snowflake-ml-python 1.7.3__py3-none-any.whl → 1.7.5__py3-none-any.whl

snowflake/ml/modeling/neighbors/radius_neighbors_classifier.py

@@ -37,6 +37,7 @@ from snowflake.ml.model.model_signature import (
     FeatureSpec,
     ModelSignature,
     _infer_signature,
+    _truncate_data,
     _rename_signature_with_snowflake_identifiers,
 )
 
@@ -57,6 +58,8 @@ _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.neighbors".replace("skle
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class RadiusNeighborsClassifier(BaseTransformer):
     r"""Classifier implementing a vote among neighbors within a given radius
     For more details on this class, see [sklearn.neighbors.RadiusNeighborsClassifier]
@@ -495,7 +498,7 @@ class RadiusNeighborsClassifier(BaseTransformer):
                 elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
                     expected_dtype = "array"
                 else:
-                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
+                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True)]
                     # We can only infer the output types from the input types if the following two statemetns are true:
                     # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
                     # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
@@ -1156,7 +1159,7 @@ class RadiusNeighborsClassifier(BaseTransformer):
 
         PROB_FUNCTIONS = ["predict_log_proba", "predict_proba", "decision_function"]
 
-        inputs = list(_infer_signature(dataset[self.input_cols], "input", use_snowflake_identifiers=True))
+        inputs = list(_infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "input", use_snowflake_identifiers=True))
         outputs: List[BaseFeatureSpec] = []
         if hasattr(self, "predict"):
             # keep mypy happy
@@ -1164,7 +1167,7 @@ class RadiusNeighborsClassifier(BaseTransformer):
             # For classifier, the type of predict is the same as the type of label
             if self._sklearn_object._estimator_type == "classifier":
                 # label columns is the desired type for output
-                outputs = list(_infer_signature(dataset[self.label_cols], "output", use_snowflake_identifiers=True))
+                outputs = list(_infer_signature(_truncate_data(dataset[self.label_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True))
                 # rename the output columns
                 outputs = list(model_signature_utils.rename_features(outputs, self.output_cols))
                 self._model_signature_dict["predict"] = ModelSignature(

snowflake/ml/modeling/neighbors/radius_neighbors_regressor.py

@@ -37,6 +37,7 @@ from snowflake.ml.model.model_signature import (
     FeatureSpec,
     ModelSignature,
     _infer_signature,
+    _truncate_data,
     _rename_signature_with_snowflake_identifiers,
 )
 
@@ -57,6 +58,8 @@ _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.neighbors".replace("skle
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class RadiusNeighborsRegressor(BaseTransformer):
     r"""Regression based on neighbors within a fixed radius
     For more details on this class, see [sklearn.neighbors.RadiusNeighborsRegressor]
@@ -480,7 +483,7 @@ class RadiusNeighborsRegressor(BaseTransformer):
                 elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
                     expected_dtype = "array"
                 else:
-                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
+                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True)]
                     # We can only infer the output types from the input types if the following two statemetns are true:
                     # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
                     # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
@@ -1137,7 +1140,7 @@ class RadiusNeighborsRegressor(BaseTransformer):
 
         PROB_FUNCTIONS = ["predict_log_proba", "predict_proba", "decision_function"]
 
-        inputs = list(_infer_signature(dataset[self.input_cols], "input", use_snowflake_identifiers=True))
+        inputs = list(_infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "input", use_snowflake_identifiers=True))
         outputs: List[BaseFeatureSpec] = []
         if hasattr(self, "predict"):
             # keep mypy happy
@@ -1145,7 +1148,7 @@ class RadiusNeighborsRegressor(BaseTransformer):
             # For classifier, the type of predict is the same as the type of label
             if self._sklearn_object._estimator_type == "classifier":
                 # label columns is the desired type for output
-                outputs = list(_infer_signature(dataset[self.label_cols], "output", use_snowflake_identifiers=True))
+                outputs = list(_infer_signature(_truncate_data(dataset[self.label_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True))
                 # rename the output columns
                 outputs = list(model_signature_utils.rename_features(outputs, self.output_cols))
                 self._model_signature_dict["predict"] = ModelSignature(

snowflake/ml/modeling/neural_network/bernoulli_rbm.py

@@ -37,6 +37,7 @@ from snowflake.ml.model.model_signature import (
     FeatureSpec,
     ModelSignature,
     _infer_signature,
+    _truncate_data,
     _rename_signature_with_snowflake_identifiers,
 )
 
@@ -57,6 +58,8 @@ _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.neural_network".replace(
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class BernoulliRBM(BaseTransformer):
     r"""Bernoulli Restricted Boltzmann Machine (RBM)
     For more details on this class, see [sklearn.neural_network.BernoulliRBM]
@@ -439,7 +442,7 @@ class BernoulliRBM(BaseTransformer):
                 elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
                     expected_dtype = "array"
                 else:
-                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
+                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True)]
                     # We can only infer the output types from the input types if the following two statemetns are true:
                     # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
                     # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
@@ -1098,7 +1101,7 @@ class BernoulliRBM(BaseTransformer):
 
         PROB_FUNCTIONS = ["predict_log_proba", "predict_proba", "decision_function"]
 
-        inputs = list(_infer_signature(dataset[self.input_cols], "input", use_snowflake_identifiers=True))
+        inputs = list(_infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "input", use_snowflake_identifiers=True))
         outputs: List[BaseFeatureSpec] = []
         if hasattr(self, "predict"):
             # keep mypy happy
@@ -1106,7 +1109,7 @@ class BernoulliRBM(BaseTransformer):
             # For classifier, the type of predict is the same as the type of label
             if self._sklearn_object._estimator_type == "classifier":
                 # label columns is the desired type for output
-                outputs = list(_infer_signature(dataset[self.label_cols], "output", use_snowflake_identifiers=True))
+                outputs = list(_infer_signature(_truncate_data(dataset[self.label_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True))
                 # rename the output columns
                 outputs = list(model_signature_utils.rename_features(outputs, self.output_cols))
                 self._model_signature_dict["predict"] = ModelSignature(

snowflake/ml/modeling/neural_network/mlp_classifier.py

@@ -37,6 +37,7 @@ from snowflake.ml.model.model_signature import (
     FeatureSpec,
     ModelSignature,
     _infer_signature,
+    _truncate_data,
     _rename_signature_with_snowflake_identifiers,
 )
 
@@ -57,6 +58,8 @@ _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.neural_network".replace(
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class MLPClassifier(BaseTransformer):
     r"""Multi-layer Perceptron classifier
     For more details on this class, see [sklearn.neural_network.MLPClassifier]
@@ -598,7 +601,7 @@ class MLPClassifier(BaseTransformer):
                 elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
                     expected_dtype = "array"
                 else:
-                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
+                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True)]
                     # We can only infer the output types from the input types if the following two statemetns are true:
                     # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
                     # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
@@ -1259,7 +1262,7 @@ class MLPClassifier(BaseTransformer):
 
         PROB_FUNCTIONS = ["predict_log_proba", "predict_proba", "decision_function"]
 
-        inputs = list(_infer_signature(dataset[self.input_cols], "input", use_snowflake_identifiers=True))
+        inputs = list(_infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "input", use_snowflake_identifiers=True))
         outputs: List[BaseFeatureSpec] = []
         if hasattr(self, "predict"):
             # keep mypy happy
@@ -1267,7 +1270,7 @@ class MLPClassifier(BaseTransformer):
             # For classifier, the type of predict is the same as the type of label
             if self._sklearn_object._estimator_type == "classifier":
                 # label columns is the desired type for output
-                outputs = list(_infer_signature(dataset[self.label_cols], "output", use_snowflake_identifiers=True))
+                outputs = list(_infer_signature(_truncate_data(dataset[self.label_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True))
                 # rename the output columns
                 outputs = list(model_signature_utils.rename_features(outputs, self.output_cols))
                 self._model_signature_dict["predict"] = ModelSignature(

snowflake/ml/modeling/neural_network/mlp_regressor.py

@@ -37,6 +37,7 @@ from snowflake.ml.model.model_signature import (
     FeatureSpec,
     ModelSignature,
     _infer_signature,
+    _truncate_data,
     _rename_signature_with_snowflake_identifiers,
 )
 
@@ -57,6 +58,8 @@ _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.neural_network".replace(
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class MLPRegressor(BaseTransformer):
     r"""Multi-layer Perceptron regressor
     For more details on this class, see [sklearn.neural_network.MLPRegressor]
@@ -591,7 +594,7 @@ class MLPRegressor(BaseTransformer):
                 elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
                     expected_dtype = "array"
                 else:
-                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
+                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True)]
                     # We can only infer the output types from the input types if the following two statemetns are true:
                     # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
                     # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
@@ -1248,7 +1251,7 @@ class MLPRegressor(BaseTransformer):
 
         PROB_FUNCTIONS = ["predict_log_proba", "predict_proba", "decision_function"]
 
-        inputs = list(_infer_signature(dataset[self.input_cols], "input", use_snowflake_identifiers=True))
+        inputs = list(_infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "input", use_snowflake_identifiers=True))
         outputs: List[BaseFeatureSpec] = []
         if hasattr(self, "predict"):
             # keep mypy happy
@@ -1256,7 +1259,7 @@ class MLPRegressor(BaseTransformer):
             # For classifier, the type of predict is the same as the type of label
             if self._sklearn_object._estimator_type == "classifier":
                 # label columns is the desired type for output
-                outputs = list(_infer_signature(dataset[self.label_cols], "output", use_snowflake_identifiers=True))
+                outputs = list(_infer_signature(_truncate_data(dataset[self.label_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True))
                 # rename the output columns
                 outputs = list(model_signature_utils.rename_features(outputs, self.output_cols))
                 self._model_signature_dict["predict"] = ModelSignature(

snowflake/ml/modeling/pipeline/pipeline.py

@@ -20,7 +20,11 @@ from snowflake.ml._internal.exceptions import error_codes, exceptions
 from snowflake.ml._internal.lineage import lineage_utils
 from snowflake.ml._internal.utils import snowpark_dataframe_utils, temp_file_utils
 from snowflake.ml.data import data_source
-from snowflake.ml.model.model_signature import ModelSignature, _infer_signature
+from snowflake.ml.model.model_signature import (
+    ModelSignature,
+    _infer_signature,
+    _truncate_data,
+)
 from snowflake.ml.modeling._internal.model_transformer_builder import (
     ModelTransformerBuilder,
 )
@@ -31,6 +35,8 @@ from snowflake.snowpark._internal import utils as snowpark_utils
 _PROJECT = "ModelDevelopment"
 _SUBPROJECT = "Framework"
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 
 def _final_step_has(attr: str) -> Callable[..., bool]:
     """Check that final_estimator has `attr`. Used together with `available_if` in `Pipeline`."""
@@ -848,6 +854,7 @@ class Pipeline(base.BaseTransformer):
         # Create a fitted sklearn pipeline object by translating each non-estimator step in pipeline with with
         # a fitted column transformer.
         sksteps = []
+        i = 0
         for i, (name, trans) in enumerate(self._get_transformers()):
             if isinstance(trans, base.BaseTransformer):
                 trans = self._construct_fitted_column_transformer_object(
@@ -885,13 +892,31 @@ class Pipeline(base.BaseTransformer):
         self._model_signature_dict = dict()
 
         input_columns = self._get_sanitized_list_of_columns(dataset.columns)
-        inputs_signature = _infer_signature(dataset[input_columns], "input", use_snowflake_identifiers=True)
+        inputs_signature = _infer_signature(
+            _truncate_data(dataset[input_columns], INFER_SIGNATURE_MAX_ROWS), "input", use_snowflake_identifiers=True
+        )
 
         estimator_step = self._get_estimator()
         if estimator_step:
             estimator_signatures = estimator_step[1].model_signatures
             for method, signature in estimator_signatures.items():
-                self._model_signature_dict[method] = ModelSignature(inputs=inputs_signature, outputs=signature.outputs)
+                # Add the inferred input signature to the model signature dictionary for each method
+                self._model_signature_dict[method] = ModelSignature(
+                    inputs=inputs_signature,
+                    outputs=(
+                        # If _drop_input_cols is True, do not include any input columns in the output signature
+                        []
+                        if self._drop_input_cols
+                        else [
+                            # Include input columns in the output signature if they are not already present
+                            # Those already present means they are overwritten by the output of the estimator
+                            spec
+                            for spec in inputs_signature
+                            if spec.name not in [_spec.name for _spec in signature.outputs]
+                        ]
+                    )
+                    + signature.outputs,  # Append the existing output signature
+                )
 
     @property
     def model_signatures(self) -> Dict[str, ModelSignature]:

snowflake/ml/modeling/preprocessing/polynomial_features.py

@@ -37,6 +37,7 @@ from snowflake.ml.model.model_signature import (
     FeatureSpec,
     ModelSignature,
     _infer_signature,
+    _truncate_data,
     _rename_signature_with_snowflake_identifiers,
 )
 
@@ -57,6 +58,8 @@ _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.preprocessing".replace("
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class PolynomialFeatures(BaseTransformer):
     r"""Generate polynomial and interaction features
     For more details on this class, see [sklearn.preprocessing.PolynomialFeatures]
@@ -334,7 +337,7 @@ class PolynomialFeatures(BaseTransformer):
         transform_kwargs: BatchInferenceKwargsTypedDict = dict()   
                                 
         if isinstance(dataset, DataFrame):
-            expected_type_inferred = ""
+            expected_type_inferred = "float"
             # when it is classifier, infer the datatype from label columns
             if expected_type_inferred == "" and 'predict' in self.model_signatures:
                 # Batch inference takes a single expected output column type. Use the first columns type for now.
@@ -412,7 +415,7 @@ class PolynomialFeatures(BaseTransformer):
         # are specific to the type of dataset used. 
         transform_kwargs: BatchInferenceKwargsTypedDict = dict()
         if isinstance(dataset, DataFrame):
-            expected_dtype = ""
+            expected_dtype = "float"
             if False:  # is child of _BaseHeterogeneousEnsemble
                 # transform() method of HeterogeneousEnsemble estimators return responses of varying shapes
                 # from (n_samples, n_estimators) to (n_samples, n_estimators * n_classes) (and everything in between)
@@ -429,7 +432,7 @@ class PolynomialFeatures(BaseTransformer):
                 elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
                     expected_dtype = "array"
                 else:
-                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
+                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True)]
                     # We can only infer the output types from the input types if the following two statemetns are true:
                     # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
                     # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
@@ -1086,7 +1089,7 @@ class PolynomialFeatures(BaseTransformer):
 
         PROB_FUNCTIONS = ["predict_log_proba", "predict_proba", "decision_function"]
 
-        inputs = list(_infer_signature(dataset[self.input_cols], "input", use_snowflake_identifiers=True))
+        inputs = list(_infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "input", use_snowflake_identifiers=True))
         outputs: List[BaseFeatureSpec] = []
         if hasattr(self, "predict"):
             # keep mypy happy
@@ -1094,7 +1097,7 @@ class PolynomialFeatures(BaseTransformer):
             # For classifier, the type of predict is the same as the type of label
             if self._sklearn_object._estimator_type == "classifier":
                 # label columns is the desired type for output
-                outputs = list(_infer_signature(dataset[self.label_cols], "output", use_snowflake_identifiers=True))
+                outputs = list(_infer_signature(_truncate_data(dataset[self.label_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True))
                 # rename the output columns
                 outputs = list(model_signature_utils.rename_features(outputs, self.output_cols))
                 self._model_signature_dict["predict"] = ModelSignature(

snowflake/ml/modeling/semi_supervised/label_propagation.py

@@ -37,6 +37,7 @@ from snowflake.ml.model.model_signature import (
     FeatureSpec,
     ModelSignature,
     _infer_signature,
+    _truncate_data,
     _rename_signature_with_snowflake_identifiers,
 )
 
@@ -57,6 +58,8 @@ _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.semi_supervised".replace
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class LabelPropagation(BaseTransformer):
     r"""Label Propagation classifier
     For more details on this class, see [sklearn.semi_supervised.LabelPropagation]
@@ -433,7 +436,7 @@ class LabelPropagation(BaseTransformer):
                 elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
                     expected_dtype = "array"
                 else:
-                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
+                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True)]
                     # We can only infer the output types from the input types if the following two statemetns are true:
                     # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
                     # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
@@ -1094,7 +1097,7 @@ class LabelPropagation(BaseTransformer):
 
         PROB_FUNCTIONS = ["predict_log_proba", "predict_proba", "decision_function"]
 
-        inputs = list(_infer_signature(dataset[self.input_cols], "input", use_snowflake_identifiers=True))
+        inputs = list(_infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "input", use_snowflake_identifiers=True))
         outputs: List[BaseFeatureSpec] = []
         if hasattr(self, "predict"):
             # keep mypy happy
@@ -1102,7 +1105,7 @@ class LabelPropagation(BaseTransformer):
             # For classifier, the type of predict is the same as the type of label
             if self._sklearn_object._estimator_type == "classifier":
                 # label columns is the desired type for output
-                outputs = list(_infer_signature(dataset[self.label_cols], "output", use_snowflake_identifiers=True))
+                outputs = list(_infer_signature(_truncate_data(dataset[self.label_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True))
                 # rename the output columns
                 outputs = list(model_signature_utils.rename_features(outputs, self.output_cols))
                 self._model_signature_dict["predict"] = ModelSignature(

snowflake/ml/modeling/semi_supervised/label_spreading.py

@@ -37,6 +37,7 @@ from snowflake.ml.model.model_signature import (
     FeatureSpec,
     ModelSignature,
     _infer_signature,
+    _truncate_data,
     _rename_signature_with_snowflake_identifiers,
 )
 
@@ -57,6 +58,8 @@ _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.semi_supervised".replace
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class LabelSpreading(BaseTransformer):
     r"""LabelSpreading model for semi-supervised learning
     For more details on this class, see [sklearn.semi_supervised.LabelSpreading]
@@ -442,7 +445,7 @@ class LabelSpreading(BaseTransformer):
                 elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
                     expected_dtype = "array"
                 else:
-                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
+                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True)]
                     # We can only infer the output types from the input types if the following two statemetns are true:
                     # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
                     # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
@@ -1103,7 +1106,7 @@ class LabelSpreading(BaseTransformer):
 
         PROB_FUNCTIONS = ["predict_log_proba", "predict_proba", "decision_function"]
 
-        inputs = list(_infer_signature(dataset[self.input_cols], "input", use_snowflake_identifiers=True))
+        inputs = list(_infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "input", use_snowflake_identifiers=True))
         outputs: List[BaseFeatureSpec] = []
         if hasattr(self, "predict"):
             # keep mypy happy
@@ -1111,7 +1114,7 @@ class LabelSpreading(BaseTransformer):
             # For classifier, the type of predict is the same as the type of label
             if self._sklearn_object._estimator_type == "classifier":
                 # label columns is the desired type for output
-                outputs = list(_infer_signature(dataset[self.label_cols], "output", use_snowflake_identifiers=True))
+                outputs = list(_infer_signature(_truncate_data(dataset[self.label_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True))
                 # rename the output columns
                 outputs = list(model_signature_utils.rename_features(outputs, self.output_cols))
                 self._model_signature_dict["predict"] = ModelSignature(

snowflake/ml/modeling/svm/linear_svc.py

@@ -37,6 +37,7 @@ from snowflake.ml.model.model_signature import (
     FeatureSpec,
     ModelSignature,
     _infer_signature,
+    _truncate_data,
     _rename_signature_with_snowflake_identifiers,
 )
 
@@ -57,6 +58,8 @@ _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.svm".replace("sklearn.",
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class LinearSVC(BaseTransformer):
     r"""Linear Support Vector Classification
     For more details on this class, see [sklearn.svm.LinearSVC]
@@ -507,7 +510,7 @@ class LinearSVC(BaseTransformer):
                 elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
                     expected_dtype = "array"
                 else:
-                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
+                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True)]
                     # We can only infer the output types from the input types if the following two statemetns are true:
                     # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
                     # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
@@ -1166,7 +1169,7 @@ class LinearSVC(BaseTransformer):
 
         PROB_FUNCTIONS = ["predict_log_proba", "predict_proba", "decision_function"]
 
-        inputs = list(_infer_signature(dataset[self.input_cols], "input", use_snowflake_identifiers=True))
+        inputs = list(_infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "input", use_snowflake_identifiers=True))
         outputs: List[BaseFeatureSpec] = []
         if hasattr(self, "predict"):
             # keep mypy happy
@@ -1174,7 +1177,7 @@ class LinearSVC(BaseTransformer):
             # For classifier, the type of predict is the same as the type of label
             if self._sklearn_object._estimator_type == "classifier":
                 # label columns is the desired type for output
-                outputs = list(_infer_signature(dataset[self.label_cols], "output", use_snowflake_identifiers=True))
+                outputs = list(_infer_signature(_truncate_data(dataset[self.label_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True))
                 # rename the output columns
                 outputs = list(model_signature_utils.rename_features(outputs, self.output_cols))
                 self._model_signature_dict["predict"] = ModelSignature(

snowflake/ml/modeling/svm/linear_svr.py

@@ -37,6 +37,7 @@ from snowflake.ml.model.model_signature import (
     FeatureSpec,
     ModelSignature,
     _infer_signature,
+    _truncate_data,
     _rename_signature_with_snowflake_identifiers,
 )
 
@@ -57,6 +58,8 @@ _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.svm".replace("sklearn.",
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class LinearSVR(BaseTransformer):
     r"""Linear Support Vector Regression
     For more details on this class, see [sklearn.svm.LinearSVR]
@@ -476,7 +479,7 @@ class LinearSVR(BaseTransformer):
                 elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
                     expected_dtype = "array"
                 else:
-                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
+                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True)]
                     # We can only infer the output types from the input types if the following two statemetns are true:
                     # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
                     # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
@@ -1133,7 +1136,7 @@ class LinearSVR(BaseTransformer):
 
         PROB_FUNCTIONS = ["predict_log_proba", "predict_proba", "decision_function"]
 
-        inputs = list(_infer_signature(dataset[self.input_cols], "input", use_snowflake_identifiers=True))
+        inputs = list(_infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "input", use_snowflake_identifiers=True))
         outputs: List[BaseFeatureSpec] = []
         if hasattr(self, "predict"):
             # keep mypy happy
@@ -1141,7 +1144,7 @@ class LinearSVR(BaseTransformer):
             # For classifier, the type of predict is the same as the type of label
             if self._sklearn_object._estimator_type == "classifier":
                 # label columns is the desired type for output
-                outputs = list(_infer_signature(dataset[self.label_cols], "output", use_snowflake_identifiers=True))
+                outputs = list(_infer_signature(_truncate_data(dataset[self.label_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True))
                 # rename the output columns
                 outputs = list(model_signature_utils.rename_features(outputs, self.output_cols))
                 self._model_signature_dict["predict"] = ModelSignature(

snowflake/ml/modeling/svm/nu_svc.py

@@ -37,6 +37,7 @@ from snowflake.ml.model.model_signature import (
     FeatureSpec,
     ModelSignature,
     _infer_signature,
+    _truncate_data,
     _rename_signature_with_snowflake_identifiers,
 )
 
@@ -57,6 +58,8 @@ _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.svm".replace("sklearn.",
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class NuSVC(BaseTransformer):
     r"""Nu-Support Vector Classification
     For more details on this class, see [sklearn.svm.NuSVC]
@@ -506,7 +509,7 @@ class NuSVC(BaseTransformer):
                 elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
                     expected_dtype = "array"
                 else:
-                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
+                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True)]
                     # We can only infer the output types from the input types if the following two statemetns are true:
                     # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
                     # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
@@ -1169,7 +1172,7 @@ class NuSVC(BaseTransformer):
 
         PROB_FUNCTIONS = ["predict_log_proba", "predict_proba", "decision_function"]
 
-        inputs = list(_infer_signature(dataset[self.input_cols], "input", use_snowflake_identifiers=True))
+        inputs = list(_infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "input", use_snowflake_identifiers=True))
         outputs: List[BaseFeatureSpec] = []
         if hasattr(self, "predict"):
             # keep mypy happy
@@ -1177,7 +1180,7 @@ class NuSVC(BaseTransformer):
             # For classifier, the type of predict is the same as the type of label
             if self._sklearn_object._estimator_type == "classifier":
                 # label columns is the desired type for output
-                outputs = list(_infer_signature(dataset[self.label_cols], "output", use_snowflake_identifiers=True))
+                outputs = list(_infer_signature(_truncate_data(dataset[self.label_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True))
                 # rename the output columns
                 outputs = list(model_signature_utils.rename_features(outputs, self.output_cols))
                 self._model_signature_dict["predict"] = ModelSignature(

snowflake/ml/modeling/svm/nu_svr.py

@@ -37,6 +37,7 @@ from snowflake.ml.model.model_signature import (
     FeatureSpec,
     ModelSignature,
     _infer_signature,
+    _truncate_data,
     _rename_signature_with_snowflake_identifiers,
 )
 
@@ -57,6 +58,8 @@ _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.svm".replace("sklearn.",
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class NuSVR(BaseTransformer):
     r"""Nu Support Vector Regression
     For more details on this class, see [sklearn.svm.NuSVR]
@@ -467,7 +470,7 @@ class NuSVR(BaseTransformer):
                 elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
                     expected_dtype = "array"
                 else:
-                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
+                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True)]
                     # We can only infer the output types from the input types if the following two statemetns are true:
                     # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
                     # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
@@ -1124,7 +1127,7 @@ class NuSVR(BaseTransformer):
 
         PROB_FUNCTIONS = ["predict_log_proba", "predict_proba", "decision_function"]
 
-        inputs = list(_infer_signature(dataset[self.input_cols], "input", use_snowflake_identifiers=True))
+        inputs = list(_infer_signature(_truncate_data(dataset[self.input_cols], INFER_SIGNATURE_MAX_ROWS), "input", use_snowflake_identifiers=True))
         outputs: List[BaseFeatureSpec] = []
         if hasattr(self, "predict"):
             # keep mypy happy
@@ -1132,7 +1135,7 @@ class NuSVR(BaseTransformer):
             # For classifier, the type of predict is the same as the type of label
             if self._sklearn_object._estimator_type == "classifier":
                 # label columns is the desired type for output
-                outputs = list(_infer_signature(dataset[self.label_cols], "output", use_snowflake_identifiers=True))
+                outputs = list(_infer_signature(_truncate_data(dataset[self.label_cols], INFER_SIGNATURE_MAX_ROWS), "output", use_snowflake_identifiers=True))
                 # rename the output columns
                 outputs = list(model_signature_utils.rename_features(outputs, self.output_cols))
                 self._model_signature_dict["predict"] = ModelSignature(