feat: Switch from Feature to Field (#2514)

* Add type annotation Signed-off-by: Felix Wang <wangfelix98@gmail.com> * Switch from Feature to Field for FeatureViewProjection Signed-off-by: Felix Wang <wangfelix98@gmail.com> * Switch from Feature to Field for BaseFeatureView Signed-off-by: Felix Wang <wangfelix98@gmail.com> * Switch from Feature to Field for RequestFeatureView Signed-off-by: Felix Wang <wangfelix98@gmail.com> * Enforce kwargs for ODFVs and switch from Feature to Field and from `features` to `schema` Signed-off-by: Felix Wang <wangfelix98@gmail.com> * Switch from Feature to Field and from `features` to `schema` for FeatureView Signed-off-by: Felix Wang <wangfelix98@gmail.com> * Fix references to `features` and Feature Signed-off-by: Felix Wang <wangfelix98@gmail.com> * Switch from `Feature` to `Field` for ODFV in tests Signed-off-by: Felix Wang <wangfelix98@gmail.com> * Switch from Feature to Field in templates Signed-off-by: Felix Wang <wangfelix98@gmail.com> * Switch from Feature to Field in example test repos Signed-off-by: Felix Wang <wangfelix98@gmail.com> * Switch from Feature to Field in registration integration tests Signed-off-by: Felix Wang <wangfelix98@gmail.com> * Switch from Feature to Field in non-registration integration tests Signed-off-by: Felix Wang <wangfelix98@gmail.com> * Switch from Feature to Field in random tests Signed-off-by: Felix Wang <wangfelix98@gmail.com> * Switch from Feature to Field in ui Signed-off-by: Felix Wang <wangfelix98@gmail.com> * Switch from Feature to Field in some universal feature views Signed-off-by: Felix Wang <wangfelix98@gmail.com> * Switch from Feature to Field in docs Signed-off-by: Felix Wang <wangfelix98@gmail.com> * Add assertion that BaseFeatureView is always initialized with a name Signed-off-by: Felix Wang <wangfelix98@gmail.com> * Fix imports in docs Signed-off-by: Felix Wang <wangfelix98@gmail.com>
feast-dev · Apr 12, 2022 · 6a03bed · 6a03bed
1 parent 90db1d1
commit 6a03bed
Show file tree

Hide file tree

Showing 38 changed files with 557 additions and 373 deletions.
diff --git a/docs/getting-started/concepts/feature-view.md b/docs/getting-started/concepts/feature-view.md
@@ -7,12 +7,14 @@ A feature view is an object that represents a logical group of time-series featu
 {% tabs %}
 {% tab title="driver_trips_feature_view.py" %}
 ```python
+from feast import BigQuerySource, FeatureView, Field, Float32, Int64
+
 driver_stats_fv = FeatureView(
     name="driver_activity",
     entities=["driver"],
-    features=[
-        Feature(name="trips_today", dtype=ValueType.INT64),
-        Feature(name="rating", dtype=ValueType.FLOAT),
+    schema=[
+        Field(name="trips_today", dtype=Int64),
+        Field(name="rating", dtype=Float32),
     ],
     batch_source=BigQuerySource(
         table_ref="feast-oss.demo_data.driver_activity"
@@ -39,11 +41,13 @@ If a feature view contains features that are not related to a specific entity, t
 {% tabs %}
 {% tab title="global_stats.py" %}
 ```python
+from feast import BigQuerySource, FeatureView, Field, Int64
+
 global_stats_fv = FeatureView(
     name="global_stats",
     entities=[],
-    features=[
-        Feature(name="total_trips_today_by_all_drivers", dtype=ValueType.INT64),
+    schema=[
+        Field(name="total_trips_today_by_all_drivers", dtype=Int64),
     ],
     batch_source=BigQuerySource(
         table_ref="feast-oss.demo_data.global_stats"
@@ -70,13 +74,15 @@ 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, Int32, ValueType
+
 location = Entity(name="location", join_key="location_id", value_type=ValueType.INT64)
 
 location_stats_fv= FeatureView(
     name="location_stats",
     entities=["location"],
-    features=[
-        Feature(name="temperature", dtype=ValueType.INT32)
+    schema=[
+        Field(name="temperature", dtype=Int32)
     ],
     batch_source=BigQuerySource(
         table_ref="feast-oss.demo_data.location_stats"
@@ -115,9 +121,11 @@ A feature is an individual measurable property. It is typically a property obser
 Features are defined as part of feature views. Since Feast does not transform data, a feature is essentially a schema that only contains a name and a type:
 
 ```python
-trips_today = Feature(
+from feast import Field, Float32
+
+trips_today = Field(
     name="trips_today",
-    dtype=ValueType.FLOAT
+    dtype=Float32
 )
 ```
 

