feast-dev · feast-ci-bot · Mar 26, 2022 · Mar 24, 2022
@@ -6,7 +6,7 @@ An entity is a collection of semantically related features. Users define entitie
 driver = Entity(name='driver', value_type=ValueType.STRING, join_key='driver_id')
 ```
 
-Entities are typically defined as part of feature views. Entities are used to identify the primary key on which feature values should be stored and retrieved. These keys are used during the lookup of feature values from the online store and the join process in point-in-time joins. It is possible to define composite entities \(more than one entity object\) in a feature view. It is also possible for feature views to have zero entities. See [feature view](feature-view.md) for more details.
+Entities are typically defined as part of feature views. Entity name is used to reference the entity from a feature view definition and join key is used to identify the physical primary key on which feature values should be stored and retrieved. These keys are used during the lookup of feature values from the online store and the join process in point-in-time joins. It is possible to define composite entities \(more than one entity object\) in a feature view. It is also possible for feature views to have zero entities. See [feature view](feature-view.md) for more details.
 
 Entities should be reused across feature views.
 

@@ -20,7 +20,10 @@ online_features = fs.get_online_features(
         'driver_locations:lon',
         'drivers_activity:trips_today'
     ],
-    entity_rows=[{'driver': 'driver_1001'}]
+    entity_rows=[
+        # {join_key: entity_value}
+        {'driver': 'driver_1001'}
+    ]
 )
 ```
 

@@ -95,14 +95,16 @@ driver_hourly_stats = FileSource(
 
 # 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",)
+# 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_key="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"],  # reference entity by name
     ttl=Duration(seconds=86400 * 1),
     features=[
         Feature(name="conv_rate", dtype=ValueType.FLOAT),
@@ -162,14 +164,16 @@ driver_hourly_stats = FileSource(
 
 # 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",)
+# 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_key="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"],  # reference entity by name
     ttl=Duration(seconds=86400 * 1),
     features=[
         Feature(name="conv_rate", dtype=ValueType.FLOAT),
@@ -213,8 +217,13 @@ from feast import FeatureStore
 # The entity dataframe is the dataframe we want to enrich with feature values
 entity_df = pd.DataFrame.from_dict(
     {
+        # entity's join key -> entity values
         "driver_id": [1001, 1002, 1003],
+
+        # label name -> label values
         "label_driver_reported_satisfaction": [1, 5, 3], 
+
+        # "event_timestamp" (reserved key) -> timestamps
         "event_timestamp": [
             datetime.now() - timedelta(minutes=11),
             datetime.now() - timedelta(minutes=36),
@@ -320,6 +329,7 @@ feature_vector = store.get_online_features(
         "driver_hourly_stats:avg_daily_trips",
     ],
     entity_rows=[
+        # {join_key: entity_value}
         {"driver_id": 1004},
         {"driver_id": 1005},
     ],

@@ -34,6 +34,7 @@ fs = FeatureStore(repo_path="path/to/feature/repo")
 online_features = fs.get_online_features(
     features=features,
     entity_rows=[
+        # {join_key: entity_value, ...}
         {"driver_id": 1001},
         {"driver_id": 1002}]
 ).to_dict()

@@ -124,7 +124,12 @@ fs.materialize_incremental(end_date=datetime.now())
 {% code title="test.py" %}
 ```python
 online_features = fs.get_online_features(
-    features=features, entity_rows=[{"driver_id": 1001}, {"driver_id": 1002}],
+    features=features,
+    entity_rows=[
+      # {join_key: entity_value}
+      {"driver_id": 1001},
+      {"driver_id": 1002}
+    ],
 ).to_dict()
 ```
 {% endcode %}