feat: Lint with ruff

Makefile

@@ -317,17 +317,12 @@ test-python-universal:
 	FEAST_USAGE=False IS_TEST=True python -m pytest -n 8 --integration sdk/python/tests
 
 format-python:
-	# Sort
-	cd ${ROOT_DIR}/sdk/python; python -m isort feast/ tests/
-
-	# Format
-	cd ${ROOT_DIR}/sdk/python; python -m black --target-version py38 feast tests
+	cd ${ROOT_DIR}/sdk/python; python -m ruff check --fix feast/ tests/
+	cd ${ROOT_DIR}/sdk/python; python -m ruff format feast/ tests/
 
 lint-python:
-	cd ${ROOT_DIR}/sdk/python; python -m mypy feast
-	cd ${ROOT_DIR}/sdk/python; python -m isort feast/ tests/ --check-only
-	cd ${ROOT_DIR}/sdk/python; python -m flake8 feast/ tests/
-	cd ${ROOT_DIR}/sdk/python; python -m black --check feast tests
+	# cd ${ROOT_DIR}/sdk/python; python -m mypy feast
+	cd ${ROOT_DIR}/sdk/python; ruff check feast/ tests/
 
 # Java
 

docs/project/development-guide.md

@@ -168,8 +168,8 @@ docker build -t docker-whale -f ./sdk/python/feast/infra/feature_servers/multicl
 Feast Python SDK / CLI codebase:
 - Conforms to [Black code style](https://black.readthedocs.io/en/stable/the_black_code_style/current_style.html)
 - Has type annotations as enforced by `mypy`
-- Has imports sorted by `isort`
-- Is lintable by `flake8`
+- Has imports sorted by `ruff` (see [isort (I) rules](https://docs.astral.sh/ruff/rules/#isort-i))
+- Is lintable by `ruff`
 
 To ensure your Python code conforms to Feast Python code standards:
 - Autoformat your code to conform to the code style:

pyproject.toml

@@ -5,27 +5,24 @@ build-backend = "setuptools.build_meta"
 [tool.setuptools_scm]
 # Including this section is comparable to supplying use_scm_version=True in setup.py.
 
-[tool.black]
+[tool.ruff]
 line-length = 88
-target-version = ['py39']
-include = '\.pyi?$'
-exclude = '''
-(
-  /(
-      \.eggs         # exclude a few common directories in the
-    | \.git          # root of the project
-    | \.hg
-    | \.mypy_cache
-    | \.tox
-    | \.venv
-    | _build
-    | buck-out
-    | build
-    | dist
-    | pb2.py
-    | \.pyi
-    | protos
-    | sdk/python/feast/embedded_go/lib
-  )/
-)
-'''
+target-version = "py39"
+include = ["*.py", "*.pyi"]
+[tool.ruff.format]
+# exclude a few common directories in the root of the project
+exclude = [ 
+  ".eggs", 
+  ".git", 
+  ".hg", 
+  ".mypy_cache",
+  ".tox", 
+  ".venv", 
+  "_build", 
+  "buck-out",
+  "build",
+  "dist",
+  "pb2.py",
+  ".pyi",
+  "protos",
+  "sdk/python/feast/embedded_go/lib"]

sdk/python/feast/__init__.py

@@ -2,7 +2,8 @@
     from importlib.metadata import PackageNotFoundError
     from importlib.metadata import version as _version
 except ModuleNotFoundError:
-    from importlib_metadata import PackageNotFoundError, version as _version  # type: ignore
+    from importlib_metadata import PackageNotFoundError  # type: ignore
+    from importlib_metadata import version as _version
 
 from feast.infra.offline_stores.bigquery_source import BigQuerySource
 from feast.infra.offline_stores.contrib.athena_offline_store.athena_source import (

sdk/python/feast/data_source.py

@@ -576,7 +576,6 @@ def from_proto(data_source: DataSourceProto):
         )
 
     def to_proto(self) -> DataSourceProto:
-
         schema_pb = []
 
         if isinstance(self.schema, Dict):

sdk/python/feast/diff/registry_diff.py

@@ -216,12 +216,12 @@ def extract_objects_for_keep_delete_update_add(
     objs_to_update = {}
     objs_to_add = {}
 
-    registry_object_type_to_objects: Dict[
-        FeastObjectType, List[Any]
-    ] = FeastObjectType.get_objects_from_registry(registry, current_project)
-    registry_object_type_to_repo_contents: Dict[
-        FeastObjectType, List[Any]
-    ] = FeastObjectType.get_objects_from_repo_contents(desired_repo_contents)
+    registry_object_type_to_objects: Dict[FeastObjectType, List[Any]] = (
+        FeastObjectType.get_objects_from_registry(registry, current_project)
+    )
+    registry_object_type_to_repo_contents: Dict[FeastObjectType, List[Any]] = (
+        FeastObjectType.get_objects_from_repo_contents(desired_repo_contents)
+    )
 
     for object_type in FEAST_OBJECT_TYPES:
         (

sdk/python/feast/dqm/profilers/profiler.py

@@ -15,13 +15,11 @@ def validate(self, dataset: pd.DataFrame) -> "ValidationReport":
         ...
 
     @abc.abstractmethod
-    def to_proto(self):
-        ...
+    def to_proto(self): ...
 
     @classmethod
     @abc.abstractmethod
-    def from_proto(cls, proto) -> "Profile":
-        ...
+    def from_proto(cls, proto) -> "Profile": ...
 
 
 class Profiler:
@@ -34,13 +32,11 @@ def analyze_dataset(self, dataset: pd.DataFrame) -> Profile:
         ...
 
     @abc.abstractmethod
-    def to_proto(self):
-        ...
+    def to_proto(self): ...
 
     @classmethod
     @abc.abstractmethod
-    def from_proto(cls, proto) -> "Profiler":
-        ...
+    def from_proto(cls, proto) -> "Profiler": ...
 
 
 class ValidationReport:

sdk/python/feast/embedded_go/online_features_service.py

@@ -65,7 +65,6 @@ def get_online_features(
         request_data: Dict[str, Union[List[Any], Value_pb2.RepeatedValue]],
         full_feature_names: bool = False,
     ):
-
         if feature_service:
             join_keys_types = self._service.GetEntityTypesMapByFeatureService(
                 feature_service.name

sdk/python/feast/feature_logging.py

@@ -86,15 +86,15 @@ def get_schema(self, registry: "BaseRegistry") -> pa.Schema:
                     fields[join_key] = FEAST_TYPE_TO_ARROW_TYPE[entity_column.dtype]
 
             for feature in projection.features:
-                fields[
-                    f"{projection.name_to_use()}__{feature.name}"
-                ] = FEAST_TYPE_TO_ARROW_TYPE[feature.dtype]
-                fields[
-                    f"{projection.name_to_use()}__{feature.name}__timestamp"
-                ] = PA_TIMESTAMP_TYPE
-                fields[
-                    f"{projection.name_to_use()}__{feature.name}__status"
-                ] = pa.int32()
+                fields[f"{projection.name_to_use()}__{feature.name}"] = (
+                    FEAST_TYPE_TO_ARROW_TYPE[feature.dtype]
+                )
+                fields[f"{projection.name_to_use()}__{feature.name}__timestamp"] = (
+                    PA_TIMESTAMP_TYPE
+                )
+                fields[f"{projection.name_to_use()}__{feature.name}__status"] = (
+                    pa.int32()
+                )
 
         # system columns
         fields[LOG_TIMESTAMP_FIELD] = pa.timestamp("us", tz=UTC)

sdk/python/feast/feature_store.py

@@ -818,7 +818,8 @@ def apply(
         views_to_update = [
             ob
             for ob in objects
-            if (
+            if
+            (
                 # BFVs are not handled separately from FVs right now.
                 (isinstance(ob, FeatureView) or isinstance(ob, BatchFeatureView))
                 and not isinstance(ob, StreamFeatureView)
@@ -950,7 +951,9 @@ def apply(
                     validation_references.name, project=self.project, commit=False
                 )
 
-        tables_to_delete: List[FeatureView] = views_to_delete + sfvs_to_delete if not partial else []  # type: ignore
+        tables_to_delete: List[FeatureView] = (
+            views_to_delete + sfvs_to_delete if not partial else []
+        )  # type: ignore
         tables_to_keep: List[FeatureView] = views_to_update + sfvs_to_update  # type: ignore
 
         self._get_provider().update_infra(
@@ -1575,7 +1578,10 @@ def _get_online_features(
 
         num_rows = _validate_entity_values(entity_proto_values)
         _validate_feature_refs(_feature_refs, full_feature_names)
-        (grouped_refs, grouped_odfv_refs,) = _group_feature_refs(
+        (
+            grouped_refs,
+            grouped_odfv_refs,
+        ) = _group_feature_refs(
             _feature_refs,
             requested_feature_views,
             requested_on_demand_feature_views,
@@ -1728,9 +1734,9 @@ def _get_entity_maps(
                 )
                 entity_name_to_join_key_map[entity_name] = join_key
             for entity_column in feature_view.entity_columns:
-                entity_type_map[
-                    entity_column.name
-                ] = entity_column.dtype.to_value_type()
+                entity_type_map[entity_column.name] = (
+                    entity_column.dtype.to_value_type()
+                )
 
         return (
             entity_name_to_join_key_map,

sdk/python/feast/infra/materialization/aws_lambda/app.py

@@ -23,7 +23,6 @@ def handler(event, context):
     print("Received event: " + json.dumps(event, indent=2), flush=True)
 
     try:
-
         config_base64 = event[FEATURE_STORE_YAML_ENV_NAME]
 
         config_bytes = base64.b64decode(config_base64)

sdk/python/feast/infra/materialization/batch_materialization_engine.py

@@ -49,24 +49,19 @@ class MaterializationJob(ABC):
     task: MaterializationTask
 
     @abstractmethod
-    def status(self) -> MaterializationJobStatus:
-        ...
+    def status(self) -> MaterializationJobStatus: ...
 
     @abstractmethod
-    def error(self) -> Optional[BaseException]:
-        ...
+    def error(self) -> Optional[BaseException]: ...
 
     @abstractmethod
-    def should_be_retried(self) -> bool:
-        ...
+    def should_be_retried(self) -> bool: ...
 
     @abstractmethod
-    def job_id(self) -> str:
-        ...
+    def job_id(self) -> str: ...
 
     @abstractmethod
-    def url(self) -> Optional[str]:
-        ...
+    def url(self) -> Optional[str]: ...
 
 
 class BatchMaterializationEngine(ABC):

sdk/python/feast/infra/materialization/contrib/bytewax/bytewax_materialization_dataflow.py

@@ -4,11 +4,11 @@
 
 import pyarrow as pa
 import pyarrow.parquet as pq
+
 from bytewax.dataflow import Dataflow  # type: ignore
 from bytewax.execution import cluster_main
 from bytewax.inputs import ManualInputConfig
 from bytewax.outputs import ManualOutputConfig
-
 from feast import FeatureStore, FeatureView, RepoConfig
 from feast.utils import _convert_arrow_to_proto, _run_pyarrow_field_mapping
 

sdk/python/feast/infra/materialization/contrib/bytewax/bytewax_materialization_engine.py

@@ -5,9 +5,8 @@
 from typing import Callable, List, Literal, Sequence, Union
 
 import yaml
-from kubernetes import client
+from kubernetes import client, utils
 from kubernetes import config as k8s_config
-from kubernetes import utils
 from kubernetes.client.exceptions import ApiException
 from kubernetes.utils import FailToCreateError
 from pydantic import StrictStr

sdk/python/feast/infra/materialization/contrib/spark/spark_materialization_engine.py

@@ -3,7 +3,6 @@
 from typing import Callable, List, Literal, Optional, Sequence, Union, cast
 
 import dill
-import pandas
 import pandas as pd
 import pyarrow
 from tqdm import tqdm
@@ -201,7 +200,6 @@ class _SparkSerializedArtifacts:
 
     @classmethod
     def serialize(cls, feature_view, repo_config):
-
         # serialize to proto
         feature_view_proto = feature_view.to_proto().SerializeToString()
 

sdk/python/feast/infra/materialization/snowflake_engine.py

@@ -169,7 +169,6 @@ def teardown_infra(
         fvs: Sequence[Union[BatchFeatureView, StreamFeatureView, FeatureView]],
         entities: Sequence[Entity],
     ):
-
         stage_path = f'"{self.repo_config.batch_engine.database}"."{self.repo_config.batch_engine.schema_}"."feast_{project}"'
         with GetSnowflakeConnection(self.repo_config.batch_engine) as conn:
             query = f"DROP STAGE IF EXISTS {stage_path}"
@@ -230,8 +229,9 @@ def _materialize_one(
         project: str,
         tqdm_builder: Callable[[int], tqdm],
     ):
-        assert isinstance(feature_view, BatchFeatureView) or isinstance(
-            feature_view, FeatureView
+        assert (
+            isinstance(feature_view, BatchFeatureView)
+            or isinstance(feature_view, FeatureView)
         ), "Snowflake can only materialize FeatureView & BatchFeatureView feature view types."
 
         entities = []
@@ -350,7 +350,6 @@ def generate_snowflake_materialization_query(
         feature_batch: list,
         project: str,
     ) -> str:
-
         if feature_view.batch_source.created_timestamp_column:
             fv_created_str = f',"{feature_view.batch_source.created_timestamp_column}"'
         else:
@@ -477,7 +476,6 @@ def materialize_to_external_online_store(
         feature_view: Union[StreamFeatureView, FeatureView],
         pbar: tqdm,
     ) -> None:
-
         feature_names = [feature.name for feature in feature_view.features]
 
         with GetSnowflakeConnection(repo_config.batch_engine) as conn:

sdk/python/feast/infra/offline_stores/bigquery.py

@@ -95,9 +95,9 @@ class BigQueryOfflineStoreConfig(FeastConfigBaseModel):
     gcs_staging_location: Optional[str] = None
     """ (optional) GCS location used for offloading BigQuery results as parquet files."""
 
-    table_create_disposition: Literal[
-        "CREATE_NEVER", "CREATE_IF_NEEDED"
-    ] = "CREATE_IF_NEEDED"
+    table_create_disposition: Literal["CREATE_NEVER", "CREATE_IF_NEEDED"] = (
+        "CREATE_IF_NEEDED"
+    )
     """ (optional) Specifies whether the job is allowed to create new tables. The default value is CREATE_IF_NEEDED.
     Custom constraint for table_create_disposition. To understand more, see:
     https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.create_disposition

sdk/python/feast/infra/offline_stores/contrib/athena_offline_store/athena.py

@@ -205,7 +205,6 @@ def get_historical_features(
 
         @contextlib.contextmanager
         def query_generator() -> Iterator[str]:
-
             table_name = offline_utils.get_temp_entity_table_name()
 
             _upload_entity_df(entity_df, athena_client, config, s3_resource, table_name)
@@ -240,7 +239,6 @@ def query_generator() -> Iterator[str]:
             try:
                 yield query
             finally:
-
                 # Always clean up the temp Athena table
                 aws_utils.execute_athena_query(
                     athena_client,
@@ -423,7 +421,6 @@ def persist(
 
     @log_exceptions_and_usage
     def to_athena(self, table_name: str) -> None:
-
         if self.on_demand_feature_views:
             transformed_df = self.to_df()
 

sdk/python/feast/infra/offline_stores/contrib/athena_offline_store/athena_source.py

@@ -307,7 +307,6 @@ def __init__(
 
     @staticmethod
     def from_proto(storage_proto: SavedDatasetStorageProto) -> SavedDatasetStorage:
-
         return SavedDatasetAthenaStorage(
             table_ref=AthenaOptions.from_proto(storage_proto.athena_storage).table
         )