diff --git a/docs/getting-started/concepts/point-in-time-joins.md b/docs/getting-started/concepts/point-in-time-joins.md
@@ -7,12 +7,14 @@ Feature values in Feast are modeled as time-series records. Below is an example
 The above table can be registered with Feast through the following feature view:
 
 ```python
+from feast import FeatureView, Field, FileSource, Float32, Int64
+
 driver_stats_fv = FeatureView(
     name="driver_hourly_stats",
     entities=["driver"],
-    features=[
-        Feature(name="trips_today", dtype=ValueType.INT64),
-        Feature(name="earnings_today", dtype=ValueType.FLOAT),
+    schema=[
+        Field(name="trips_today", dtype=Int64),
+        Field(name="earnings_today", dtype=Float32),
     ],
     ttl=timedelta(hours=2),
     batch_source=FileSource(

diff --git a/docs/getting-started/quickstart.md b/docs/getting-started/quickstart.md
@@ -80,16 +80,16 @@ online_store:
 ```python
 # This is an example feature definition file
 
-from google.protobuf.duration_pb2 import Duration
+from datetime import timedelta
 
-from feast import Entity, Feature, FeatureView, FileSource, ValueType
+from feast import Entity, FeatureView, Field, FileSource, Float32, Int64, ValueType
 
 # 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
 # for more info.
 driver_hourly_stats = FileSource(
     path="/content/feature_repo/data/driver_stats.parquet",
-    event_timestamp_column="event_timestamp",
+    timestamp_field="event_timestamp",
     created_timestamp_column="created",
 )
 
@@ -106,10 +106,10 @@ driver_hourly_stats_view = FeatureView(
     name="driver_hourly_stats",
     entities=["driver"],  # reference entity by name
     ttl=Duration(seconds=86400 * 1),
-    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,
@@ -149,16 +149,16 @@ feast apply
 ```python
 # This is an example feature definition file
 
-from google.protobuf.duration_pb2 import Duration
+from datetime import timedelta
 
-from feast import Entity, Feature, FeatureView, FileSource, ValueType
+from feast import Entity, FeatureView, Field, FileSource, Float32, Int64, ValueType
 
 # 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
 # for more info.
 driver_hourly_stats = FileSource(
     path="/content/feature_repo/data/driver_stats.parquet",
-    event_timestamp_column="event_timestamp",
+    timestamp_field="event_timestamp",
     created_timestamp_column="created",
 )
 
@@ -175,10 +175,10 @@ driver_hourly_stats_view = FeatureView(
     name="driver_hourly_stats",
     entities=["driver"],  # reference entity by name
     ttl=Duration(seconds=86400 * 1),
-    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,

diff --git a/docs/reference/data-sources/push.md b/docs/reference/data-sources/push.md
@@ -14,7 +14,7 @@ When using a PushSource as a stream source in the definition of a feature view,
 ### Defining a push source
 
 ```python
-from feast import PushSource, ValueType, BigQuerySource, FeatureView, Feature
+from feast import PushSource, ValueType, BigQuerySource, FeatureView, Feature, Field, Int64
 
 push_source = PushSource(
     name="push_source",
@@ -25,7 +25,7 @@ push_source = PushSource(
 fv = FeatureView(
     name="feature view",
     entities=["user_id"],
-    features=[Feature(name="life_time_value", dtype=ValueType.INT64)],
+    schema=[Field(name="life_time_value", dtype=Int64)],
     stream_source=push_source,
 )
 ```

diff --git a/docs/reference/feature-repository.md b/docs/reference/feature-repository.md
@@ -89,7 +89,7 @@ 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, ValueType
+from feast import BigQuerySource, Entity, Feature, FeatureView, Field, Float32, String, ValueType
 
 driver_locations_source = BigQuerySource(
     table_ref="rh_prod.ride_hailing_co.drivers",
@@ -107,9 +107,9 @@ driver_locations = FeatureView(
     name="driver_locations",
     entities=["driver"],
     ttl=timedelta(days=1),
-    features=[
-        Feature(name="lat", dtype=ValueType.FLOAT),
-        Feature(name="lon", dtype=ValueType.STRING),
+    schema=[
+        Field(name="lat", dtype=Float32),
+        Field(name="lon", dtype=String),
     ],
     batch_source=driver_locations_source,
 )

diff --git a/docs/reference/feature-repository/README.md b/docs/reference/feature-repository/README.md
@@ -94,7 +94,7 @@ 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, ValueType
+from feast import BigQuerySource, Entity, Feature, FeatureView, Field, Float32, String, ValueType
 
 driver_locations_source = BigQuerySource(
     table_ref="rh_prod.ride_hailing_co.drivers",
@@ -112,9 +112,9 @@ driver_locations = FeatureView(
     name="driver_locations",
     entities=["driver"],
     ttl=timedelta(days=1),
-    features=[
-        Feature(name="lat", dtype=ValueType.FLOAT),
-        Feature(name="lon", dtype=ValueType.STRING),
+    schema=[
+        Field(name="lat", dtype=Float32),
+        Field(name="lon", dtype=String),
     ],
     batch_source=driver_locations_source,
 )

diff --git a/docs/tutorials/validating-historical-features.md b/docs/tutorials/validating-historical-features.md
@@ -107,7 +107,7 @@ pyarrow.parquet.write_table(entities_2019_table, "entities.parquet")
 import pyarrow.parquet
 import pandas as pd
 
-from feast import Feature, FeatureView, Entity, FeatureStore
+from feast import Feature, FeatureView, Entity, FeatureStore, Field, Float64, Int64
 from feast.value_type import ValueType
 from feast.data_format import ParquetFormat
 from feast.on_demand_feature_view import on_demand_feature_view
@@ -137,10 +137,10 @@ trips_stats_fv = FeatureView(
     name='trip_stats',
     entities=['taxi'],
     features=[
-        Feature("total_miles_travelled", ValueType.DOUBLE),
-        Feature("total_trip_seconds", ValueType.DOUBLE),
-        Feature("total_earned", ValueType.DOUBLE),
-        Feature("trip_count", ValueType.INT64),
+        Field(name="total_miles_travelled", dtype=Float64),
+        Field(name="total_trip_seconds", dtype=Float64),
+        Field(name="total_earned", dtype=Float64),
+        Field(name="trip_count", dtype=Int64),
 
     ],
     ttl=Duration(seconds=86400),

diff --git a/protos/feast/core/FeatureView.proto b/protos/feast/core/FeatureView.proto
@@ -48,7 +48,7 @@ message FeatureViewSpec {
     // Feature View. Not updatable.
     repeated string entities = 3;
 
-    // List of features specifications for each feature defined with this feature view.
+    // List of specifications for each field defined as part of this feature view.
     repeated FeatureSpecV2 features = 4;
 
     // Description of the feature view.

diff --git a/sdk/python/feast/__init__.py b/sdk/python/feast/__init__.py
@@ -13,9 +13,22 @@
 from .feature_service import FeatureService
 from .feature_store import FeatureStore
 from .feature_view import FeatureView
+from .field import Field
 from .on_demand_feature_view import OnDemandFeatureView
 from .repo_config import RepoConfig
 from .request_feature_view import RequestFeatureView
+from .types import (
+    Array,
+    Bool,
+    Bytes,
+    Float32,
+    Float64,
+    Int32,
+    Int64,
+    Invalid,
+    String,
+    UnixTimestamp,
+)
 from .value_type import ValueType
 
 logging.basicConfig(
@@ -35,6 +48,7 @@
     "KafkaSource",
     "KinesisSource",
     "Feature",
+    "Field",
     "FeatureService",
     "FeatureStore",
     "FeatureView",
@@ -48,4 +62,15 @@
     "RequestFeatureView",
     "SnowflakeSource",
     "PushSource",
+    # Types
+    "Array",
+    "Invalid",
+    "Bytes",
+    "String",
+    "Bool",
+    "Int32",
+    "Int64",
+    "Float32",
+    "Float64",
+    "UnixTimestamp",
 ]
diff --git a/sdk/python/feast/base_feature_view.py b/sdk/python/feast/base_feature_view.py
@@ -18,8 +18,8 @@
 from google.protobuf.json_format import MessageToJson
 from proto import Message
 
-from feast.feature import Feature
 from feast.feature_view_projection import FeatureViewProjection
+from feast.field import Field
 
 
 class BaseFeatureView(ABC):
@@ -41,7 +41,7 @@ class BaseFeatureView(ABC):
     """
 
     name: str
-    features: List[Feature]
+    features: List[Field]
     description: str
     tags: Dict[str, str]
     owner: str
@@ -53,8 +53,8 @@ class BaseFeatureView(ABC):
     def __init__(
         self,
         *,
-        name: Optional[str] = None,
-        features: Optional[List[Feature]] = None,
+        name: str,
+        features: Optional[List[Field]] = None,
         description: str = "",
         tags: Optional[Dict[str, str]] = None,
         owner: str = "",
@@ -64,7 +64,7 @@ def __init__(
 
         Args:
             name: The unique name of the base feature view.
-            features: The list of features defined as part of this base feature view.
+            features (optional): The list of features defined as part of this base feature view.
             description (optional): A human-readable description.
             tags (optional): A dictionary of key-value pairs to store arbitrary metadata.
             owner (optional): The owner of the base feature view, typically the email of the
@@ -73,12 +73,9 @@ def __init__(
         Raises:
             ValueError: A field mapping conflicts with an Entity or a Feature.
         """
-        if not name:
-            raise ValueError("Name needs to be provided")
+        assert name is not None
         self.name = name
-
         self.features = features or []
-
         self.description = description
         self.tags = tags or {}
         self.owner = owner