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 <[email protected]>

* Convert iterator to list so it can be used repeatedly

Signed-off-by: Felix Wang <[email protected]>

* Format

Signed-off-by: Felix Wang <[email protected]>

Author: felixwang9817

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