snowflake-ml-python 1.5.0__py3-none-any.whl → 1.5.2__py3-none-any.whl

snowflake/ml/modeling/ensemble/bagging_classifier.py

@@ -638,7 +638,14 @@ class BaggingClassifier(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/ensemble/bagging_regressor.py

@@ -638,7 +638,14 @@ class BaggingRegressor(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/ensemble/extra_trees_classifier.py

@@ -741,7 +741,14 @@ class ExtraTreesClassifier(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/ensemble/extra_trees_regressor.py

@@ -720,7 +720,14 @@ class ExtraTreesRegressor(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/ensemble/gradient_boosting_classifier.py

@@ -753,7 +753,14 @@ class GradientBoostingClassifier(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/ensemble/gradient_boosting_regressor.py

@@ -762,7 +762,14 @@ class GradientBoostingRegressor(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/ensemble/hist_gradient_boosting_classifier.py

@@ -734,7 +734,14 @@ class HistGradientBoostingClassifier(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/ensemble/hist_gradient_boosting_regressor.py

@@ -725,7 +725,14 @@ class HistGradientBoostingRegressor(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/ensemble/isolation_forest.py

@@ -627,7 +627,14 @@ class IsolationForest(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/ensemble/random_forest_classifier.py

@@ -737,7 +737,14 @@ class RandomForestClassifier(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/ensemble/random_forest_regressor.py

@@ -716,7 +716,14 @@ class RandomForestRegressor(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/ensemble/stacking_regressor.py

@@ -621,7 +621,14 @@ class StackingRegressor(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/ensemble/voting_classifier.py

@@ -603,7 +603,14 @@ class VotingClassifier(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/ensemble/voting_regressor.py

@@ -585,7 +585,14 @@ class VotingRegressor(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/feature_selection/generic_univariate_select.py

@@ -573,7 +573,14 @@ class GenericUnivariateSelect(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/feature_selection/select_fdr.py

@@ -569,7 +569,14 @@ class SelectFdr(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/feature_selection/select_fpr.py

@@ -569,7 +569,14 @@ class SelectFpr(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/feature_selection/select_fwe.py

@@ -569,7 +569,14 @@ class SelectFwe(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/feature_selection/select_k_best.py

@@ -570,7 +570,14 @@ class SelectKBest(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/feature_selection/select_percentile.py

@@ -569,7 +569,14 @@ class SelectPercentile(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/feature_selection/sequential_feature_selector.py

@@ -627,7 +627,14 @@ class SequentialFeatureSelector(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/feature_selection/variance_threshold.py

@@ -560,7 +560,14 @@ class VarianceThreshold(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/framework/base.py

@@ -16,7 +16,7 @@ from snowflake.ml._internal.exceptions import (
     exceptions,
     modeling_error_messages,
 )
-from snowflake.ml._internal.lineage import data_source, dataset_dataframe
+from snowflake.ml._internal.lineage import data_source, lineage_utils
 from snowflake.ml._internal.utils import identifier, parallelize
 from snowflake.ml.modeling.framework import _utils
 from snowflake.snowpark import functions as F
@@ -430,8 +430,9 @@ class BaseEstimator(Base):
     )
     def fit(self, dataset: Union[snowpark.DataFrame, pd.DataFrame]) -> "BaseEstimator":
         """Runs universal logics for all fit implementations."""
-        if isinstance(dataset, dataset_dataframe.DatasetDataFrame):
-            self._data_sources = dataset._get_sources()
+        self._data_sources = getattr(dataset, lineage_utils.DATA_SOURCES_ATTR, None)
+        if self._data_sources:
+            assert all(isinstance(ds, data_source.DataSource) for ds in self._data_sources)
         return self._fit(dataset)
 
     @abstractmethod

snowflake/ml/modeling/gaussian_process/gaussian_process_classifier.py

@@ -653,7 +653,14 @@ class GaussianProcessClassifier(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/gaussian_process/gaussian_process_regressor.py

@@ -644,7 +644,14 @@ class GaussianProcessRegressor(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/impute/iterative_imputer.py

@@ -688,7 +688,14 @@ class IterativeImputer(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/impute/knn_imputer.py

@@ -614,7 +614,14 @@ class KNNImputer(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/impute/missing_indicator.py

@@ -588,7 +588,14 @@ class MissingIndicator(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/impute/simple_imputer.py

@@ -158,6 +158,7 @@ class SimpleImputer(base.BaseTransformer):
 
         self.fill_value = fill_value
         self.missing_values = missing_values
+        self.statistics_: Dict[str, Any] = {}
         # TODO(hayu): [SNOW-752265] Support SimpleImputer keep_empty_features.
         #  Add back when `keep_empty_features` is supported.
         # self.keep_empty_features = keep_empty_features
@@ -229,8 +230,27 @@ class SimpleImputer(base.BaseTransformer):
 
         return input_col_datatypes
 
+    def fit(self, dataset: Union[snowpark.DataFrame, pd.DataFrame]) -> "SimpleImputer":
+        if isinstance(dataset, snowpark.DataFrame):
+            return self._fit_snowpark(dataset)
+        else:
+            return self._fit_sklearn(dataset)
+
+    def _fit_sklearn(self, dataset: pd.DataFrame) -> "SimpleImputer":
+        dataset = self._use_input_cols_only(dataset)
+        sklearn_simple_imputer = self._create_sklearn_object()
+        sklearn_simple_imputer = sklearn_simple_imputer.fit(dataset)
+        self._sklearn_object = sklearn_simple_imputer
+        for input_col, fill_value in zip(self.input_cols, sklearn_simple_imputer.statistics_.tolist()):
+            self.statistics_[input_col] = fill_value
+        self._sklearn_fit_dtype = sklearn_simple_imputer._fit_dtype
+        self.n_features_in_ = len(self.input_cols)
+        self.feature_names_in_ = self.input_cols
+        self._is_fitted = True
+        return self
+
     @telemetry.send_api_usage_telemetry(project=base.PROJECT, subproject=_SUBPROJECT)
-    def fit(self, dataset: snowpark.DataFrame) -> "SimpleImputer":
+    def _fit_snowpark(self, dataset: snowpark.DataFrame) -> "SimpleImputer":
         """
         Compute values to impute for the dataset according to the strategy.
 
@@ -245,7 +265,6 @@ class SimpleImputer(base.BaseTransformer):
         # In order to fit, the input columns should have the same type.
         input_col_datatypes = self._get_dataset_input_col_datatypes(dataset)
 
-        self.statistics_: Dict[str, Any] = {}
         statement_params = telemetry.get_statement_params(base.PROJECT, _SUBPROJECT, self.__class__.__name__)
 
         if self.strategy == "constant":

snowflake/ml/modeling/kernel_approximation/additive_chi2_sampler.py

@@ -563,7 +563,14 @@ class AdditiveChi2Sampler(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/kernel_approximation/nystroem.py

@@ -611,7 +611,14 @@ class Nystroem(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/kernel_approximation/polynomial_count_sketch.py

@@ -587,7 +587,14 @@ class PolynomialCountSketch(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/kernel_approximation/rbf_sampler.py

@@ -574,7 +574,14 @@ class RBFSampler(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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:

snowflake/ml/modeling/kernel_approximation/skewed_chi2_sampler.py

@@ -572,7 +572,14 @@ class SkewedChi2Sampler(BaseTransformer):
     ) -> 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)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, 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: