Closed WeichenXu123 closed 4 years ago
@mengxr
Because there's this PR https://github.com/uber/petastorm/pull/512
we don't need add a selected_field
into TransformSpec. We can directly infer schema from transformed result(and schema field order will be the field order of the transformed result pandas dataframe).
Create a new PR https://github.com/uber/petastorm/pull/513
[WIP]Keep petastorm dataset/dataloader schema fields order the same with spark dataframe.