snowflake-ml-python 1.5.1__py3-none-any.whl → 1.5.2__py3-none-any.whl

snowflake/ml/modeling/naive_bayes/categorical_nb.py

@@ -590,7 +590,14 @@ class CategoricalNB(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/naive_bayes/complement_nb.py

@@ -584,7 +584,14 @@ class ComplementNB(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/naive_bayes/gaussian_nb.py

@@ -565,7 +565,14 @@ class GaussianNB(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/naive_bayes/multinomial_nb.py

@@ -578,7 +578,14 @@ class MultinomialNB(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/neighbors/k_neighbors_classifier.py

@@ -635,7 +635,14 @@ class KNeighborsClassifier(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/neighbors/k_neighbors_regressor.py

@@ -637,7 +637,14 @@ class KNeighborsRegressor(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/neighbors/kernel_density.py

@@ -612,7 +612,14 @@ class KernelDensity(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/neighbors/local_outlier_factor.py

@@ -644,7 +644,14 @@ class LocalOutlierFactor(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/neighbors/nearest_centroid.py

@@ -575,7 +575,14 @@ class NearestCentroid(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/neighbors/nearest_neighbors.py

@@ -623,7 +623,14 @@ class NearestNeighbors(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/neighbors/neighborhood_components_analysis.py

@@ -648,7 +648,14 @@ class NeighborhoodComponentsAnalysis(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/neighbors/radius_neighbors_classifier.py

@@ -647,7 +647,14 @@ class RadiusNeighborsClassifier(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/neighbors/radius_neighbors_regressor.py

@@ -637,7 +637,14 @@ class RadiusNeighborsRegressor(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/neural_network/bernoulli_rbm.py

@@ -596,7 +596,14 @@ class BernoulliRBM(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/neural_network/mlp_classifier.py

@@ -749,7 +749,14 @@ class MLPClassifier(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/neural_network/mlp_regressor.py

@@ -745,7 +745,14 @@ class MLPRegressor(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/parameters/enable_anonymous_sproc.py

@@ -0,0 +1,5 @@
+"""Enables the anonymous stored procedures for running modeling fit"""
+
+from snowflake.ml.modeling._internal.snowpark_implementations import snowpark_trainer
+
+snowpark_trainer._ENABLE_ANONYMOUS_SPROC = True

snowflake/ml/modeling/preprocessing/polynomial_features.py

@@ -586,7 +586,14 @@ class PolynomialFeatures(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/semi_supervised/label_propagation.py

@@ -590,7 +590,14 @@ class LabelPropagation(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/semi_supervised/label_spreading.py

@@ -599,7 +599,14 @@ class LabelSpreading(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/svm/linear_svc.py

@@ -655,7 +655,14 @@ class LinearSVC(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/svm/linear_svr.py

@@ -627,7 +627,14 @@ class LinearSVR(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/svm/nu_svc.py

@@ -661,7 +661,14 @@ class NuSVC(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/svm/nu_svr.py

@@ -622,7 +622,14 @@ class NuSVR(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/svm/svc.py

@@ -664,7 +664,14 @@ class SVC(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/svm/svr.py

@@ -625,7 +625,14 @@ class SVR(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/tree/decision_tree_classifier.py

@@ -692,7 +692,14 @@ class DecisionTreeClassifier(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/tree/decision_tree_regressor.py

@@ -674,7 +674,14 @@ class DecisionTreeRegressor(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/tree/extra_tree_classifier.py

@@ -684,7 +684,14 @@ class ExtraTreeClassifier(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/tree/extra_tree_regressor.py

@@ -666,7 +666,14 @@ class ExtraTreeRegressor(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/xgboost/xgb_classifier.py

@@ -784,7 +784,14 @@ class XGBClassifier(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/xgboost/xgb_regressor.py

@@ -783,7 +783,14 @@ class XGBRegressor(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/xgboost/xgbrf_classifier.py

@@ -788,7 +788,14 @@ class XGBRFClassifier(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/xgboost/xgbrf_regressor.py

@@ -788,7 +788,14 @@ class XGBRFRegressor(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: