project.yaml

version: "3.0"

expectations:
  population_size: 1

actions:
  # query_APCS_Der_Diagnosis_All:
  #   run: >
  #     sqlrunner:latest
  #       queries/APCS.Der_Diagnosis_All.sql
  #       --output output/APCS.Der_Diagnosis_All.csv
  #   outputs:
  #     highly_sensitive:
  #       output: output/APCS.Der_Diagnosis_All.csv

  query_APCS_Der__Spell_Primary_Diagnosis:
    run: >
      sqlrunner:latest
        queries/APCS_Der.Spell_Primary_Diagnosis.sql
        --output output/gAPCS_Der.Spell_Primary_Diagnosis.csv
    outputs:
      highly_sensitive:
        output: output/gAPCS_Der.Spell_Primary_Diagnosis.csv

  query_CodedEvent__CTV3Code:
    run: >
      sqlrunner:latest
        queries/CodedEvent.CTV3Code.sql
        --output output/gCodedEvent.CTV3Code.csv
    outputs:
      highly_sensitive:
        output: output/gCodedEvent.CTV3Code.csv

  query_CodedEvent_SNOMED__ConceptID:
    run: >
      sqlrunner:latest
        queries/CodedEvent_SNOMED.ConceptID.sql
        --output output/gCodedEvent_SNOMED.ConceptID.csv
    outputs:
      highly_sensitive:
        output: output/gCodedEvent_SNOMED.ConceptID.csv

  # query_EC_Diagnosis_EC_Diagnosis_XX:
  #   run: >
  #     sqlrunner:latest
  #       queries/EC_Diagnosis.EC_Diagnosis_XX.sql
  #       --output output/EC_Diagnosis.EC_Diagnosis_XX.csv
  #   outputs:
  #     highly_sensitive:
  #       output: output/EC_Diagnosis.EC_Diagnosis_XX.csv

  # query_EC_Diagnosis_Discharge_Destination_SNOMED_CT:
  #   run: >
  #     sqlrunner:latest
  #       queries/EC_Diagnosis.Discharge_Destination_SNOMED_CT.sql
  #       --output output/EC_Diagnosis.Discharge_Destination_SNOMED_CT.csv
  #   outputs:
  #     highly_sensitive:
  #       output: output/EC_Diagnosis.Discharge_Destination_SNOMED_CT.csv

  # query_MedicationDictionary_DMD_ID:
  #   run: >
  #     sqlrunner:latest
  #       queries/MedicationDictionary.DMD_ID.sql
  #       --output output/MedicationDictionary.DMD_ID.csv
  #   outputs:
  #     highly_sensitive:
  #       output: output/MedicationDictionary.DMD_ID.csv

  # query_ONS_Deaths_icd10XX:
  #   run: >
  #     sqlrunner:latest
  #       queries/ONS_Deaths.icd10XX.sql
  #       --output output/ONS_Deaths.icd10XX.csv
  #   outputs:
  #     highly_sensitive:
  #       output: output/ONS_Deaths.icd10XX.csv

# This action (1) joins all different datasets
# (2) removes rows with count less than 10
# (3) rounds numbers to the nearest 10
  tidy_data:
    run: r:latest analysis/tidy_data.R
    needs:
      - query_APCS_Der__Spell_Primary_Diagnosis
      - query_CodedEvent__CTV3Code
      - query_CodedEvent_SNOMED__ConceptID
      # - query_APCS_Der_Diagnosis_All
      # - query_EC_Diagnosis_EC_Diagnosis_XX
      # - query_EC_Diagnosis_Discharge_Destination_SNOMED_CT
      # - query_MedicationDictionary_DMD_ID
      # - query_ONS_Deaths_icd10XX
    outputs:
      moderately_sensitive:
        output: output/output.csv

  generate_report:
    run: r:latest -e 'rmarkdown::render("analysis/report.Rmd", knit_root_dir = "/workspace", output_dir = "output/")'
    needs:
      - tidy_data
    outputs:
      moderately_sensitive:
        output: output/report.html