Hello,
Thank you for your work. I’ve been running the pipeline and wanted to clarify the expected output up to Step 4. I did not encounter any errors, but some expected folders appear to be missing or empty.
The preprocessed_timeseries, formatted_medication, partially_processed_timeseries and formatted_timeseries folders (which I believe should contain the harmonized data before blending) are empty. Instead, I see long_medication and long_timeseries, which seem to contain blended data. I wanted to check if this is the expected.
Additionally, I was wondering if this data is being downsampled at this stage? If so, is there a way to adjust the downsampling interval (e.g., avoid downsampling to hourly resolution)?
Thanks.
Hello,
Thank you for your work. I’ve been running the pipeline and wanted to clarify the expected output up to Step 4. I did not encounter any errors, but some expected folders appear to be missing or empty.
The preprocessed_timeseries, formatted_medication, partially_processed_timeseries and formatted_timeseries folders (which I believe should contain the harmonized data before blending) are empty. Instead, I see long_medication and long_timeseries, which seem to contain blended data. I wanted to check if this is the expected.
Additionally, I was wondering if this data is being downsampled at this stage? If so, is there a way to adjust the downsampling interval (e.g., avoid downsampling to hourly resolution)?
Thanks.