Pandas UDF is the ideal connection between PySpark and DL model inference workload. However, user needs to load the model file first to make predictions. It is common to see models of size ~100MB or bigger. If the Pandas UDF execution is limited to each batch, user needs to repeatedly load the same model for every batch in the same python worker process, which is inefficient.
We can provide users the iterator of batches in pd.DataFrame and let user code handle it:
The type of each batch is:
- a pd.Series if UDF is called with a single non-struct-type column
- a tuple of pd.Series if UDF is called with more than one Spark DF columns
- a pd.DataFrame if UDF is called with a single StructType column
If the UDF doesn't return the same number of records for the entire partition, user should see an error. We don't restrict that every yield should match the input batch size.
Another benefit is with iterator interface and asyncio from Python, it is flexible for users to implement data pipelining.