Add data preparation scripts for UK Biobank analysis

Browse Source

- 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.

...

This commit is contained in:

Jiarui Li

2025-12-04 11:26:49 +08:00

parent d48c62466f

commit 9ca8909e3a

8 changed files with 5420 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

1257

labels.csv Normal file

File diff suppressed because it is too large Load Diff