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

snowflake/ml/model/_packager/model_handlers/model_objective_utils.py

@@ -0,0 +1,116 @@
+import json
+from dataclasses import dataclass
+from typing import TYPE_CHECKING, Any, Union
+
+from snowflake.ml.model import model_signature, type_hints
+from snowflake.ml.model._packager.model_handlers import _utils as handlers_utils
+
+if TYPE_CHECKING:
+    import lightgbm
+    import xgboost
+
+
+@dataclass
+class ModelObjectiveAndOutputType:
+    objective: type_hints.ModelObjective
+    output_type: model_signature.DataType
+
+
+def get_model_objective_lightgbm(model: Union["lightgbm.Booster", "lightgbm.LGBMModel"]) -> type_hints.ModelObjective:
+
+    import lightgbm
+
+    _BINARY_CLASSIFICATION_OBJECTIVES = ["binary"]
+    _MULTI_CLASSIFICATION_OBJECTIVES = ["multiclass", "multiclassova"]
+    _RANKING_OBJECTIVES = ["lambdarank", "rank_xendcg"]
+    _REGRESSION_OBJECTIVES = [
+        "regression",
+        "regression_l1",
+        "huber",
+        "fair",
+        "poisson",
+        "quantile",
+        "tweedie",
+        "mape",
+        "gamma",
+    ]
+
+    # does not account for cross-entropy and custom
+    if isinstance(model, lightgbm.LGBMClassifier):
+        num_classes = handlers_utils.get_num_classes_if_exists(model)
+        if num_classes == 2:
+            return type_hints.ModelObjective.BINARY_CLASSIFICATION
+        return type_hints.ModelObjective.MULTI_CLASSIFICATION
+    if isinstance(model, lightgbm.LGBMRanker):
+        return type_hints.ModelObjective.RANKING
+    if isinstance(model, lightgbm.LGBMRegressor):
+        return type_hints.ModelObjective.REGRESSION
+    model_objective = model.params["objective"]
+    if model_objective in _BINARY_CLASSIFICATION_OBJECTIVES:
+        return type_hints.ModelObjective.BINARY_CLASSIFICATION
+    if model_objective in _MULTI_CLASSIFICATION_OBJECTIVES:
+        return type_hints.ModelObjective.MULTI_CLASSIFICATION
+    if model_objective in _RANKING_OBJECTIVES:
+        return type_hints.ModelObjective.RANKING
+    if model_objective in _REGRESSION_OBJECTIVES:
+        return type_hints.ModelObjective.REGRESSION
+    return type_hints.ModelObjective.UNKNOWN
+
+
+def get_model_objective_xgb(model: Union["xgboost.Booster", "xgboost.XGBModel"]) -> type_hints.ModelObjective:
+
+    import xgboost
+
+    _BINARY_CLASSIFICATION_OBJECTIVE_PREFIX = ["binary:"]
+    _MULTI_CLASSIFICATION_OBJECTIVE_PREFIX = ["multi:"]
+    _RANKING_OBJECTIVE_PREFIX = ["rank:"]
+    _REGRESSION_OBJECTIVE_PREFIX = ["reg:"]
+
+    model_objective = ""
+    if isinstance(model, xgboost.Booster):
+        model_params = json.loads(model.save_config())
+        model_objective = model_params.get("learner", {}).get("objective", "")
+    else:
+        if hasattr(model, "get_params"):
+            model_objective = model.get_params().get("objective", "")
+
+    if isinstance(model_objective, dict):
+        model_objective = model_objective.get("name", "")
+    for classification_objective in _BINARY_CLASSIFICATION_OBJECTIVE_PREFIX:
+        if classification_objective in model_objective:
+            return type_hints.ModelObjective.BINARY_CLASSIFICATION
+    for classification_objective in _MULTI_CLASSIFICATION_OBJECTIVE_PREFIX:
+        if classification_objective in model_objective:
+            return type_hints.ModelObjective.MULTI_CLASSIFICATION
+    for ranking_objective in _RANKING_OBJECTIVE_PREFIX:
+        if ranking_objective in model_objective:
+            return type_hints.ModelObjective.RANKING
+    for regression_objective in _REGRESSION_OBJECTIVE_PREFIX:
+        if regression_objective in model_objective:
+            return type_hints.ModelObjective.REGRESSION
+    return type_hints.ModelObjective.UNKNOWN
+
+
+def get_model_objective_and_output_type(model: Any) -> ModelObjectiveAndOutputType:
+    import xgboost
+
+    if isinstance(model, xgboost.Booster) or isinstance(model, xgboost.XGBModel):
+        model_objective = get_model_objective_xgb(model)
+        output_type = model_signature.DataType.DOUBLE
+        if model_objective == type_hints.ModelObjective.MULTI_CLASSIFICATION:
+            output_type = model_signature.DataType.STRING
+        return ModelObjectiveAndOutputType(objective=model_objective, output_type=output_type)
+
+    import lightgbm
+
+    if isinstance(model, lightgbm.Booster) or isinstance(model, lightgbm.LGBMModel):
+        model_objective = get_model_objective_lightgbm(model)
+        output_type = model_signature.DataType.DOUBLE
+        if model_objective in [
+            type_hints.ModelObjective.BINARY_CLASSIFICATION,
+            type_hints.ModelObjective.MULTI_CLASSIFICATION,
+        ]:
+            output_type = model_signature.DataType.STRING
+        return ModelObjectiveAndOutputType(objective=model_objective, output_type=output_type)
+
+    raise ValueError(f"Model type {type(model)} is not supported")

