snowflake-ml-python 1.4.1__py3-none-any.whl → 1.5.0__py3-none-any.whl

snowflake/ml/modeling/xgboost/xgbrf_classifier.py

@@ -59,12 +59,6 @@ _SUBPROJECT = "".join([s.capitalize() for s in "xgboost".replace("sklearn.", "")
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
-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 XGBRFClassifier(BaseTransformer):
     r"""scikit-learn API for XGBoost random forest classification
     For more details on this class, see [xgboost.XGBRFClassifier]
@@ -487,20 +481,17 @@ class XGBRFClassifier(BaseTransformer):
         self,
         dataset: DataFrame,
         inference_method: str,
-    ) -> List[str]:
-        """Util method to run validate that batch inference can be run on a snowpark dataframe and
-        return the available package that exists in the snowflake anaconda channel
+    ) -> None:
+        """Util method to run validate that batch inference can be run on a snowpark dataframe.
 
         Args:
             dataset: snowpark dataframe
             inference_method: the inference method such as predict, score...
-
+            
         Raises:
             SnowflakeMLException: If the estimator is not fitted, raise error
             SnowflakeMLException: If the session is None, raise error
 
-        Returns:
-            A list of available package that exists in the snowflake anaconda channel
         """
         if not self._is_fitted:
             raise exceptions.SnowflakeMLException(
@@ -518,9 +509,7 @@ class XGBRFClassifier(BaseTransformer):
                     "Session must not specified for snowpark dataset."
                 ),
             )
-        # Validate that key package version in user workspace are supported in snowflake conda channel
-        return pkg_version_utils.get_valid_pkg_versions_supported_in_snowflake_conda_channel(
-            pkg_versions=self._get_dependencies(), session=session, subproject=_SUBPROJECT)
+
 
     @available_if(original_estimator_has_callable("predict"))  # type: ignore[misc]
     @telemetry.send_api_usage_telemetry(
@@ -568,7 +557,8 @@ class XGBRFClassifier(BaseTransformer):
 
                 expected_type_inferred = convert_sp_to_sf_type(label_cols_signatures[0].as_snowpark_type())
             
-            self._deps = self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(
                 dataset._session, Session
             )  # mypy does not recognize the check in _batch_inference_validate_snowpark()
@@ -651,10 +641,8 @@ class XGBRFClassifier(BaseTransformer):
                     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])
             
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method=inference_method,
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(dataset._session, Session) # mypy does not recognize the check in _batch_inference_validate_snowpark()
 
             transform_kwargs = dict(
@@ -721,16 +709,40 @@ class XGBRFClassifier(BaseTransformer):
         self._is_fitted = True
         return output_result
 
+            
+    @available_if(original_estimator_has_callable("fit_transform"))  # type: ignore[misc]
+    def fit_transform(self, dataset: Union[DataFrame, pd.DataFrame], output_cols_prefix: str = "fit_transform_",) -> Union[DataFrame, pd.DataFrame]:
+        """ Method not supported for this class.
 
-    @available_if(_is_fit_transform_method_enabled())  # type: ignore[misc]
-    def fit_transform(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
-        """ 
+
+        Raises:
+            TypeError: Supported dataset types: snowpark.DataFrame, pandas.DataFrame.
+
+        Args:
+            dataset: Union[snowflake.snowpark.DataFrame, pandas.DataFrame]
+                Snowpark or Pandas DataFrame.
+        output_cols_prefix: Prefix for the response columns
         Returns:
             Transformed dataset.
         """
-        self.fit(dataset)
-        assert self._sklearn_object is not None
-        return self._sklearn_object.embedding_
+        self._infer_input_output_cols(dataset)
+        super()._check_dataset_type(dataset)
+        model_trainer = ModelTrainerBuilder.build_fit_transform(
+            estimator=self._sklearn_object,
+            dataset=dataset,
+            input_cols=self.input_cols,
+            label_cols=self.label_cols,
+            sample_weight_col=self.sample_weight_col,
+            autogenerated=self._autogenerated,
+            subproject=_SUBPROJECT,
+        )
+        output_result, fitted_estimator = model_trainer.train_fit_transform(
+            drop_input_cols=self._drop_input_cols,
+            expected_output_cols_list=self.output_cols,
+        )
+        self._sklearn_object = fitted_estimator
+        self._is_fitted = True
+        return output_result
 
 
     def _get_output_column_names(self, output_cols_prefix: str, output_cols: Optional[List[str]] = None) -> List[str]:
@@ -823,10 +835,8 @@ class XGBRFClassifier(BaseTransformer):
         expected_output_cols = self._get_output_column_names(output_cols_prefix)
 
         if isinstance(dataset, DataFrame):
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method=inference_method,
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(
                 dataset._session, Session
             )  # mypy does not recognize the check in _batch_inference_validate_snowpark()
@@ -893,10 +903,8 @@ class XGBRFClassifier(BaseTransformer):
         transform_kwargs: BatchInferenceKwargsTypedDict = dict()  
 
         if isinstance(dataset, DataFrame):
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method=inference_method,
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(
                 dataset._session, Session
             )  # mypy does not recognize the check in _batch_inference_validate_snowpark()
@@ -958,10 +966,8 @@ class XGBRFClassifier(BaseTransformer):
         expected_output_cols = self._get_output_column_names(output_cols_prefix)
 
         if isinstance(dataset, DataFrame):
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method=inference_method,
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(
                 dataset._session, Session
             )  # mypy does not recognize the check in _batch_inference_validate_snowpark()
@@ -1027,10 +1033,8 @@ class XGBRFClassifier(BaseTransformer):
         expected_output_cols = self._get_output_column_names(output_cols_prefix)
 
         if isinstance(dataset, DataFrame):
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method=inference_method,
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(dataset._session, Session) # mypy does not recognize the check in _batch_inference_validate_snowpark()
             transform_kwargs = dict(
                 session=dataset._session,
@@ -1094,17 +1098,15 @@ class XGBRFClassifier(BaseTransformer):
         transform_kwargs: ScoreKwargsTypedDict = dict()  
 
         if isinstance(dataset, DataFrame):
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method="score",
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method="score")
+            self._deps = self._get_dependencies()
             selected_cols = self._get_active_columns()
             if len(selected_cols) > 0:
                 dataset = dataset.select(selected_cols)
             assert isinstance(dataset._session, Session) # keep mypy happy
             transform_kwargs = dict(
                 session=dataset._session,
-                dependencies=["snowflake-snowpark-python"] + self._deps,
+                dependencies=self._deps,
                 score_sproc_imports=['xgboost'],
             )
         elif isinstance(dataset, pd.DataFrame):
@@ -1169,11 +1171,8 @@ class XGBRFClassifier(BaseTransformer):
 
         if isinstance(dataset, DataFrame):
 
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method=inference_method,
-
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(dataset._session, Session) # mypy does not recognize the check in _batch_inference_validate_snowpark()
             transform_kwargs = dict(
                 session = dataset._session,

snowflake/ml/modeling/xgboost/xgbrf_regressor.py

@@ -59,12 +59,6 @@ _SUBPROJECT = "".join([s.capitalize() for s in "xgboost".replace("sklearn.", "")
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
-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 XGBRFRegressor(BaseTransformer):
     r"""scikit-learn API for XGBoost random forest regression
     For more details on this class, see [xgboost.XGBRFRegressor]
@@ -487,20 +481,17 @@ class XGBRFRegressor(BaseTransformer):
         self,
         dataset: DataFrame,
         inference_method: str,
-    ) -> List[str]:
-        """Util method to run validate that batch inference can be run on a snowpark dataframe and
-        return the available package that exists in the snowflake anaconda channel
+    ) -> None:
+        """Util method to run validate that batch inference can be run on a snowpark dataframe.
 
         Args:
             dataset: snowpark dataframe
             inference_method: the inference method such as predict, score...
-
+            
         Raises:
             SnowflakeMLException: If the estimator is not fitted, raise error
             SnowflakeMLException: If the session is None, raise error
 
-        Returns:
-            A list of available package that exists in the snowflake anaconda channel
         """
         if not self._is_fitted:
             raise exceptions.SnowflakeMLException(
@@ -518,9 +509,7 @@ class XGBRFRegressor(BaseTransformer):
                     "Session must not specified for snowpark dataset."
                 ),
             )
-        # Validate that key package version in user workspace are supported in snowflake conda channel
-        return pkg_version_utils.get_valid_pkg_versions_supported_in_snowflake_conda_channel(
-            pkg_versions=self._get_dependencies(), session=session, subproject=_SUBPROJECT)
+
 
     @available_if(original_estimator_has_callable("predict"))  # type: ignore[misc]
     @telemetry.send_api_usage_telemetry(
@@ -568,7 +557,8 @@ class XGBRFRegressor(BaseTransformer):
 
                 expected_type_inferred = convert_sp_to_sf_type(label_cols_signatures[0].as_snowpark_type())
             
-            self._deps = self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(
                 dataset._session, Session
             )  # mypy does not recognize the check in _batch_inference_validate_snowpark()
@@ -651,10 +641,8 @@ class XGBRFRegressor(BaseTransformer):
                     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])
             
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method=inference_method,
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(dataset._session, Session) # mypy does not recognize the check in _batch_inference_validate_snowpark()
 
             transform_kwargs = dict(
@@ -721,16 +709,40 @@ class XGBRFRegressor(BaseTransformer):
         self._is_fitted = True
         return output_result
 
+            
+    @available_if(original_estimator_has_callable("fit_transform"))  # type: ignore[misc]
+    def fit_transform(self, dataset: Union[DataFrame, pd.DataFrame], output_cols_prefix: str = "fit_transform_",) -> Union[DataFrame, pd.DataFrame]:
+        """ Method not supported for this class.
 
