fix: Switch from join_key to join_keys in tests and docs (#2580)

* Switch from `join_key` to `join_keys` in tests and docs

Signed-off-by: Felix Wang <wangfelix98@gmail.com>

* Convert iterator to list so it can be used repeatedly

Signed-off-by: Felix Wang <wangfelix98@gmail.com>

* Format

Signed-off-by: Felix Wang <wangfelix98@gmail.com>

docs/getting-started/concepts/entity.md

@@ -3,7 +3,7 @@
 An entity is a collection of semantically related features. Users define entities to map to the domain of their use case. For example, a ride-hailing service could have customers and drivers as their entities, which group related features that correspond to these customers and drivers.
 
 ```python
-driver = Entity(name='driver', value_type=ValueType.STRING, join_key='driver_id')
+driver = Entity(name='driver', value_type=ValueType.STRING, join_keys=['driver_id'])
 ```
 
 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.

docs/getting-started/concepts/feature-view.md

@@ -79,7 +79,7 @@ It is suggested that you dynamically specify the new FeatureView name using `.wi
 from feast import BigQuerySource, Entity, FeatureView, Field, ValueType
 from feast.types import Int32
 
-location = Entity(name="location", join_key="location_id", value_type=ValueType.INT64)
+location = Entity(name="location", join_keys=["location_id"], value_type=ValueType.INT64)
 
 location_stats_fv= FeatureView(
     name="location_stats",

docs/getting-started/quickstart.md

@@ -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_key="driver_id", description="driver id",)
+driver = Entity(name="driver", value_type=ValueType.INT64, 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
@@ -168,7 +168,7 @@ 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_key="driver_id", description="driver id",)
+driver = Entity(name="driver", value_type=ValueType.INT64, 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

docs/tutorials/validating-historical-features.md

@@ -129,7 +129,7 @@ batch_source = FileSource(
 
 
 ```python
-taxi_entity = Entity(name='taxi', join_key='taxi_id')
+taxi_entity = Entity(name='taxi', join_keys=['taxi_id'])
 ```
 
 

sdk/python/feast/feature_view.py

@@ -45,7 +45,7 @@
 DUMMY_ENTITY_NAME = "__dummy"
 DUMMY_ENTITY_VAL = ""
 DUMMY_ENTITY = Entity(
-    name=DUMMY_ENTITY_NAME, join_key=DUMMY_ENTITY_ID, value_type=ValueType.STRING,
+    name=DUMMY_ENTITY_NAME, join_keys=[DUMMY_ENTITY_ID], value_type=ValueType.STRING,
 )
 
 

sdk/python/feast/inference.py

@@ -32,7 +32,9 @@ def update_entities_with_inferred_types_from_feature_views(
         if not (incomplete_entities_keys & set(view.entities)):
             continue  # skip if view doesn't contain any entities that need inference
 
-        col_names_and_types = view.batch_source.get_table_column_names_and_types(config)
+        col_names_and_types = list(
+            view.batch_source.get_table_column_names_and_types(config)
+        )
         for entity_name in view.entities:
             if entity_name in incomplete_entities:
                 entity = incomplete_entities[entity_name]

sdk/python/feast/templates/aws/driver_repo.py

@@ -9,10 +9,10 @@
 driver = Entity(
     # Name of the entity. Must be unique within a project
     name="driver",
-    # The join key of an entity describes the storage level field/column on which
-    # features can be looked up. The join key is also used to join feature
+    # The join keys of an entity describe the storage level field/column on which
+    # features can be looked up. The join keys are also used to join feature
     # tables/views when building feature vectors
-    join_key="driver_id",
+    join_keys=["driver_id"],
     # The storage level type for an entity
     value_type=ValueType.INT64,
 )

sdk/python/feast/templates/gcp/driver_repo.py

@@ -9,10 +9,10 @@
 driver = Entity(
     # Name of the entity. Must be unique within a project
     name="driver",
-    # The join key of an entity describes the storage level field/column on which
-    # features can be looked up. The join key is also used to join feature
+    # The join keys of an entity describe the storage level field/column on which
+    # features can be looked up. The join keys are also used to join feature
     # tables/views when building feature vectors
-    join_key="driver_id",
+    join_keys=["driver_id"],
     # The storage level type for an entity
     value_type=ValueType.INT64,
 )

sdk/python/feast/templates/local/example.py

@@ -16,7 +16,7 @@
 
 # Define an entity for the driver. You can think of entity as a primary key used to
 # fetch features.
-driver = Entity(name="driver", join_key="driver_id", value_type=ValueType.INT64,)
+driver = Entity(name="driver", join_keys=["driver_id"], value_type=ValueType.INT64,)
 
 # 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

sdk/python/feast/templates/snowflake/driver_repo.py

@@ -11,10 +11,10 @@
 driver = Entity(
     # Name of the entity. Must be unique within a project
     name="driver",
-    # The join key of an entity describes the storage level field/column on which
-    # features can be looked up. The join key is also used to join feature
+    # The join keys of an entity describe the storage level field/column on which
+    # features can be looked up. The join keys are also used to join feature
     # tables/views when building feature vectors
-    join_key="driver_id",
+    join_keys=["driver_id"],
 )
 
 # Indicates a data source from which feature values can be retrieved. Sources are queried when building training

sdk/python/tests/example_repos/example_feature_repo_1.py

@@ -45,14 +45,14 @@
 
 driver = Entity(
     name="driver",  # The name is derived from this argument, not object name.
-    join_key="driver_id",
+    join_keys=["driver_id"],
     value_type=ValueType.INT64,
     description="driver id",
 )
 
 customer = Entity(
     name="customer",  # The name is derived from this argument, not object name.
-    join_key="customer_id",
+    join_keys=["customer_id"],
     value_type=ValueType.STRING,
 )
 

sdk/python/tests/example_repos/example_feature_repo_with_entity_join_key.py

@@ -15,7 +15,7 @@
     name="driver_id",
     value_type=ValueType.INT64,
     description="driver id",
-    join_key="driver",
+    join_keys=["driver"],
 )
 
 

sdk/python/tests/integration/feature_repos/universal/entities.py

@@ -6,7 +6,7 @@ def driver(value_type: ValueType = ValueType.INT64):
         name="driver",  # The name is derived from this argument, not object name.
         value_type=value_type,
         description="driver id",
-        join_key="driver_id",
+        join_keys=["driver_id"],
     )
 
 

sdk/python/tests/integration/offline_store/test_universal_historical_retrieval.py

@@ -689,7 +689,7 @@ def test_historical_features_from_bigquery_sources_containing_backfills(environm
         created_timestamp_column="created",
     )
 
-    driver = Entity(name="driver", join_key="driver_id", value_type=ValueType.INT64)
+    driver = Entity(name="driver", join_keys=["driver_id"], value_type=ValueType.INT64)
     driver_fv = FeatureView(
         name="driver_stats",
         entities=["driver"],

sdk/python/tests/integration/registration/test_feature_store.py

@@ -219,7 +219,9 @@ def test_feature_view_inference_success(test_feature_store, dataframe_source):
     with prep_file_source(
         df=dataframe_source, event_timestamp_column="ts_1"
     ) as file_source:
-        entity = Entity(name="id", join_key="id_join_key", value_type=ValueType.INT64)
+        entity = Entity(
+            name="id", join_keys=["id_join_key"], value_type=ValueType.INT64
+        )
 
         fv1 = FeatureView(
             name="fv1",
@@ -436,7 +438,7 @@ def test_reapply_feature_view_success(test_feature_store, dataframe_source):
         df=dataframe_source, event_timestamp_column="ts_1"
     ) as file_source:
 
-        e = Entity(name="id", join_key="id_join_key", value_type=ValueType.STRING)
+        e = Entity(name="id", join_keys=["id_join_key"], value_type=ValueType.STRING)
 
         # Create Feature View
         fv1 = FeatureView(

sdk/python/tests/integration/registration/test_inference.py

@@ -24,12 +24,13 @@
 from feast.inference import (
     update_data_sources_with_inferred_event_timestamp_col,
     update_entities_with_inferred_types_from_feature_views,
+    update_feature_views_with_inferred_features,
 )
 from feast.infra.offline_stores.contrib.spark_offline_store.spark_source import (
     SparkSource,
 )
 from feast.on_demand_feature_view import on_demand_feature_view
-from feast.types import String, UnixTimestamp
+from feast.types import Float32, String, UnixTimestamp
 from tests.utils.data_source_utils import (
     prep_file_source,
     simple_bq_source_using_query_arg,
@@ -53,8 +54,8 @@ def test_update_entities_with_inferred_types_from_feature_views(
             name="fv2", entities=["id"], batch_source=file_source_2, ttl=None,
         )
 
-        actual_1 = Entity(name="id", join_key="id_join_key")
-        actual_2 = Entity(name="id", join_key="id_join_key")
+        actual_1 = Entity(name="id", join_keys=["id_join_key"])
+        actual_2 = Entity(name="id", join_keys=["id_join_key"])
 
         update_entities_with_inferred_types_from_feature_views(
             [actual_1], [fv1], RepoConfig(provider="local", project="test")
@@ -63,16 +64,16 @@ def test_update_entities_with_inferred_types_from_feature_views(
             [actual_2], [fv2], RepoConfig(provider="local", project="test")
         )
         assert actual_1 == Entity(
-            name="id", join_key="id_join_key", value_type=ValueType.INT64
+            name="id", join_keys=["id_join_key"], value_type=ValueType.INT64
         )
         assert actual_2 == Entity(
-            name="id", join_key="id_join_key", value_type=ValueType.STRING
+            name="id", join_keys=["id_join_key"], value_type=ValueType.STRING
         )
 
         with pytest.raises(RegistryInferenceFailure):
             # two viable data types
             update_entities_with_inferred_types_from_feature_views(
-                [Entity(name="id", join_key="id_join_key")],
+                [Entity(name="id", join_keys=["id_join_key"])],
                 [fv1, fv2],
                 RepoConfig(provider="local", project="test"),
             )
@@ -173,9 +174,9 @@ def test_on_demand_features_type_inference():
 
     @on_demand_feature_view(
         sources={"date_request": date_request},
-        features=[
-            Feature(name="output", dtype=ValueType.UNIX_TIMESTAMP),
-            Feature(name="string_output", dtype=ValueType.STRING),
+        schema=[
+            Field(name="output", dtype=UnixTimestamp),
+            Field(name="string_output", dtype=String),
         ],
     )
     def test_view(features_df: pd.DataFrame) -> pd.DataFrame:
@@ -284,3 +285,50 @@ def test_view_with_missing_feature(features_df: pd.DataFrame) -> pd.DataFrame:
 
     with pytest.raises(SpecifiedFeaturesNotPresentError):
         test_view_with_missing_feature.infer_features()
+
+
+def test_update_feature_views_with_inferred_features():
+    file_source = FileSource(name="test", path="test path")
+    entity1 = Entity(name="test1", join_keys=["test_column_1"])
+    entity2 = Entity(name="test2", join_keys=["test_column_2"])
+    feature_view_1 = FeatureView(
+        name="test1",
+        entities=[entity1],
+        schema=[
+            Field(name="feature", dtype=Float32),
+            Field(name="test_column_1", dtype=String),
+        ],
+        source=file_source,
+    )
+    feature_view_2 = FeatureView(
+        name="test2",
+        entities=[entity1, entity2],
+        schema=[
+            Field(name="feature", dtype=Float32),
+            Field(name="test_column_1", dtype=String),
+            Field(name="test_column_2", dtype=String),
+        ],
+        source=file_source,
+    )
+
+    assert len(feature_view_1.schema) == 2
+    assert len(feature_view_1.features) == 2
+
+    # The entity field should be deleted from the schema and features of the feature view.
+    update_feature_views_with_inferred_features(
+        [feature_view_1], [entity1], RepoConfig(provider="local", project="test")
+    )
+    assert len(feature_view_1.schema) == 1
+    assert len(feature_view_1.features) == 1
+
+    assert len(feature_view_2.schema) == 3
+    assert len(feature_view_2.features) == 3
+
+    # The entity fields should be deleted from the schema and features of the feature view.
+    update_feature_views_with_inferred_features(
+        [feature_view_2],
+        [entity1, entity2],
+        RepoConfig(provider="local", project="test"),
+    )
+    assert len(feature_view_2.schema) == 1
+    assert len(feature_view_2.features) == 1