snowflake/ml/model/_packager/model_handlers/sklearn.py

@@ -45,23 +45,23 @@ class SKLModelHandler(_base.BaseModelHandler[Union["sklearn.base.BaseEstimator",
     @classmethod
     def get_model_objective(
         cls, model: Union["sklearn.base.BaseEstimator", "sklearn.pipeline.Pipeline"]
-    ) -> model_meta_schema.ModelObjective:
+    ) -> model_types.ModelObjective:
         import sklearn.pipeline
         from sklearn.base import is_classifier, is_regressor
 
         if isinstance(model, sklearn.pipeline.Pipeline):
-            return model_meta_schema.ModelObjective.UNKNOWN
+            return model_types.ModelObjective.UNKNOWN
         if is_regressor(model):
-            return model_meta_schema.ModelObjective.REGRESSION
+            return model_types.ModelObjective.REGRESSION
         if is_classifier(model):
             classes_list = getattr(model, "classes_", [])
             num_classes = getattr(model, "n_classes_", None) or len(classes_list)
             if isinstance(num_classes, int):
                 if num_classes > 2:
-                    return model_meta_schema.ModelObjective.MULTI_CLASSIFICATION
-                return model_meta_schema.ModelObjective.BINARY_CLASSIFICATION
-            return model_meta_schema.ModelObjective.UNKNOWN
-        return model_meta_schema.ModelObjective.UNKNOWN
+                    return model_types.ModelObjective.MULTI_CLASSIFICATION
+                return model_types.ModelObjective.BINARY_CLASSIFICATION
+            return model_types.ModelObjective.UNKNOWN
+        return model_types.ModelObjective.UNKNOWN
 
     @classmethod
     def can_handle(
@@ -95,6 +95,18 @@ class SKLModelHandler(_base.BaseModelHandler[Union["sklearn.base.BaseEstimator",
 
         return cast(Union["sklearn.base.BaseEstimator", "sklearn.pipeline.Pipeline"], model)
 
+    @staticmethod
+    def get_explainability_supported_background(
+        sample_input_data: Optional[model_types.SupportedDataType] = None,
+    ) -> Optional[pd.DataFrame]:
+        if isinstance(sample_input_data, pd.DataFrame) or isinstance(sample_input_data, sp_df.DataFrame):
+            return (
+                sample_input_data
+                if isinstance(sample_input_data, pd.DataFrame)
+                else snowpark_handler.SnowparkDataFrameHandler.convert_to_df(sample_input_data)
+            )
+        return None
+
     @classmethod
     def save_model(
         cls,
@@ -106,32 +118,30 @@ class SKLModelHandler(_base.BaseModelHandler[Union["sklearn.base.BaseEstimator",
         is_sub_model: Optional[bool] = False,
         **kwargs: Unpack[model_types.SKLModelSaveOptions],
     ) -> None:
-        enable_explainability = kwargs.get("enable_explainability", False)
+        # setting None by default to distinguish if users did not set it
+        enable_explainability = kwargs.get("enable_explainability", None)
 
         import sklearn.base
         import sklearn.pipeline
 
         assert isinstance(model, sklearn.base.BaseEstimator) or isinstance(model, sklearn.pipeline.Pipeline)
 
-        enable_explainability = kwargs.get("enable_explainability", False)
+        background_data = cls.get_explainability_supported_background(sample_input_data)
+
+        # if users did not ask then we enable if we have background data
+        if enable_explainability is None and background_data is not None:
+            enable_explainability = True
         if enable_explainability:
-            # TODO: Currently limited to pandas df, need to extend to other types.
-            if sample_input_data is None or not (
-                isinstance(sample_input_data, pd.DataFrame) or isinstance(sample_input_data, sp_df.DataFrame)
-            ):
+            # if users set it explicitly but no background data then error out
+            if background_data is None:
                 raise ValueError(
                     "Sample input data is required to enable explainability. Currently we only support this for "
                     + "`pandas.DataFrame` and `snowflake.snowpark.dataframe.DataFrame`."
                 )
-            sample_input_data_pandas = (
-                sample_input_data
-                if isinstance(sample_input_data, pd.DataFrame)
-                else snowpark_handler.SnowparkDataFrameHandler.convert_to_df(sample_input_data)
-            )
             data_blob_path = os.path.join(model_blobs_dir_path, cls.EXPLAIN_ARTIFACTS_DIR)
             os.makedirs(data_blob_path, exist_ok=True)
             with open(os.path.join(data_blob_path, name + cls.BG_DATA_FILE_SUFFIX), "wb") as f:
-                sample_input_data_pandas.to_parquet(f)
+                background_data.to_parquet(f)
 
         if not is_sub_model:
             target_methods = handlers_utils.get_target_methods(
@@ -159,9 +169,13 @@ class SKLModelHandler(_base.BaseModelHandler[Union["sklearn.base.BaseEstimator",
                 get_prediction_fn=get_prediction,
             )
 
+            model_objective = cls.get_model_objective(model)
+            model_meta.model_objective = model_objective
+
             if enable_explainability:
                 output_type = model_signature.DataType.DOUBLE
-                if cls.get_model_objective(model) == model_meta_schema.ModelObjective.MULTI_CLASSIFICATION:
+
+                if model_objective == model_types.ModelObjective.MULTI_CLASSIFICATION:
                     output_type = model_signature.DataType.STRING
                 model_meta = handlers_utils.add_explain_method_signature(
                     model_meta=model_meta,
@@ -184,10 +198,8 @@ class SKLModelHandler(_base.BaseModelHandler[Union["sklearn.base.BaseEstimator",
         model_meta.min_snowpark_ml_version = cls._MIN_SNOWPARK_ML_VERSION
 
         if enable_explainability:
-            model_meta.env.include_if_absent(
-                [model_env.ModelDependency(requirement="shap", pip_name="shap")],
-                check_local_version=True,
-            )
+            model_meta.env.include_if_absent([model_env.ModelDependency(requirement="shap", pip_name="shap")])
+            model_meta.explain_algorithm = model_meta_schema.ModelExplainAlgorithm.SHAP
 
         model_meta.env.include_if_absent(
             [model_env.ModelDependency(requirement="scikit-learn", pip_name="scikit-learn")], check_local_version=True

snowflake/ml/model/_packager/model_handlers/snowmlmodel.py

@@ -1,20 +1,27 @@
 import os
 import warnings
-from typing import TYPE_CHECKING, Callable, Dict, Optional, Type, cast, final
+from typing import TYPE_CHECKING, Any, Callable, Dict, Optional, Type, cast, final
 
 import cloudpickle
 import numpy as np
 import pandas as pd
+from packaging import version
 from typing_extensions import TypeGuard, Unpack
 
 from snowflake.ml._internal import type_utils
+from snowflake.ml._internal.exceptions import exceptions
 from snowflake.ml.model import custom_model, model_signature, type_hints as model_types
 from snowflake.ml.model._packager.model_env import model_env
-from snowflake.ml.model._packager.model_handlers import _base
+from snowflake.ml.model._packager.model_handlers import (
+    _base,
+    _utils as handlers_utils,
+    model_objective_utils,
+)
 from snowflake.ml.model._packager.model_handlers_migrator import base_migrator
 from snowflake.ml.model._packager.model_meta import (
     model_blob_meta,
     model_meta as model_meta_api,
+    model_meta_schema,
 )
 from snowflake.ml.model._signatures import numpy_handler, utils as model_signature_utils
 
@@ -62,6 +69,53 @@ class SnowMLModelHandler(_base.BaseModelHandler["BaseEstimator"]):
 
         return cast("BaseEstimator", model)
 
+    @classmethod
+    def _get_local_version_package(cls, pkg_name: str) -> Optional[version.Version]:
+        import importlib_metadata
+        from packaging import version
+
+        local_version = None
+
+        try:
+            local_dist = importlib_metadata.distribution(pkg_name)  # type: ignore[no-untyped-call]
+            local_version = version.parse(local_dist.version)
+        except importlib_metadata.PackageNotFoundError:
+            pass
+
+        return local_version
+
+    @classmethod
+    def _can_support_xgb(cls, enable_explainability: Optional[bool]) -> bool:
+
+        local_xgb_version = cls._get_local_version_package("xgboost")
+
+        if local_xgb_version and local_xgb_version >= version.parse("2.1.0"):
+            if enable_explainability:
+                warnings.warn(
+                    f"This version of xgboost {local_xgb_version} does not work with shap 0.42.1."
+                    + "If you want model explanations, lower the xgboost version to <2.1.0.",
+                    category=UserWarning,
+                    stacklevel=1,
+                )
+            return False
+        return True
+
+    @classmethod
+    def _get_supported_object_for_explainability(
+        cls, estimator: "BaseEstimator", enable_explainability: Optional[bool]
+    ) -> Any:
+        methods = ["to_xgboost", "to_lightgbm"]
+        for method_name in methods:
+            if hasattr(estimator, method_name):
+                try:
+                    result = getattr(estimator, method_name)()
+                    if method_name == "to_xgboost" and not cls._can_support_xgb(enable_explainability):
+                        return None
+                    return result
+                except exceptions.SnowflakeMLException:
+                    pass  # Do nothing and continue to the next method
+        return None
+
     @classmethod
     def save_model(
         cls,
@@ -73,9 +127,8 @@ class SnowMLModelHandler(_base.BaseModelHandler["BaseEstimator"]):
         is_sub_model: Optional[bool] = False,
         **kwargs: Unpack[model_types.SNOWModelSaveOptions],
     ) -> None:
-        enable_explainability = kwargs.get("enable_explainability", False)
-        if enable_explainability:
-            raise NotImplementedError("Explainability is not supported for Snowpark ML model.")
+
+        enable_explainability = kwargs.get("enable_explainability", None)
 
         from snowflake.ml.modeling.framework.base import BaseEstimator
 
@@ -105,6 +158,26 @@ class SnowMLModelHandler(_base.BaseModelHandler["BaseEstimator"]):
                         raise ValueError(f"Target method {method_name} does not exist in the model.")
                 model_meta.signatures = temp_model_signature_dict
 
+        if enable_explainability or enable_explainability is None:
+            python_base_obj = cls._get_supported_object_for_explainability(model, enable_explainability)
+            if python_base_obj is None:
+                if enable_explainability:  # if user set enable_explainability to True, throw error else silently skip
+                    raise ValueError("Explain only support for xgboost or lightgbm Snowpark ML models.")
+                # set None to False so we don't include shap in the environment
+                enable_explainability = False
+            else:
+                model_objective_and_output_type = model_objective_utils.get_model_objective_and_output_type(
+                    python_base_obj
+                )
+                model_meta.model_objective = model_objective_and_output_type.objective
+                model_meta = handlers_utils.add_explain_method_signature(
+                    model_meta=model_meta,
+                    explain_method="explain",
+                    target_method="predict",
+                    output_return_type=model_objective_and_output_type.output_type,
+                )
+                enable_explainability = True
+
         model_blob_path = os.path.join(model_blobs_dir_path, name)
         os.makedirs(model_blob_path, exist_ok=True)
         with open(os.path.join(model_blob_path, cls.MODEL_BLOB_FILE_OR_DIR), "wb") as f:
@@ -122,7 +195,29 @@ class SnowMLModelHandler(_base.BaseModelHandler["BaseEstimator"]):
         model_dependencies = model._get_dependencies()
         for dep in model_dependencies:
             pkg_name = dep.split("==")[0]
-            _include_if_absent_pkgs.append(model_env.ModelDependency(requirement=pkg_name, pip_name=pkg_name))
+            if pkg_name != "xgboost":
+                _include_if_absent_pkgs.append(model_env.ModelDependency(requirement=pkg_name, pip_name=pkg_name))
+                continue
+
+            local_xgb_version = cls._get_local_version_package("xgboost")
+            if local_xgb_version and local_xgb_version >= version.parse("2.0.0") and enable_explainability:
+                model_meta.env.include_if_absent(
+                    [
+                        model_env.ModelDependency(requirement="xgboost==2.0.*", pip_name="xgboost"),
+                    ],
+                    check_local_version=False,
+                )
+            else:
+                model_meta.env.include_if_absent(
+                    [
+                        model_env.ModelDependency(requirement="xgboost", pip_name="xgboost"),
+                    ],
+                    check_local_version=True,
+                )
+
+        if enable_explainability:
+            model_meta.env.include_if_absent([model_env.ModelDependency(requirement="shap", pip_name="shap")])
+            model_meta.explain_algorithm = model_meta_schema.ModelExplainAlgorithm.SHAP
         model_meta.env.include_if_absent(_include_if_absent_pkgs, check_local_version=True)
 
     @classmethod
@@ -177,6 +272,24 @@ class SnowMLModelHandler(_base.BaseModelHandler["BaseEstimator"]):
 
                     return model_signature_utils.rename_pandas_df(df, signature.outputs)
 
+                @custom_model.inference_api
+                def explain_fn(self: custom_model.CustomModel, X: pd.DataFrame) -> pd.DataFrame:
+                    import shap
+
+                    methods = ["to_xgboost", "to_lightgbm"]
+                    for method_name in methods:
+                        try:
+                            base_model = getattr(raw_model, method_name)()
+                            explainer = shap.TreeExplainer(base_model)
+                            df = pd.DataFrame(explainer(X).values)
+                            return model_signature_utils.rename_pandas_df(df, signature.outputs)
+                        except exceptions.SnowflakeMLException:
+                            pass  # Do nothing and continue to the next method
+                    raise ValueError("The model must be an xgboost or lightgbm estimator.")
+
+                if target_method == "explain":
+                    return explain_fn
+
                 return fn
 
             type_method_dict = {}

snowflake/ml/model/_packager/model_handlers/torchscript.py

@@ -111,7 +111,7 @@ class TorchScriptHandler(_base.BaseModelHandler["torch.jit.ScriptModule"]):  # t
         model_blob_path = os.path.join(model_blobs_dir_path, name)
         os.makedirs(model_blob_path, exist_ok=True)
         with open(os.path.join(model_blob_path, cls.MODEL_BLOB_FILE_OR_DIR), "wb") as f:
-            torch.jit.save(model, f)  # type:ignore[attr-defined]
+            torch.jit.save(model, f)  # type:ignore[no-untyped-call, attr-defined]
         base_meta = model_blob_meta.ModelBlobMeta(
             name=name,
             model_type=cls.HANDLER_TYPE,
@@ -141,7 +141,7 @@ class TorchScriptHandler(_base.BaseModelHandler["torch.jit.ScriptModule"]):  # t
         model_blob_metadata = model_blobs_metadata[name]
         model_blob_filename = model_blob_metadata.path
         with open(os.path.join(model_blob_path, model_blob_filename), "rb") as f:
-            m = torch.jit.load(  # type:ignore[attr-defined]
+            m = torch.jit.load(  # type:ignore[no-untyped-call, attr-defined]
                 f, map_location="cuda" if kwargs.get("use_gpu", False) else "cpu"
             )
         assert isinstance(m, torch.jit.ScriptModule)  # type:ignore[attr-defined]

snowflake/ml/model/_packager/model_handlers/xgboost.py

@@ -1,6 +1,6 @@
 # mypy: disable-error-code="import"
-import json
 import os
+import warnings
 from typing import (
     TYPE_CHECKING,
     Any,
@@ -13,14 +13,20 @@ from typing import (
     final,
 )
 
+import importlib_metadata
 import numpy as np
 import pandas as pd
+from packaging import version
 from typing_extensions import TypeGuard, Unpack
 
 from snowflake.ml._internal import type_utils
 from snowflake.ml.model import custom_model, model_signature, type_hints as model_types
 from snowflake.ml.model._packager.model_env import model_env
-from snowflake.ml.model._packager.model_handlers import _base, _utils as handlers_utils
+from snowflake.ml.model._packager.model_handlers import (
+    _base,
+    _utils as handlers_utils,
+    model_objective_utils,
+)
 from snowflake.ml.model._packager.model_handlers_migrator import base_migrator
 from snowflake.ml.model._packager.model_meta import (
     model_blob_meta,
@@ -47,41 +53,6 @@ class XGBModelHandler(_base.BaseModelHandler[Union["xgboost.Booster", "xgboost.X
 
     MODEL_BLOB_FILE_OR_DIR = "model.ubj"
     DEFAULT_TARGET_METHODS = ["predict", "predict_proba"]
-    _BINARY_CLASSIFICATION_OBJECTIVE_PREFIX = ["binary:"]
-    _MULTI_CLASSIFICATION_OBJECTIVE_PREFIX = ["multi:"]
-    _RANKING_OBJECTIVE_PREFIX = ["rank:"]
-    _REGRESSION_OBJECTIVE_PREFIX = ["reg:"]
-
-    @classmethod
-    def get_model_objective(
-        cls, model: Union["xgboost.Booster", "xgboost.XGBModel"]
-    ) -> model_meta_schema.ModelObjective:
-        import xgboost
-
-        if isinstance(model, xgboost.XGBClassifier) or isinstance(model, xgboost.XGBRFClassifier):
-            num_classes = handlers_utils.get_num_classes_if_exists(model)
-            if num_classes == 2:
-                return model_meta_schema.ModelObjective.BINARY_CLASSIFICATION
-            return model_meta_schema.ModelObjective.MULTI_CLASSIFICATION
-        if isinstance(model, xgboost.XGBRegressor) or isinstance(model, xgboost.XGBRFRegressor):
-            return model_meta_schema.ModelObjective.REGRESSION
-        if isinstance(model, xgboost.XGBRanker):
-            return model_meta_schema.ModelObjective.RANKING
-        model_params = json.loads(model.save_config())
-        model_objective = model_params["learner"]["objective"]
-        for classification_objective in cls._BINARY_CLASSIFICATION_OBJECTIVE_PREFIX:
-            if classification_objective in model_objective:
-                return model_meta_schema.ModelObjective.BINARY_CLASSIFICATION
-        for classification_objective in cls._MULTI_CLASSIFICATION_OBJECTIVE_PREFIX:
-            if classification_objective in model_objective:
-                return model_meta_schema.ModelObjective.MULTI_CLASSIFICATION
-        for ranking_objective in cls._RANKING_OBJECTIVE_PREFIX:
-            if ranking_objective in model_objective:
-                return model_meta_schema.ModelObjective.RANKING
-        for regression_objective in cls._REGRESSION_OBJECTIVE_PREFIX:
-            if regression_objective in model_objective:
-                return model_meta_schema.ModelObjective.REGRESSION
-        return model_meta_schema.ModelObjective.UNKNOWN
 
     @classmethod
     def can_handle(
@@ -116,10 +87,29 @@ class XGBModelHandler(_base.BaseModelHandler[Union["xgboost.Booster", "xgboost.X
         is_sub_model: Optional[bool] = False,
         **kwargs: Unpack[model_types.XGBModelSaveOptions],
     ) -> None:
+        enable_explainability = kwargs.get("enable_explainability", True)
+
         import xgboost
 
         assert isinstance(model, xgboost.Booster) or isinstance(model, xgboost.XGBModel)
 
+        local_xgb_version = None
+
+        try:
+            local_dist = importlib_metadata.distribution("xgboost")  # type: ignore[no-untyped-call]
+            local_xgb_version = version.parse(local_dist.version)
+        except importlib_metadata.PackageNotFoundError:
+            pass
+
+        if local_xgb_version and local_xgb_version >= version.parse("2.1.0") and enable_explainability:
+            warnings.warn(
+                f"This version of xgboost {local_xgb_version} does not work with shap 0.42.1."
+                + "If you want model explanations, lower the xgboost version to <2.1.0.",
+                category=UserWarning,
+                stacklevel=1,
+            )
+            enable_explainability = False
+
         if not is_sub_model:
             target_methods = handlers_utils.get_target_methods(
                 model=model,
@@ -148,17 +138,16 @@ class XGBModelHandler(_base.BaseModelHandler[Union["xgboost.Booster", "xgboost.X
                 sample_input_data=sample_input_data,
                 get_prediction_fn=get_prediction,
             )
-            model_objective = cls.get_model_objective(model)
-            model_meta.model_objective = model_objective
-            if kwargs.get("enable_explainability", True):
-                output_type = model_signature.DataType.DOUBLE
-                if model_objective == model_meta_schema.ModelObjective.MULTI_CLASSIFICATION:
-                    output_type = model_signature.DataType.STRING
+            model_objective_and_output = model_objective_utils.get_model_objective_and_output_type(model)
+            model_meta.model_objective = handlers_utils.validate_model_objective(
+                model_meta.model_objective, model_objective_and_output.objective
+            )
+            if enable_explainability:
                 model_meta = handlers_utils.add_explain_method_signature(
                     model_meta=model_meta,
                     explain_method="explain",
                     target_method="predict",
-                    output_return_type=output_type,
+                    output_return_type=model_objective_and_output.output_type,
                 )
                 model_meta.function_properties = {
                     "explain": {model_meta_schema.FunctionProperties.PARTITIONED.value: False}
@@ -180,15 +169,26 @@ class XGBModelHandler(_base.BaseModelHandler[Union["xgboost.Booster", "xgboost.X
         model_meta.env.include_if_absent(
             [
                 model_env.ModelDependency(requirement="scikit-learn", pip_name="scikit-learn"),
-                model_env.ModelDependency(requirement="xgboost", pip_name="xgboost"),
             ],
             check_local_version=True,
         )
-        if kwargs.get("enable_explainability", True):
+        if local_xgb_version and local_xgb_version >= version.parse("2.0.0") and enable_explainability:
             model_meta.env.include_if_absent(
-                [model_env.ModelDependency(requirement="shap", pip_name="shap")],
+                [
+                    model_env.ModelDependency(requirement="xgboost==2.0.*", pip_name="xgboost"),
+                ],
+                check_local_version=False,
+            )
+        else:
+            model_meta.env.include_if_absent(
+                [
+                    model_env.ModelDependency(requirement="xgboost", pip_name="xgboost"),
+                ],
                 check_local_version=True,
             )
+
+        if enable_explainability:
+            model_meta.env.include_if_absent([model_env.ModelDependency(requirement="shap", pip_name="shap")])
             model_meta.explain_algorithm = model_meta_schema.ModelExplainAlgorithm.SHAP
         model_meta.env.cuda_version = kwargs.get("cuda_version", model_env.DEFAULT_CUDA_VERSION)
 
@@ -269,7 +269,7 @@ class XGBModelHandler(_base.BaseModelHandler[Union["xgboost.Booster", "xgboost.X
                     import shap
 
                     explainer = shap.TreeExplainer(raw_model)
-                    df = pd.DataFrame(explainer(X).values)
+                    df = handlers_utils.convert_explanations_to_2D_df(raw_model, explainer(X).values)
                     return model_signature_utils.rename_pandas_df(df, signature.outputs)
 
                 if target_method == "explain":

snowflake/ml/model/_packager/model_meta/model_meta.py

@@ -55,6 +55,7 @@ def create_model_metadata(
     conda_dependencies: Optional[List[str]] = None,
     pip_requirements: Optional[List[str]] = None,
     python_version: Optional[str] = None,
+    model_objective: model_types.ModelObjective = model_types.ModelObjective.UNKNOWN,
     **kwargs: Any,
 ) -> Generator["ModelMetadata", None, None]:
     """Create a generator for model metadata object. Use generator to ensure correct register and unregister for
@@ -74,6 +75,9 @@ def create_model_metadata(
         pip_requirements: List of pip Python packages requirements for running the model. Defaults to None.
         python_version: A string of python version where model is run. Used for user override. If specified as None,
             current version would be captured. Defaults to None.
+        model_objective: The objective of the Model Version. It is an enum class ModelObjective with values REGRESSION,
+            BINARY_CLASSIFICATION, MULTI_CLASSIFICATION, RANKING, or UNKNOWN. By default it is set to
+            ModelObjective.UNKNOWN and may be overridden by inferring from the Model Object.
         **kwargs: Dict of attributes and values of the metadata. Used when loading from file.
 
     Raises:
@@ -131,6 +135,7 @@ def create_model_metadata(
         model_type=model_type,
         signatures=signatures,
         function_properties=function_properties,
+        model_objective=model_objective,
     )
 
     code_dir_path = os.path.join(model_dir_path, MODEL_CODE_DIR)
@@ -261,7 +266,7 @@ class ModelMetadata:
         min_snowpark_ml_version: Optional[str] = None,
         models: Optional[Dict[str, model_blob_meta.ModelBlobMeta]] = None,
         original_metadata_version: Optional[str] = model_meta_schema.MODEL_METADATA_VERSION,
-        model_objective: Optional[model_meta_schema.ModelObjective] = model_meta_schema.ModelObjective.UNKNOWN,
+        model_objective: model_types.ModelObjective = model_types.ModelObjective.UNKNOWN,
         explain_algorithm: Optional[model_meta_schema.ModelExplainAlgorithm] = None,
     ) -> None:
         self.name = name
@@ -287,9 +292,7 @@ class ModelMetadata:
 
         self.original_metadata_version = original_metadata_version
 
-        self.model_objective: model_meta_schema.ModelObjective = (
-            model_objective or model_meta_schema.ModelObjective.UNKNOWN
-        )
+        self.model_objective: model_types.ModelObjective = model_objective
         self.explain_algorithm: Optional[model_meta_schema.ModelExplainAlgorithm] = explain_algorithm
 
     @property
@@ -387,7 +390,7 @@ class ModelMetadata:
             signatures=loaded_meta["signatures"],
             version=original_loaded_meta_version,
             min_snowpark_ml_version=loaded_meta_min_snowpark_ml_version,
-            model_objective=loaded_meta.get("model_objective", model_meta_schema.ModelObjective.UNKNOWN.value),
+            model_objective=loaded_meta.get("model_objective", model_types.ModelObjective.UNKNOWN.value),
             explainability=loaded_meta.get("explainability", None),
             function_properties=loaded_meta.get("function_properties", {}),
         )
@@ -442,8 +445,8 @@ class ModelMetadata:
             min_snowpark_ml_version=model_dict["min_snowpark_ml_version"],
             models=models,
             original_metadata_version=model_dict["version"],
-            model_objective=model_meta_schema.ModelObjective(
-                model_dict.get("model_objective", model_meta_schema.ModelObjective.UNKNOWN.value)
+            model_objective=model_types.ModelObjective(
+                model_dict.get("model_objective", model_types.ModelObjective.UNKNOWN.value)
             ),
             explain_algorithm=explanation_algorithm,
             function_properties=model_dict.get("function_properties", {}),