stages: subset: cmd: python src/subset_data.py deps: - src/subset_data.py - data/raw/Wellcome-grants-awarded-1-October-2005-to-04-05-2022.csv params: - n_docs outs: - data/processed/wellcome_grant_descriptions.csv entities: cmd: python src/process_docs.py deps: - src/process_docs.py - data/processed/wellcome_grant_descriptions.csv outs: - data/processed/entities.jsonl: cache: false