-    @available_if(_is_fit_transform_method_enabled())  # type: ignore[misc]
-    def fit_transform(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
-        """ 
+
+        Raises:
+            TypeError: Supported dataset types: snowpark.DataFrame, pandas.DataFrame.
+
+        Args:
+            dataset: Union[snowflake.snowpark.DataFrame, pandas.DataFrame]
+                Snowpark or Pandas DataFrame.
+        output_cols_prefix: Prefix for the response columns
         Returns:
             Transformed dataset.
         """
-        self.fit(dataset)
-        assert self._sklearn_object is not None
-        return self._sklearn_object.embedding_
+        self._infer_input_output_cols(dataset)
+        super()._check_dataset_type(dataset)
+        model_trainer = ModelTrainerBuilder.build_fit_transform(
+            estimator=self._sklearn_object,
+            dataset=dataset,
+            input_cols=self.input_cols,
+            label_cols=self.label_cols,
+            sample_weight_col=self.sample_weight_col,
+            autogenerated=self._autogenerated,
+            subproject=_SUBPROJECT,
+        )
+        output_result, fitted_estimator = model_trainer.train_fit_transform(
+            drop_input_cols=self._drop_input_cols,
+            expected_output_cols_list=self.output_cols,
+        )
+        self._sklearn_object = fitted_estimator
+        self._is_fitted = True
+        return output_result
 
 
     def _get_output_column_names(self, output_cols_prefix: str, output_cols: Optional[List[str]] = None) -> List[str]:
@@ -821,10 +833,8 @@ class XGBRFRegressor(BaseTransformer):
         expected_output_cols = self._get_output_column_names(output_cols_prefix)
 
         if isinstance(dataset, DataFrame):
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method=inference_method,
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(
                 dataset._session, Session
             )  # mypy does not recognize the check in _batch_inference_validate_snowpark()
@@ -889,10 +899,8 @@ class XGBRFRegressor(BaseTransformer):
         transform_kwargs: BatchInferenceKwargsTypedDict = dict()  
 
         if isinstance(dataset, DataFrame):
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method=inference_method,
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(
                 dataset._session, Session
             )  # mypy does not recognize the check in _batch_inference_validate_snowpark()
@@ -954,10 +962,8 @@ class XGBRFRegressor(BaseTransformer):
         expected_output_cols = self._get_output_column_names(output_cols_prefix)
 
         if isinstance(dataset, DataFrame):
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method=inference_method,
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(
                 dataset._session, Session
             )  # mypy does not recognize the check in _batch_inference_validate_snowpark()
@@ -1023,10 +1029,8 @@ class XGBRFRegressor(BaseTransformer):
         expected_output_cols = self._get_output_column_names(output_cols_prefix)
 
         if isinstance(dataset, DataFrame):
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method=inference_method,
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(dataset._session, Session) # mypy does not recognize the check in _batch_inference_validate_snowpark()
             transform_kwargs = dict(
                 session=dataset._session,
@@ -1090,17 +1094,15 @@ class XGBRFRegressor(BaseTransformer):
         transform_kwargs: ScoreKwargsTypedDict = dict()  
 
         if isinstance(dataset, DataFrame):
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method="score",
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method="score")
+            self._deps = self._get_dependencies()
             selected_cols = self._get_active_columns()
             if len(selected_cols) > 0:
                 dataset = dataset.select(selected_cols)
             assert isinstance(dataset._session, Session) # keep mypy happy
             transform_kwargs = dict(
                 session=dataset._session,
-                dependencies=["snowflake-snowpark-python"] + self._deps,
+                dependencies=self._deps,
                 score_sproc_imports=['xgboost'],
             )
         elif isinstance(dataset, pd.DataFrame):
@@ -1165,11 +1167,8 @@ class XGBRFRegressor(BaseTransformer):
 
         if isinstance(dataset, DataFrame):
 
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method=inference_method,
-
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(dataset._session, Session) # mypy does not recognize the check in _batch_inference_validate_snowpark()
             transform_kwargs = dict(
                 session = dataset._session,