Job request: 5385

version: '3.0'

expectations:
  population_size: 1000

actions:
  
  generate_study_population:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_general_population
    outputs:
      highly_sensitive:
        cohort: output/input_general_population.csv

  generate_study_population_covid_primarycare:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_covid_primarycare
    outputs:
      highly_sensitive:
        cohort: output/input_covid_primarycare.csv
  
  generate_study_population_covid_SGSS:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_covid_SGSS
    outputs:
      highly_sensitive:
        cohort: output/input_covid_SGSS.csv
  
  generate_study_population_covid_admission:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_covid_admission
    outputs:
      highly_sensitive:
        cohort: output/input_covid_admission.csv
  
  # generate_study_population_covid_icu:
  #   run: cohortextractor:latest generate_cohort --study-definition study_definition_covid_icu
  #   outputs:
  #     highly_sensitive:
  #       cohort: output/input_covid_icu.csv

  generate_study_population_covid_death_ons:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_covid_death_ons
    outputs:
      highly_sensitive:
        cohort: output/input_covid_death_ons.csv
  
  generate_study_population_covid_death_cpns:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_covid_death_cpns
    outputs:
      highly_sensitive:
        cohort: output/input_covid_death_cpns.csv
  
  process:
    run: r:latest analysis/process.R
    needs: [generate_study_population_covid_primarycare, generate_study_population_covid_SGSS,generate_study_population_covid_admission,generate_study_population_covid_death_ons,generate_study_population_covid_death_cpns]
    outputs:
      highly_sensitive:
        cohort1.1: output/case_covid_infection.csv
        cohort1.2: output/control_covid_infection.csv 
        #cohort1.3: output/case_covid_infection_*.csv # for monthly matching
        cohort2: output/case_covid_admission.csv
        cohort3: output/case_covid_icu_death.csv

  rmd_report_input_check: # check above 
    run: r:latest -e 'rmarkdown::render("analysis/input_check.Rmd",  knit_root_dir
      = "/workspace",  output_dir = "/workspace/output", output_format = c("html_document")   )'
    needs: [process]
    outputs:
      moderately_sensitive:
        html: output/RMD_input_check_report.html
        
  matching_1:
    run: python:latest python analysis/matching_outcome_1.py
    needs: [generate_study_population, process]
    outputs:
      moderately_sensitive: 
        matching_report1: output/matching_report_general_population_infection.txt
      highly_sensitive: 
        combined1: output/matched_combined_general_population_infection.csv

  matching_2:
    run: python:latest python analysis/matching_outcome_2.py
    needs: [process]
    outputs:
      moderately_sensitive: 
        matching_report2: output/matching_report_infection_hosp.txt
      highly_sensitive: 
        combined2: output/matched_combined_infection_hosp.csv

  matching_3:
    run: python:latest python analysis/matching_outcome_3.py
    needs: [process]
    outputs:
      moderately_sensitive: 
        matching_report3: output/matching_report_hosp_icu_death.txt 
      highly_sensitive: 
        combined3: output/matched_combined_hosp_icu_death.csv

  extract_variables_outcome_1:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_outcome_1
    needs: [matching_1]
    outputs:
      highly_sensitive:
        cohort: output/input_outcome_1.csv
  
  extract_variables_outcome_2:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_outcome_2
    needs: [matching_2]
    outputs:
      highly_sensitive:
        cohort: output/input_outcome_2.csv

  extract_variables_outcome_3:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_outcome_3
    needs: [matching_3]
    outputs:
      highly_sensitive:
        cohort: output/input_outcome_3.csv

  variables:
    run: r:latest analysis/variables.R
    needs: [matching_1,matching_2,matching_3,extract_variables_outcome_1,extract_variables_outcome_2,extract_variables_outcome_3]
    outputs:
      highly_sensitive:
        cohort1: output/matched_outcome1.csv
        cohort2: output/matched_outcome2.csv
        cohort3: output/matched_outcome3.csv
        # cohort1.3: output/case_covid_infection_*.csv # for monthly matching
        # cohort2: output/case_covid_admission.csv
        # cohort3: output/case_covid_icu_death.csv

  rmd_report:
    run: r:latest -e 'rmarkdown::render("analysis/matching_report.Rmd", knit_root_dir = "/workspace", output_dir="/workspace/output")'
    needs: [variables]
    outputs:
      moderately_sensitive:
        html: output/RMD_matching_report.html
  

 

# ## monthly matching datasets
#   generate_study_population_month:
#     run: cohortextractor:latest generate_cohort --study-definition study_definition_general_population --index-date-range "2020-02-01 to 2021-12-01 by month" --skip-existing --output-dir=output/measures --output-format=csv.gz
#     outputs:
#       highly_sensitive:
#         cohort: output/measures/input_general_population_*.csv.gz
  
#   exclusion:
#     run: r:latest analysis/exclusion.R
#     needs: [process, generate_study_population_month]
#     outputs:
#        highly_sensitive:
#         cohort4: output/control_general_population_*.csv