to_sf_type
-from snowflake.ml.modeling._internal.snowpark_handlers import SnowparkHandlers as HandlersImpl
+from snowflake.ml.modeling._internal.snowpark_implementations.snowpark_handlers import SnowparkHandlers as HandlersImpl
 from snowflake.ml.modeling._internal.model_trainer_builder import ModelTrainerBuilder
 from snowflake.ml.modeling._internal.model_trainer import ModelTrainer
 from snowflake.ml.modeling._internal.estimator_utils import (
@@ -35,7 +35,7 @@ from snowflake.ml.modeling._internal.estimator_utils import (
     transform_snowml_obj_to_sklearn_obj,
     validate_sklearn_args,
 )
-from snowflake.ml.modeling._internal.estimator_protocols import FitPredictHandlers
+from snowflake.ml.modeling._internal.estimator_protocols import TransformerHandlers
 
 from snowflake.ml.model.model_signature import (
     DataType,
@@ -199,7 +199,7 @@ class VotingClassifier(BaseTransformer):
         self._model_signature_dict: Optional[Dict[str, ModelSignature]] = None
         # If user used snowpark dataframe during fit, here it stores the snowpark input_cols, otherwise the processed input_cols
         self._snowpark_cols: Optional[List[str]] = self.input_cols
-        self._handlers: FitPredictHandlers = HandlersImpl(class_name=VotingClassifier.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=VotingClassifier.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -561,6 +561,22 @@ class VotingClassifier(BaseTransformer):
                 # each row containing a list of values.
                 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 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"
+                elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
+                    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:
+                    # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
+                    # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
+                    if all(x == output_types[0] for x in output_types) and len(output_types) == len(self.output_cols):
+                        expected_dtype = convert_sp_to_sf_type(output_types[0])
+            
             output_df = self._batch_inference(
                 dataset=dataset,
                 inference_method="transform",

snowflake/ml/modeling/ensemble/voting_regressor.py

@@ -26,7 +26,7 @@ from snowflake.ml._internal.env_utils import SNOWML_SPROC_ENV
 from snowflake.ml._internal.utils import pkg_version_utils, identifier
 from snowflake.snowpark import DataFrame, Session
 from snowflake.snowpark._internal.type_utils import convert_sp_to_sf_type
-from snowflake.ml.modeling._internal.snowpark_handlers import SnowparkHandlers as HandlersImpl
+from snowflake.ml.modeling._internal.snowpark_implementations.snowpark_handlers import SnowparkHandlers as HandlersImpl
 from snowflake.ml.modeling._internal.model_trainer_builder import ModelTrainerBuilder
 from snowflake.ml.modeling._internal.model_trainer import ModelTrainer
 from snowflake.ml.modeling._internal.estimator_utils import (
@@ -35,7 +35,7 @@ from snowflake.ml.modeling._internal.estimator_utils import (
     transform_snowml_obj_to_sklearn_obj,
     validate_sklearn_args,
 )
-from snowflake.ml.modeling._internal.estimator_protocols import FitPredictHandlers
+from snowflake.ml.modeling._internal.estimator_protocols import TransformerHandlers
 
 from snowflake.ml.model.model_signature import (
     DataType,
@@ -181,7 +181,7 @@ class VotingRegressor(BaseTransformer):
         self._model_signature_dict: Optional[Dict[str, ModelSignature]] = None
         # If user used snowpark dataframe during fit, here it stores the snowpark input_cols, otherwise the processed input_cols
         self._snowpark_cols: Optional[List[str]] = self.input_cols
-        self._handlers: FitPredictHandlers = HandlersImpl(class_name=VotingRegressor.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=VotingRegressor.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -543,6 +543,22 @@ class VotingRegressor(BaseTransformer):
                 # each row containing a list of values.
                 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 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"
+                elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
+                    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:
+                    # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
+                    # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
+                    if all(x == output_types[0] for x in output_types) and len(output_types) == len(self.output_cols):
+                        expected_dtype = convert_sp_to_sf_type(output_types[0])
+            
             output_df = self._batch_inference(
                 dataset=dataset,
                 inference_method="transform",

