snowflake-ml-python 1.1.2__py3-none-any.whl → 1.2.1__py3-none-any.whl

snowflake/ml/modeling/feature_selection/generic_univariate_select.py

@@ -55,6 +55,18 @@ _PROJECT = "ModelDevelopment"
 _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.feature_selection".replace("sklearn.", "").split("_")])
 
 
+def _is_fit_predict_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_predict", None))
+    return check
+
+
+def _is_fit_transform_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_transform", None))
+    return check
+
+
 class GenericUnivariateSelect(BaseTransformer):
     r"""Univariate feature selector with configurable strategy
     For more details on this class, see [sklearn.feature_selection.GenericUnivariateSelect]
@@ -139,7 +151,9 @@ class GenericUnivariateSelect(BaseTransformer):
         self.set_label_cols(label_cols)
         self.set_passthrough_cols(passthrough_cols)
         self.set_drop_input_cols(drop_input_cols)
-        self.set_sample_weight_col(sample_weight_col)        
+        self.set_sample_weight_col(sample_weight_col)
+        self._use_external_memory_version = False
+        self._batch_size = -1        
         deps: Set[str] = set([f'numpy=={np.__version__}', f'scikit-learn=={sklearn.__version__}', f'cloudpickle=={cp.__version__}'])
         
         self._deps = list(deps)
@@ -217,11 +231,6 @@ class GenericUnivariateSelect(BaseTransformer):
         if isinstance(dataset, DataFrame):
             session = dataset._session
             assert session is not None  # keep mypy happy
-            # Validate that key package version in user workspace are supported in snowflake conda channel
-            # If customer doesn't have package in conda channel, replace the ones have the closest versions
-            self._deps = pkg_version_utils.get_valid_pkg_versions_supported_in_snowflake_conda_channel(
-                pkg_versions=self._get_dependencies(), session=session, subproject=_SUBPROJECT)
-            
             # Specify input columns so column pruning will be enforced
             selected_cols = self._get_active_columns()
             if len(selected_cols) > 0:
@@ -249,7 +258,9 @@ class GenericUnivariateSelect(BaseTransformer):
             label_cols=self.label_cols,
             sample_weight_col=self.sample_weight_col,
             autogenerated=self._autogenerated,
-            subproject=_SUBPROJECT
+            subproject=_SUBPROJECT,
+            use_external_memory_version=self._use_external_memory_version,
+            batch_size=self._batch_size,
         )
         self._sklearn_object = model_trainer.train()
         self._is_fitted = True
@@ -520,6 +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",
@@ -535,8 +562,8 @@ class GenericUnivariateSelect(BaseTransformer):
 
         return output_df
     
-    @available_if(original_estimator_has_callable("fit_predict"))  # type: ignore[misc]
-    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> npt.NDArray[Any]:
+    @available_if(_is_fit_predict_method_enabled())  # type: ignore[misc]
+    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
         """ Method not supported for this class.
 
 
@@ -549,13 +576,21 @@ class GenericUnivariateSelect(BaseTransformer):
         Returns:
             Predicted dataset.
         """
-        if False:
-            self.fit(dataset)
-            assert self._sklearn_object is not None
-            labels : npt.NDArray[Any] = self._sklearn_object.labels_
-            return labels
-        else:
-            raise NotImplementedError
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.labels_
+
+
+    @available_if(_is_fit_transform_method_enabled())  # type: ignore[misc]
+    def fit_transform(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
+        """ 
+        Returns:
+            Transformed dataset.
+        """
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.embedding_
+
 
     def _get_output_column_names(self, output_cols_prefix: str, output_cols: Optional[List[str]] = None) -> List[str]:
         """ Returns the list of output columns for predict_proba(), decision_function(), etc.. functions.

snowflake/ml/modeling/feature_selection/select_fdr.py

@@ -55,6 +55,18 @@ _PROJECT = "ModelDevelopment"
 _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.feature_selection".replace("sklearn.", "").split("_")])
 
 
+def _is_fit_predict_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_predict", None))
+    return check
+
+
+def _is_fit_transform_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_transform", None))
+    return check
+
+
 class SelectFdr(BaseTransformer):
     r"""Filter: Select the p-values for an estimated false discovery rate
     For more details on this class, see [sklearn.feature_selection.SelectFdr]
@@ -136,7 +148,9 @@ class SelectFdr(BaseTransformer):
         self.set_label_cols(label_cols)
         self.set_passthrough_cols(passthrough_cols)
         self.set_drop_input_cols(drop_input_cols)
-        self.set_sample_weight_col(sample_weight_col)        
+        self.set_sample_weight_col(sample_weight_col)
+        self._use_external_memory_version = False
+        self._batch_size = -1        
         deps: Set[str] = set([f'numpy=={np.__version__}', f'scikit-learn=={sklearn.__version__}', f'cloudpickle=={cp.__version__}'])
         
         self._deps = list(deps)
@@ -213,11 +227,6 @@ class SelectFdr(BaseTransformer):
         if isinstance(dataset, DataFrame):
             session = dataset._session
             assert session is not None  # keep mypy happy
-            # Validate that key package version in user workspace are supported in snowflake conda channel
-            # If customer doesn't have package in conda channel, replace the ones have the closest versions
-            self._deps = pkg_version_utils.get_valid_pkg_versions_supported_in_snowflake_conda_channel(
-                pkg_versions=self._get_dependencies(), session=session, subproject=_SUBPROJECT)
-            
             # Specify input columns so column pruning will be enforced
             selected_cols = self._get_active_columns()
             if len(selected_cols) > 0:
@@ -245,7 +254,9 @@ class SelectFdr(BaseTransformer):
             label_cols=self.label_cols,
             sample_weight_col=self.sample_weight_col,
             autogenerated=self._autogenerated,
-            subproject=_SUBPROJECT
+            subproject=_SUBPROJECT,
+            use_external_memory_version=self._use_external_memory_version,
+            batch_size=self._batch_size,
         )
         self._sklearn_object = model_trainer.train()
         self._is_fitted = True
@@ -516,6 +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",
@@ -531,8 +558,8 @@ class SelectFdr(BaseTransformer):
 
         return output_df
     
-    @available_if(original_estimator_has_callable("fit_predict"))  # type: ignore[misc]
-    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> npt.NDArray[Any]:
+    @available_if(_is_fit_predict_method_enabled())  # type: ignore[misc]
+    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
         """ Method not supported for this class.
 
 
@@ -545,13 +572,21 @@ class SelectFdr(BaseTransformer):
         Returns:
             Predicted dataset.
         """
-        if False:
-            self.fit(dataset)
-            assert self._sklearn_object is not None
-            labels : npt.NDArray[Any] = self._sklearn_object.labels_
-            return labels
-        else:
-            raise NotImplementedError
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.labels_
+
+
+    @available_if(_is_fit_transform_method_enabled())  # type: ignore[misc]
+    def fit_transform(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
+        """ 
+        Returns:
+            Transformed dataset.
+        """
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.embedding_
+
 
     def _get_output_column_names(self, output_cols_prefix: str, output_cols: Optional[List[str]] = None) -> List[str]:
         """ Returns the list of output columns for predict_proba(), decision_function(), etc.. functions.

snowflake/ml/modeling/feature_selection/select_fpr.py

@@ -55,6 +55,18 @@ _PROJECT = "ModelDevelopment"
 _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.feature_selection".replace("sklearn.", "").split("_")])
 
 
+def _is_fit_predict_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_predict", None))
+    return check
+
+
+def _is_fit_transform_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_transform", None))
+    return check
+
+
 class SelectFpr(BaseTransformer):
     r"""Filter: Select the pvalues below alpha based on a FPR test
     For more details on this class, see [sklearn.feature_selection.SelectFpr]
@@ -136,7 +148,9 @@ class SelectFpr(BaseTransformer):
         self.set_label_cols(label_cols)
         self.set_passthrough_cols(passthrough_cols)
         self.set_drop_input_cols(drop_input_cols)
-        self.set_sample_weight_col(sample_weight_col)        
+        self.set_sample_weight_col(sample_weight_col)
+        self._use_external_memory_version = False
+        self._batch_size = -1        
         deps: Set[str] = set([f'numpy=={np.__version__}', f'scikit-learn=={sklearn.__version__}', f'cloudpickle=={cp.__version__}'])
         
         self._deps = list(deps)
@@ -213,11 +227,6 @@ class SelectFpr(BaseTransformer):
         if isinstance(dataset, DataFrame):
             session = dataset._session
             assert session is not None  # keep mypy happy
-            # Validate that key package version in user workspace are supported in snowflake conda channel
-            # If customer doesn't have package in conda channel, replace the ones have the closest versions
-            self._deps = pkg_version_utils.get_valid_pkg_versions_supported_in_snowflake_conda_channel(
-                pkg_versions=self._get_dependencies(), session=session, subproject=_SUBPROJECT)
-            
             # Specify input columns so column pruning will be enforced
             selected_cols = self._get_active_columns()
             if len(selected_cols) > 0:
@@ -245,7 +254,9 @@ class SelectFpr(BaseTransformer):
             label_cols=self.label_cols,
             sample_weight_col=self.sample_weight_col,
             autogenerated=self._autogenerated,
-            subproject=_SUBPROJECT
+            subproject=_SUBPROJECT,
+            use_external_memory_version=self._use_external_memory_version,
+            batch_size=self._batch_size,
         )
         self._sklearn_object = model_trainer.train()
         self._is_fitted = True
@@ -516,6 +527,22 @@ class SelectFpr(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",
@@ -531,8 +558,8 @@ class SelectFpr(BaseTransformer):
 
         return output_df
     
-    @available_if(original_estimator_has_callable("fit_predict"))  # type: ignore[misc]
-    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> npt.NDArray[Any]:
+    @available_if(_is_fit_predict_method_enabled())  # type: ignore[misc]
+    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
         """ Method not supported for this class.
 
 
@@ -545,13 +572,21 @@ class SelectFpr(BaseTransformer):
         Returns:
             Predicted dataset.
         """
-        if False:
-            self.fit(dataset)
-            assert self._sklearn_object is not None
-            labels : npt.NDArray[Any] = self._sklearn_object.labels_
-            return labels
-        else:
-            raise NotImplementedError
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.labels_
+
+
+    @available_if(_is_fit_transform_method_enabled())  # type: ignore[misc]
+    def fit_transform(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
+        """ 
+        Returns:
+            Transformed dataset.
+        """
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.embedding_
+
 
     def _get_output_column_names(self, output_cols_prefix: str, output_cols: Optional[List[str]] = None) -> List[str]:
         """ Returns the list of output columns for predict_proba(), decision_function(), etc.. functions.

snowflake/ml/modeling/feature_selection/select_fwe.py

@@ -55,6 +55,18 @@ _PROJECT = "ModelDevelopment"
 _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.feature_selection".replace("sklearn.", "").split("_")])
 
 
+def _is_fit_predict_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_predict", None))
+    return check
+
+
+def _is_fit_transform_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_transform", None))
+    return check
+
+
 class SelectFwe(BaseTransformer):
     r"""Filter: Select the p-values corresponding to Family-wise error rate
     For more details on this class, see [sklearn.feature_selection.SelectFwe]
@@ -136,7 +148,9 @@ class SelectFwe(BaseTransformer):
         self.set_label_cols(label_cols)
         self.set_passthrough_cols(passthrough_cols)
         self.set_drop_input_cols(drop_input_cols)
-        self.set_sample_weight_col(sample_weight_col)        
+        self.set_sample_weight_col(sample_weight_col)
+        self._use_external_memory_version = False
+        self._batch_size = -1        
         deps: Set[str] = set([f'numpy=={np.__version__}', f'scikit-learn=={sklearn.__version__}', f'cloudpickle=={cp.__version__}'])
         
         self._deps = list(deps)
@@ -213,11 +227,6 @@ class SelectFwe(BaseTransformer):
         if isinstance(dataset, DataFrame):
             session = dataset._session
             assert session is not None  # keep mypy happy
-            # Validate that key package version in user workspace are supported in snowflake conda channel
-            # If customer doesn't have package in conda channel, replace the ones have the closest versions
-            self._deps = pkg_version_utils.get_valid_pkg_versions_supported_in_snowflake_conda_channel(
-                pkg_versions=self._get_dependencies(), session=session, subproject=_SUBPROJECT)
-            
             # Specify input columns so column pruning will be enforced
             selected_cols = self._get_active_columns()
             if len(selected_cols) > 0:
@@ -245,7 +254,9 @@ class SelectFwe(BaseTransformer):
             label_cols=self.label_cols,
             sample_weight_col=self.sample_weight_col,
             autogenerated=self._autogenerated,
-            subproject=_SUBPROJECT
+            subproject=_SUBPROJECT,
+            use_external_memory_version=self._use_external_memory_version,
+            batch_size=self._batch_size,
         )
         self._sklearn_object = model_trainer.train()
         self._is_fitted = True
@@ -516,6 +527,22 @@ class SelectFwe(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",
@@ -531,8 +558,8 @@ class SelectFwe(BaseTransformer):
 
         return output_df
     
-    @available_if(original_estimator_has_callable("fit_predict"))  # type: ignore[misc]
-    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> npt.NDArray[Any]:
+    @available_if(_is_fit_predict_method_enabled())  # type: ignore[misc]
+    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
         """ Method not supported for this class.
 
 
@@ -545,13 +572,21 @@ class SelectFwe(BaseTransformer):
         Returns:
             Predicted dataset.
         """
-        if False:
-            self.fit(dataset)
-            assert self._sklearn_object is not None
-            labels : npt.NDArray[Any] = self._sklearn_object.labels_
-            return labels
-        else:
-            raise NotImplementedError
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.labels_
+
+
+    @available_if(_is_fit_transform_method_enabled())  # type: ignore[misc]
+    def fit_transform(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
+        """ 
+        Returns:
+            Transformed dataset.
+        """
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.embedding_
+
 
     def _get_output_column_names(self, output_cols_prefix: str, output_cols: Optional[List[str]] = None) -> List[str]:
         """ Returns the list of output columns for predict_proba(), decision_function(), etc.. functions.

snowflake/ml/modeling/feature_selection/select_k_best.py

@@ -55,6 +55,18 @@ _PROJECT = "ModelDevelopment"
 _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.feature_selection".replace("sklearn.", "").split("_")])
 
 
+def _is_fit_predict_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_predict", None))
+    return check
+
+
+def _is_fit_transform_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_transform", None))
+    return check
+
+
 class SelectKBest(BaseTransformer):
     r"""Select features according to the k highest scores
     For more details on this class, see [sklearn.feature_selection.SelectKBest]
@@ -137,7 +149,9 @@ class SelectKBest(BaseTransformer):
         self.set_label_cols(label_cols)
         self.set_passthrough_cols(passthrough_cols)
         self.set_drop_input_cols(drop_input_cols)
-        self.set_sample_weight_col(sample_weight_col)        
+        self.set_sample_weight_col(sample_weight_col)
+        self._use_external_memory_version = False
+        self._batch_size = -1        
         deps: Set[str] = set([f'numpy=={np.__version__}', f'scikit-learn=={sklearn.__version__}', f'cloudpickle=={cp.__version__}'])
         
         self._deps = list(deps)
@@ -214,11 +228,6 @@ class SelectKBest(BaseTransformer):
         if isinstance(dataset, DataFrame):
             session = dataset._session
             assert session is not None  # keep mypy happy
-            # Validate that key package version in user workspace are supported in snowflake conda channel
-            # If customer doesn't have package in conda channel, replace the ones have the closest versions
-            self._deps = pkg_version_utils.get_valid_pkg_versions_supported_in_snowflake_conda_channel(
-                pkg_versions=self._get_dependencies(), session=session, subproject=_SUBPROJECT)
-            
             # Specify input columns so column pruning will be enforced
             selected_cols = self._get_active_columns()
             if len(selected_cols) > 0:
@@ -246,7 +255,9 @@ class SelectKBest(BaseTransformer):
             label_cols=self.label_cols,
             sample_weight_col=self.sample_weight_col,
             autogenerated=self._autogenerated,
-            subproject=_SUBPROJECT
+            subproject=_SUBPROJECT,
+            use_external_memory_version=self._use_external_memory_version,
+            batch_size=self._batch_size,
         )
         self._sklearn_object = model_trainer.train()
         self._is_fitted = True
@@ -517,6 +528,22 @@ class SelectKBest(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",
@@ -532,8 +559,8 @@ class SelectKBest(BaseTransformer):
 
         return output_df
     
-    @available_if(original_estimator_has_callable("fit_predict"))  # type: ignore[misc]
-    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> npt.NDArray[Any]:
+    @available_if(_is_fit_predict_method_enabled())  # type: ignore[misc]
+    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
         """ Method not supported for this class.
 
 
@@ -546,13 +573,21 @@ class SelectKBest(BaseTransformer):
         Returns:
             Predicted dataset.
         """
-        if False:
-            self.fit(dataset)
-            assert self._sklearn_object is not None
-            labels : npt.NDArray[Any] = self._sklearn_object.labels_
-            return labels
-        else:
-            raise NotImplementedError
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.labels_
+
+
+    @available_if(_is_fit_transform_method_enabled())  # type: ignore[misc]
+    def fit_transform(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
+        """ 
+        Returns:
+            Transformed dataset.
+        """
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.embedding_
+
 
     def _get_output_column_names(self, output_cols_prefix: str, output_cols: Optional[List[str]] = None) -> List[str]:
         """ Returns the list of output columns for predict_proba(), decision_function(), etc.. functions.