Job request: 19859

version: '3.0'

expectations:

  population_size: 10000

actions:

  ## # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # 
  ## DO NOT EDIT project.yaml DIRECTLY 
  ## This file is created by create_project_actions.R 
  ## Edit and run create_project_actions.R to update the project.yaml 
  ## # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # 
  ## Generate vaccination eligibility information 

  vax_eligibility_inputs:
    run: r:latest analysis/metadates.R
    outputs:
      highly_sensitive:
        study_dates_json: output/study_dates.json
        vax_jcvi_groups: output/vax_jcvi_groups.csv
        vax_eligible_dates: output/vax_eligible_dates.csv

  ## Generate dummy data for study_definition - population_prelim 

  generate_study_population_prelim:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_prelim
      --output-format feather
    needs:
    - vax_eligibility_inputs
    outputs:
      highly_sensitive:
        cohort: output/input_prelim.feather

  ## Generate dates for all study cohorts 

  generate_index_dates:
    run: r:latest analysis/prelim.R
    needs:
    - vax_eligibility_inputs
    - generate_study_population_prelim
    outputs:
      highly_sensitive:
        index_dates: output/index_dates.csv

  ## Generate dummy data for study_definition - prevax 

  generate_study_population_prevax:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_prevax
      --output-format csv.gz
    needs:
    - vax_eligibility_inputs
    - generate_index_dates
    outputs:
      highly_sensitive:
        cohort: output/input_prevax.csv.gz

  ## Generate dummy data for study_definition - vax 

  generate_study_population_vax:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_vax
      --output-format csv.gz
    needs:
    - generate_index_dates
    - vax_eligibility_inputs
    outputs:
      highly_sensitive:
        cohort: output/input_vax.csv.gz

  ## Generate dummy data for study_definition - unvax 

  generate_study_population_unvax:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_unvax
      --output-format csv.gz
    needs:
    - vax_eligibility_inputs
    - generate_index_dates
    outputs:
      highly_sensitive:
        cohort: output/input_unvax.csv.gz

  ## Preprocess data -prevax 

  preprocess_data_prevax:
    run: r:latest analysis/preprocess/preprocess_data.R prevax
    needs:
    - generate_index_dates
    - generate_study_population_prevax
    outputs:
      moderately_sensitive:
        describe: output/not-for-review/describe_input_prevax_stage0.txt
        describe_venn: output/not-for-review/describe_venn_prevax.txt
      highly_sensitive:
        cohort: output/input_prevax.rds
        venn: output/venn_prevax.rds

  ## Preprocess data - vax 

  preprocess_data_vax:
    run: r:latest analysis/preprocess/preprocess_data.R vax
    needs:
    - generate_index_dates
    - generate_study_population_vax
    outputs:
      moderately_sensitive:
        describe: output/not-for-review/describe_input_vax_stage0.txt
        descrive_venn: output/not-for-review/describe_venn_vax.txt
      highly_sensitive:
        cohort: output/input_vax.rds
        venn: output/venn_vax.rds

  ## Preprocess data -unvax 

  preprocess_data_unvax:
    run: r:latest analysis/preprocess/preprocess_data.R unvax
    needs:
    - generate_index_dates
    - generate_study_population_unvax
    outputs:
      moderately_sensitive:
        describe: output/not-for-review/describe_input_unvax_stage0.txt
        describe_venn: output/not-for-review/describe_venn_unvax.txt
      highly_sensitive:
        cohort: output/input_unvax.rds
        venn: output/venn_unvax.rds

  ## Stage 1 - Data cleaning - all cohorts 

  stage1_data_cleaning_all:
    run: r:latest analysis/preprocess/Stage1_data_cleaning.R all
    needs:
    - preprocess_data_prevax
    - preprocess_data_vax
    - preprocess_data_unvax
    - vax_eligibility_inputs
    outputs:
      moderately_sensitive:
        refactoring: output/not-for-review/meta_data_factors_*.csv
        QA_rules: output/review/descriptives/QA_summary_*.csv
        IE_criteria: output/review/descriptives/Cohort_flow_*.csv
        histograms: output/not-for-review/numeric_histograms_*.svg
      highly_sensitive:
        cohort: output/input_*.rds

  describe_file-input_prevax_stage1:
    run: r:latest analysis/describe_file.R input_prevax_stage1 rds
    needs:
    - stage1_data_cleaning_all
    outputs:
      moderately_sensitive:
        describe_model_input: output/describe-input_prevax_stage1.txt

  describe_file-input_vax_stage1:
    run: r:latest analysis/describe_file.R input_vax_stage1 rds
    needs:
    - stage1_data_cleaning_all
    outputs:
      moderately_sensitive:
        describe_model_input: output/describe-input_vax_stage1.txt

  describe_file-input_unvax_stage1:
    run: r:latest analysis/describe_file.R input_unvax_stage1 rds
    needs:
    - stage1_data_cleaning_all
    outputs:
      moderately_sensitive:
        describe_model_input: output/describe-input_unvax_stage1.txt

  create_stage1_ids:
    run: r:latest analysis/preprocess/Stage1_ids.R
    needs:
    - stage1_data_cleaning_all
    outputs:
      highly_sensitive:
        stage1_ids: output/stage1_ids.csv

  ## Study_definition - repeat events step 1 

  generate_study_population_repeat_events_1:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_repeat_events_1
      --output-file output/repeat_events/input_repeat_events_1.csv.gz
    needs:
    - vax_eligibility_inputs
    - generate_index_dates
    - create_stage1_ids
    outputs:
      highly_sensitive:
        cohort: output/repeat_events/input_repeat_events_1.csv.gz

  ## Preflight - repeat events step 2 

  preflight_repeat_events_2:
    run: r:latest analysis/repeat_events/preflight_repeat_events.R 2
    needs:
    - generate_study_population_repeat_events_1
    outputs:
      moderately_sensitive:
        max_events: output/repeat_events/max_events.json
      highly_sensitive:
        out_date: output/repeat_events/out_date_2.csv.gz
        patient_ids: output/repeat_events/patient_ids_*.rds

  ## Study_definition - repeat events step 2 

  generate_study_population_repeat_events_2:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_repeat_events_x
      --output-file output/repeat_events/input_repeat_events_2.csv.gz --param step=2
    needs:
    - vax_eligibility_inputs
    - generate_index_dates
    - create_stage1_ids
    - preflight_repeat_events_2
    outputs:
      highly_sensitive:
        cohort: output/repeat_events/input_repeat_events_2.csv.gz

  ## Preflight - repeat events step 3 

  preflight_repeat_events_3:
    run: r:latest analysis/repeat_events/preflight_repeat_events.R 3
    needs:
    - generate_study_population_repeat_events_2
    - preflight_repeat_events_2
    outputs:
      highly_sensitive:
        out_date: output/repeat_events/out_date_3.csv.gz

  ## Study_definition - repeat events step 3 

  generate_study_population_repeat_events_3:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_repeat_events_x
      --output-file output/repeat_events/input_repeat_events_3.csv.gz --param step=3
    needs:
    - vax_eligibility_inputs
    - generate_index_dates
    - create_stage1_ids
    - preflight_repeat_events_2
    - preflight_repeat_events_3
    outputs:
      highly_sensitive:
        cohort: output/repeat_events/input_repeat_events_3.csv.gz