- Introduced `prepare_data.R` for merging disease and other data from CSV files.
- Added `prepare_data.py` for processing UK Biobank data, including:
- Mapping field IDs to human-readable names.
- Handling date variables and converting them to offsets.
- Processing disease events and constructing tabular features.
- Splitting data into training, validation, and test sets.
- Saving processed data to binary and CSV formats.
