snowflake-ml-python 1.2.1__py3-none-any.whl → 1.2.2__py3-none-any.whl

snowflake/ml/model/model_signature.py

@@ -1,6 +1,18 @@
 import enum
+import json
 import warnings
-from typing import Any, Dict, List, Literal, Optional, Sequence, Tuple, Type
+from typing import (
+    Any,
+    Dict,
+    List,
+    Literal,
+    Optional,
+    Sequence,
+    Tuple,
+    Type,
+    Union,
+    cast,
+)
 
 import numpy as np
 import pandas as pd
@@ -337,6 +349,31 @@ class SnowparkIdentifierRule(enum.Enum):
             assert_never(self)
 
 
+def _get_dataframe_values_range(
+    df: snowflake.snowpark.DataFrame,
+) -> Dict[str, Union[Tuple[int, int], Tuple[float, float]]]:
+    columns = [
+        F.array_construct(F.min(field.name), F.max(field.name)).as_(field.name)
+        for field in df.schema.fields
+        if isinstance(field.datatype, spt._NumericType)
+    ]
+    if not columns:
+        return {}
+    res = df.select(columns).collect()
+    if len(res) != 1:
+        raise snowml_exceptions.SnowflakeMLException(
+            error_code=error_codes.INTERNAL_SNOWML_ERROR,
+            original_exception=ValueError(f"Unable to get the value range of fields {df.columns}"),
+        )
+    return cast(
+        Dict[str, Union[Tuple[int, int], Tuple[float, float]]],
+        {
+            sql_identifier.SqlIdentifier(k, case_sensitive=True).identifier(): (json.loads(v)[0], json.loads(v)[1])
+            for k, v in res[0].as_dict().items()
+        },
+    )
+
+
 def _validate_snowpark_data(
     data: snowflake.snowpark.DataFrame, features: Sequence[core.BaseFeatureSpec]
 ) -> SnowparkIdentifierRule:
@@ -361,6 +398,7 @@ def _validate_snowpark_data(
         SnowparkIdentifierRule.NORMALIZED: [],
     }
     schema = data.schema
+    values_range = _get_dataframe_values_range(data)
     for identifier_rule in errors.keys():
         for feature in features:
             try:
@@ -401,8 +439,11 @@ def _validate_snowpark_data(
                                     + f"Feature is a scalar feature, while {field.name} is not."
                                 ),
                             )
+                            continue
                         try:
-                            _validate_snowpark_type_feature(data, field, ft_type, feature.name)
+                            _validate_snowpark_type_feature(
+                                data, field, ft_type, feature.name, values_range.get(field.name, None)
+                            )
                         except snowml_exceptions.SnowflakeMLException as e:
                             errors[identifier_rule].append(e.original_exception)
                     break
@@ -433,17 +474,12 @@ If using the inferred names from model signatures, there are the following error
 
 
 def _validate_snowpark_type_feature(
-    df: snowflake.snowpark.DataFrame, field: spt.StructField, ft_type: DataType, ft_name: str
+    df: snowflake.snowpark.DataFrame,
+    field: spt.StructField,
+    ft_type: DataType,
+    ft_name: str,
+    value_range: Optional[Union[Tuple[int, int], Tuple[float, float]]],
 ) -> None:
-    def get_value_range(field_name: str) -> Tuple[int, int]:
-        res = df.select(F.min(field_name).as_("MIN"), F.max(field_name).as_("MAX")).collect()
-        if len(res) != 1:
-            raise snowml_exceptions.SnowflakeMLException(
-                error_code=error_codes.INTERNAL_SNOWML_ERROR,
-                original_exception=ValueError(f"Unable to get the value range of field {field_name}"),
-            )
-        return res[0].MIN, res[0].MAX
-
     field_data_type = field.datatype
     col_name = identifier.get_unescaped_names(field.name)
 
@@ -465,16 +501,27 @@ def _validate_snowpark_type_feature(
                 error_code=error_codes.INVALID_DATA,
                 original_exception=ValueError(
                     f"Data Validation Error in feature {ft_name}: "
-                    + f"Feature type {ft_type} is not met by column {col_name}."
+                    f"Feature type {ft_type} is not met by column {col_name} "
+                    f"because of its original type {field_data_type}"
+                ),
+            )
+        if value_range is None:
+            raise snowml_exceptions.SnowflakeMLException(
+                error_code=error_codes.INVALID_DATA,
+                original_exception=ValueError(
+                    f"Data Validation Error in feature {ft_name}: "
+                    f"Feature type {ft_type} is not met by column {col_name} "
+                    f"because of its original type {field_data_type} is non-Numeric."
                 ),
             )
-        min_v, max_v = get_value_range(field.name)
+        min_v, max_v = value_range
         if max_v > np.iinfo(ft_type._numpy_type).max or min_v < np.iinfo(ft_type._numpy_type).min:
             raise snowml_exceptions.SnowflakeMLException(
                 error_code=error_codes.INVALID_DATA,
                 original_exception=ValueError(
                     f"Data Validation Error in feature {ft_name}: "
-                    + f"Feature type {ft_type} is not met by column {col_name}."
+                    f"Feature type {ft_type} is not met by column {col_name} "
+                    f"because it overflows with min"
                 ),
             )
     elif ft_type in [core.DataType.FLOAT, core.DataType.DOUBLE]:
@@ -494,7 +541,16 @@ def _validate_snowpark_type_feature(
                     + f"Feature type {ft_type} is not met by column {col_name}."
                 ),
             )
-        min_v, max_v = get_value_range(field.name)
+        if value_range is None:
+            raise snowml_exceptions.SnowflakeMLException(
+                error_code=error_codes.INVALID_DATA,
+                original_exception=ValueError(
+                    f"Data Validation Error in feature {ft_name}: "
+                    f"Feature type {ft_type} is not met by column {col_name} "
+                    f"because of its original type {field_data_type} is non-Numeric."
+                ),
+            )
+        min_v, max_v = value_range
         if (
             max_v > np.finfo(ft_type._numpy_type).max  # type: ignore[arg-type]
             or min_v < np.finfo(ft_type._numpy_type).min  # type: ignore[arg-type]

