project.yaml

version: '4.0'

actions:
  dummy_dataset_1:
    run: r:latest analysis/dummy_definition_1.R
    outputs:
      highly_sensitive:
        dataset: output/dummy_dataset_1.csv.gz

  generate_dataset_1:
    run: ehrql:v1 generate-dataset analysis/dataset_definition_1.py 
      --output output/dataset_1.csv.gz
      --dummy-data-file output/dummy_dataset_1.csv.gz
    needs: [dummy_dataset_1]
    outputs:
      highly_sensitive:
        dataset: output/dataset_1.csv.gz
  
  dummy_dataset_2a:
    run: r:latest analysis/dummy_definition_2a.R
    outputs:
      highly_sensitive:
        dataset: output/dummy_dataset_2a.arrow

  dummy_dataset_2b:
    run: r:latest analysis/dummy_definition_2b.R
    outputs:
      highly_sensitive:
        dataset: output/dummy_dataset_2b.arrow

  dummy_dataset_2c:
      run: ehrql:v1 generate-dataset analysis/dataset_definition_2.py
        --output output/dummy_dataset_2c.arrow
        --dummy-data-file output/dummy_dataset_2b.arrow
      needs: [dummy_dataset_2b]
      outputs:
        highly_sensitive:
          dataset: output/dummy_dataset_2c.arrow

  generate_dataset_2:
    run: ehrql:v1 generate-dataset analysis/dataset_definition_2.py
      --output output/dataset_2.arrow
    outputs:
      highly_sensitive:
        dataset: output/dataset_2.arrow

#  compare_dataset_2:
#    run: r:latest analysis/compare_definition_2.R
#    needs: [dummy_dataset_2a, dummy_dataset_2b, dummy_dataset_2c, generate_dataset_2]
#    outputs:
#      highly_sensitive:
#        csv: output/compare_dataset_2.csv