snowflake-ml-python 1.3.1__py3-none-any.whl → 1.4.1__py3-none-any.whl

snowflake/ml/modeling/impute/missing_indicator.py

@@ -33,6 +33,15 @@ from snowflake.ml.modeling._internal.transformer_protocols import (
     BatchInferenceKwargsTypedDict,
     ScoreKwargsTypedDict
 )
+from snowflake.ml.model._signatures import utils as model_signature_utils
+from snowflake.ml.model.model_signature import (
+    BaseFeatureSpec,
+    DataType,
+    FeatureSpec,
+    ModelSignature,
+    _infer_signature,
+    _rename_signature_with_snowflake_identifiers,
+)
 
 from snowflake.ml.modeling._internal.model_transformer_builder import ModelTransformerBuilder
 
@@ -43,16 +52,6 @@ from snowflake.ml.modeling._internal.estimator_utils import (
     validate_sklearn_args,
 )
 
-from snowflake.ml.model.model_signature import (
-    DataType,
-    FeatureSpec,
-    ModelSignature,
-    _infer_signature,
-    _rename_signature_with_snowflake_identifiers,
-    BaseFeatureSpec,
-)
-from snowflake.ml.model._signatures import utils as model_signature_utils
-
 _PROJECT = "ModelDevelopment"
 # Derive subproject from module name by removing "sklearn"
 # and converting module name from underscore to CamelCase
@@ -224,12 +223,7 @@ class MissingIndicator(BaseTransformer):
         )
         return selected_cols
 
-    @telemetry.send_api_usage_telemetry(
-        project=_PROJECT,
-        subproject=_SUBPROJECT,
-        custom_tags=dict([("autogen", True)]),
-    )
-    def fit(self, dataset: Union[DataFrame, pd.DataFrame]) -> "MissingIndicator":
+    def _fit(self, dataset: Union[DataFrame, pd.DataFrame]) -> "MissingIndicator":
         """Fit the transformer on `X`
         For more details on this function, see [sklearn.impute.MissingIndicator.fit]
         (https://scikit-learn.org/stable/modules/generated/sklearn.impute.MissingIndicator.html#sklearn.impute.MissingIndicator.fit)
@@ -256,12 +250,14 @@ class MissingIndicator(BaseTransformer):
 
             self._snowpark_cols = dataset.select(self.input_cols).columns
 
-             # If we are already in a stored procedure, no need to kick off another one.
+            # If we are already in a stored procedure, no need to kick off another one.
             if SNOWML_SPROC_ENV in os.environ:
                 statement_params = telemetry.get_function_usage_statement_params(
                     project=_PROJECT,
                     subproject=_SUBPROJECT,
-                    function_name=telemetry.get_statement_params_full_func_name(inspect.currentframe(), MissingIndicator.__class__.__name__),
+                    function_name=telemetry.get_statement_params_full_func_name(
+                        inspect.currentframe(), MissingIndicator.__class__.__name__
+                    ),
                     api_calls=[Session.call],
                     custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
                 )
@@ -282,7 +278,7 @@ class MissingIndicator(BaseTransformer):
         )
         self._sklearn_object = model_trainer.train()
         self._is_fitted = True
-        self._get_model_signatures(dataset)
+        self._generate_model_signatures(dataset)
         return self
 
     def _batch_inference_validate_snowpark(
@@ -356,7 +352,9 @@ class MissingIndicator(BaseTransformer):
             # when it is classifier, infer the datatype from label columns
             if expected_type_inferred == "" and 'predict' in self.model_signatures:
                 # Batch inference takes a single expected output column type. Use the first columns type for now.
-                label_cols_signatures = [row for row in self.model_signatures['predict'].outputs if row.name in self.output_cols]
+                label_cols_signatures = [
+                    row for row in self.model_signatures['predict'].outputs if row.name in self.output_cols
+                ]
                 if len(label_cols_signatures) == 0:
                     error_str = f"Output columns {self.output_cols} do not match model signatures {self.model_signatures['predict'].outputs}."
                     raise exceptions.SnowflakeMLException(
@@ -364,25 +362,22 @@ class MissingIndicator(BaseTransformer):
                         original_exception=ValueError(error_str),
                     )
 
-                expected_type_inferred = convert_sp_to_sf_type(
-                    label_cols_signatures[0].as_snowpark_type()
-                )
+                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)
-            assert isinstance(dataset._session, Session) # mypy does not recognize the check in _batch_inference_validate_snowpark()
+            assert isinstance(
+                dataset._session, Session
+            )  # mypy does not recognize the check in _batch_inference_validate_snowpark()
 
             transform_kwargs = dict(
-                session = dataset._session,
-                dependencies = self._deps,
-                drop_input_cols = self._drop_input_cols,
-                expected_output_cols_type = expected_type_inferred,
+                session=dataset._session,
+                dependencies=self._deps,
+                drop_input_cols=self._drop_input_cols,
+                expected_output_cols_type=expected_type_inferred,
             )
 
         elif isinstance(dataset, pd.DataFrame):
-            transform_kwargs = dict(
-                snowpark_input_cols = self._snowpark_cols,
-                drop_input_cols = self._drop_input_cols
-                )
+            transform_kwargs = dict(snowpark_input_cols=self._snowpark_cols, drop_input_cols=self._drop_input_cols)
 
         transform_handlers = ModelTransformerBuilder.build(
             dataset=dataset,
@@ -424,7 +419,7 @@ class MissingIndicator(BaseTransformer):
             Transformed dataset.
         """
         super()._check_dataset_type(dataset)
-        inference_method="transform"
+        inference_method = "transform"
 
         # This dictionary contains optional kwargs for batch inference. These kwargs
         # are specific to the type of dataset used. 
@@ -461,17 +456,14 @@ class MissingIndicator(BaseTransformer):
             assert isinstance(dataset._session, Session) # mypy does not recognize the check in _batch_inference_validate_snowpark()
 
             transform_kwargs = dict(
-                session = dataset._session,
-                dependencies = self._deps,
-                drop_input_cols = self._drop_input_cols,
-                expected_output_cols_type = expected_dtype,
+                session=dataset._session,
+                dependencies=self._deps,
+                drop_input_cols=self._drop_input_cols,
+                expected_output_cols_type=expected_dtype,
             )
 
         elif isinstance(dataset, pd.DataFrame):
-            transform_kwargs = dict(
-                snowpark_input_cols = self._snowpark_cols,
-                drop_input_cols = self._drop_input_cols
-                )
+            transform_kwargs = dict(snowpark_input_cols=self._snowpark_cols, drop_input_cols=self._drop_input_cols)
 
         transform_handlers = ModelTransformerBuilder.build(
             dataset=dataset,
@@ -490,7 +482,11 @@ class MissingIndicator(BaseTransformer):
         return output_df
     
     @available_if(original_estimator_has_callable("fit_predict"))  # type: ignore[misc]
-    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame], output_cols_prefix: str = "fit_predict_",) -> Union[DataFrame, pd.DataFrame]:
+    def fit_predict(
+        self,
+        dataset: Union[DataFrame, pd.DataFrame],
+        output_cols_prefix: str = "fit_predict_",
+    ) -> Union[DataFrame, pd.DataFrame]:
         """ Method not supported for this class.
 
 
@@ -515,7 +511,9 @@ class MissingIndicator(BaseTransformer):
         )
         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_list=(
+                self.output_cols if self.output_cols else self._get_output_column_names(output_cols_prefix)
+            ),
         )
         self._sklearn_object = fitted_estimator
         self._is_fitted = True
@@ -532,6 +530,62 @@ class MissingIndicator(BaseTransformer):
         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.
+        Returns a list with output_cols_prefix as the only element if the estimator is not a classifier.
+        """
+        output_cols_prefix = identifier.resolve_identifier(output_cols_prefix)
+        # The following condition is introduced for kneighbors methods, and not used in other methods
+        if output_cols:
+            output_cols = [
+                identifier.concat_names([output_cols_prefix, identifier.resolve_identifier(c)])
+                for c in output_cols
+            ]
+        elif getattr(self._sklearn_object, "classes_", None) is None:
+            output_cols = [output_cols_prefix]
+        elif self._sklearn_object is not None:
+            classes = self._sklearn_object.classes_
+            if isinstance(classes, numpy.ndarray):
+                output_cols = [f'{output_cols_prefix}{str(c)}' for c in classes.tolist()]
+            elif isinstance(classes, list) and len(classes) > 0 and isinstance(classes[0], numpy.ndarray):
+                # If the estimator is a multioutput estimator, classes_ will be a list of ndarrays.
+                output_cols = []
+                for i, cl in enumerate(classes):
+                    # For binary classification, there is only one output column for each class
+                    # ndarray as the two classes are complementary.
+                    if len(cl) == 2:
+                        output_cols.append(f'{output_cols_prefix}{i}_{cl[0]}')
+                    else:
+                        output_cols.extend([
+                            f'{output_cols_prefix}{i}_{c}' for c in cl.tolist()
+                        ])
+        else:
+            output_cols = []
+
+        # Make sure column names are valid snowflake identifiers.
+        assert output_cols is not None  # Make MyPy happy
+        rv = [identifier.rename_to_valid_snowflake_identifier(c) for c in output_cols]
+
+        return rv
+
+    def _align_expected_output_names(
+        self, method: str, dataset: DataFrame, expected_output_cols_list: List[str], output_cols_prefix: str
+    ) -> List[str]:
+        # 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
+        output_df_pd = getattr(self, method)(dataset.limit(1).to_pandas(), output_cols_prefix)
+        output_df_columns = list(output_df_pd.columns)
+        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
+        # otherwise, use the sklearn estimator's output
+        else:
+            return sorted(list(output_df_columns_set), key=lambda x: output_df_columns.index(x))
+
     @available_if(original_estimator_has_callable("predict_proba"))  # type: ignore[misc]
     @telemetry.send_api_usage_telemetry(
         project=_PROJECT,
@@ -562,24 +616,28 @@ class MissingIndicator(BaseTransformer):
         # are specific to the type of dataset used. 
         transform_kwargs: BatchInferenceKwargsTypedDict = dict() 
 
+        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,
             )
-            assert isinstance(dataset._session, Session) # mypy does not recognize the check in _batch_inference_validate_snowpark()
+            assert isinstance(
+                dataset._session, Session
+            )  # mypy does not recognize the check in _batch_inference_validate_snowpark()
             transform_kwargs = dict(
                 session=dataset._session,
                 dependencies=self._deps,
-                drop_input_cols = self._drop_input_cols,
+                drop_input_cols=self._drop_input_cols,
                 expected_output_cols_type="float",
             )
+            expected_output_cols = self._align_expected_output_names(
+                inference_method, dataset, expected_output_cols, output_cols_prefix
+            )
 
         elif isinstance(dataset, pd.DataFrame):
-            transform_kwargs = dict(
-                snowpark_input_cols = self._snowpark_cols,
-                drop_input_cols = self._drop_input_cols
-                )
+            transform_kwargs = dict(snowpark_input_cols=self._snowpark_cols, drop_input_cols=self._drop_input_cols)
 
         transform_handlers = ModelTransformerBuilder.build(
             dataset=dataset,
@@ -591,7 +649,7 @@ class MissingIndicator(BaseTransformer):
         output_df: DATAFRAME_TYPE = transform_handlers.batch_inference(
             inference_method=inference_method,
             input_cols=self.input_cols,
-            expected_output_cols=self._get_output_column_names(output_cols_prefix),
+            expected_output_cols=expected_output_cols,
             **transform_kwargs
         )
         return output_df
@@ -621,7 +679,8 @@ class MissingIndicator(BaseTransformer):
             Output dataset with log probability of the sample for each class in the model.
         """
         super()._check_dataset_type(dataset)
-        inference_method="predict_log_proba"
+        inference_method = "predict_log_proba"
+        expected_output_cols = self._get_output_column_names(output_cols_prefix)
 
         # This dictionary contains optional kwargs for batch inference. These kwargs
         # are specific to the type of dataset used. 
@@ -632,18 +691,20 @@ class MissingIndicator(BaseTransformer):
                 dataset=dataset,
                 inference_method=inference_method,
             )
-            assert isinstance(dataset._session, Session) # mypy does not recognize the check in _batch_inference_validate_snowpark()
+            assert isinstance(
+                dataset._session, Session
+            )  # mypy does not recognize the check in _batch_inference_validate_snowpark()
             transform_kwargs = dict(
                 session=dataset._session,
                 dependencies=self._deps,
-                drop_input_cols = self._drop_input_cols,
+                drop_input_cols=self._drop_input_cols,
                 expected_output_cols_type="float",
             )
+            expected_output_cols = self._align_expected_output_names(
+                inference_method, dataset, expected_output_cols, output_cols_prefix
+            )
         elif isinstance(dataset, pd.DataFrame):
-            transform_kwargs = dict(
-                snowpark_input_cols = self._snowpark_cols,
-                drop_input_cols = self._drop_input_cols
-                )
+            transform_kwargs = dict(snowpark_input_cols=self._snowpark_cols, drop_input_cols=self._drop_input_cols)
 
         transform_handlers = ModelTransformerBuilder.build(
             dataset=dataset,
@@ -656,7 +717,7 @@ class MissingIndicator(BaseTransformer):
         output_df: DATAFRAME_TYPE = transform_handlers.batch_inference(
             inference_method=inference_method,
             input_cols=self.input_cols,
-            expected_output_cols=self._get_output_column_names(output_cols_prefix),
+            expected_output_cols=expected_output_cols,
             **transform_kwargs
         )
         return output_df
@@ -682,30 +743,34 @@ class MissingIndicator(BaseTransformer):
             Output dataset with results of the decision function for the samples in input dataset.
         """
         super()._check_dataset_type(dataset)
-        inference_method="decision_function"
+        inference_method = "decision_function"
 
         # This dictionary contains optional kwargs for batch inference. These kwargs
         # are specific to the type of dataset used. 
         transform_kwargs: BatchInferenceKwargsTypedDict = dict()  
 
+        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,
             )
-            assert isinstance(dataset._session, Session) # mypy does not recognize the check in _batch_inference_validate_snowpark()
+            assert isinstance(
+                dataset._session, Session
+            )  # mypy does not recognize the check in _batch_inference_validate_snowpark()
             transform_kwargs = dict(
                 session=dataset._session,
                 dependencies=self._deps,
-                drop_input_cols = self._drop_input_cols,
+                drop_input_cols=self._drop_input_cols,
                 expected_output_cols_type="float",
             )
+            expected_output_cols = self._align_expected_output_names(
+                inference_method, dataset, expected_output_cols, output_cols_prefix
+            )
 
         elif isinstance(dataset, pd.DataFrame):
-            transform_kwargs = dict(
-                snowpark_input_cols = self._snowpark_cols,
-                drop_input_cols = self._drop_input_cols
-                )
+            transform_kwargs = dict(snowpark_input_cols=self._snowpark_cols, drop_input_cols=self._drop_input_cols)
 
         transform_handlers = ModelTransformerBuilder.build(
             dataset=dataset,
@@ -718,7 +783,7 @@ class MissingIndicator(BaseTransformer):
         output_df: DATAFRAME_TYPE = transform_handlers.batch_inference(
             inference_method=inference_method,
             input_cols=self.input_cols,
-            expected_output_cols=self._get_output_column_names(output_cols_prefix),
+            expected_output_cols=expected_output_cols,
             **transform_kwargs
         )
         return output_df
@@ -747,12 +812,14 @@ class MissingIndicator(BaseTransformer):
             Output dataset with probability of the sample for each class in the model.
         """
         super()._check_dataset_type(dataset)
-        inference_method="score_samples"
+        inference_method = "score_samples"
 
         # This dictionary contains optional kwargs for batch inference. These kwargs
         # are specific to the type of dataset used. 
         transform_kwargs: BatchInferenceKwargsTypedDict = dict()
 
+        expected_output_cols = self._get_output_column_names(output_cols_prefix)
+
         if isinstance(dataset, DataFrame):
             self._deps = self._batch_inference_validate_snowpark(
                 dataset=dataset,
@@ -765,6 +832,9 @@ class MissingIndicator(BaseTransformer):
                 drop_input_cols = self._drop_input_cols,
                 expected_output_cols_type="float",
             )
+            expected_output_cols = self._align_expected_output_names(
+                inference_method, dataset, expected_output_cols, output_cols_prefix
+            )
 
         elif isinstance(dataset, pd.DataFrame):
             transform_kwargs = dict(
@@ -783,7 +853,7 @@ class MissingIndicator(BaseTransformer):
         output_df: DATAFRAME_TYPE = transform_handlers.batch_inference(
             inference_method=inference_method,
             input_cols=self.input_cols,
-            expected_output_cols=self._get_output_column_names(output_cols_prefix),
+            expected_output_cols=expected_output_cols,
             **transform_kwargs
         )
         return output_df
@@ -928,50 +998,84 @@ class MissingIndicator(BaseTransformer):
         )
         return output_df
 
