def from_proto(cls, feature_table_proto: FeatureTableProto):
"""
Creates a feature table from a protobuf representation of a feature table
Args:
feature_table_proto: A protobuf representation of a feature table
Returns:
Returns a FeatureTableProto object based on the feature table protobuf
"""
feature_table = cls(
name=feature_table_proto.spec.name,
entities=[entity for entity in feature_table_proto.spec.entities],
features=[
Feature.from_proto(feature)
for feature in feature_table_proto.spec.features
],
labels=feature_table_proto.spec.labels,
max_age=(None if feature_table_proto.spec.max_age.seconds == 0
and feature_table_proto.spec.max_age.nanos == 0 else
feature_table_proto.spec.max_age),
batch_source=DataSource.from_proto(
feature_table_proto.spec.batch_source),
stream_source=(
None
if not feature_table_proto.spec.stream_source.ByteSize() else
DataSource.from_proto(feature_table_proto.spec.stream_source)),
)
feature_table._created_timestamp = feature_table_proto.meta.created_timestamp
return feature_table
def from_proto(cls, feature_view_proto: FeatureViewProto):
"""
Creates a feature view from a protobuf representation of a feature view.
Args:
feature_view_proto: A protobuf representation of a feature view.
Returns:
A FeatureViewProto object based on the feature view protobuf.
"""
batch_source = DataSource.from_proto(feature_view_proto.spec.batch_source)
stream_source = (
DataSource.from_proto(feature_view_proto.spec.stream_source)
if feature_view_proto.spec.HasField("stream_source")
else None
)
feature_view = cls(
name=feature_view_proto.spec.name,
entities=[entity for entity in feature_view_proto.spec.entities],
features=[
Feature(
name=feature.name,
dtype=ValueType(feature.value_type),
labels=dict(feature.labels),
)
for feature in feature_view_proto.spec.features
],
tags=dict(feature_view_proto.spec.tags),
online=feature_view_proto.spec.online,
ttl=(
None
if feature_view_proto.spec.ttl.seconds == 0
and feature_view_proto.spec.ttl.nanos == 0
else feature_view_proto.spec.ttl
),
batch_source=batch_source,
stream_source=stream_source,
)
if feature_view_proto.meta.HasField("created_timestamp"):
feature_view.created_timestamp = (
feature_view_proto.meta.created_timestamp.ToDatetime()
)
if feature_view_proto.meta.HasField("last_updated_timestamp"):
feature_view.last_updated_timestamp = (
feature_view_proto.meta.last_updated_timestamp.ToDatetime()
)
for interval in feature_view_proto.meta.materialization_intervals:
feature_view.materialization_intervals.append(
(
utils.make_tzaware(interval.start_time.ToDatetime()),
utils.make_tzaware(interval.end_time.ToDatetime()),
)
)
return feature_view
def from_proto(cls, feature_view_proto: FeatureViewProto):
"""
Creates a feature view from a protobuf representation of a feature view.
Args:
feature_view_proto: A protobuf representation of a feature view.
Returns:
A FeatureViewProto object based on the feature view protobuf.
"""
batch_source = DataSource.from_proto(
feature_view_proto.spec.batch_source)
stream_source = (
DataSource.from_proto(feature_view_proto.spec.stream_source)
if feature_view_proto.spec.HasField("stream_source") else None)
feature_view = cls(
name=feature_view_proto.spec.name,
entities=[entity for entity in feature_view_proto.spec.entities],
schema=[
Field.from_proto(field_proto)
for field_proto in feature_view_proto.spec.features
],
description=feature_view_proto.spec.description,
tags=dict(feature_view_proto.spec.tags),
owner=feature_view_proto.spec.owner,
online=feature_view_proto.spec.online,
ttl=(timedelta(
days=0) if feature_view_proto.spec.ttl.ToNanoseconds() == 0
else feature_view_proto.spec.ttl.ToTimedelta()),
source=batch_source,
)
if stream_source:
feature_view.stream_source = stream_source
# FeatureViewProjections are not saved in the FeatureView proto.
# Create the default projection.
feature_view.projection = FeatureViewProjection.from_definition(
feature_view)
if feature_view_proto.meta.HasField("created_timestamp"):
feature_view.created_timestamp = (
feature_view_proto.meta.created_timestamp.ToDatetime())
if feature_view_proto.meta.HasField("last_updated_timestamp"):
feature_view.last_updated_timestamp = (
feature_view_proto.meta.last_updated_timestamp.ToDatetime())
for interval in feature_view_proto.meta.materialization_intervals:
feature_view.materialization_intervals.append((
utils.make_tzaware(interval.start_time.ToDatetime()),
utils.make_tzaware(interval.end_time.ToDatetime()),
))
return feature_view
def GetHistoricalFeatures(self, request: GetHistoricalFeaturesRequest,
context):
"""Produce a training dataset, return a job id that will provide a file reference"""
if not self.is_whitelisted(request.project):
raise ValueError(
f"Project {request.project} is not whitelisted. Please contact your Feast administrator to whitelist it."
)
job = start_historical_feature_retrieval_job(
client=self.client,
project=request.project,
entity_source=DataSource.from_proto(request.entity_source),
feature_tables=self.client._get_feature_tables_from_feature_refs(
list(request.feature_refs), request.project),
output_format=request.output_format,
output_path=request.output_location,
)
output_file_uri = job.get_output_file_uri(block=False)
job_start_timestamp = Timestamp()
job_start_timestamp.FromDatetime(job.get_start_time())
return GetHistoricalFeaturesResponse(
id=job.get_id(),
output_file_uri=output_file_uri,
job_start_time=job_start_timestamp,
)
def from_proto(cls, feature_view_proto: FeatureViewProto):
"""
Creates a feature view from a protobuf representation of a feature view
Args:
feature_view_proto: A protobuf representation of a feature view
Returns:
Returns a FeatureViewProto object based on the feature view protobuf
"""
feature_view = cls(
name=feature_view_proto.spec.name,
entities=[entity for entity in feature_view_proto.spec.entities],
features=[
Feature(
name=feature.name,
dtype=ValueType(feature.value_type),
labels=feature.labels,
) for feature in feature_view_proto.spec.features
],
tags=dict(feature_view_proto.spec.tags),
online=feature_view_proto.spec.online,
ttl=(None if feature_view_proto.spec.ttl.seconds == 0
and feature_view_proto.spec.ttl.nanos == 0 else
feature_view_proto.spec.ttl),
input=DataSource.from_proto(feature_view_proto.spec.input),
)
feature_view.created_timestamp = feature_view_proto.meta.created_timestamp
return feature_view
def GetHistoricalFeatures(self, request, context):
"""Produce a training dataset, return a job id that will provide a file reference"""
job = self.client.get_historical_features(
request.feature_refs,
entity_source=DataSource.from_proto(request.entity_source),
project=request.project,
output_location=request.output_location,
)
output_file_uri = job.get_output_file_uri(block=False)
return GetHistoricalFeaturesResponse(id=job.get_id(),
output_file_uri=output_file_uri)
def GetHistoricalFeatures(self, request: GetHistoricalFeaturesRequest,
context):
"""Produce a training dataset, return a job id that will provide a file reference"""
job = start_historical_feature_retrieval_job(
client=self.client,
project=request.project,
entity_source=DataSource.from_proto(request.entity_source),
feature_tables=self.client._get_feature_tables_from_feature_refs(
list(request.feature_refs), request.project),
output_format=request.output_format,
output_path=request.output_location,
)
output_file_uri = job.get_output_file_uri(block=False)
return GetHistoricalFeaturesResponse(id=job.get_id(),
output_file_uri=output_file_uri)
def list_data_sources(self,
project: str,
allow_cache: bool = False) -> List[DataSource]:
"""
Retrieve a list of data sources from the registry
Args:
project: Filter data source based on project name
allow_cache: Whether to allow returning data sources from a cached registry
Returns:
List of data sources
"""
registry_proto = self._get_registry_proto(allow_cache=allow_cache)
data_sources = []
for data_source_proto in registry_proto.data_sources:
if data_source_proto.project == project:
data_sources.append(DataSource.from_proto(data_source_proto))
return data_sources
def get_data_source(self,
name: str,
project: str,
allow_cache: bool = False) -> DataSource:
"""
Retrieves a data source.
Args:
name: Name of data source
project: Feast project that this data source belongs to
allow_cache: Whether to allow returning this data source from a cached registry
Returns:
Returns either the specified data source, or raises an exception if none is found
"""
registry = self._get_registry_proto(allow_cache=allow_cache)
for data_source in registry.data_sources:
if data_source.project == project and data_source.name == name:
return DataSource.from_proto(data_source)
raise DataSourceObjectNotFoundException(name, project=project)