snowflake-ml-python 1.0.1__py3-none-any.whl → 1.0.3__py3-none-any.whl

snowflake/ml/modeling/preprocessing/one_hot_encoder.py

@@ -800,7 +800,7 @@ class OneHotEncoder(base.BaseTransformer):
         state_df = dataset._session.create_dataframe(state_pandas)
 
         transformed_dataset = dataset
-        origional_dataset_columns = transformed_dataset.columns[:]
+        original_dataset_columns = transformed_dataset.columns[:]
         all_output_cols = []
         for input_col in self.input_cols:
             output_cols = [
@@ -818,7 +818,7 @@ class OneHotEncoder(base.BaseTransformer):
 
         transformed_dataset = self._handle_unknown_in_transform(transformed_dataset)
         # Reorder columns. Passthrough columns are added at the right to the output of the transformers.
-        transformed_dataset = transformed_dataset[all_output_cols + origional_dataset_columns]
+        transformed_dataset = transformed_dataset[all_output_cols + original_dataset_columns]
         return transformed_dataset
 
     def _transform_snowpark_sparse_udf(self, dataset: snowpark.DataFrame) -> snowpark.DataFrame:
@@ -895,15 +895,14 @@ class OneHotEncoder(base.BaseTransformer):
             Output dataset.
         """
         encoder_sklearn = self.to_sklearn()
-
         transformed_dataset = encoder_sklearn.transform(dataset[self.input_cols])
 
-        if not self.sparse:
-            dataset = dataset.copy()
-            dataset[self.get_output_cols()] = transformed_dataset
-            return dataset
+        if self.sparse:
+            return transformed_dataset
 
-        return transformed_dataset
+        dataset = dataset.copy()
+        dataset[self.get_output_cols()] = transformed_dataset
+        return dataset
 
     def _create_unfitted_sklearn_object(self) -> preprocessing.OneHotEncoder:
         sklearn_args = self.get_sklearn_args(
@@ -1331,17 +1330,17 @@ class OneHotEncoder(base.BaseTransformer):
             Output columns.
         """
         if self.sparse:
-            output_cols = self.output_cols
-        else:
-            output_cols = (
-                [
-                    identifier.quote_name_without_upper_casing(col)
-                    for input_col in self.input_cols
-                    for col in self._dense_output_cols_mappings[input_col]
-                ]
-                if self._dense_output_cols_mappings
-                else []
-            )
+            return self.output_cols
+
+        output_cols = (
+            [
+                identifier.get_inferred_name(col)
+                for input_col in self.input_cols
+                for col in self._dense_output_cols_mappings[input_col]
+            ]
+            if self._dense_output_cols_mappings
+            else []
+        )
         return output_cols
 
     def _get_dense_output_cols_mappings(self) -> None:

snowflake/ml/modeling/preprocessing/ordinal_encoder.py

@@ -121,6 +121,7 @@ class OrdinalEncoder(base.BaseTransformer):
         self.categories_: Dict[str, type_utils.LiteralNDArrayType] = {}
         self._categories_list: List[type_utils.LiteralNDArrayType] = []
         self._missing_indices: Dict[int, int] = {}
+        self._infrequent_enabled = False
         self._vocab_table_name = "snowml_preprocessing_ordinal_encoder_temp_table_" + uuid.uuid4().hex
 
         self.set_input_cols(input_cols)
@@ -547,6 +548,7 @@ class OrdinalEncoder(base.BaseTransformer):
         if self._is_fitted:
             encoder.categories_ = self._categories_list
             encoder._missing_indices = self._missing_indices
+            encoder._infrequent_enabled = self._infrequent_enabled
         return encoder
 
     def _validate_keywords(self) -> None:

snowflake/ml/modeling/preprocessing/polynomial_features.py

@@ -7,6 +7,7 @@
 #
 import inspect
 import os
+import posixpath
 from typing import Iterable, Optional, Union, List, Any, Dict, Callable, Set
 from uuid import uuid4
 
@@ -27,6 +28,7 @@ from snowflake.ml._internal.utils.temp_file_utils import cleanup_temp_files, get
 from snowflake.snowpark import DataFrame, Session
 from snowflake.snowpark.functions import pandas_udf, sproc
 from snowflake.snowpark.types import PandasSeries
+from snowflake.snowpark._internal.type_utils import convert_sp_to_sf_type
 
 from snowflake.ml.model.model_signature import (
     DataType,
@@ -208,7 +210,6 @@ class PolynomialFeatures(BaseTransformer):
         sample_weight_col: Optional[str] = None,
     ) -> None:
         super().__init__()
-        self.id = str(uuid4()).replace("-", "_").upper()
         deps: Set[str] = set([f'numpy=={np.__version__}', f'scikit-learn=={sklearn.__version__}', f'cloudpickle=={cp.__version__}'])
         
         self._deps = list(deps)
@@ -231,6 +232,15 @@ class PolynomialFeatures(BaseTransformer):
         self.set_drop_input_cols(drop_input_cols)
         self.set_sample_weight_col(sample_weight_col)
 
+    def _get_rand_id(self) -> str:
+        """
+        Generate random id to be used in sproc and stage names.
+
+        Returns:
+            Random id string usable in sproc, table, and stage names.
+        """
+        return str(uuid4()).replace("-", "_").upper()
+
     def _infer_input_output_cols(self, dataset: Union[DataFrame, pd.DataFrame]) -> None:
         """
         Infer `self.input_cols` and `self.output_cols` if they are not explicitly set.
@@ -309,7 +319,7 @@ class PolynomialFeatures(BaseTransformer):
             cp.dump(self._sklearn_object, local_transform_file)
 
         # Create temp stage to run fit.
-        transform_stage_name = "SNOWML_TRANSFORM_{safe_id}".format(safe_id=self.id)
+        transform_stage_name = "SNOWML_TRANSFORM_{safe_id}".format(safe_id=self._get_rand_id())
         stage_creation_query = f"CREATE OR REPLACE TEMPORARY STAGE {transform_stage_name};"
         SqlResultValidator(
             session=session,
@@ -322,11 +332,12 @@ class PolynomialFeatures(BaseTransformer):
             expected_value=f"Stage area {transform_stage_name} successfully created."
         ).validate()
 
-        stage_transform_file_name = os.path.join(transform_stage_name, os.path.basename(local_transform_file_name))
+        # Use posixpath to construct stage paths
+        stage_transform_file_name = posixpath.join(transform_stage_name, os.path.basename(local_transform_file_name))
+        stage_result_file_name = posixpath.join(transform_stage_name, os.path.basename(local_transform_file_name))
         local_result_file_name = get_temp_file_path()
-        stage_result_file_name = os.path.join(transform_stage_name, os.path.basename(local_transform_file_name))
 
-        fit_sproc_name = "SNOWML_FIT_{safe_id}".format(safe_id=self.id)
+        fit_sproc_name = "SNOWML_FIT_{safe_id}".format(safe_id=self._get_rand_id())
         statement_params = telemetry.get_function_usage_statement_params(
             project=_PROJECT,
             subproject=_SUBPROJECT,
@@ -352,6 +363,7 @@ class PolynomialFeatures(BaseTransformer):
             replace=True,
             session=session,
             statement_params=statement_params,
+            anonymous=True
         )
         def fit_wrapper_sproc(
             session: Session,
@@ -360,7 +372,8 @@ class PolynomialFeatures(BaseTransformer):
             stage_result_file_name: str,
             input_cols: List[str],
             label_cols: List[str],
-            sample_weight_col: Optional[str]
+            sample_weight_col: Optional[str],
+            statement_params: Dict[str, str]
         ) -> str:
             import cloudpickle as cp
             import numpy as np
@@ -427,15 +440,15 @@ class PolynomialFeatures(BaseTransformer):
             api_calls=[Session.call],
             custom_tags=dict([("autogen", True)]),
         )
-        sproc_export_file_name = session.call(
-            fit_sproc_name,
+        sproc_export_file_name = fit_wrapper_sproc(
+            session,
             query,
             stage_transform_file_name,
             stage_result_file_name,
             identifier.get_unescaped_names(self.input_cols),
             identifier.get_unescaped_names(self.label_cols),
             identifier.get_unescaped_names(self.sample_weight_col),
-            statement_params=statement_params,
+            statement_params,
         )
 
         if "|" in sproc_export_file_name:
@@ -445,7 +458,7 @@ class PolynomialFeatures(BaseTransformer):
                 print("\n".join(fields[1:]))
 
         session.file.get(
-            os.path.join(stage_result_file_name, sproc_export_file_name),
+            posixpath.join(stage_result_file_name, sproc_export_file_name),
             local_result_file_name,
             statement_params=statement_params
         )
@@ -491,7 +504,7 @@ class PolynomialFeatures(BaseTransformer):
 
         # Register vectorized UDF for batch inference
         batch_inference_udf_name = "SNOWML_BATCH_INFERENCE_{safe_id}_{method}".format(
-                safe_id=self.id, method=inference_method)
+                safe_id=self._get_rand_id(), method=inference_method)
 
         # Need to do this since if we use self._sklearn_object directly in the UDF, Snowpark
         # will try to pickle all of self which fails.
@@ -583,7 +596,7 @@ class PolynomialFeatures(BaseTransformer):
             return transformed_pandas_df.to_dict("records")
 
         batch_inference_table_name = "SNOWML_BATCH_INFERENCE_INPUT_TABLE_{safe_id}".format(
-            safe_id=self.id
+            safe_id=self._get_rand_id()
         )
 
         pass_through_columns = self._get_pass_through_columns(dataset)
@@ -639,26 +652,37 @@ class PolynomialFeatures(BaseTransformer):
         # input cols need to match unquoted / quoted
         input_cols = self.input_cols
         unquoted_input_cols = identifier.get_unescaped_names(self.input_cols)
+        quoted_input_cols = identifier.get_escaped_names(unquoted_input_cols)
 
         estimator = self._sklearn_object
 
-        input_df = dataset[input_cols] # Select input columns with quoted column names.
-        if hasattr(estimator, "feature_names_in_"):
-            missing_features = []
-            for i, f in enumerate(getattr(estimator, "feature_names_in_")):
-                if i >= len(input_cols) or (input_cols[i] != f and unquoted_input_cols[i] != f):
-                    missing_features.append(f)
-
-            if len(missing_features) > 0:
-                raise ValueError(
-                    "The feature names should match with those that were passed during fit.\n"
-                    f"Features seen during fit call but not present in the input: {missing_features}\n"
-                    f"Features in the input dataframe : {input_cols}\n"
-                )
-            input_df.columns = getattr(estimator, "feature_names_in_")
-        else:
-            # Just rename the column names to unquoted identifiers.
-            input_df.columns = unquoted_input_cols # Replace the quoted columns identifier with unquoted column ids.
+        features_required_by_estimator =  getattr(estimator, "feature_names_in_") if hasattr(estimator, "feature_names_in_") else unquoted_input_cols
+        missing_features = []
+        features_in_dataset = set(dataset.columns)
+        columns_to_select = []
+        for i, f in enumerate(features_required_by_estimator):
+            if (
+                    i >= len(input_cols)
+                or (input_cols[i] != f and unquoted_input_cols[i] != f and quoted_input_cols[i] != f)
+                or (input_cols[i] not in features_in_dataset and unquoted_input_cols[i] not in features_in_dataset 
+                    and quoted_input_cols[i] not in features_in_dataset)
+                ):
+                missing_features.append(f)
+            elif input_cols[i] in features_in_dataset:
+                columns_to_select.append(input_cols[i])
+            elif unquoted_input_cols[i] in features_in_dataset:
+                columns_to_select.append(unquoted_input_cols[i])
+            else:
+                columns_to_select.append(quoted_input_cols[i])
+
+        if len(missing_features) > 0:
+            raise ValueError(
+                "The feature names should match with those that were passed during fit.\n"
+                f"Features seen during fit call but not present in the input: {missing_features}\n"
+                f"Features in the input dataframe : {input_cols}\n"
+            )
+        input_df = dataset[columns_to_select]
+        input_df.columns = features_required_by_estimator
 
         transformed_numpy_array = getattr(estimator, inference_method)(
             input_df
@@ -737,11 +761,18 @@ class PolynomialFeatures(BaseTransformer):
             Transformed dataset.
         """
         if isinstance(dataset, DataFrame):
+            expected_type_inferred = ""
+            # when it is classifier, infer the datatype from label columns
+            if expected_type_inferred == "" and 'predict' in self.model_signatures:
+                expected_type_inferred = convert_sp_to_sf_type(
+                    self.model_signatures['predict'].outputs[0].as_snowpark_type()
+                )
+            
             output_df = self._batch_inference(
                 dataset=dataset,
                 inference_method="predict",
                 expected_output_cols_list=self.output_cols,
-                expected_output_cols_type="",
+                expected_output_cols_type=expected_type_inferred,
             )
         elif isinstance(dataset, pd.DataFrame):
             output_df = self._sklearn_inference(
@@ -814,10 +845,10 @@ class PolynomialFeatures(BaseTransformer):
 
     def _get_output_column_names(self, output_cols_prefix: str) -> List[str]:
         """ Returns the list of output columns for predict_proba(), decision_function(), etc.. functions.
-        Returns an empty list if current object is not a classifier or not yet fitted.
+        Returns a list with output_cols_prefix as the only element if the estimator is not a classifier.
         """
         if getattr(self._sklearn_object, "classes_", None) is None:
-            return []
+            return [output_cols_prefix]
 
         classes = self._sklearn_object.classes_
         if isinstance(classes, numpy.ndarray):
@@ -1042,7 +1073,7 @@ class PolynomialFeatures(BaseTransformer):
             cp.dump(self._sklearn_object, local_score_file)
 
         # Create temp stage to run score.
-        score_stage_name = "SNOWML_SCORE_{safe_id}".format(safe_id=self.id)
+        score_stage_name = "SNOWML_SCORE_{safe_id}".format(safe_id=self._get_rand_id())
         session = dataset._session
         stage_creation_query = f"CREATE OR REPLACE TEMPORARY STAGE {score_stage_name};"
         SqlResultValidator(
@@ -1056,8 +1087,9 @@ class PolynomialFeatures(BaseTransformer):
             expected_value=f"Stage area {score_stage_name} successfully created."
         ).validate()
 
-        stage_score_file_name = os.path.join(score_stage_name, os.path.basename(local_score_file_name))
-        score_sproc_name = "SNOWML_SCORE_{safe_id}".format(safe_id=self.id)
+        # Use posixpath to construct stage paths
+        stage_score_file_name = posixpath.join(score_stage_name, os.path.basename(local_score_file_name))
+        score_sproc_name = "SNOWML_SCORE_{safe_id}".format(safe_id=self._get_rand_id())
         statement_params = telemetry.get_function_usage_statement_params(
             project=_PROJECT,
             subproject=_SUBPROJECT,
@@ -1083,6 +1115,7 @@ class PolynomialFeatures(BaseTransformer):
             replace=True,
             session=session,
             statement_params=statement_params,
+            anonymous=True
         )
         def score_wrapper_sproc(
             session: Session,
@@ -1090,7 +1123,8 @@ class PolynomialFeatures(BaseTransformer):
             stage_score_file_name: str,
             input_cols: List[str],
             label_cols: List[str],
-            sample_weight_col: Optional[str]
+            sample_weight_col: Optional[str],
+            statement_params: Dict[str, str]
         ) -> float:
             import cloudpickle as cp
             import numpy as np
@@ -1140,14 +1174,14 @@ class PolynomialFeatures(BaseTransformer):
             api_calls=[Session.call],
             custom_tags=dict([("autogen", True)]),
         )
-        score = session.call(
-            score_sproc_name,
+        score = score_wrapper_sproc(
+            session,
             query,
             stage_score_file_name,
             identifier.get_unescaped_names(self.input_cols),
             identifier.get_unescaped_names(self.label_cols),
             identifier.get_unescaped_names(self.sample_weight_col),
-            statement_params=statement_params,
+            statement_params,
         )
 
         cleanup_temp_files([local_score_file_name])
@@ -1165,18 +1199,20 @@ class PolynomialFeatures(BaseTransformer):
             if self._sklearn_object._estimator_type == 'classifier':
                 outputs = _infer_signature(dataset[self.label_cols], "output")  # label columns is the desired type for output
                 outputs = _rename_features(outputs, self.output_cols)  # rename the output columns
-                self._model_signature_dict["predict"] = ModelSignature(inputs, outputs)
+                self._model_signature_dict["predict"] = ModelSignature(inputs, 
+                                                                       ([] if self._drop_input_cols else inputs) + outputs)
             # For regressor, the type of predict is float64
             elif self._sklearn_object._estimator_type == 'regressor':
                 outputs = [FeatureSpec(dtype=DataType.DOUBLE, name=c) for c in self.output_cols]
-                self._model_signature_dict["predict"] = ModelSignature(inputs, outputs)
-
+                self._model_signature_dict["predict"] = ModelSignature(inputs, 
+                                                                       ([] if self._drop_input_cols else inputs) + outputs)
         for prob_func in PROB_FUNCTIONS:
             if hasattr(self, prob_func):
                 output_cols_prefix: str = f"{prob_func}_"
                 output_column_names = self._get_output_column_names(output_cols_prefix)
                 outputs = [FeatureSpec(dtype=DataType.DOUBLE, name=c) for c in output_column_names]
-                self._model_signature_dict[prob_func] = ModelSignature(inputs, outputs)
+                self._model_signature_dict[prob_func] = ModelSignature(inputs, 
+                                                                       ([] if self._drop_input_cols else inputs) + outputs)
 
     @property
     def model_signatures(self) -> Dict[str, ModelSignature]: