snowflake-ml-python 1.6.1__py3-none-any.whl → 1.6.2__py3-none-any.whl

snowflake/ml/modeling/xgboost/xgb_regressor.py

@@ -4,18 +4,17 @@
 #
 import inspect
 import os
-import posixpath
-from typing import Iterable, Optional, Union, List, Any, Dict, Callable, Set
-from typing_extensions import TypeGuard
+from typing import Iterable, Optional, Union, List, Any, Dict, Set, Tuple
 from uuid import uuid4
 
 import cloudpickle as cp
-import pandas as pd
 import numpy as np
+import pandas as pd
 from numpy import typing as npt
 
 
 import numpy
+import sklearn
 import xgboost
 from sklearn.utils.metaestimators import available_if
 
@@ -23,12 +22,11 @@ from snowflake.ml.modeling.framework.base import BaseTransformer, _process_cols
 from snowflake.ml._internal import telemetry
 from snowflake.ml._internal.exceptions import error_codes, exceptions, modeling_error_messages
 from snowflake.ml._internal.env_utils import SNOWML_SPROC_ENV
-from snowflake.ml._internal.utils import pkg_version_utils, identifier
+from snowflake.ml._internal.utils import identifier
 from snowflake.snowpark import DataFrame, Session
 from snowflake.snowpark._internal.type_utils import convert_sp_to_sf_type
 from snowflake.ml.modeling._internal.model_trainer_builder import ModelTrainerBuilder
 from snowflake.ml.modeling._internal.transformer_protocols import (
-    ModelTransformHandlers,
     BatchInferenceKwargsTypedDict,
     ScoreKwargsTypedDict
 )
@@ -361,7 +359,7 @@ class XGBRegressor(BaseTransformer):
         self.set_sample_weight_col(sample_weight_col)
         self._use_external_memory_version = use_external_memory_version
         self._batch_size = batch_size        
-        deps: Set[str] = set([f'numpy=={np.__version__}', f'xgboost=={xgboost.__version__}', f'cloudpickle=={cp.__version__}'])
+        deps: Set[str] = set([f'numpy=={np.__version__}', f'scikit-learn=={sklearn.__version__}', f'xgboost=={xgboost.__version__}', f'cloudpickle=={cp.__version__}'])
         
         self._deps = list(deps)
         
@@ -694,12 +692,23 @@ class XGBRegressor(BaseTransformer):
             autogenerated=self._autogenerated,
             subproject=_SUBPROJECT,
         )
-        output_result, fitted_estimator = model_trainer.train_fit_predict(
-            drop_input_cols=self._drop_input_cols,
-            expected_output_cols_list=(
-                self.output_cols if self.output_cols else self._get_output_column_names(output_cols_prefix)
-            ),
+        expected_output_cols = (
+            self.output_cols if self.output_cols else self._get_output_column_names(output_cols_prefix)
         )
+        if isinstance(dataset, DataFrame):
+            expected_output_cols, example_output_pd_df = self._align_expected_output(
+                "fit_predict", dataset, expected_output_cols, output_cols_prefix
+            )
+            output_result, fitted_estimator = model_trainer.train_fit_predict(
+                drop_input_cols=self._drop_input_cols,
+                expected_output_cols_list=expected_output_cols,
+                example_output_pd_df=example_output_pd_df,
+            )
+        else:
+            output_result, fitted_estimator = model_trainer.train_fit_predict(
+                drop_input_cols=self._drop_input_cols,
+                expected_output_cols_list=expected_output_cols,
+            )
         self._sklearn_object = fitted_estimator
         self._is_fitted = True
         return output_result
@@ -778,12 +787,41 @@ class XGBRegressor(BaseTransformer):
 
         return rv
 
-    def _align_expected_output_names(
-        self, method: str, dataset: DataFrame, expected_output_cols_list: List[str], output_cols_prefix: str
-    ) -> List[str]:
+    def _align_expected_output(
+        self, method: str, dataset: DataFrame, expected_output_cols_list: List[str], output_cols_prefix: str,
+    ) -> Tuple[List[str], pd.DataFrame]:
+        """ Run 1 line of data with the desired method, and return one tuple that consists of the output column names 
+        and output dataframe with 1 line.
+        If the method is fit_predict, run 2 lines of data. 
+        """
         # in case the inferred output column names dimension is different 
         # we use one line of snowpark dataframe and put it into sklearn estimator using pandas
-        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # For fit_predict method, a minimum of 2 is required by MinCovDet, BayesianGaussianMixture
+        # so change the minimum of number of rows to 2
+        num_examples = 2
+        statement_params = telemetry.get_function_usage_statement_params(
+            project=_PROJECT,
+            subproject=_SUBPROJECT,
+            function_name=telemetry.get_statement_params_full_func_name(
+                inspect.currentframe(), XGBRegressor.__class__.__name__
+            ),
+            api_calls=[Session.call],
+            custom_tags={"autogen": True} if self._autogenerated else None,
+        )
+        if output_cols_prefix == "fit_predict_":
+            if hasattr(self._sklearn_object, "n_clusters"):
+                # cluster classes such as BisectingKMeansTest requires # of examples >= n_clusters
+                num_examples = self._sklearn_object.n_clusters
+            elif hasattr(self._sklearn_object, "min_samples"):
+                # OPTICS default min_samples 5, which requires at least 5 lines of data
+                num_examples = self._sklearn_object.min_samples
+            elif hasattr(self._sklearn_object, "n_neighbors") and hasattr(self._sklearn_object, "n_samples"):
+                # LocalOutlierFactor expects n_neighbors <= n_samples
+                num_examples = self._sklearn_object.n_neighbors
+            sample_pd_df = dataset.select(self.input_cols).limit(num_examples).to_pandas(statement_params=statement_params)
+        else:
+            sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas(statement_params=statement_params)
 
         # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
         # seen during the fit.
@@ -795,12 +833,14 @@ class XGBRegressor(BaseTransformer):
         output_df_columns_set: Set[str] = set(output_df_columns) - set(dataset.columns)
         if self.sample_weight_col:
             output_df_columns_set -= set(self.sample_weight_col)
+        
         # if the dimension of inferred output column names is correct; use it
         if len(expected_output_cols_list) == len(output_df_columns_set):
-            return expected_output_cols_list
+            return expected_output_cols_list, output_df_pd
         # otherwise, use the sklearn estimator's output
         else:
-            return sorted(list(output_df_columns_set), key=lambda x: output_df_columns.index(x))
+            expected_output_cols_list = sorted(list(output_df_columns_set), key=lambda x: output_df_columns.index(x))
+            return expected_output_cols_list, output_df_pd[expected_output_cols_list]
 
     @available_if(original_estimator_has_callable("predict_proba"))  # type: ignore[misc]
     @telemetry.send_api_usage_telemetry(
@@ -846,7 +886,7 @@ class XGBRegressor(BaseTransformer):
                 drop_input_cols=self._drop_input_cols,
                 expected_output_cols_type="float",
             )
-            expected_output_cols = self._align_expected_output_names(
+            expected_output_cols, _ = self._align_expected_output(
                 inference_method, dataset, expected_output_cols, output_cols_prefix
             )
 
@@ -912,7 +952,7 @@ class XGBRegressor(BaseTransformer):
                 drop_input_cols=self._drop_input_cols,
                 expected_output_cols_type="float",
             )
-            expected_output_cols = self._align_expected_output_names(
+            expected_output_cols, _ = self._align_expected_output(
                 inference_method, dataset, expected_output_cols, output_cols_prefix
             )
         elif isinstance(dataset, pd.DataFrame):
@@ -975,7 +1015,7 @@ class XGBRegressor(BaseTransformer):
                 drop_input_cols=self._drop_input_cols,
                 expected_output_cols_type="float",
             )
-            expected_output_cols = self._align_expected_output_names(
+            expected_output_cols, _ = self._align_expected_output(
                 inference_method, dataset, expected_output_cols, output_cols_prefix
             )
 
@@ -1040,7 +1080,7 @@ class XGBRegressor(BaseTransformer):
                 drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type="float",
             )
-            expected_output_cols = self._align_expected_output_names(
+            expected_output_cols, _ = self._align_expected_output(
                 inference_method, dataset, expected_output_cols, output_cols_prefix
             )
 
@@ -1105,7 +1145,7 @@ class XGBRegressor(BaseTransformer):
             transform_kwargs = dict(
                 session=dataset._session,
                 dependencies=self._deps,
-                score_sproc_imports=['xgboost'],
+                score_sproc_imports=['xgboost', 'sklearn'],
             )
         elif isinstance(dataset, pd.DataFrame):
             # pandas_handler.score() does not require any extra kwargs.

snowflake/ml/modeling/xgboost/xgbrf_classifier.py

@@ -4,18 +4,17 @@
 #
 import inspect
 import os
-import posixpath
-from typing import Iterable, Optional, Union, List, Any, Dict, Callable, Set
-from typing_extensions import TypeGuard
+from typing import Iterable, Optional, Union, List, Any, Dict, Set, Tuple
 from uuid import uuid4
 
 import cloudpickle as cp
-import pandas as pd
 import numpy as np
+import pandas as pd
 from numpy import typing as npt
 
 
 import numpy
+import sklearn
 import xgboost
 from sklearn.utils.metaestimators import available_if
 
@@ -23,12 +22,11 @@ from snowflake.ml.modeling.framework.base import BaseTransformer, _process_cols
 from snowflake.ml._internal import telemetry
 from snowflake.ml._internal.exceptions import error_codes, exceptions, modeling_error_messages
 from snowflake.ml._internal.env_utils import SNOWML_SPROC_ENV
-from snowflake.ml._internal.utils import pkg_version_utils, identifier
+from snowflake.ml._internal.utils import identifier
 from snowflake.snowpark import DataFrame, Session
 from snowflake.snowpark._internal.type_utils import convert_sp_to_sf_type
 from snowflake.ml.modeling._internal.model_trainer_builder import ModelTrainerBuilder
 from snowflake.ml.modeling._internal.transformer_protocols import (
-    ModelTransformHandlers,
     BatchInferenceKwargsTypedDict,
     ScoreKwargsTypedDict
 )
@@ -363,7 +361,7 @@ class XGBRFClassifier(BaseTransformer):
         self.set_sample_weight_col(sample_weight_col)
         self._use_external_memory_version = use_external_memory_version
         self._batch_size = batch_size        
-        deps: Set[str] = set([f'numpy=={np.__version__}', f'xgboost=={xgboost.__version__}', f'cloudpickle=={cp.__version__}'])
+        deps: Set[str] = set([f'numpy=={np.__version__}', f'scikit-learn=={sklearn.__version__}', f'xgboost=={xgboost.__version__}', f'cloudpickle=={cp.__version__}'])
         
         self._deps = list(deps)
         
@@ -699,12 +697,23 @@ class XGBRFClassifier(BaseTransformer):
             autogenerated=self._autogenerated,
             subproject=_SUBPROJECT,
         )
-        output_result, fitted_estimator = model_trainer.train_fit_predict(
-            drop_input_cols=self._drop_input_cols,
-            expected_output_cols_list=(
-                self.output_cols if self.output_cols else self._get_output_column_names(output_cols_prefix)
-            ),
+        expected_output_cols = (
+            self.output_cols if self.output_cols else self._get_output_column_names(output_cols_prefix)
         )
+        if isinstance(dataset, DataFrame):
+            expected_output_cols, example_output_pd_df = self._align_expected_output(
+                "fit_predict", dataset, expected_output_cols, output_cols_prefix
+            )
+            output_result, fitted_estimator = model_trainer.train_fit_predict(
+                drop_input_cols=self._drop_input_cols,
+                expected_output_cols_list=expected_output_cols,
+                example_output_pd_df=example_output_pd_df,
+            )
+        else:
+            output_result, fitted_estimator = model_trainer.train_fit_predict(
+                drop_input_cols=self._drop_input_cols,
+                expected_output_cols_list=expected_output_cols,
+            )
         self._sklearn_object = fitted_estimator
         self._is_fitted = True
         return output_result
@@ -783,12 +792,41 @@ class XGBRFClassifier(BaseTransformer):
 
