I have a record which I want to ingest into a feature group of a sagemaker feature store. The feature name 'z' is fractional in definition schema. I have some missing data from feature 'z'. When I try to ingest it, I get errors:
[{'FeatureName': 'ji', 'ValueAsString': '8829a094'}, {'FeatureName': 'time', 'ValueAsString': '2020-08-27T13:00:00Z'}, {'FeatureName': 't2', 'ValueAsString': '289.26111111111106'}, {'FeatureName': 're', 'ValueAsString': '86'}, {'FeatureName': 'pwat', 'ValueAsString': '0.9609375'}, {'FeatureName': 'li700', 'ValueAsString': '3'}, {'FeatureName': 'c', 'ValueAsString': '0'}, {'FeatureName': 'd', 'ValueAsString': '0'}, {'FeatureName': 'x', 'ValueAsString': '0'}, {'FeatureName': 'y', 'ValueAsString': '0.0'}, {'FeatureName': 'z', 'ValueAsString': 'None'}]
Attempted to parse the feature value for the feature named [z] into a FeatureValue of type Fractional. The provided value must be within the range of a double precision floating point number defined by the IEEE 754 standard. The input format can be in either decimal form or scientific notation.
How do you deal with missing data for ingesting into feature groups?
found the answer myself: