snowflake-ml-python 1.7.2__py3-none-any.whl → 1.7.4__py3-none-any.whl

snowflake/ml/modeling/_internal/model_transformer_builder.py

@@ -1,16 +1,11 @@
-import os
 from typing import Optional, Union
 
 import pandas as pd
 
 from snowflake import snowpark
-from snowflake.ml.modeling._internal.constants import IN_ML_RUNTIME_ENV_VAR
 from snowflake.ml.modeling._internal.local_implementations.pandas_handlers import (
     PandasTransformHandlers,
 )
-from snowflake.ml.modeling._internal.ml_runtime_implementations.ml_runtime_handlers import (
-    MLRuntimeTransformHandlers,
-)
 from snowflake.ml.modeling._internal.snowpark_implementations.snowpark_handlers import (
     SnowparkTransformHandlers,
 )
@@ -63,14 +58,6 @@ class ModelTransformerBuilder:
             )
 
         elif isinstance(dataset, snowpark.DataFrame):
-            if os.environ.get(IN_ML_RUNTIME_ENV_VAR):
-                return MLRuntimeTransformHandlers(
-                    dataset=dataset,
-                    estimator=estimator,
-                    class_name=class_name,
-                    subproject=subproject,
-                    autogenerated=autogenerated,
-                )
             return SnowparkTransformHandlers(
                 dataset=dataset,
                 estimator=estimator,

snowflake/ml/modeling/calibration/calibrated_classifier_cv.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.calibration".replace("sk
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class CalibratedClassifierCV(BaseTransformer):
     r"""Probability calibration with isotonic regression or logistic regression
     For more details on this class, see [sklearn.calibration.CalibratedClassifierCV]
@@ -465,7 +468,7 @@ class CalibratedClassifierCV(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`.
@@ -1126,7 +1129,7 @@ class CalibratedClassifierCV(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
@@ -1134,7 +1137,7 @@ class CalibratedClassifierCV(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/cluster/affinity_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.cluster".replace("sklear
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class AffinityPropagation(BaseTransformer):
     r"""Perform Affinity Propagation Clustering of data
     For more details on this class, see [sklearn.cluster.AffinityPropagation]
@@ -449,7 +452,7 @@ class AffinityPropagation(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`.
@@ -1106,7 +1109,7 @@ class AffinityPropagation(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
@@ -1114,7 +1117,7 @@ class AffinityPropagation(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/cluster/agglomerative_clustering.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.cluster".replace("sklear
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class AgglomerativeClustering(BaseTransformer):
     r"""Agglomerative Clustering
     For more details on this class, see [sklearn.cluster.AgglomerativeClustering]
@@ -478,7 +481,7 @@ class AgglomerativeClustering(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`.
@@ -1135,7 +1138,7 @@ class AgglomerativeClustering(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
@@ -1143,7 +1146,7 @@ class AgglomerativeClustering(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/cluster/birch.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.cluster".replace("sklear
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class Birch(BaseTransformer):
     r"""Implements the BIRCH clustering algorithm
     For more details on this class, see [sklearn.cluster.Birch]
@@ -442,7 +445,7 @@ class Birch(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`.
@@ -1101,7 +1104,7 @@ class Birch(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
@@ -1109,7 +1112,7 @@ class Birch(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/cluster/bisecting_k_means.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.cluster".replace("sklear
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class BisectingKMeans(BaseTransformer):
     r"""Bisecting K-Means clustering
     For more details on this class, see [sklearn.cluster.BisectingKMeans]
@@ -491,7 +494,7 @@ class BisectingKMeans(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`.
@@ -1152,7 +1155,7 @@ class BisectingKMeans(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
@@ -1160,7 +1163,7 @@ class BisectingKMeans(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/cluster/dbscan.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.cluster".replace("sklear
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class DBSCAN(BaseTransformer):
     r"""Perform DBSCAN clustering from vector array or distance matrix
     For more details on this class, see [sklearn.cluster.DBSCAN]
@@ -458,7 +461,7 @@ class DBSCAN(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`.
@@ -1115,7 +1118,7 @@ class DBSCAN(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
@@ -1123,7 +1126,7 @@ class DBSCAN(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/cluster/feature_agglomeration.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.cluster".replace("sklear
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class FeatureAgglomeration(BaseTransformer):
     r"""Agglomerate features
     For more details on this class, see [sklearn.cluster.FeatureAgglomeration]
@@ -477,7 +480,7 @@ class FeatureAgglomeration(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`.
@@ -1136,7 +1139,7 @@ class FeatureAgglomeration(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
@@ -1144,7 +1147,7 @@ class FeatureAgglomeration(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/cluster/k_means.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.cluster".replace("sklear
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class KMeans(BaseTransformer):
     r"""K-Means clustering
     For more details on this class, see [sklearn.cluster.KMeans]
@@ -481,7 +484,7 @@ class KMeans(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`.
@@ -1142,7 +1145,7 @@ class KMeans(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
@@ -1150,7 +1153,7 @@ class KMeans(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/cluster/mean_shift.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.cluster".replace("sklear
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class MeanShift(BaseTransformer):
     r"""Mean shift clustering using a flat kernel
     For more details on this class, see [sklearn.cluster.MeanShift]
@@ -460,7 +463,7 @@ class MeanShift(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`.
@@ -1117,7 +1120,7 @@ class MeanShift(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
@@ -1125,7 +1128,7 @@ class MeanShift(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/cluster/mini_batch_k_means.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.cluster".replace("sklear
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class MiniBatchKMeans(BaseTransformer):
     r"""Mini-Batch K-Means clustering
     For more details on this class, see [sklearn.cluster.MiniBatchKMeans]
@@ -512,7 +515,7 @@ class MiniBatchKMeans(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`.
@@ -1173,7 +1176,7 @@ class MiniBatchKMeans(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
@@ -1181,7 +1184,7 @@ class MiniBatchKMeans(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/cluster/optics.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.cluster".replace("sklear
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class OPTICS(BaseTransformer):
     r"""Estimate clustering structure from vector array
     For more details on this class, see [sklearn.cluster.OPTICS]
@@ -528,7 +531,7 @@ class OPTICS(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`.
@@ -1185,7 +1188,7 @@ class OPTICS(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
@@ -1193,7 +1196,7 @@ class OPTICS(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/cluster/spectral_biclustering.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.cluster".replace("sklear
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class SpectralBiclustering(BaseTransformer):
     r"""Spectral biclustering (Kluger, 2003)
     For more details on this class, see [sklearn.cluster.SpectralBiclustering]
@@ -466,7 +469,7 @@ class SpectralBiclustering(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`.
@@ -1121,7 +1124,7 @@ class SpectralBiclustering(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
@@ -1129,7 +1132,7 @@ class SpectralBiclustering(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/cluster/spectral_clustering.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.cluster".replace("sklear
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
+INFER_SIGNATURE_MAX_ROWS = 100
+
 class SpectralClustering(BaseTransformer):
     r"""Apply clustering to a projection of the normalized Laplacian
     For more details on this class, see [sklearn.cluster.SpectralClustering]
@@ -525,7 +528,7 @@ class SpectralClustering(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`.
@@ -1182,7 +1185,7 @@ class SpectralClustering(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
@@ -1190,7 +1193,7 @@ class SpectralClustering(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(