Project import generated by Copybara. (#98)

GitOrigin-RevId: e6f7fd62eecf65ab1db362c8c4d2cb8a5fb32c9a

Co-authored-by: Snowflake Authors <noreply@snowflake.com>

CHANGELOG.md

@@ -1,6 +1,67 @@
 # Release History
 
-## 1.4.1
+## 1.5.0
+
+### Bug Fixes
+
+- Registry: Fix invalid parameter 'SHOW_MODEL_DETAILS_IN_SHOW_VERSIONS_IN_MODEL' error.
+
+### Behavior Changes
+
+- Model Development: The behavior of `fit_transform` for all estimators is changed.
+  Firstly, it will cover all the estimator that contains this function,
+  secondly, the output would be the union of pandas DataFrame and snowpark DataFrame.
+
+#### Model Registry (PrPr)
+
+`snowflake.ml.registry.artifact` and related `snowflake.ml.model_registry.ModelRegistry` APIs have been removed.
+
+- Removed `snowflake.ml.registry.artifact` module.
+- Removed `ModelRegistry.log_artifact()`, `ModelRegistry.list_artifacts()`, `ModelRegistry.get_artifact()`
+- Removed `artifacts` argument from `ModelRegistry.log_model()`
+
+#### Dataset (PrPr)
+
+`snowflake.ml.dataset.Dataset` has been redesigned to be backed by Snowflake Dataset entities.
+
+- New `Dataset`s can be created with `Dataset.create()` and existing `Dataset`s may be loaded
+  with `Dataset.load()`.
+- `Dataset`s now maintain an immutable `selected_version` state. The `Dataset.create_version()` and
+  `Dataset.load_version()` APIs return new `Dataset` objects with the requested `selected_version` state.
+- Added `dataset.create_from_dataframe()` and `dataset.load_dataset()` convenience APIs as a shortcut
+  to creating and loading `Dataset`s with a pre-selected version.
+- `Dataset.materialized_table` and `Dataset.snapshot_table` no longer exist with `Dataset.fully_qualified_name`
+  as the closest equivalent.
+- `Dataset.df` no longer exists. Instead, use `DatasetReader.read.to_snowpark_dataframe()`.
+- `Dataset.owner` has been moved to `Dataset.selected_version.owner`
+- `Dataset.desc` has been moved to `DatasetVersion.selected_version.comment`
+- `Dataset.timestamp_col`, `Dataset.label_cols`, `Dataset.feature_store_metadata`, and
+  `Dataset.schema_version` have been removed.
+
+#### Feature Store (PrPr)
+
+`FeatureStore.generate_dataset` argument list has been changed to match the new
+`snowflake.ml.dataset.Dataset` definition
+
+- `materialized_table` has been removed and replaced with `name` and `version`.
+- `name` moved to first positional argument
+- `save_mode` has been removed as `merge` behavior is no longer supported. The new behavior is always `errorifexists`.
+
+### New Features
+
+- Registry: Add `export` method to `ModelVersion` instance to export model files.
+- Registry: Add `load` method to `ModelVersion` instance to load the underlying object from the model.
+- Registry: Add `Model.rename` method to `Model` instance to rename or move a model.
+
+#### Dataset (PrPr)
+
+- Added Snowpark DataFrame integration using `Dataset.read.to_snowpark_dataframe()`
+- Added Pandas DataFrame integration using `Dataset.read.to_pandas()`
+- Added PyTorch and TensorFlow integrations using `Dataset.read.to_torch_datapipe()`
+    and `Dataset.read.to_tf_dataset()` respectively.
+- Added `fsspec` style file integration using `Dataset.read.files()` and `Dataset.read.filesystem()`
+
+## 1.4.1 (2024-04-18)
 
 ### New Features
 

ci/conda_recipe/meta.yaml

@@ -17,7 +17,7 @@ build:
   noarch: python
 package:
   name: snowflake-ml-python
-  version: 1.4.1
+  version: 1.5.0
 requirements:
   build:
     - python

codegen/sklearn_wrapper_generator.py

@@ -13,6 +13,7 @@
 NP_CONSTANTS = [c for c in dir(np) if type(getattr(np, c, None)) == float or type(getattr(np, c, None)) == int]
 LOAD_BREAST_CANCER = "load_breast_cancer"
 LOAD_IRIS = "load_iris"
+LOAD_DIGITS = "load_digits"
 LOAD_DIABETES = "load_diabetes"
 
 
@@ -278,6 +279,7 @@ def _is_deterministic(class_object: Tuple[str, type]) -> bool:
         return not (
             WrapperGeneratorFactory._is_class_of_type(class_object[1], "LinearDiscriminantAnalysis")
             or WrapperGeneratorFactory._is_class_of_type(class_object[1], "BernoulliRBM")
+            or WrapperGeneratorFactory._is_class_of_type(class_object[1], "TSNE")
         )
 
     @staticmethod
@@ -739,6 +741,7 @@ def _populate_function_doc_fields(self) -> None:
         _METHODS = [
             "fit",
             "fit_predict",
+            "fit_transform",
             "predict",
             "predict_log_proba",
             "predict_proba",
@@ -775,6 +778,7 @@ def _populate_function_doc_fields(self) -> None:
         self.transform_docstring = self.estimator_function_docstring["transform"]
         self.predict_docstring = self.estimator_function_docstring["predict"]
         self.fit_predict_docstring = self.estimator_function_docstring["fit_predict"]
+        self.fit_transform_docstring = self.estimator_function_docstring["fit_transform"]
         self.predict_proba_docstring = self.estimator_function_docstring["predict_proba"]
         self.score_samples_docstring = self.estimator_function_docstring["score_samples"]
         self.predict_log_proba_docstring = self.estimator_function_docstring["predict_log_proba"]
@@ -898,6 +902,8 @@ def _populate_integ_test_fields(self) -> None:
             self.test_dataset_func = LOAD_BREAST_CANCER
         elif self._is_regressor:
             self.test_dataset_func = LOAD_DIABETES
+        elif WrapperGeneratorFactory._is_class_of_type(self.class_object[1], "SpectralEmbedding"):
+            self.test_dataset_func = LOAD_DIGITS
         else:
             self.test_dataset_func = LOAD_IRIS
 

codegen/sklearn_wrapper_template.py_template

@@ -54,12 +54,6 @@ _SUBPROJECT = "".join([s.capitalize() for s in "{transform.root_module_name}".re
 
 DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
-def _is_fit_transform_method_enabled() -> Callable[[Any], bool]:	
-    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:	
-        return {transform.fit_transform_manifold_function_support} and callable(getattr(self._sklearn_object, "fit_transform", None))	
-    return check	
-
-
 class {transform.original_class_name}(BaseTransformer):
     r"""{transform.estimator_class_docstring}
     """
@@ -174,20 +168,17 @@ class {transform.original_class_name}(BaseTransformer):
         self,
         dataset: DataFrame,
         inference_method: str,
-    ) -> List[str]:
-        """Util method to run validate that batch inference can be run on a snowpark dataframe and
-        return the available package that exists in the snowflake anaconda channel
+    ) -> None:
+        """Util method to run validate that batch inference can be run on a snowpark dataframe.
 
         Args:
             dataset: snowpark dataframe
             inference_method: the inference method such as predict, score...
-
+            
         Raises:
             SnowflakeMLException: If the estimator is not fitted, raise error
             SnowflakeMLException: If the session is None, raise error
 
-        Returns:
-            A list of available package that exists in the snowflake anaconda channel
         """
         if not self._is_fitted:
             raise exceptions.SnowflakeMLException(
@@ -205,9 +196,7 @@ class {transform.original_class_name}(BaseTransformer):
                     "Session must not specified for snowpark dataset."
                 ),
             )
-        # Validate that key package version in user workspace are supported in snowflake conda channel
-        return pkg_version_utils.get_valid_pkg_versions_supported_in_snowflake_conda_channel(
-            pkg_versions=self._get_dependencies(), session=session, subproject=_SUBPROJECT)
+
 
     @available_if(original_estimator_has_callable("predict"))  # type: ignore[misc]
     @telemetry.send_api_usage_telemetry(
@@ -246,7 +235,8 @@ class {transform.original_class_name}(BaseTransformer):
 
                 expected_type_inferred = convert_sp_to_sf_type(label_cols_signatures[0].as_snowpark_type())
 
-            self._deps = self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(
                 dataset._session, Session
             )  # mypy does not recognize the check in _batch_inference_validate_snowpark()
@@ -321,10 +311,8 @@ class {transform.original_class_name}(BaseTransformer):
                     if all(x == output_types[0] for x in output_types) and len(output_types) == len(self.output_cols):
                         expected_dtype = convert_sp_to_sf_type(output_types[0])
 
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method=inference_method,
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(dataset._session, Session) # mypy does not recognize the check in _batch_inference_validate_snowpark()
 
             transform_kwargs = dict(
@@ -383,16 +371,32 @@ class {transform.original_class_name}(BaseTransformer):
         self._is_fitted = True
         return output_result
 
-
-    @available_if(_is_fit_transform_method_enabled())  # type: ignore[misc]
-    def fit_transform(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
+            
+    @available_if(original_estimator_has_callable("fit_transform"))  # type: ignore[misc]
+    def fit_transform(self, dataset: Union[DataFrame, pd.DataFrame], output_cols_prefix: str = "fit_transform_",) -> Union[DataFrame, pd.DataFrame]:
         """ {transform.fit_transform_docstring}
+        output_cols_prefix: Prefix for the response columns
         Returns:
             Transformed dataset.
         """
-        self.fit(dataset)
-        assert self._sklearn_object is not None
-        return self._sklearn_object.embedding_
+        self._infer_input_output_cols(dataset)
+        super()._check_dataset_type(dataset)
+        model_trainer = ModelTrainerBuilder.build_fit_transform(
+            estimator=self._sklearn_object,
+            dataset=dataset,
+            input_cols=self.input_cols,
+            label_cols=self.label_cols,
+            sample_weight_col=self.sample_weight_col,
+            autogenerated=self._autogenerated,
+            subproject=_SUBPROJECT,
+        )
+        output_result, fitted_estimator = model_trainer.train_fit_transform(
+            drop_input_cols=self._drop_input_cols,
+            expected_output_cols_list=self.output_cols,
+        )
+        self._sklearn_object = fitted_estimator
+        self._is_fitted = True
+        return output_result
 
 
     def _get_output_column_names(self, output_cols_prefix: str, output_cols: Optional[List[str]] = None) -> List[str]:
@@ -475,10 +479,8 @@ class {transform.original_class_name}(BaseTransformer):
         expected_output_cols = self._get_output_column_names(output_cols_prefix)
 
         if isinstance(dataset, DataFrame):
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method=inference_method,
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(
                 dataset._session, Session
             )  # mypy does not recognize the check in _batch_inference_validate_snowpark()
@@ -535,10 +537,8 @@ class {transform.original_class_name}(BaseTransformer):
         transform_kwargs: BatchInferenceKwargsTypedDict = dict()  
 
         if isinstance(dataset, DataFrame):
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method=inference_method,
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(
                 dataset._session, Session
             )  # mypy does not recognize the check in _batch_inference_validate_snowpark()
@@ -592,10 +592,8 @@ class {transform.original_class_name}(BaseTransformer):
         expected_output_cols = self._get_output_column_names(output_cols_prefix)
 
         if isinstance(dataset, DataFrame):
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method=inference_method,
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(
                 dataset._session, Session
             )  # mypy does not recognize the check in _batch_inference_validate_snowpark()
@@ -653,10 +651,8 @@ class {transform.original_class_name}(BaseTransformer):
         expected_output_cols = self._get_output_column_names(output_cols_prefix)
 
         if isinstance(dataset, DataFrame):
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method=inference_method,
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(dataset._session, Session) # mypy does not recognize the check in _batch_inference_validate_snowpark()
             transform_kwargs = dict(
                 session=dataset._session,
@@ -710,17 +706,15 @@ class {transform.original_class_name}(BaseTransformer):
         transform_kwargs: ScoreKwargsTypedDict = dict()  
 
         if isinstance(dataset, DataFrame):
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method="score",
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method="score")
+            self._deps = self._get_dependencies()
             selected_cols = self._get_active_columns()
             if len(selected_cols) > 0:
                 dataset = dataset.select(selected_cols)
             assert isinstance(dataset._session, Session) # keep mypy happy
             transform_kwargs = dict(
                 session=dataset._session,
-                dependencies=["snowflake-snowpark-python"] + self._deps,
+                dependencies=self._deps,
                 score_sproc_imports={transform.score_sproc_imports},
             )
         elif isinstance(dataset, pd.DataFrame):
@@ -778,11 +772,8 @@ class {transform.original_class_name}(BaseTransformer):
         if isinstance(dataset, DataFrame):
             # TODO: Solve inconsistent neigh_ind with sklearn due to different precisions in case of close distances.
 
-            self._deps = self._batch_inference_validate_snowpark(
-                dataset=dataset,
-                inference_method=inference_method,
-
-            )
+            self._batch_inference_validate_snowpark(dataset=dataset, inference_method=inference_method)
+            self._deps = self._get_dependencies()
             assert isinstance(dataset._session, Session) # mypy does not recognize the check in _batch_inference_validate_snowpark()
             transform_kwargs = dict(
                 session = dataset._session,

codegen/transformer_autogen_test_template.py_template

@@ -13,7 +13,6 @@ from snowflake.ml.utils.connection_params import SnowflakeLoginOptions
 from snowflake.snowpark import Session, DataFrame
 
 
-
 class {transform.test_class_name}(TestCase):
     def setUp(self) -> None:
         """Creates Snowpark and Snowflake environments for testing."""
@@ -125,7 +124,7 @@ class {transform.test_class_name}(TestCase):
 
         sklearn_reg.fit(**args)
 
-        inference_methods = ["transform", "predict", "fit_predict"]
+        inference_methods = ["transform", "predict", "fit_predict", "fit_transform"]
         for m in inference_methods:
             if callable(getattr(sklearn_reg, m, None)):
                 if m == 'predict':
@@ -151,7 +150,7 @@ class {transform.test_class_name}(TestCase):
 
                     # TODO(snandamuri): Implement type inference for transform and predict methods to return results with
                     # correct datatype.
-                    if m == 'transform':
+                    if m == 'transform' or m == 'fit_transform':
                         actual_arr = output_df_pandas.astype("float64").to_numpy()
                     else:
                         actual_arr = output_df_pandas.to_numpy()
@@ -163,7 +162,12 @@ class {transform.test_class_name}(TestCase):
                     ]
                     actual_arr = output_df_pandas[actual_output_cols].to_numpy()
 
-                sklearn_numpy_arr = getattr(sklearn_reg, m)(input_df_pandas[input_cols])
+                if m == 'fit_transform':
+                    sklearn_numpy_arr = sklearn_reg.fit_transform(**args)
+                else:
+                    sklearn_numpy_arr = getattr(sklearn_reg, m)(input_df_pandas[input_cols])
+
+
                 if len(sklearn_numpy_arr.shape) == 3:
                     # VotingClassifier will return results of shape (n_classifiers, n_samples, n_classes)
                     # when voting = "soft" and flatten_transform = False. We can't handle unflatten transforms,

snowflake/ml/_internal/BUILD.bazel

@@ -41,7 +41,6 @@ py_library(
     srcs = ["env_utils.py"],
     deps = [
         ":env",
-        "//snowflake/ml/_internal/exceptions",
         "//snowflake/ml/_internal/utils:query_result_checker",
         "//snowflake/ml/_internal/utils:retryable_http",
     ],