feast-dev · feast-ci-bot · Aug 4, 2022 · Aug 3, 2022 · Aug 3, 2022 · Aug 3, 2022
@@ -74,16 +74,17 @@ It is suggested that you dynamically specify the new FeatureView name using `.wi
 {% tabs %}
 {% tab title="location_stats_feature_view.py" %}
 ```python
-from feast import BigQuerySource, Entity, FeatureView, Field, ValueType
-from feast.types import Int32
+from feast import BigQuerySource, Entity, FeatureView, Field
+from feast.types import Int32, Int64
 
-location = Entity(name="location", join_keys=["location_id"], value_type=ValueType.INT64)
+location = Entity(name="location", join_keys=["location_id"])
 
 location_stats_fv= FeatureView(
     name="location_stats",
     entities=["location"],
     schema=[
-        Field(name="temperature", dtype=Int32)
+        Field(name="temperature", dtype=Int32),
+        Field(name="location_id", dtype=Int64),
     ],
     source=BigQuerySource(
         table="feast-oss.demo_data.location_stats"

@@ -82,7 +82,7 @@ online_store:
 
 from datetime import timedelta
 
-from feast import Entity, FeatureService, FeatureView, Field, FileSource, ValueType
+from feast import Entity, FeatureService, FeatureView, Field, FileSource
 from feast.types import Float32, Int64
 
 # Read data from parquet files. Parquet is convenient for local development mode. For
@@ -98,7 +98,7 @@ driver_hourly_stats = FileSource(
 # fetch features.
 # Entity has a name used for later reference (in a feature view, eg)
 # and join_key to identify physical field name used in storages
-driver = Entity(name="driver", value_type=ValueType.INT64, join_keys=["driver_id"], description="driver id",)
+driver = Entity(name="driver", join_keys=["driver_id"], description="driver id",)
 
 # Our parquet files contain sample data that includes a driver_id column, timestamps and
 # three feature column. Here we define a Feature View that will allow us to serve this
@@ -111,6 +111,7 @@ driver_hourly_stats_view = FeatureView(
         Field(name="conv_rate", dtype=Float32),
         Field(name="acc_rate", dtype=Float32),
         Field(name="avg_daily_trips", dtype=Int64),
+        Field(name="driver_id", dtype=Int64),
     ],
     online=True,
     source=driver_hourly_stats,
@@ -165,7 +166,7 @@ feast apply
 
 from datetime import timedelta
 
-from feast import Entity, FeatureView, Field, FileSource, ValueType
+from feast import Entity, FeatureView, Field, FileSource
 from feast.types import Float32, Int64
 
 # Read data from parquet files. Parquet is convenient for local development mode. For
@@ -181,7 +182,7 @@ driver_hourly_stats = FileSource(
 # fetch features.
 # Entity has a name used for later reference (in a feature view, eg)
 # and join_key to identify physical field name used in storages
-driver = Entity(name="driver", value_type=ValueType.INT64, join_keys=["driver_id"], description="driver id",)
+driver = Entity(name="driver", join_keys=["driver_id"], description="driver id",)
 
 # Our parquet files contain sample data that includes a driver_id column, timestamps and
 # three feature column. Here we define a Feature View that will allow us to serve this
@@ -194,6 +195,7 @@ driver_hourly_stats_view = FeatureView(
         Field(name="conv_rate", dtype=Float32),
         Field(name="acc_rate", dtype=Float32),
         Field(name="avg_daily_trips", dtype=Int64),
+        Field(name="driver_id", dtype=Int64),
     ],
     online=True,
     source=driver_hourly_stats,

@@ -89,8 +89,8 @@ A feature repository can also contain one or more Python files that contain feat
 ```python
 from datetime import timedelta
 
-from feast import BigQuerySource, Entity, Feature, FeatureView, Field, ValueType
-from feast.types import Float32, String
+from feast import BigQuerySource, Entity, Feature, FeatureView, Field
+from feast.types import Float32, Int64, String
 
 driver_locations_source = BigQuerySource(
     table="rh_prod.ride_hailing_co.drivers",
@@ -100,7 +100,6 @@ driver_locations_source = BigQuerySource(
 
 driver = Entity(
     name="driver",
-    value_type=ValueType.INT64,
     description="driver id",
 )
 
@@ -111,6 +110,7 @@ driver_locations = FeatureView(
     schema=[
         Field(name="lat", dtype=Float32),
         Field(name="lon", dtype=String),
+        Field(name="driver", dtype=Int64),
     ],
     source=driver_locations_source,
 )

@@ -94,8 +94,8 @@ A feature repository can also contain one or more Python files that contain feat
 ```python
 from datetime import timedelta
 
-from feast import BigQuerySource, Entity, Feature, FeatureView, Field, ValueType
-from feast.types import Float32, String
+from feast import BigQuerySource, Entity, Feature, FeatureView, Field
+from feast.types import Float32, Int64, String
 
 driver_locations_source = BigQuerySource(
     table_ref="rh_prod.ride_hailing_co.drivers",
@@ -105,7 +105,6 @@ driver_locations_source = BigQuerySource(
 
 driver = Entity(
     name="driver",
-    value_type=ValueType.INT64,
     description="driver id",
 )
 
@@ -116,6 +115,7 @@ driver_locations = FeatureView(
     schema=[
         Field(name="lat", dtype=Float32),
         Field(name="lon", dtype=String),
+        Field(name="driver", dtype=Int64),
     ],
     source=driver_locations_source,
 )

@@ -2,9 +2,10 @@
 
 from google.protobuf.duration_pb2 import Duration
 
-from feast import Entity, Feature, FeatureView, FileSource, ValueType, FeatureService
+from feast import Entity, Feature, FeatureView, Field, FileSource, FeatureService
 from feast.feature_logging import LoggingConfig
 from feast.infra.offline_stores.file_source import FileLoggingDestination
+from feast.types import Float32, Int64
 
 # Read data from parquet files. Parquet is convenient for local development mode. For
 # production, you can use your favorite DWH, such as BigQuery. See Feast documentation
@@ -17,19 +18,19 @@
 
 # Define an entity for the driver. You can think of entity as a primary key used to
 # fetch features.
-driver = Entity(name="driver_id", value_type=ValueType.INT64, description="driver id",)
+driver = Entity(name="driver_id", description="driver id")
 
 # Our parquet files contain sample data that includes a driver_id column, timestamps and
 # three feature column. Here we define a Feature View that will allow us to serve this
 # data to our model online.
 driver_hourly_stats_view = FeatureView(
     name="driver_hourly_stats",
-    entities=["driver_id"],
+    entities=[driver],
     ttl=Duration(seconds=86400 * 365 * 10),
-    features=[
-        Feature(name="conv_rate", dtype=ValueType.FLOAT),
-        Feature(name="acc_rate", dtype=ValueType.FLOAT),
-        Feature(name="avg_daily_trips", dtype=ValueType.INT64),
+    schema=[
+        Field(name="conv_rate", dtype=Float32),
+        Field(name="acc_rate", dtype=Float32),
+        Field(name="avg_daily_trips", dtype=Int64),
     ],
     online=True,
     batch_source=driver_hourly_stats,

@@ -71,7 +71,7 @@ def transformed_conv_rate(features_df: pd.DataFrame) -> pd.DataFrame:
     path="benchmark_data.parquet", timestamp_field="event_timestamp",
 )
 
-entity = Entity(name="entity", value_type=ValueType.STRING,)
+entity = Entity(name="entity")
 
 benchmark_feature_views = [
     FeatureView(

@@ -11,7 +11,6 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-import warnings
 from datetime import datetime
 from typing import Dict, List, Optional
 
@@ -33,7 +32,10 @@ class Entity:
 
     Attributes:
         name: The unique name of the entity.
-        value_type (deprecated): The type of the entity, such as string or float.
+        value_type: The type of the entity, such as string or float.
+        join_keys: A list of properties that uniquely identifies different entities within the
+            collection. This currently only supports a list of size one, but is intended to
+            eventually support multiple join keys.
         join_key: A property that uniquely identifies different entities within the
             collection. The join_key property is typically used for joining entities
             with their associated features. If not specified, defaults to the name.
@@ -42,108 +44,62 @@ class Entity:
         owner: The owner of the entity, typically the email of the primary maintainer.
         created_timestamp: The time when the entity was created.
         last_updated_timestamp: The time when the entity was last updated.
-        join_keys: A list of properties that uniquely identifies different entities within the
-            collection. This is meant to replace the `join_key` parameter, but currently only
-            supports a list of size one.
     """
 
     name: str
     value_type: ValueType
+    join_keys: List[str]
     join_key: str
     description: str
     tags: Dict[str, str]
     owner: str
     created_timestamp: Optional[datetime]
     last_updated_timestamp: Optional[datetime]
-    join_keys: List[str]
 
     @log_exceptions
     def __init__(
         self,
-        *args,
-        name: Optional[str] = None,
-        value_type: Optional[ValueType] = None,
+        *,
+        name: str,
+        join_keys: Optional[List[str]] = None,
         description: str = "",
-        join_key: Optional[str] = None,
         tags: Optional[Dict[str, str]] = None,
         owner: str = "",
-        join_keys: Optional[List[str]] = None,
     ):
         """
         Creates an Entity object.
 
         Args:
             name: The unique name of the entity.
-            value_type (deprecated): The type of the entity, such as string or float.
-            description: A human-readable description.
-            join_key (deprecated): A property that uniquely identifies different entities within the
-                collection. The join_key property is typically used for joining entities
-                with their associated features. If not specified, defaults to the name.
-            tags: A dictionary of key-value pairs to store arbitrary metadata.
-            owner: The owner of the entity, typically the email of the primary maintainer.
-            join_keys: A list of properties that uniquely identifies different entities within the
-                collection. This is meant to replace the `join_key` parameter, but currently only
-                supports a list of size one.
+            join_keys (optional): A list of properties that uniquely identifies different entities
+                within the collection. This currently only supports a list of size one, but is
+                intended to eventually support multiple join keys.
+            description (optional): A human-readable description.
+            tags (optional): A dictionary of key-value pairs to store arbitrary metadata.
+            owner (optional): The owner of the entity, typically the email of the primary maintainer.
 
         Raises:
             ValueError: Parameters are specified incorrectly.
         """
-        if len(args) == 1:
-            warnings.warn(
-                (
-                    "Entity name should be specified as a keyword argument instead of a positional arg."
-                    "Feast 0.24+ will not support positional arguments to construct Entities"
-                ),
-                DeprecationWarning,
-            )
-        if len(args) > 1:
-            raise ValueError(
-                "All arguments to construct an entity should be specified as keyword arguments only"
-            )
-
-        self.name = args[0] if len(args) > 0 else name
-
-        if not self.name:
-            raise ValueError("Name needs to be specified")
-
-        if value_type:
-            warnings.warn(
-                (
-                    "The `value_type` parameter is being deprecated. Instead, the type of an entity "
-                    "should be specified as a Field in the schema of a feature view. Feast 0.24 and "
-                    "onwards will not support the `value_type` parameter. The `entities` parameter of "
-                    "feature views should also be changed to a List[Entity] instead of a List[str]; if "
-                    "this is not done, entity columns will be mistakenly interpreted as feature columns."
-                ),
-                DeprecationWarning,
-            )
-        self.value_type = value_type or ValueType.UNKNOWN
+        self.name = name
+        self.value_type = ValueType.UNKNOWN
 
         # For now, both the `join_key` and `join_keys` attributes are set correctly,
         # so both are usable.
-        # TODO(felixwang9817): Remove the usage of `join_key` throughout the codebase
-        # when the usage of `join_key` as a parameter is removed.
-        if join_key:
-            warnings.warn(
-                (
-                    "The `join_key` parameter is being deprecated in favor of the `join_keys` parameter. "
-                    "Please switch from using `join_key` to `join_keys`. Feast 0.24 and onwards will not "
-                    "support the `join_key` parameter."
-                ),
-                DeprecationWarning,
-            )
-        self.join_keys = join_keys or []
+        # TODO(felixwang9817): Fully remove the usage of `join_key` throughout the codebase,
+        # at which point the `join_key` attribute no longer needs to be set.
         if join_keys and len(join_keys) > 1:
             raise ValueError(
                 "An entity may only have single join key. "
                 "Multiple join keys will be supported in the future."
             )
-        if join_keys and len(join_keys) == 1:
+        elif join_keys and len(join_keys) == 1:
+            self.join_keys = join_keys
             self.join_key = join_keys[0]
         else:
-            self.join_key = join_key if join_key else self.name
-        if not self.join_keys:
+            self.join_key = self.name
             self.join_keys = [self.join_key]
+
         self.description = description
         self.tags = tags if tags is not None else {}
         self.owner = owner

@@ -14,9 +14,8 @@
 
 driver = Entity(
     name="driver_id",
-    value_type=ValueType.INT64,
     description="driver id",
-    join_key="driver_id",  # Changed to `join_keys` in 0.20
+    join_keys=["driver_id"],  # Changed to `join_keys` in 0.20
 )
 
 

@@ -1,6 +1,6 @@
 from datetime import timedelta
 
-from feast import Entity, FeatureView, Field, FileSource, ValueType
+from feast import Entity, FeatureView, Field, FileSource
 from feast.types import Float32, Int32, Int64
 
 driver_hourly_stats = FileSource(
@@ -9,7 +9,7 @@
     created_timestamp_column="created",
 )
 
-driver = Entity(name="driver_id", value_type=ValueType.INT64, description="driver id")
+driver = Entity(name="driver_id", description="driver id")
 
 
 driver_hourly_stats_view = FeatureView(

@@ -45,8 +45,7 @@ def test_lambda_materialization_consistency():
     fs = lambda_environment.feature_store
     driver = Entity(
         name="driver_id",
-        join_key="driver_id",
-        value_type=ValueType.INT64,
+        join_keys=["driver_id"],
     )
 
     driver_stats_fv = FeatureView(