+    
+
+    def to_sklearn(self) -> Any:
+        """Get sklearn.impute.MissingIndicator object.
+        """
+        if self._sklearn_object is None:
+            self._sklearn_object = self._create_sklearn_object()
+        return self._sklearn_object
+
+    def to_xgboost(self) -> Any:
+        raise exceptions.SnowflakeMLException(
+            error_code=error_codes.METHOD_NOT_ALLOWED,
+            original_exception=AttributeError(
+                modeling_error_messages.UNSUPPORTED_MODEL_CONVERSION.format(
+                    "to_xgboost()", 
+                    "to_sklearn()"
+                )
+            ),
+        )
+
+    def to_lightgbm(self) -> Any:
+        raise exceptions.SnowflakeMLException(
+            error_code=error_codes.METHOD_NOT_ALLOWED,
+            original_exception=AttributeError(
+                modeling_error_messages.UNSUPPORTED_MODEL_CONVERSION.format(
+                    "to_lightgbm()", 
+                    "to_sklearn()"
+                )
+            ),
+        )
 
-    def _get_model_signatures(self, dataset: Union[DataFrame, pd.DataFrame]) -> None:
+    def _get_dependencies(self) -> List[str]:
+        return self._deps
+
+
+    def _generate_model_signatures(self, dataset: Union[DataFrame, pd.DataFrame]) -> None:
         self._model_signature_dict = dict()
 
         PROB_FUNCTIONS = ["predict_log_proba", "predict_proba", "decision_function"]
 
-        inputs = list(_infer_signature(dataset[self.input_cols], "input"))
+        inputs = list(_infer_signature(dataset[self.input_cols], "input", use_snowflake_identifiers=True))
         outputs: List[BaseFeatureSpec] = []
         if hasattr(self, "predict"):
             # keep mypy happy
-            assert self._sklearn_object is not None and hasattr(self._sklearn_object, "_estimator_type") 
+            assert self._sklearn_object is not None and hasattr(self._sklearn_object, "_estimator_type")
             # For classifier, the type of predict is the same as the type of label
-            if self._sklearn_object._estimator_type == 'classifier':
-                 # label columns is the desired type for output
+            if self._sklearn_object._estimator_type == "classifier":
+                # label columns is the desired type for output
                 outputs = list(_infer_signature(dataset[self.label_cols], "output", use_snowflake_identifiers=True))
                 # rename the output columns
                 outputs = list(model_signature_utils.rename_features(outputs, self.output_cols))
-                self._model_signature_dict["predict"] = ModelSignature(inputs,
-                                                                       ([] if self._drop_input_cols else inputs)
-                                                                       + outputs)
+                self._model_signature_dict["predict"] = ModelSignature(
+                    inputs, ([] if self._drop_input_cols else inputs) + outputs
+                )
             # For mixture models that use the density mixin, `predict` returns the argmax of the log prob.
             # For outlier models, returns -1 for outliers and 1 for inliers.
-            # Clusterer returns int64 cluster labels. 
+            # Clusterer returns int64 cluster labels.
             elif self._sklearn_object._estimator_type in ["DensityEstimator", "clusterer", "outlier_detector"]:
                 outputs = [FeatureSpec(dtype=DataType.INT64, name=c) for c in self.output_cols]
-                self._model_signature_dict["predict"] = ModelSignature(inputs,
-                                                                       ([] if self._drop_input_cols else inputs)
-                                                                       + outputs)
-            
+                self._model_signature_dict["predict"] = ModelSignature(
+                    inputs, ([] if self._drop_input_cols else inputs) + outputs
+                )
+
             # For regressor, the type of predict is float64
-            elif self._sklearn_object._estimator_type == 'regressor':
+            elif self._sklearn_object._estimator_type == "regressor":
                 outputs = [FeatureSpec(dtype=DataType.DOUBLE, name=c) for c in self.output_cols]
-                self._model_signature_dict["predict"] = ModelSignature(inputs,
-                                                                       ([] if self._drop_input_cols else inputs)
-                                                                       + outputs)
-                
+                self._model_signature_dict["predict"] = ModelSignature(
+                    inputs, ([] if self._drop_input_cols else inputs) + outputs
+                )
+
         for prob_func in PROB_FUNCTIONS:
             if hasattr(self, prob_func):
                 output_cols_prefix: str = f"{prob_func}_"
                 output_column_names = self._get_output_column_names(output_cols_prefix)
                 outputs = [FeatureSpec(dtype=DataType.DOUBLE, name=c) for c in output_column_names]
-                self._model_signature_dict[prob_func] = ModelSignature(inputs,
-                                                                       ([] if self._drop_input_cols else inputs)
-                                                                       + outputs)
+                self._model_signature_dict[prob_func] = ModelSignature(
+                    inputs, ([] if self._drop_input_cols else inputs) + outputs
+                )
 
         # Output signature names may still need to be renamed, since they were not created with `_infer_signature`.
         items = list(self._model_signature_dict.items())
@@ -984,10 +1088,10 @@ class MissingIndicator(BaseTransformer):
         """Returns model signature of current class.
 
         Raises:
-            exceptions.SnowflakeMLException: If estimator is not fitted, then model signature cannot be inferred
+            SnowflakeMLException: If estimator is not fitted, then model signature cannot be inferred
 
         Returns:
-            Dict[str, ModelSignature]: each method and its input output signature
+            Dict with each method and its input output signature
         """
         if self._model_signature_dict is None:
             raise exceptions.SnowflakeMLException(
@@ -995,35 +1099,3 @@ class MissingIndicator(BaseTransformer):
                 original_exception=RuntimeError("Estimator not fitted before accessing property model_signatures!"),
             )
         return self._model_signature_dict
-
-    def to_sklearn(self) -> Any:
-        """Get sklearn.impute.MissingIndicator object.
-        """
-        if self._sklearn_object is None:
-            self._sklearn_object = self._create_sklearn_object()
-        return self._sklearn_object
-
-    def to_xgboost(self) -> Any:
-        raise exceptions.SnowflakeMLException(
-            error_code=error_codes.METHOD_NOT_ALLOWED,
-            original_exception=AttributeError(
-                modeling_error_messages.UNSUPPORTED_MODEL_CONVERSION.format(
-                    "to_xgboost()", 
-                    "to_sklearn()"
-                )
-            ),
-        )
-
-    def to_lightgbm(self) -> Any:
-        raise exceptions.SnowflakeMLException(
-            error_code=error_codes.METHOD_NOT_ALLOWED,
-            original_exception=AttributeError(
-                modeling_error_messages.UNSUPPORTED_MODEL_CONVERSION.format(
-                    "to_lightgbm()", 
-                    "to_sklearn()"
-                )
-            ),
-        )
-
-    def _get_dependencies(self) -> List[str]:
-        return self._deps

snowflake/ml/modeling/impute/simple_imputer.py

@@ -74,8 +74,6 @@ _NUMERIC_TYPES = [
 ]
 
 
-# TODO(thoyt): Implement logic for `add_indicator` parameter and `indicator_` attribute.Requires
-#  `snowflake.ml.impute.MissingIndicator` to be implemented.
 class SimpleImputer(base.BaseTransformer):
     """
     Univariate imputer for completing missing values with simple strategies.
@@ -96,7 +94,8 @@ class SimpleImputer(base.BaseTransformer):
             * If "most_frequent", replace missing using the most frequent value along each column.
               Can be used with strings or numeric data.
               If there is more than one such value, only the smallest is returned.
-            * If "constant", replace the missing values with `fill_value`. Can be used with strings or numeric data.
+            * If "constant", replace the missing values with `fill_value`, including columns that are entirely
+              null. Can be used with strings or numeric data.
 
         fill_value: Optional[str]
             When `strategy == "constant"`, `fill_value` is used to replace all occurrences of `missing_values`.
@@ -262,18 +261,8 @@ class SimpleImputer(base.BaseTransformer):
                         break
 
             for input_col in self.input_cols:
-                # Check whether input column is empty if necessary.
-                if (
-                    # TODO(hayu): [SNOW-752265] Support SimpleImputer keep_empty_features.
-                    #  Add back when `keep_empty_features` is supported.
-                    # not self.keep_empty_features
-                    # and dataset.filter(F.col(input_col).is_not_null()).count(statement_params=statement_params) == 0
-                    dataset.filter(F.col(input_col).is_not_null()).count(statement_params=statement_params)
-                    == 0
-                ):
-                    self.statistics_[input_col] = np.nan
-                else:
-                    self.statistics_[input_col] = self.fill_value
+                self.statistics_[input_col] = self.fill_value
+
         else:
             state = STRATEGY_TO_STATE_DICT[self.strategy]
             assert state is not None