snowflake/ml/model/type_hints.py

@@ -3,6 +3,7 @@ from typing import (
     TYPE_CHECKING,
     Any,
     Dict,
+    List,
     Literal,
     Optional,
     Sequence,
@@ -173,6 +174,13 @@ class SnowparkContainerServiceDeployOptions(DeployOptions):
     debug_mode: When set to True, deployment artifacts will be persisted in a local temp directory.
     enable_ingress: When set to True, will expose HTTP endpoint for access to the predict method of the created
         service.
+    external_access_integrations: External Access Integrations name used to build image and deploy the model.
+        Please refer to the doc for how to create an External Access Integrations: https://docs.snowflake.com/
+        developer-guide/snowpark-container-services/additional-considerations-services-jobs
+        #configuring-network-capabilities .
+        To make sure your image could be built, access to the following endpoint must be allowed.
+        docker.com:80, docker.com:443, anaconda.com:80, anaconda.com:443, anaconda.org:80, anaconda.org:443,
+        pypi.org:80, pypi.org:443
     """
 
     compute_pool: str
@@ -187,6 +195,7 @@ class SnowparkContainerServiceDeployOptions(DeployOptions):
     model_in_image: NotRequired[bool]
     debug_mode: NotRequired[bool]
     enable_ingress: NotRequired[bool]
+    external_access_integrations: List[str]
 
 
 class ModelMethodSaveOptions(TypedDict):

snowflake/ml/modeling/_internal/estimator_protocols.py

@@ -6,47 +6,7 @@ from snowflake.snowpark import DataFrame, Session
 
 
 # TODO: Add more specific entities to type hint estimators instead of using `object`.
-class FitPredictHandlers(Protocol):
-    def batch_inference(
-        self,
-        dataset: DataFrame,
-        session: Session,
-        estimator: object,
-        dependencies: List[str],
-        inference_method: str,
-        input_cols: List[str],
-        pass_through_columns: List[str],
-        expected_output_cols_list: List[str],
-        expected_output_cols_type: str = "",
-    ) -> DataFrame:
-        raise NotImplementedError
-
-    def score_pandas(
-        self,
-        dataset: pd.DataFrame,
-        estimator: object,
-        input_cols: List[str],
-        label_cols: List[str],
-        sample_weight_col: Optional[str],
-    ) -> float:
-        raise NotImplementedError
-
-    def score_snowpark(
-        self,
-        dataset: DataFrame,
-        session: Session,
-        estimator: object,
-        dependencies: List[str],
-        score_sproc_imports: List[str],
-        input_cols: List[str],
-        label_cols: List[str],
-        sample_weight_col: Optional[str],
-    ) -> float:
-        raise NotImplementedError
-
-
-# TODO: Add more specific entities to type hint estimators instead of using `object`.
-class CVHandlers(Protocol):
+class TransformerHandlers(Protocol):
     def batch_inference(
         self,
         dataset: DataFrame,

snowflake/ml/modeling/_internal/model_trainer_builder.py

@@ -4,17 +4,21 @@ import pandas as pd
 from sklearn import model_selection
 
 from snowflake.ml._internal.exceptions import error_codes, exceptions
-from snowflake.ml.modeling._internal.distributed_hpo_trainer import (
-    DistributedHPOTrainer,
-)
 from snowflake.ml.modeling._internal.estimator_utils import (
     get_module_name,
     is_single_node,
 )
+from snowflake.ml.modeling._internal.local_implementations.pandas_trainer import (
+    PandasModelTrainer,
+)
 from snowflake.ml.modeling._internal.model_trainer import ModelTrainer
-from snowflake.ml.modeling._internal.pandas_trainer import PandasModelTrainer
-from snowflake.ml.modeling._internal.snowpark_trainer import SnowparkModelTrainer
-from snowflake.ml.modeling._internal.xgboost_external_memory_trainer import (
+from snowflake.ml.modeling._internal.snowpark_implementations.distributed_hpo_trainer import (
+    DistributedHPOTrainer,
+)
+from snowflake.ml.modeling._internal.snowpark_implementations.snowpark_trainer import (
+    SnowparkModelTrainer,
+)
+from snowflake.ml.modeling._internal.snowpark_implementations.xgboost_external_memory_trainer import (
     XGBoostExternalMemoryTrainer,
 )
 from snowflake.snowpark import DataFrame, Session
@@ -76,9 +80,9 @@ class ModelTrainerBuilder:
         batch_size: int = -1,
     ) -> ModelTrainer:
         """
-        Builder method that creates an approproiate ModelTrainer instance based on the given params.
+        Builder method that creates an appropriate ModelTrainer instance based on the given params.
         """
-        assert input_cols is not None  # Make MyPy happpy
+        assert input_cols is not None  # Make MyPy happy
         if isinstance(dataset, pd.DataFrame):
             return PandasModelTrainer(
                 estimator=estimator,
@@ -100,7 +104,7 @@ class ModelTrainerBuilder:
                 "subproject": subproject,
             }
 
-            assert dataset._session is not None  # Make MyPy happpy
+            assert dataset._session is not None  # Make MyPy happy
             if isinstance(estimator, model_selection.GridSearchCV) or isinstance(
                 estimator, model_selection.RandomizedSearchCV
             ):

snowflake/ml/modeling/_internal/{distributed_hpo_trainer.py → snowpark_implementations/distributed_hpo_trainer.py}

@@ -24,7 +24,9 @@ from snowflake.ml._internal.utils.temp_file_utils import (
 from snowflake.ml.modeling._internal.model_specifications import (
     ModelSpecificationsBuilder,
 )
-from snowflake.ml.modeling._internal.snowpark_trainer import SnowparkModelTrainer
+from snowflake.ml.modeling._internal.snowpark_implementations.snowpark_trainer import (
+    SnowparkModelTrainer,
+)
 from snowflake.snowpark import DataFrame, Session, functions as F
 from snowflake.snowpark._internal.utils import (
     TempObjectType,

snowflake/ml/modeling/_internal/{xgboost_external_memory_trainer.py → snowpark_implementations/xgboost_external_memory_trainer.py}

@@ -23,7 +23,9 @@ from snowflake.ml.modeling._internal.model_specifications import (
     ModelSpecifications,
     ModelSpecificationsBuilder,
 )
-from snowflake.ml.modeling._internal.snowpark_trainer import SnowparkModelTrainer
+from snowflake.ml.modeling._internal.snowpark_implementations.snowpark_trainer import (
+    SnowparkModelTrainer,
+)
 from snowflake.snowpark import (
     DataFrame,
     Session,

snowflake/ml/modeling/calibration/calibrated_classifier_cv.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,
@@ -229,7 +229,7 @@ class CalibratedClassifierCV(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=CalibratedClassifierCV.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=CalibratedClassifierCV.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:

snowflake/ml/modeling/cluster/affinity_propagation.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,
@@ -204,7 +204,7 @@ class AffinityPropagation(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=AffinityPropagation.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=AffinityPropagation.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:

snowflake/ml/modeling/cluster/agglomerative_clustering.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,
@@ -237,7 +237,7 @@ class AgglomerativeClustering(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=AgglomerativeClustering.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=AgglomerativeClustering.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:

snowflake/ml/modeling/cluster/birch.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,
@@ -195,7 +195,7 @@ class Birch(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=Birch.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=Birch.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:

snowflake/ml/modeling/cluster/bisecting_k_means.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,
@@ -244,7 +244,7 @@ class BisectingKMeans(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=BisectingKMeans.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=BisectingKMeans.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:

snowflake/ml/modeling/cluster/dbscan.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,
@@ -212,7 +212,7 @@ class DBSCAN(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=DBSCAN.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=DBSCAN.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:

snowflake/ml/modeling/cluster/feature_agglomeration.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,
@@ -244,7 +244,7 @@ class FeatureAgglomeration(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=FeatureAgglomeration.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=FeatureAgglomeration.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:

snowflake/ml/modeling/cluster/k_means.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,
@@ -239,7 +239,7 @@ class KMeans(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=KMeans.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=KMeans.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:

snowflake/ml/modeling/cluster/mean_shift.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,
@@ -215,7 +215,7 @@ class MeanShift(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=MeanShift.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=MeanShift.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:

snowflake/ml/modeling/cluster/mini_batch_k_means.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,
@@ -265,7 +265,7 @@ class MiniBatchKMeans(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=MiniBatchKMeans.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=MiniBatchKMeans.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:

snowflake/ml/modeling/cluster/optics.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,
@@ -285,7 +285,7 @@ class OPTICS(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=OPTICS.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=OPTICS.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str:

snowflake/ml/modeling/cluster/spectral_biclustering.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,
@@ -223,7 +223,7 @@ class SpectralBiclustering(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=SpectralBiclustering.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
+        self._handlers: TransformerHandlers = HandlersImpl(class_name=SpectralBiclustering.__class__.__name__, subproject=_SUBPROJECT, autogenerated=True)
         self._autogenerated = True
 
     def _get_rand_id(self) -> str: