schema: '2.0'
stages:
  subset:
    cmd: python src/subset_data.py
    deps:
    - path: data/raw/Wellcome-grants-awarded-1-October-2005-to-04-05-2022.csv
      md5: 5c0d0e532709648b61625e7e130dfaa4
      size: 31028261
    - path: src/subset_data.py
      md5: f4cffd497cb8341cf05728e89cbb0871
      size: 1008
    params:
      params.yaml:
        n_docs: 500
    outs:
    - path: data/processed/wellcome_grant_descriptions.csv
      md5: 18dd6a7611d7f53b1067def7ba075cba
      size: 644736
  entities:
    cmd: python src/process_docs.py
    deps:
    - path: data/processed/wellcome_grant_descriptions.csv
      md5: 18dd6a7611d7f53b1067def7ba075cba
      size: 644736
    - path: src/process_docs.py
      md5: 54d0e1cf9a85cba745fe80206b7c71d0
      size: 1723
    outs:
    - path: data/processed/entities.jsonl
      md5: ca8a907b4d66d5541bc1b6b508abd7eb
      size: 94862