def version(self):
"""
Returns version information from Feast Core and Feast Serving
"""
import pkg_resources
result = {
"sdk": {"version": pkg_resources.get_distribution("feast").version},
"serving": "not configured",
"core": "not configured",
}
if self.serving_url:
serving_version = self._serving_service.GetFeastServingInfo(
GetFeastServingInfoRequest(),
timeout=self._config.getint(CONFIG_GRPC_CONNECTION_TIMEOUT_DEFAULT_KEY),
metadata=self._get_grpc_metadata(),
).version
result["serving"] = {"url": self.serving_url, "version": serving_version}
if self.core_url:
core_version = self._core_service.GetFeastCoreVersion(
GetFeastCoreVersionRequest(),
timeout=self._config.getint(CONFIG_GRPC_CONNECTION_TIMEOUT_DEFAULT_KEY),
metadata=self._get_grpc_metadata(),
).version
result["core"] = {"url": self.core_url, "version": core_version}
return result
def version(self):
"""
Returns version information from Feast Core and Feast Serving
"""
result = {}
if self.serving_url:
self._connect_serving()
serving_version = self._serving_service_stub.GetFeastServingInfo(
GetFeastServingInfoRequest(),
timeout=self._config.getint(
CONFIG_GRPC_CONNECTION_TIMEOUT_DEFAULT_KEY),
).version
result["serving"] = {
"url": self.serving_url,
"version": serving_version
}
if self.core_url:
self._connect_core()
core_version = self._core_service_stub.GetFeastCoreVersion(
GetFeastCoreVersionRequest(),
timeout=self._config.getint(
CONFIG_GRPC_CONNECTION_TIMEOUT_DEFAULT_KEY),
).version
result["core"] = {"url": self.core_url, "version": core_version}
return result
def version(self):
"""
Returns version information from Feast Core and Feast Serving
:return: Dictionary containing Core and Serving versions and status
"""
self._connect_core()
self._connect_serving()
core_version = ""
serving_version = ""
core_status = "not connected"
serving_status = "not connected"
try:
core_version = self._core_service_stub.GetFeastCoreVersion(
GetFeastCoreVersionRequest(),
timeout=GRPC_CONNECTION_TIMEOUT_DEFAULT).version
core_status = "connected"
except grpc.RpcError as e:
print(
format_grpc_exception("GetFeastCoreVersion", e.code(),
e.details()))
try:
serving_version = self._serving_service_stub.GetFeastServingInfo(
GetFeastServingInfoRequest(),
timeout=GRPC_CONNECTION_TIMEOUT_DEFAULT).version
serving_status = "connected"
except grpc.RpcError as e:
print(
format_grpc_exception("GetFeastServingInfo", e.code(),
e.details()))
return {
"core": {
"url": self.core_url,
"version": core_version,
"status": core_status,
},
"serving": {
"url": self.serving_url,
"version": serving_version,
"status": serving_status,
},
}
def version(self, sdk_only=False):
"""
Returns version information from Feast Core and Feast Serving
"""
import pkg_resources
try:
sdk_version = pkg_resources.get_distribution("feast").version
except pkg_resources.DistributionNotFound:
sdk_version = "local build"
if sdk_only:
return sdk_version
result = {
"sdk": {
"version": sdk_version
},
"serving": "not configured",
"core": "not configured",
}
if self.serving_url:
serving_version = self._serving_service.GetFeastServingInfo(
GetFeastServingInfoRequest(),
timeout=self._config.getint(opt.GRPC_CONNECTION_TIMEOUT),
metadata=self._get_grpc_metadata(),
).version
result["serving"] = {
"url": self.serving_url,
"version": serving_version
}
if self.core_url:
core_version = self._core_service.GetFeastCoreVersion(
GetFeastCoreVersionRequest(),
timeout=self._config.getint(opt.GRPC_CONNECTION_TIMEOUT),
metadata=self._get_grpc_metadata(),
).version
result["core"] = {"url": self.core_url, "version": core_version}
return result
def get_batch_features(
self,
feature_refs: List[str],
entity_rows: Union[pd.DataFrame, str],
default_project: str = None,
) -> RetrievalJob:
"""
Retrieves historical features from a Feast Serving deployment.
Args:
feature_refs (List[str]):
List of feature references that will be returned for each entity.
Each feature reference should have the following format
"project/feature:version".
entity_rows (Union[pd.DataFrame, str]):
Pandas dataframe containing entities and a 'datetime' column.
Each entity in a feature set must be present as a column in this
dataframe. The datetime column must contain timestamps in
datetime64 format.
default_project: Default project where feature values will be found.
Returns:
feast.job.RetrievalJob:
Returns a retrival job object that can be used to monitor retrieval
progress asynchronously, and can be used to materialize the
results.
Examples:
>>> from feast import Client
>>> from datetime import datetime
>>>
>>> feast_client = Client(core_url="localhost:6565", serving_url="localhost:6566")
>>> feature_refs = ["my_project/bookings_7d:1", "booking_14d"]
>>> entity_rows = pd.DataFrame(
>>> {
>>> "datetime": [pd.datetime.now() for _ in range(3)],
>>> "customer": [1001, 1002, 1003],
>>> }
>>> )
>>> feature_retrieval_job = feast_client.get_batch_features(
>>> feature_refs, entity_rows, default_project="my_project")
>>> df = feature_retrieval_job.to_dataframe()
>>> print(df)
"""
self._connect_serving()
feature_references = _build_feature_references(
feature_refs=feature_refs, default_project=default_project)
# Retrieve serving information to determine store type and
# staging location
serving_info = self._serving_service_stub.GetFeastServingInfo(
GetFeastServingInfoRequest(),
timeout=self._config.getint(
CONFIG_GRPC_CONNECTION_TIMEOUT_DEFAULT_KEY),
) # type: GetFeastServingInfoResponse
if serving_info.type != FeastServingType.FEAST_SERVING_TYPE_BATCH:
raise Exception(
f'You are connected to a store "{self._serving_url}" which '
f"does not support batch retrieval ")
if isinstance(entity_rows, pd.DataFrame):
# Pandas DataFrame detected
# Remove timezone from datetime column
if isinstance(entity_rows["datetime"].dtype,
pd.core.dtypes.dtypes.DatetimeTZDtype):
entity_rows["datetime"] = pd.DatetimeIndex(
entity_rows["datetime"]).tz_localize(None)
elif isinstance(entity_rows, str):
# String based source
if not entity_rows.endswith((".avro", "*")):
raise Exception(
f"Only .avro and wildcard paths are accepted as entity_rows"
)
else:
raise Exception(f"Only pandas.DataFrame and str types are allowed"
f" as entity_rows, but got {type(entity_rows)}.")
# Export and upload entity row DataFrame to staging location
# provided by Feast
staged_files = export_source_to_staging_location(
entity_rows, serving_info.job_staging_location) # type: List[str]
request = GetBatchFeaturesRequest(
features=feature_references,
dataset_source=DatasetSource(file_source=DatasetSource.FileSource(
file_uris=staged_files,
data_format=DataFormat.DATA_FORMAT_AVRO)),
)
# Retrieve Feast Job object to manage life cycle of retrieval
response = self._serving_service_stub.GetBatchFeatures(request)
return RetrievalJob(response.job, self._serving_service_stub)
def get_batch_features(self, feature_ids: List[str],
entity_rows: pd.DataFrame) -> Job:
"""
Retrieves historical features from a Feast Serving deployment.
Args:
feature_ids: List of feature ids that will be returned for each entity.
Each feature id should have the following format "feature_set_name:version:feature_name".
entity_rows: Pandas dataframe containing entities and a 'datetime' column. Each entity in
a feature set must be present as a column in this dataframe. The datetime column must
contain timestamps in datetime64 format
Returns:
Feast batch retrieval job: feast.job.Job
Example usage:
============================================================
>>> from feast import Client
>>> from datetime import datetime
>>>
>>> feast_client = Client(core_url="localhost:6565", serving_url="localhost:6566")
>>> feature_ids = ["customer:1:bookings_7d"]
>>> entity_rows = pd.DataFrame(
>>> {
>>> "datetime": [pd.datetime.now() for _ in range(3)],
>>> "customer": [1001, 1002, 1003],
>>> }
>>> )
>>> feature_retrieval_job = feast_client.get_batch_features(feature_ids, entity_rows)
>>> df = feature_retrieval_job.to_dataframe()
>>> print(df)
"""
self._connect_serving()
try:
fs_request = _build_feature_set_request(feature_ids)
# Validate entity rows based on entities in Feast Core
self._validate_entity_rows_for_batch_retrieval(
entity_rows, fs_request)
# We want the timestamp column naming to be consistent with the
# rest of Feast
entity_rows.columns = [
"event_timestamp" if col == "datetime" else col
for col in entity_rows.columns
]
# Remove timezone from datetime column
if isinstance(
entity_rows["event_timestamp"].dtype,
pd.core.dtypes.dtypes.DatetimeTZDtype,
):
entity_rows["event_timestamp"] = pd.DatetimeIndex(
entity_rows["event_timestamp"]).tz_localize(None)
# Retrieve serving information to determine store type and staging location
serving_info = self._serving_service_stub.GetFeastServingInfo(
GetFeastServingInfoRequest(),
timeout=GRPC_CONNECTION_TIMEOUT_DEFAULT
) # type: GetFeastServingInfoResponse
if serving_info.type != FeastServingType.FEAST_SERVING_TYPE_BATCH:
raise Exception(
f'You are connected to a store "{self._serving_url}" which does not support batch retrieval'
)
# Export and upload entity row dataframe to staging location provided by Feast
staged_file = export_dataframe_to_staging_location(
entity_rows, serving_info.job_staging_location) # type: str
request = GetBatchFeaturesRequest(
feature_sets=fs_request,
dataset_source=DatasetSource(
file_source=DatasetSource.FileSource(
file_uris=[staged_file],
data_format=DataFormat.DATA_FORMAT_AVRO)),
)
# Retrieve Feast Job object to manage life cycle of retrieval
response = self._serving_service_stub.GetBatchFeatures(request)
return Job(response.job, self._serving_service_stub)
except grpc.RpcError as e:
print(
format_grpc_exception("GetBatchFeatures", e.code(),
e.details()))
