def _infer_pd_column_type(column, series, rows_to_sample):
dtype = None
sample_count = 0
# Loop over all rows for this column to infer types
for key, value in series.iteritems():
sample_count += 1
# Stop sampling at the row limit
if sample_count > rows_to_sample:
continue
# Infer the specific type for this row
current_dtype = python_type_to_feast_value_type(name=column, value=value)
# Make sure the type is consistent for column
if dtype:
if dtype != current_dtype:
raise ValueError(
f"Type mismatch detected in column {column}. Both "
f"the types {current_dtype} and {dtype} "
f"have been found."
)
else:
# Store dtype in field to type map if it isnt already
dtype = current_dtype
return dtype
def create_feature_view(feature_dtype, feature_is_list, data_source):
return driver_feature_view(
data_source,
value_type=python_type_to_feast_value_type(
feature_dtype,
value=get_feature_values_for_dtype(feature_dtype,
feature_is_list)[0],
),
)
def _infer_online_entity_rows(
entity_rows: List[Union[GetOnlineFeaturesRequest.EntityRow, Dict[str,
Any]]],
) -> List[GetOnlineFeaturesRequest.EntityRow]:
"""
Builds a list of EntityRow protos from Python native type format passed by user.
Args:
entity_rows: A list of dictionaries where each key is an entity and each value is
feast.types.Value or Python native form.
Returns:
A list of EntityRow protos parsed from args.
"""
# Maintain backward compatibility with users providing EntityRow Proto
if entity_rows and isinstance(entity_rows[0],
GetOnlineFeaturesRequest.EntityRow):
warnings.warn(
"entity_rows parameter will only be accepting Dict format from Feast v0.7 onwards",
DeprecationWarning,
)
entity_rows_proto = cast(
List[Union[GetOnlineFeaturesRequest.EntityRow]], entity_rows)
return entity_rows_proto
entity_rows_dicts = cast(List[Dict[str, Any]], entity_rows)
entity_row_list = []
entity_type_map = dict()
for entity in entity_rows_dicts:
fields = {}
for key, value in entity.items():
# Allow for feast.types.Value
if isinstance(value, Value):
proto_value = value
else:
# Infer the specific type for this row
current_dtype = python_type_to_feast_value_type(name=key,
value=value)
if key not in entity_type_map:
entity_type_map[key] = current_dtype
else:
if current_dtype != entity_type_map[key]:
raise TypeError(
f"Input entity {key} has mixed types, {current_dtype} and {entity_type_map[key]}. That is not allowed. "
)
proto_value = _python_value_to_proto_value(
current_dtype, value)
fields[key] = proto_value
entity_row_list.append(
GetOnlineFeaturesRequest.EntityRow(fields=fields))
return entity_row_list
def infer_features(self):
"""
Infers the set of features associated to this feature view from the input source.
Args:
config: Configuration object used to configure the feature store.
Raises:
RegistryInferenceFailure: The set of features could not be inferred.
"""
df = pd.DataFrame()
for input in self.inputs.values():
if type(input) == FeatureView:
feature_view = cast(FeatureView, input)
for feature in feature_view.features:
dtype = feast_value_type_to_pandas_type(feature.dtype)
df[f"{feature_view.name}__{feature.name}"] = pd.Series(
dtype=dtype)
df[f"{feature.name}"] = pd.Series(dtype=dtype)
else:
request_data = cast(RequestDataSource, input)
for feature_name, feature_type in request_data.schema.items():
dtype = feast_value_type_to_pandas_type(feature_type)
df[f"{feature_name}"] = pd.Series(dtype=dtype)
output_df: pd.DataFrame = self.udf.__call__(df)
inferred_features = []
for f, dt in zip(output_df.columns, output_df.dtypes):
inferred_features.append(
Feature(name=f,
dtype=python_type_to_feast_value_type(
f, type_name=str(dt))))
if self.features:
missing_features = []
for specified_features in self.features:
if specified_features not in inferred_features:
missing_features.append(specified_features)
if missing_features:
raise errors.SpecifiedFeaturesNotPresentError(
[f.name for f in missing_features], self.name)
else:
self.features = inferred_features
if not self.features:
raise RegistryInferenceFailure(
"OnDemandFeatureView",
f"Could not infer Features for the feature view '{self.name}'.",
)
def infer_features(self):
"""
Infers the set of features associated to this feature view from the input source.
Raises:
RegistryInferenceFailure: The set of features could not be inferred.
"""
df = pd.DataFrame()
for feature_view_projection in self.source_feature_view_projections.values(
):
for feature in feature_view_projection.features:
dtype = feast_value_type_to_pandas_type(
feature.dtype.to_value_type())
df[f"{feature_view_projection.name}__{feature.name}"] = pd.Series(
dtype=dtype)
df[f"{feature.name}"] = pd.Series(dtype=dtype)
for request_data in self.source_request_sources.values():
for field in request_data.schema:
dtype = feast_value_type_to_pandas_type(
field.dtype.to_value_type())
df[f"{field.name}"] = pd.Series(dtype=dtype)
output_df: pd.DataFrame = self.udf.__call__(df)
inferred_features = []
for f, dt in zip(output_df.columns, output_df.dtypes):
inferred_features.append(
Field(
name=f,
dtype=from_value_type(
python_type_to_feast_value_type(f, type_name=str(dt))),
))
if self.features:
missing_features = []
for specified_features in self.features:
if specified_features not in inferred_features:
missing_features.append(specified_features)
if missing_features:
raise SpecifiedFeaturesNotPresentError(
[f.name for f in missing_features], self.name)
else:
self.features = inferred_features
if not self.features:
raise RegistryInferenceFailure(
"OnDemandFeatureView",
f"Could not infer Features for the feature view '{self.name}'.",
)
def _infer_online_entity_rows(
entity_rows: List[Dict[str, Any]],
) -> List[GetOnlineFeaturesRequest.EntityRow]:
"""
Builds a list of EntityRow protos from Python native type format passed by user.
Args:
entity_rows: A list of dictionaries where each key is an entity and each value is
feast.types.Value or Python native form.
Returns:
A list of EntityRow protos parsed from args.
"""
entity_rows_dicts = cast(List[Dict[str, Any]], entity_rows)
entity_row_list = []
entity_type_map = dict()
for entity in entity_rows_dicts:
fields = {}
for key, value in entity.items():
# Allow for feast.types.Value
if isinstance(value, Value):
proto_value = value
else:
# Infer the specific type for this row
current_dtype = python_type_to_feast_value_type(name=key,
value=value)
if key not in entity_type_map:
entity_type_map[key] = current_dtype
else:
if current_dtype != entity_type_map[key]:
raise TypeError(
f"Input entity {key} has mixed types, {current_dtype} and {entity_type_map[key]}. That is not allowed. "
)
proto_value = _python_value_to_proto_value(
current_dtype, value)
fields[key] = proto_value
entity_row_list.append(
GetOnlineFeaturesRequest.EntityRow(fields=fields))
return entity_row_list
