Job request: 6778

version: '3.0'

expectations:
  population_size: 1000

actions:
  

  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

  process_1:  # Covid ons death
    run: r:latest analysis/process_1.R
    needs: [generate_study_population_covid_primarycare, generate_study_population_covid_SGSS]
    outputs:
      highly_sensitive:
        case: output/case_covid_hosp.csv 
        control: output/control_covid_infection.csv 

  process_2: # died any cause
    run: r:latest analysis/process_2.R
    needs: [generate_study_population_covid_primarycare, generate_study_population_covid_SGSS]
    outputs:
      highly_sensitive:
        control: output/control_covid_infection_2.csv

  check_input: # 
    run: r:latest -e 'rmarkdown::render("analysis/check_input.Rmd", knit_root_dir = "/workspace", output_dir = "output")'
    needs: [extract_variables,matching,process_matching,extract_variables_outcome_2_2,extract_variables_outcome_2_4,extract_variables_outcome_2_6,matching_2,process_1,generate_study_population_covid_primarycare, generate_study_population_covid_SGSS]
    outputs:
      moderately_sensitive:
        html: output/check_input.html
        
# OS matching without replacement, ratio 2-4-6
  matching_2:
    run: python:latest python analysis/matching_outcome_2.py
    needs: [process_1]
    outputs:
      moderately_sensitive: 
        matching_report2: output/matching_report_infection_hosp_2.txt
        matching_report4: output/matching_report_infection_hosp_4.txt
        matching_report6: output/matching_report_infection_hosp_6.txt
      highly_sensitive: 
        combined2: output/matched_combined_infection_hosp_2.csv
        combined4: output/matched_combined_infection_hosp_4.csv
        combined6: output/matched_combined_infection_hosp_6.csv

  extract_variables_outcome_2_2: 
    run: cohortextractor:latest generate_cohort --study-definition study_definition_outcome_2_2
    needs: [matching_2]
    outputs:
      highly_sensitive:
        cohort: output/input_outcome_2_2.csv
    
  extract_variables_outcome_2_4: 
    run: cohortextractor:latest generate_cohort --study-definition study_definition_outcome_2_4
    needs: [matching_2]
    outputs:
      highly_sensitive:
        cohort: output/input_outcome_2_4.csv
  
  extract_variables_outcome_2_6: 
    run: cohortextractor:latest generate_cohort --study-definition study_definition_outcome_2_6
    needs: [matching_2]
    outputs:
      highly_sensitive:
        cohort: output/input_outcome_2_6.csv

  check_matching_2:
    run: r:latest -e 'rmarkdown::render("analysis/check_matching_2.Rmd", knit_root_dir = "/workspace", output_dir="/workspace/output")'
    needs: [matching_2]
    outputs:
      moderately_sensitive:
        html: output/check_matching_2.html

  process_matching: # add variables 
    run: r:latest analysis/process_matching.R
    needs: [extract_variables_outcome_2_6,extract_variables_outcome_2_4,extract_variables_outcome_2_2,matching_2]
    outputs:
      highly_sensitive:
        cohort1: output/matched_outcome_2.csv
        cohort2: output/matched_outcome_4.csv
        cohort3: output/matched_outcome_6.csv

  check_exposures_6:
    run: r:latest -e 'rmarkdown::render("analysis/check_exposures_6.Rmd", knit_root_dir = "/workspace", output_dir="/workspace/output")'
    needs: [process_matching]
    outputs:
      moderately_sensitive:
        html: output/check_exposures_6.html 

  check_exposures_4:
    run: r:latest -e 'rmarkdown::render("analysis/check_exposures_4.Rmd", knit_root_dir = "/workspace", output_dir="/workspace/output")'
    needs: [process_matching]
    outputs:
      moderately_sensitive:
        html: output/check_exposures_4.html 

  check_exposures_2:
    run: r:latest -e 'rmarkdown::render("analysis/check_exposures_2.Rmd", knit_root_dir = "/workspace", output_dir="/workspace/output")'
    needs: [process_matching]
    outputs:
      moderately_sensitive:
        html: output/check_exposures_2.html 

# R MatchIt

  matching: # matching with replacement
    run: r:latest -e 'rmarkdown::render("analysis/matching.Rmd", knit_root_dir = "/workspace", output_dir="/workspace/output")'
    needs: [process_1]
    outputs:
      moderately_sensitive:
        html: output/matching.html
      highly_sensitive: 
        rds1: output/matched_patients.rds
        rds2: output/unmatched_patients.rds
        csv: output/matched_patients_id.csv

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


  extract_variables: 
    run: cohortextractor:latest generate_cohort --study-definition study_definition_outcome
    needs: [matching]
    outputs:
      highly_sensitive:
        cohort: output/input_outcome.csv
  
  process_Rmatching: # add variables 
    run: r:latest analysis/process_Rmatching.R
    needs: [extract_variables,matching]
    outputs:
      highly_sensitive:
        cohort1: output/matched_outcome.rds