snowflake/ml/modeling/feature_selection/generic_univariate_select.py

@@ -27,7 +27,7 @@ from snowflake.ml._internal.env_utils import SNOWML_SPROC_ENV
 from snowflake.ml._internal.utils import pkg_version_utils, identifier
 from snowflake.snowpark import DataFrame, Session
 from snowflake.snowpark._internal.type_utils import convert_sp_to_sf_type
-from snowflake.ml.modeling._internal.snowpark_handlers import SnowparkHandlers as HandlersImpl
+from snowflake.ml.modeling._internal.snowpark_implementations.snowpark_handlers import SnowparkHandlers as HandlersImpl
 from snowflake.ml.modeling._internal.model_trainer_builder import ModelTrainerBuilder
 from snowflake.ml.modeling._internal.model_trainer import ModelTrainer
 from snowflake.ml.modeling._internal.estimator_utils import (
@@ -36,7 +36,7 @@ from snowflake.ml.modeling._internal.estimator_utils import (
     transform_snowml_obj_to_sklearn_obj,
     validate_sklearn_args,
 )
-from snowflake.ml.modeling._internal.estimator_protocols import FitPredictHandlers
+from snowflake.ml.modeling._internal.estimator_protocols import TransformerHandlers
 
 from snowflake.ml.model.model_signature import (
     DataType,
@@ -171,7 +171,7 @@ class GenericUnivariateSelect(BaseTransformer):
         self._model_signature_dict: Optional[Dict[str, ModelSignature]] = None
         # If user used snowpark dataframe during fit, here it stores the snowpark input_cols, otherwise the processed input_cols
         self._snowpark_cols: Optional[List[str]] = self.input_cols
-        self._handlers: FitPredictHandlers = HandlersImpl(class_name=GenericUnivariateSelect.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=GenericUnivariateSelect.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -531,6 +531,22 @@ class GenericUnivariateSelect(BaseTransformer):
                 # each row containing a list of values.
                 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 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"
+                elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
+                    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:
+                    # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
+                    # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
+                    if all(x == output_types[0] for x in output_types) and len(output_types) == len(self.output_cols):
+                        expected_dtype = convert_sp_to_sf_type(output_types[0])
+            
             output_df = self._batch_inference(
                 dataset=dataset,
                 inference_method="transform",

snowflake/ml/modeling/feature_selection/select_fdr.py

@@ -27,7 +27,7 @@ from snowflake.ml._internal.env_utils import SNOWML_SPROC_ENV
 from snowflake.ml._internal.utils import pkg_version_utils, identifier
 from snowflake.snowpark import DataFrame, Session
 from snowflake.snowpark._internal.type_utils import convert_sp_to_sf_type
-from snowflake.ml.modeling._internal.snowpark_handlers import SnowparkHandlers as HandlersImpl
+from snowflake.ml.modeling._internal.snowpark_implementations.snowpark_handlers import SnowparkHandlers as HandlersImpl
 from snowflake.ml.modeling._internal.model_trainer_builder import ModelTrainerBuilder
 from snowflake.ml.modeling._internal.model_trainer import ModelTrainer
 from snowflake.ml.modeling._internal.estimator_utils import (
@@ -36,7 +36,7 @@ from snowflake.ml.modeling._internal.estimator_utils import (
     transform_snowml_obj_to_sklearn_obj,
     validate_sklearn_args,
 )
-from snowflake.ml.modeling._internal.estimator_protocols import FitPredictHandlers
+from snowflake.ml.modeling._internal.estimator_protocols import TransformerHandlers
 
 from snowflake.ml.model.model_signature import (
     DataType,
@@ -167,7 +167,7 @@ class SelectFdr(BaseTransformer):
         self._model_signature_dict: Optional[Dict[str, ModelSignature]] = None
         # If user used snowpark dataframe during fit, here it stores the snowpark input_cols, otherwise the processed input_cols
         self._snowpark_cols: Optional[List[str]] = self.input_cols
-        self._handlers: FitPredictHandlers = HandlersImpl(class_name=SelectFdr.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=SelectFdr.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -527,6 +527,22 @@ class SelectFdr(BaseTransformer):
                 # each row containing a list of values.
                 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 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"
+                elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
+                    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:
+                    # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
+                    # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
+                    if all(x == output_types[0] for x in output_types) and len(output_types) == len(self.output_cols):
+                        expected_dtype = convert_sp_to_sf_type(output_types[0])
+            
             output_df = self._batch_inference(
                 dataset=dataset,
                 inference_method="transform",