snowflake-ml-python 1.5.3__py3-none-any.whl → 1.6.0__py3-none-any.whl

snowflake/ml/modeling/covariance/shrunk_covariance.py

@@ -76,8 +76,10 @@ class ShrunkCovariance(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/decomposition/dictionary_learning.py

@@ -76,8 +76,10 @@ class DictionaryLearning(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/decomposition/factor_analysis.py

@@ -76,8 +76,10 @@ class FactorAnalysis(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/decomposition/fast_ica.py

@@ -76,8 +76,10 @@ class FastICA(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/decomposition/incremental_pca.py

@@ -76,8 +76,10 @@ class IncrementalPCA(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/decomposition/kernel_pca.py

@@ -76,8 +76,10 @@ class KernelPCA(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/decomposition/mini_batch_dictionary_learning.py

@@ -76,8 +76,10 @@ class MiniBatchDictionaryLearning(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/decomposition/mini_batch_sparse_pca.py

@@ -76,8 +76,10 @@ class MiniBatchSparsePCA(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/decomposition/pca.py

@@ -76,8 +76,10 @@ class PCA(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/decomposition/sparse_pca.py

@@ -76,8 +76,10 @@ class SparsePCA(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/decomposition/truncated_svd.py

@@ -76,8 +76,10 @@ class TruncatedSVD(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/ensemble/isolation_forest.py

@@ -76,8 +76,10 @@ class IsolationForest(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/feature_selection/sequential_feature_selector.py

@@ -76,8 +76,10 @@ class SequentialFeatureSelector(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/feature_selection/variance_threshold.py

@@ -76,8 +76,10 @@ class VarianceThreshold(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/impute/iterative_imputer.py

@@ -77,8 +77,10 @@ class IterativeImputer(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/impute/knn_imputer.py

@@ -76,8 +76,10 @@ class KNNImputer(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/impute/missing_indicator.py

@@ -76,8 +76,10 @@ class MissingIndicator(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/impute/simple_imputer.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python3
 import copy
+import warnings
 from typing import Any, Dict, Iterable, Optional, Type, Union
 
 import numpy as np
@@ -10,6 +11,7 @@ from sklearn import impute
 from snowflake import snowpark
 from snowflake.ml._internal import telemetry
 from snowflake.ml._internal.exceptions import error_codes, exceptions
+from snowflake.ml._internal.utils import formatting
 from snowflake.ml.modeling.framework import _utils, base
 from snowflake.snowpark import functions as F, types as T
 from snowflake.snowpark._internal import utils as snowpark_utils
@@ -171,6 +173,14 @@ class SimpleImputer(base.BaseTransformer):
         self.set_output_cols(output_cols)
         self.set_passthrough_cols(passthrough_cols)
 
+    def _is_integer_type(self, column_type: T.DataType) -> bool:
+        return (
+            isinstance(column_type, T.ByteType)
+            or isinstance(column_type, T.ShortType)
+            or isinstance(column_type, T.IntegerType)
+            or isinstance(column_type, T.LongType)
+        )
+
     def _reset(self) -> None:
         """
         Reset internal data-dependent state of the imputer, if necessary.
@@ -389,6 +399,22 @@ class SimpleImputer(base.BaseTransformer):
                 # Use `fillna` for replacing nans. Check if the column has a string data type, or coerce a float.
                 if not isinstance(input_col_datatypes[input_col], T.StringType):
                     statistic = float(statistic)
+
+                if self._is_integer_type(input_col_datatypes[input_col]):
+                    if statistic.is_integer():
+                        statistic = int(statistic)
+                    else:
+                        warnings.warn(
+                            formatting.unwrap(
+                                f"""
+                                Integer column may not be imputed with a non-integer value {statistic}.
+                                In order to impute a non-integer value, convert the column to FloatType before imputing.
+                                """
+                            ),
+                            category=UserWarning,
+                            stacklevel=1,
+                        )
+
                 transformed_dataset = transformed_dataset.na.fill({output_col: statistic})
             else:
                 transformed_dataset = transformed_dataset.na.replace(

snowflake/ml/modeling/kernel_approximation/additive_chi2_sampler.py

@@ -76,8 +76,10 @@ class AdditiveChi2Sampler(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/kernel_approximation/nystroem.py

@@ -76,8 +76,10 @@ class Nystroem(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/kernel_approximation/polynomial_count_sketch.py

@@ -76,8 +76,10 @@ class PolynomialCountSketch(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/kernel_approximation/rbf_sampler.py

@@ -76,8 +76,10 @@ class RBFSampler(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/kernel_approximation/skewed_chi2_sampler.py

@@ -76,8 +76,10 @@ class SkewedChi2Sampler(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/linear_model/sgd_one_class_svm.py

@@ -76,8 +76,10 @@ class SGDOneClassSVM(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/manifold/isomap.py

@@ -76,8 +76,10 @@ class Isomap(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/manifold/mds.py

@@ -76,8 +76,10 @@ class MDS(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/manifold/spectral_embedding.py

@@ -76,8 +76,10 @@ class SpectralEmbedding(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/manifold/tsne.py

@@ -76,8 +76,10 @@ class TSNE(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/metrics/ranking.py

@@ -102,6 +102,7 @@ def precision_recall_curve(
         ],
         statement_params=statement_params,
         anonymous=True,
+        execute_as="caller",
     )
     def precision_recall_curve_anon_sproc(session: snowpark.Session) -> bytes:
         for query in queries[:-1]:
@@ -249,6 +250,7 @@ def roc_auc_score(
         ],
         statement_params=statement_params,
         anonymous=True,
+        execute_as="caller",
     )
     def roc_auc_score_anon_sproc(session: snowpark.Session) -> bytes:
         for query in queries[:-1]:
@@ -352,6 +354,7 @@ def roc_curve(
         ],
         statement_params=statement_params,
         anonymous=True,
+        execute_as="caller",
     )
     def roc_curve_anon_sproc(session: snowpark.Session) -> bytes:
         for query in queries[:-1]:

snowflake/ml/modeling/metrics/regression.py

@@ -87,6 +87,7 @@ def d2_absolute_error_score(
         ],
         statement_params=statement_params,
         anonymous=True,
+        execute_as="caller",
     )
     def d2_absolute_error_score_anon_sproc(session: snowpark.Session) -> bytes:
         for query in queries[:-1]:
@@ -184,6 +185,7 @@ def d2_pinball_score(
         ],
         statement_params=statement_params,
         anonymous=True,
+        execute_as="caller",
     )
     def d2_pinball_score_anon_sproc(session: snowpark.Session) -> bytes:
         for query in queries[:-1]:
@@ -299,6 +301,7 @@ def explained_variance_score(
         ],
         statement_params=statement_params,
         anonymous=True,
+        execute_as="caller",
     )
     def explained_variance_score_anon_sproc(session: snowpark.Session) -> bytes:
         for query in queries[:-1]:

snowflake/ml/modeling/mixture/bayesian_gaussian_mixture.py

@@ -76,8 +76,10 @@ class BayesianGaussianMixture(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/mixture/gaussian_mixture.py

@@ -76,8 +76,10 @@ class GaussianMixture(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/neighbors/kernel_density.py

@@ -76,8 +76,10 @@ class KernelDensity(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/neighbors/local_outlier_factor.py

@@ -76,8 +76,10 @@ class LocalOutlierFactor(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/neighbors/nearest_neighbors.py

@@ -76,8 +76,10 @@ class NearestNeighbors(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/neural_network/bernoulli_rbm.py

@@ -76,8 +76,10 @@ class BernoulliRBM(BaseTransformer):
         initialization with the `set_input_cols` method.
     
     label_cols: Optional[Union[str, List[str]]]
-        This parameter is optional and will be ignored during fit. It is present here for API consistency by convention.
-                    
+        A string or list of strings representing column names that contain labels.
+        Label columns must be specified with this parameter during initialization
+        or with the `set_label_cols` method before fitting.
+
     output_cols: Optional[Union[str, List[str]]]
         A string or list of strings representing column names that will store the
         output of predict and transform operations. The length of output_cols must

snowflake/ml/modeling/pipeline/pipeline.py

@@ -99,10 +99,6 @@ class Pipeline(base.BaseTransformer):
         must implement `fit` and `transform` methods.
         The final step can be a transform or estimator, that is, it must implement
         `fit` and `transform`/`predict` methods.
-        TODO: SKLearn pipeline expects last step(and only the last step) to be an estimator obj or a dummy
-                estimator(like None or passthrough). Currently this Pipeline class works with a list of all
-                transforms or a list of transforms ending with an estimator. Should we change this implementation
-                to only work with list of steps ending with an estimator or a dummy estimator like SKLearn?
 
         Args:
             steps: List of (name, transform) tuples (implementing `fit`/`transform`) that
@@ -111,6 +107,10 @@ class Pipeline(base.BaseTransformer):
         """
         super().__init__()
         self.steps = steps
+        # TODO(snandamuri): SKLearn pipeline expects last step(and only the last step) to be an estimator obj or a dummy
+        # estimator(like None or passthrough). Currently this Pipeline class works with a list of all
+        # transforms or a list of transforms ending with an estimator. Should we change this implementation
+        # to only work with list of steps ending with an estimator or a dummy estimator like SKLearn?
         self._is_final_step_estimator = Pipeline._is_estimator(steps[-1][1])
         self._is_fitted = False
         self._feature_names_in: List[np.ndarray[Any, np.dtype[Any]]] = []
@@ -378,6 +378,7 @@ class Pipeline(base.BaseTransformer):
                 anonymous=True,
                 imports=imports,  # type: ignore[arg-type]
                 statement_params=sproc_statement_params,
+                execute_as="caller",
             )
 
             sproc_export_file_name: str = pipeline_within_one_sproc(