         return rv
 
-    def _align_expected_output_names(
-        self, method: str, dataset: DataFrame, expected_output_cols_list: List[str], output_cols_prefix: str
-    ) -> List[str]:
+    def _align_expected_output(
+        self, method: str, dataset: DataFrame, expected_output_cols_list: List[str], output_cols_prefix: str,
+    ) -> Tuple[List[str], pd.DataFrame]:
+        """ Run 1 line of data with the desired method, and return one tuple that consists of the output column names 
+        and output dataframe with 1 line.
+        If the method is fit_predict, run 2 lines of data. 
+        """
         # in case the inferred output column names dimension is different 
         # we use one line of snowpark dataframe and put it into sklearn estimator using pandas
-        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # For fit_predict method, a minimum of 2 is required by MinCovDet, BayesianGaussianMixture
+        # so change the minimum of number of rows to 2
+        num_examples = 2
+        statement_params = telemetry.get_function_usage_statement_params(
+            project=_PROJECT,
+            subproject=_SUBPROJECT,
+            function_name=telemetry.get_statement_params_full_func_name(
+                inspect.currentframe(), XGBRFClassifier.__class__.__name__
+            ),
+            api_calls=[Session.call],
+            custom_tags={"autogen": True} if self._autogenerated else None,
+        )
+        if output_cols_prefix == "fit_predict_":
+            if hasattr(self._sklearn_object, "n_clusters"):
+                # cluster classes such as BisectingKMeansTest requires # of examples >= n_clusters
+                num_examples = self._sklearn_object.n_clusters
+            elif hasattr(self._sklearn_object, "min_samples"):
+                # OPTICS default min_samples 5, which requires at least 5 lines of data
+                num_examples = self._sklearn_object.min_samples
+            elif hasattr(self._sklearn_object, "n_neighbors") and hasattr(self._sklearn_object, "n_samples"):
+                # LocalOutlierFactor expects n_neighbors <= n_samples
+                num_examples = self._sklearn_object.n_neighbors
+            sample_pd_df = dataset.select(self.input_cols).limit(num_examples).to_pandas(statement_params=statement_params)
+        else:
+            sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas(statement_params=statement_params)
 
         # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
         # seen during the fit.
@@ -800,12 +838,14 @@ class XGBRFClassifier(BaseTransformer):
         output_df_columns_set: Set[str] = set(output_df_columns) - set(dataset.columns)
         if self.sample_weight_col:
             output_df_columns_set -= set(self.sample_weight_col)
+        
         # if the dimension of inferred output column names is correct; use it
         if len(expected_output_cols_list) == len(output_df_columns_set):
-            return expected_output_cols_list
+            return expected_output_cols_list, output_df_pd
         # otherwise, use the sklearn estimator's output
         else:
-            return sorted(list(output_df_columns_set), key=lambda x: output_df_columns.index(x))
+            expected_output_cols_list = sorted(list(output_df_columns_set), key=lambda x: output_df_columns.index(x))
+            return expected_output_cols_list, output_df_pd[expected_output_cols_list]
 
     @available_if(original_estimator_has_callable("predict_proba"))  # type: ignore[misc]
     @telemetry.send_api_usage_telemetry(
@@ -853,7 +893,7 @@ class XGBRFClassifier(BaseTransformer):
                 drop_input_cols=self._drop_input_cols,
                 expected_output_cols_type="float",
             )
-            expected_output_cols = self._align_expected_output_names(
+            expected_output_cols, _ = self._align_expected_output(
                 inference_method, dataset, expected_output_cols, output_cols_prefix
             )
 
@@ -921,7 +961,7 @@ class XGBRFClassifier(BaseTransformer):
                 drop_input_cols=self._drop_input_cols,
                 expected_output_cols_type="float",
             )
-            expected_output_cols = self._align_expected_output_names(
+            expected_output_cols, _ = self._align_expected_output(
                 inference_method, dataset, expected_output_cols, output_cols_prefix
             )
         elif isinstance(dataset, pd.DataFrame):
@@ -984,7 +1024,7 @@ class XGBRFClassifier(BaseTransformer):
                 drop_input_cols=self._drop_input_cols,
                 expected_output_cols_type="float",
             )
-            expected_output_cols = self._align_expected_output_names(
+            expected_output_cols, _ = self._align_expected_output(
                 inference_method, dataset, expected_output_cols, output_cols_prefix
             )
 
@@ -1049,7 +1089,7 @@ class XGBRFClassifier(BaseTransformer):
                 drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type="float",
             )
-            expected_output_cols = self._align_expected_output_names(
+            expected_output_cols, _ = self._align_expected_output(
                 inference_method, dataset, expected_output_cols, output_cols_prefix
             )
 
@@ -1114,7 +1154,7 @@ class XGBRFClassifier(BaseTransformer):
             transform_kwargs = dict(
                 session=dataset._session,
                 dependencies=self._deps,
-                score_sproc_imports=['xgboost'],
+                score_sproc_imports=['xgboost', 'sklearn'],
             )
         elif isinstance(dataset, pd.DataFrame):
             # pandas_handler.score() does not require any extra kwargs.

snowflake/ml/modeling/xgboost/xgbrf_regressor.py

@@ -4,18 +4,17 @@
 #
 import inspect
 import os
-import posixpath
-from typing import Iterable, Optional, Union, List, Any, Dict, Callable, Set
-from typing_extensions import TypeGuard
+from typing import Iterable, Optional, Union, List, Any, Dict, Set, Tuple
 from uuid import uuid4
 
 import cloudpickle as cp
-import pandas as pd
 import numpy as np
+import pandas as pd
 from numpy import typing as npt
 
 
 import numpy
+import sklearn
 import xgboost
 from sklearn.utils.metaestimators import available_if
 
@@ -23,12 +22,11 @@ from snowflake.ml.modeling.framework.base import BaseTransformer, _process_cols
 from snowflake.ml._internal import telemetry
 from snowflake.ml._internal.exceptions import error_codes, exceptions, modeling_error_messages
 from snowflake.ml._internal.env_utils import SNOWML_SPROC_ENV
-from snowflake.ml._internal.utils import pkg_version_utils, identifier
+from snowflake.ml._internal.utils import identifier
 from snowflake.snowpark import DataFrame, Session
 from snowflake.snowpark._internal.type_utils import convert_sp_to_sf_type
 from snowflake.ml.modeling._internal.model_trainer_builder import ModelTrainerBuilder
 from snowflake.ml.modeling._internal.transformer_protocols import (
-    ModelTransformHandlers,
     BatchInferenceKwargsTypedDict,
     ScoreKwargsTypedDict
 )
@@ -363,7 +361,7 @@ class XGBRFRegressor(BaseTransformer):
         self.set_sample_weight_col(sample_weight_col)
         self._use_external_memory_version = use_external_memory_version
         self._batch_size = batch_size        
-        deps: Set[str] = set([f'numpy=={np.__version__}', f'xgboost=={xgboost.__version__}', f'cloudpickle=={cp.__version__}'])
+        deps: Set[str] = set([f'numpy=={np.__version__}', f'scikit-learn=={sklearn.__version__}', f'xgboost=={xgboost.__version__}', f'cloudpickle=={cp.__version__}'])
         
         self._deps = list(deps)
         
@@ -699,12 +697,23 @@ class XGBRFRegressor(BaseTransformer):
             autogenerated=self._autogenerated,
             subproject=_SUBPROJECT,
         )
-        output_result, fitted_estimator = model_trainer.train_fit_predict(
-            drop_input_cols=self._drop_input_cols,
-            expected_output_cols_list=(
-                self.output_cols if self.output_cols else self._get_output_column_names(output_cols_prefix)
-            ),
+        expected_output_cols = (
+            self.output_cols if self.output_cols else self._get_output_column_names(output_cols_prefix)
         )
+        if isinstance(dataset, DataFrame):
+            expected_output_cols, example_output_pd_df = self._align_expected_output(
+                "fit_predict", dataset, expected_output_cols, output_cols_prefix
+            )
+            output_result, fitted_estimator = model_trainer.train_fit_predict(
+                drop_input_cols=self._drop_input_cols,
+                expected_output_cols_list=expected_output_cols,
+                example_output_pd_df=example_output_pd_df,
+            )
+        else:
+            output_result, fitted_estimator = model_trainer.train_fit_predict(
+                drop_input_cols=self._drop_input_cols,
+                expected_output_cols_list=expected_output_cols,
+            )
         self._sklearn_object = fitted_estimator
         self._is_fitted = True
         return output_result
@@ -783,12 +792,41 @@ class XGBRFRegressor(BaseTransformer):
 
         return rv
 
-    def _align_expected_output_names(
-        self, method: str, dataset: DataFrame, expected_output_cols_list: List[str], output_cols_prefix: str
-    ) -> List[str]:
+    def _align_expected_output(
+        self, method: str, dataset: DataFrame, expected_output_cols_list: List[str], output_cols_prefix: str,
+    ) -> Tuple[List[str], pd.DataFrame]:
+        """ Run 1 line of data with the desired method, and return one tuple that consists of the output column names 
+        and output dataframe with 1 line.
+        If the method is fit_predict, run 2 lines of data. 
+        """
         # in case the inferred output column names dimension is different 
         # we use one line of snowpark dataframe and put it into sklearn estimator using pandas
-        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # For fit_predict method, a minimum of 2 is required by MinCovDet, BayesianGaussianMixture
+        # so change the minimum of number of rows to 2
+        num_examples = 2
+        statement_params = telemetry.get_function_usage_statement_params(
+            project=_PROJECT,
+            subproject=_SUBPROJECT,
+            function_name=telemetry.get_statement_params_full_func_name(
+                inspect.currentframe(), XGBRFRegressor.__class__.__name__
+            ),
+            api_calls=[Session.call],
+            custom_tags={"autogen": True} if self._autogenerated else None,
+        )
+        if output_cols_prefix == "fit_predict_":
+            if hasattr(self._sklearn_object, "n_clusters"):
+                # cluster classes such as BisectingKMeansTest requires # of examples >= n_clusters
+                num_examples = self._sklearn_object.n_clusters
+            elif hasattr(self._sklearn_object, "min_samples"):
+                # OPTICS default min_samples 5, which requires at least 5 lines of data
+                num_examples = self._sklearn_object.min_samples
+            elif hasattr(self._sklearn_object, "n_neighbors") and hasattr(self._sklearn_object, "n_samples"):
+                # LocalOutlierFactor expects n_neighbors <= n_samples
+                num_examples = self._sklearn_object.n_neighbors
+            sample_pd_df = dataset.select(self.input_cols).limit(num_examples).to_pandas(statement_params=statement_params)
+        else:
+            sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas(statement_params=statement_params)
 
         # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
         # seen during the fit.
@@ -800,12 +838,14 @@ class XGBRFRegressor(BaseTransformer):
         output_df_columns_set: Set[str] = set(output_df_columns) - set(dataset.columns)
         if self.sample_weight_col:
             output_df_columns_set -= set(self.sample_weight_col)
+        
         # if the dimension of inferred output column names is correct; use it
         if len(expected_output_cols_list) == len(output_df_columns_set):
-            return expected_output_cols_list
+            return expected_output_cols_list, output_df_pd
         # otherwise, use the sklearn estimator's output
         else:
-            return sorted(list(output_df_columns_set), key=lambda x: output_df_columns.index(x))
+            expected_output_cols_list = sorted(list(output_df_columns_set), key=lambda x: output_df_columns.index(x))
+            return expected_output_cols_list, output_df_pd[expected_output_cols_list]
 
     @available_if(original_estimator_has_callable("predict_proba"))  # type: ignore[misc]
     @telemetry.send_api_usage_telemetry(
@@ -851,7 +891,7 @@ class XGBRFRegressor(BaseTransformer):
                 drop_input_cols=self._drop_input_cols,
                 expected_output_cols_type="float",
             )
-            expected_output_cols = self._align_expected_output_names(
+            expected_output_cols, _ = self._align_expected_output(
                 inference_method, dataset, expected_output_cols, output_cols_prefix
             )
 
@@ -917,7 +957,7 @@ class XGBRFRegressor(BaseTransformer):
                 drop_input_cols=self._drop_input_cols,
                 expected_output_cols_type="float",
             )
-            expected_output_cols = self._align_expected_output_names(
+            expected_output_cols, _ = self._align_expected_output(
                 inference_method, dataset, expected_output_cols, output_cols_prefix
             )
         elif isinstance(dataset, pd.DataFrame):
@@ -980,7 +1020,7 @@ class XGBRFRegressor(BaseTransformer):
                 drop_input_cols=self._drop_input_cols,
                 expected_output_cols_type="float",
             )
-            expected_output_cols = self._align_expected_output_names(
+            expected_output_cols, _ = self._align_expected_output(
                 inference_method, dataset, expected_output_cols, output_cols_prefix
             )
 
@@ -1045,7 +1085,7 @@ class XGBRFRegressor(BaseTransformer):
                 drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type="float",
             )
-            expected_output_cols = self._align_expected_output_names(
+            expected_output_cols, _ = self._align_expected_output(
                 inference_method, dataset, expected_output_cols, output_cols_prefix
             )
 
@@ -1110,7 +1150,7 @@ class XGBRFRegressor(BaseTransformer):
             transform_kwargs = dict(
                 session=dataset._session,
                 dependencies=self._deps,
-                score_sproc_imports=['xgboost'],
+                score_sproc_imports=['xgboost', 'sklearn'],
             )
         elif isinstance(dataset, pd.DataFrame):
             # pandas_handler.score() does not require any extra kwargs.

snowflake/ml/registry/_manager/model_manager.py

@@ -50,6 +50,7 @@ class ModelManager:
         sample_input_data: Optional[model_types.SupportedDataType] = None,
         code_paths: Optional[List[str]] = None,
         ext_modules: Optional[List[ModuleType]] = None,
+        model_objective: model_types.ModelObjective = model_types.ModelObjective.UNKNOWN,
         options: Optional[model_types.ModelSaveOption] = None,
         statement_params: Optional[Dict[str, Any]] = None,
     ) -> model_version_impl.ModelVersion:
@@ -89,6 +90,7 @@ class ModelManager:
             sample_input_data=sample_input_data,
             code_paths=code_paths,
             ext_modules=ext_modules,
+            model_objective=model_objective,
             options=options,
             statement_params=statement_params,
         )
@@ -108,6 +110,7 @@ class ModelManager:
         sample_input_data: Optional[model_types.SupportedDataType] = None,
         code_paths: Optional[List[str]] = None,
         ext_modules: Optional[List[ModuleType]] = None,
+        model_objective: model_types.ModelObjective = model_types.ModelObjective.UNKNOWN,
         options: Optional[model_types.ModelSaveOption] = None,
         statement_params: Optional[Dict[str, Any]] = None,
     ) -> model_version_impl.ModelVersion:
@@ -156,6 +159,7 @@ class ModelManager:
             code_paths=code_paths,
             ext_modules=ext_modules,
             options=options,
+            model_objective=model_objective,
         )
         statement_params = telemetry.add_statement_params_custom_tags(
             statement_params, model_metadata.telemetry_metadata()

snowflake/ml/registry/model_registry.py

@@ -576,7 +576,7 @@ fully integrated into the new registry.
         raw_stage_path = uri.get_snowflake_stage_path_from_uri(model_uri)
         if not raw_stage_path:
             return None
-        (db, schema, stage, _) = identifier.parse_schema_level_object_identifier(raw_stage_path)
+        (db, schema, stage, _) = identifier.parse_snowflake_stage_path(raw_stage_path)
         return identifier.get_schema_level_object_identifier(db, schema, stage)
 
     def _list_selected_models(

snowflake/ml/registry/registry.py

@@ -244,8 +244,7 @@ class Registry:
             warnings.warn(
                 "Models logged specifying `pip_requirements` can not be executed "
                 "in Snowflake Warehouse where all dependencies are required to be retrieved "
-                "from Snowflake Anaconda Channel. Specify model save option `include_pip_dependencies`"
-                "to log model with pip dependencies.",
+                "from Snowflake Anaconda Channel.",
                 category=UserWarning,
                 stacklevel=1,
             )

snowflake/ml/version.py

@@ -1 +1 @@
-VERSION="1.6.1"
+VERSION="1.6.2"

{snowflake_ml_python-1.6.1.dist-info → snowflake_ml_python-1.6.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: snowflake-ml-python
-Version: 1.6.1
+Version: 1.6.2
 Summary: The machine learning client library that is used for interacting with Snowflake to build machine learning solutions.
 Author-email: "Snowflake, Inc" <support@snowflake.com>
 License: 
@@ -253,7 +253,7 @@ Requires-Dist: snowflake-connector-python[pandas] <4,>=3.5.0
 Requires-Dist: snowflake-snowpark-python <2,>=1.17.0
 Requires-Dist: sqlparse <1,>=0.4
 Requires-Dist: typing-extensions <5,>=4.1.0
-Requires-Dist: xgboost <2,>=1.7.3
+Requires-Dist: xgboost <2.1,>=1.7.3
 Provides-Extra: all
 Requires-Dist: catboost <2,>=1.2.0 ; extra == 'all'
 Requires-Dist: lightgbm <5,>=3.3.5 ; extra == 'all'
@@ -373,7 +373,27 @@ be compatibility issues. Server-side functionality that `snowflake-ml-python` de
 
 # Release History
 
-## 1.6.1 (TBD)
+## 1.6.2 (TBD)
+
+### Bug Fixes
+
+- Modeling: Support XGBoost version that is larger than 2.
+
+- Data: Fix multiple epoch iteration over `DataConnector.to_torch_datapipe()` DataPipes.
+- Generic: Fix a bug that when an invalid name is provided to argument where fully qualified name is expected, it will
+  be parsed wrongly. Now it raises an exception correctly.
+- Model Explainability: Handle explanations for multiclass XGBoost classification models
+- Model Explainability: Workarounds and better error handling for XGB>2.1.0 not working with SHAP==0.42.1
+
+### New Features
+
+- Data: Add top-level exports for `DataConnector` and `DataSource` to `snowflake.ml.data`.
+- Data: Add native batching support via `batch_size` and `drop_last_batch` arguments to `DataConnector.to_torch_dataset()`
+- Feature Store: update_feature_view() supports taking feature view object as argument.
+
+### Behavior Changes
+
+## 1.6.1 (2024-08-12)
 
 ### Bug Fixes
 
@@ -390,7 +410,6 @@ be compatibility issues. Server-side functionality that `snowflake-ml-python` de
 ### New Features
 
 - Enable `set_params` to set the parameters of the underlying sklearn estimator, if the snowflake-ml model has been fit.
-- Data: Add top-level exports for `DataConnector` and `DataSource` to `snowflake.ml.data`.
 - Data: Add `snowflake.ml.data.ingestor_utils` module with utility functions helpful for `DataIngestor` implementations.
 - Data: Add new `to_torch_dataset()` connector to `DataConnector` to replace deprecated DataPipe.
 - Registry: Option to `enable_explainability` set to True by default for XGBoost, LightGBM and CatBoost as PuPr feature.