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

snowflake/ml/modeling/metrics/regression.py

@@ -108,7 +108,8 @@ def d2_absolute_error_score(
         result_module = cloudpickle.loads(pickled_snowflake_result)
         return result_module.serialize(session, score)  # type: ignore[no-any-return]
 
-    result_object = result.deserialize(session, d2_absolute_error_score_anon_sproc(session))
+    kwargs = telemetry.get_sproc_statement_params_kwargs(d2_absolute_error_score_anon_sproc, statement_params)
+    result_object = result.deserialize(session, d2_absolute_error_score_anon_sproc(session, **kwargs))
     score: Union[float, npt.NDArray[np.float_]] = result_object
     return score
 
@@ -205,7 +206,8 @@ def d2_pinball_score(
         result_module = cloudpickle.loads(pickled_result_module)
         return result_module.serialize(session, score)  # type: ignore[no-any-return]
 
-    result_object = result.deserialize(session, d2_pinball_score_anon_sproc(session))
+    kwargs = telemetry.get_sproc_statement_params_kwargs(d2_pinball_score_anon_sproc, statement_params)
+    result_object = result.deserialize(session, d2_pinball_score_anon_sproc(session, **kwargs))
 
     score: Union[float, npt.NDArray[np.float_]] = result_object
     return score
@@ -319,7 +321,8 @@ def explained_variance_score(
         result_module = cloudpickle.loads(pickled_result_module)
         return result_module.serialize(session, score)  # type: ignore[no-any-return]
 
-    result_object = result.deserialize(session, explained_variance_score_anon_sproc(session))
+    kwargs = telemetry.get_sproc_statement_params_kwargs(explained_variance_score_anon_sproc, statement_params)
+    result_object = result.deserialize(session, explained_variance_score_anon_sproc(session, **kwargs))
     score: Union[float, npt.NDArray[np.float_]] = result_object
     return score
 

snowflake/ml/modeling/mixture/bayesian_gaussian_mixture.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,
@@ -287,7 +287,7 @@ class BayesianGaussianMixture(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=BayesianGaussianMixture.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=BayesianGaussianMixture.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -647,6 +647,22 @@ class BayesianGaussianMixture(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/mixture/gaussian_mixture.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,
@@ -260,7 +260,7 @@ class GaussianMixture(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=GaussianMixture.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=GaussianMixture.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -620,6 +620,22 @@ class GaussianMixture(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/model_selection/grid_search_cv.py

@@ -3,7 +3,6 @@
 # Do not modify the auto-generated code(except automatic reformatting by precommit hooks).
 #
 from typing import Any, Dict, Iterable, List, Optional, Set, Union
-from uuid import uuid4
 
 import cloudpickle as cp
 import numpy as np
@@ -22,7 +21,7 @@ from snowflake.ml.model.model_signature import (
     ModelSignature,
     _infer_signature,
 )
-from snowflake.ml.modeling._internal.estimator_protocols import CVHandlers
+from snowflake.ml.modeling._internal.estimator_protocols import TransformerHandlers
 from snowflake.ml.modeling._internal.estimator_utils import (
     gather_dependencies,
     original_estimator_has_callable,
@@ -30,7 +29,7 @@ from snowflake.ml.modeling._internal.estimator_utils import (
     validate_sklearn_args,
 )
 from snowflake.ml.modeling._internal.model_trainer_builder import ModelTrainerBuilder
-from snowflake.ml.modeling._internal.snowpark_handlers import (
+from snowflake.ml.modeling._internal.snowpark_implementations.snowpark_handlers import (
     SnowparkHandlers as HandlersImpl,
 )
 from snowflake.ml.modeling.framework.base import BaseTransformer
@@ -266,20 +265,11 @@ class GridSearchCV(BaseTransformer):
         self.set_drop_input_cols(drop_input_cols)
         self.set_sample_weight_col(sample_weight_col)
         self.set_passthrough_cols(passthrough_cols)
-        self._handlers: CVHandlers = HandlersImpl(
+        self._handlers: TransformerHandlers = HandlersImpl(
             class_name=self.__class__.__name__,
             subproject=_SUBPROJECT,
         )
 
-    def _get_rand_id(self) -> str:
-        """
-        Generate random id to be used in sproc and stage names.
-
-        Returns:
-            Random id string usable in sproc, table, and stage names.
-        """
-        return str(uuid4()).replace("-", "_").upper()
-
     def _get_active_columns(self) -> List[str]:
         """ "Get the list of columns that are relevant to the transformer."""
         selected_cols = (

snowflake/ml/modeling/model_selection/randomized_search_cv.py

@@ -1,5 +1,4 @@
 from typing import Any, Dict, Iterable, List, Optional, Set, Union
-from uuid import uuid4
 
 import cloudpickle as cp
 import numpy as np
@@ -19,7 +18,7 @@ from snowflake.ml.model.model_signature import (
     ModelSignature,
     _infer_signature,
 )
-from snowflake.ml.modeling._internal.estimator_protocols import CVHandlers
+from snowflake.ml.modeling._internal.estimator_protocols import TransformerHandlers
 from snowflake.ml.modeling._internal.estimator_utils import (
     gather_dependencies,
     original_estimator_has_callable,
@@ -27,7 +26,7 @@ from snowflake.ml.modeling._internal.estimator_utils import (
     validate_sklearn_args,
 )
 from snowflake.ml.modeling._internal.model_trainer_builder import ModelTrainerBuilder
-from snowflake.ml.modeling._internal.snowpark_handlers import (
+from snowflake.ml.modeling._internal.snowpark_implementations.snowpark_handlers import (
     SnowparkHandlers as HandlersImpl,
 )
 from snowflake.ml.modeling.framework.base import BaseTransformer
@@ -278,20 +277,11 @@ class RandomizedSearchCV(BaseTransformer):
         self.set_drop_input_cols(drop_input_cols)
         self.set_sample_weight_col(sample_weight_col)
         self.set_passthrough_cols(passthrough_cols)
-        self._handlers: CVHandlers = HandlersImpl(
+        self._handlers: TransformerHandlers = HandlersImpl(
             class_name=self.__class__.__name__,
             subproject=_SUBPROJECT,
         )
 
-    def _get_rand_id(self) -> str:
-        """
-        Generate random id to be used in sproc and stage names.
-
-        Returns:
-            Random id string usable in sproc, table, and stage names.
-        """
-        return str(uuid4()).replace("-", "_").upper()
-
     def _get_active_columns(self) -> List[str]:
         """ "Get the list of columns that are relevant to the transformer."""
         selected_cols = (

snowflake/ml/modeling/multiclass/one_vs_one_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,
@@ -172,7 +172,7 @@ class OneVsOneClassifier(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=OneVsOneClassifier.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=OneVsOneClassifier.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -532,6 +532,22 @@ class OneVsOneClassifier(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/multiclass/one_vs_rest_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,
@@ -181,7 +181,7 @@ class OneVsRestClassifier(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=OneVsRestClassifier.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=OneVsRestClassifier.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -541,6 +541,22 @@ class OneVsRestClassifier(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/multiclass/output_code_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,
@@ -184,7 +184,7 @@ class OutputCodeClassifier(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=OutputCodeClassifier.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=OutputCodeClassifier.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -544,6 +544,22 @@ class OutputCodeClassifier(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/naive_bayes/bernoulli_nb.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,
@@ -184,7 +184,7 @@ class BernoulliNB(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=BernoulliNB.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=BernoulliNB.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -544,6 +544,22 @@ class BernoulliNB(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/naive_bayes/categorical_nb.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,
@@ -190,7 +190,7 @@ class CategoricalNB(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=CategoricalNB.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=CategoricalNB.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -550,6 +550,22 @@ class CategoricalNB(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/naive_bayes/complement_nb.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,
@@ -184,7 +184,7 @@ class ComplementNB(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=ComplementNB.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=ComplementNB.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -544,6 +544,22 @@ class ComplementNB(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/naive_bayes/gaussian_nb.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,
@@ -165,7 +165,7 @@ class GaussianNB(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=GaussianNB.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=GaussianNB.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -525,6 +525,22 @@ class GaussianNB(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/naive_bayes/multinomial_nb.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,
@@ -178,7 +178,7 @@ class MultinomialNB(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=MultinomialNB.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=MultinomialNB.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:
@@ -538,6 +538,22 @@ class MultinomialNB(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",