Skip to content

Job request: 16722

Organisation:
DataLab
Workspace:
strepa_scarlet
ID:
pimpij6znvg664da
View repo View project.yaml

This page shows the technical details of what happened when authorised researcher Christine Cunningham requested one or more actions to be run against real patient data in the project, within a secure environment.

By cross-referencing the indicated Requested Actions with the Pipeline section below, you can infer what security level various outputs were written to. Outputs marked as highly_sensitive can never be viewed directly by a researcher; they can only request that code runs against them. Outputs marked as moderately_sensitive can be viewed by an approved researcher by logging into a highly secure environment. Only outputs marked as moderately_sensitive can be requested for release to the public, via a controlled output review service.

Jobs

Pipeline

Show project.yaml 
version: '3.0'

expectations:
  population_size: 1000

actions:
  generate_study_population_report_ethnicity:
    run: cohortextractor:latest generate_cohort 
      --study-definition study_definition_ethnicity_report --output-dir output/report --output-format=csv.gz
    outputs:
      highly_sensitive:
        cohort: output/report/input_ethnicity_report.csv.gz

  ### Curation check ###
  curation_monthly:
    run: cohortextractor:latest generate_cohort
      --study-definition study_definition_report
      --index-date-range "2019-01-01 to 2019-01-01 by month"
      --param frequency=monthly
      --output-dir=output/curation
      --output-format=csv.gz
    outputs:
      highly_sensitive:
        cohort: output/curation/input_report_2019-01-01.csv.gz

  dataset_report_monthly:
      run: python:latest python analysis/dataset_report.py
           --input-files output/curation/input_report_2019-01-01.csv.gz
           --output-dir output/curation/
           --granularity "year"
      needs: [curation_monthly]
      outputs:
        moderately_sensitive:
          # Only output the single summary file
          cohort_report: output/curation/input_report_2019-01-01.html

  curation_weekly:
    run: cohortextractor:latest generate_cohort
      --study-definition study_definition_report
      --index-date-range "2022-07-01 to 2022-07-28 by week"
      --param frequency=weekly
      --output-dir=output/curation
      --output-format=csv.gz
      --skip-existing
    outputs:
      highly_sensitive:
        cohort: output/curation/input_report_2022-07*.csv.gz

  dataset_report_weekly:
      run: python:latest python analysis/dataset_report.py
           --input-files output/curation/input_report_2022-07-01.csv.gz
           --output-dir output/curation/
           --granularity "day"
      needs: [curation_weekly]
      outputs:
        moderately_sensitive:
          # Only output the single summary file
          cohort_report: output/curation/input_report_2022-07-01.html

  curation_measures_weekly:
    run: cohortextractor:latest generate_measures
      --study-definition study_definition_report
      --output-dir=output/curation
      --param frequency=weekly
    needs: [curation_weekly]
    outputs:
      moderately_sensitive:
        measure_csv: output/curation/measure_event_*.csv

  curation_diagnostics:
    run: cohortextractor:latest generate_cohort
      --study-definition study_definition_diagnostics_curation
      --index-date-range "2019-01-01 to 2019-01-01 by month"
      --output-dir=output/curation
      --output-format=feather
    outputs:
      highly_sensitive:
        cohort: output/curation/input_diagnostics_curation_2019-01-01.feather

  dataset_report_diagnostics:
      run: python:latest python analysis/dataset_report.py
           --input-files output/curation/input_diagnostics_curation_2019-01-01.feather
           --output-dir output/curation/
           --granularity "day"
      needs: [curation_diagnostics]
      outputs:
        moderately_sensitive:
          # Only output the single summary file
          cohort_report: output/curation/input_diagnostics_curation_2019-01-01.html

  curation_with:
    run: cohortextractor:latest generate_cohort
      --study-definition study_definition_with_curation
      --index-date-range "2018-01-01 to 2018-04-01 by month"
      --output-dir=output/curation
      --output-format=feather
    outputs:
      highly_sensitive:
        cohort: output/curation/input_with_curation_2018-*-01.feather

  dataset_report_with:
      run: python:latest python analysis/dataset_report.py
           --input-files output/curation/input_with_curation_2018-*-01.feather
           --output-dir output/curation/
           --granularity "day"
           diff --col-1 "scarlet_fever_date" --col-2 "any_prescription_date"
      needs: [curation_with]
      outputs:
        moderately_sensitive:
          # Only output the single summary file
          cohort_report: output/curation/input_with_curation_2018-*-01.html
  ### End curation check ###

  ### MONTHLY ###
  generate_study_population_report_monthly_0:
    run: cohortextractor:latest generate_cohort
      --study-definition study_definition_report
      --index-date-range "2018-01-01 to 2018-12-01 by month"
      --param frequency=monthly
      --output-dir=output/report
      --output-format=csv.gz
    outputs:
      highly_sensitive:
        cohort: output/report/input_*-01.csv.gz

  generate_study_population_report_monthly_1:
    run: cohortextractor:latest generate_cohort
      --study-definition study_definition_report
      --index-date-range "2019-01-01 to 2019-12-01 by month"
      --param frequency=monthly
      --output-dir=output/report
      --output-format=csv.gz
    outputs:
      highly_sensitive:
        cohort: output/report/input*-01.csv.gz

  generate_study_population_report_monthly_2:
    run: cohortextractor:latest generate_cohort
      --study-definition study_definition_report
      --index-date-range "2020-01-01 to 2020-12-01 by month"
      --param frequency=monthly
      --output-dir=output/report
      --output-format=csv.gz
    outputs:
      highly_sensitive:
        cohort: output/report/inpu*-01.csv.gz
  
  generate_study_population_report_monthly_3:
    run: cohortextractor:latest generate_cohort
      --study-definition study_definition_report
      --index-date-range "2021-01-01 to 2021-12-01 by month"
      --param frequency=monthly
      --output-dir=output/report
      --output-format=csv.gz
    outputs:
      highly_sensitive:
        cohort: output/report/inp*-01.csv.gz

  generate_study_population_report_monthly_4:
    run: cohortextractor:latest generate_cohort
      --study-definition study_definition_report
      --index-date-range "2022-01-01 to 2022-12-01 by month"
      --param frequency=monthly
      --output-dir=output/report
      --output-format=csv.gz
    outputs:
      highly_sensitive:
        cohort: output/report/in*-01.csv.gz

  generate_study_population_report_monthly_5:
    run: cohortextractor:latest generate_cohort
      --study-definition study_definition_report
      --index-date-range "2023-01-01 to 2023-02-01 by month"
      --param frequency=monthly
      --output-dir=output/report
      --output-format=csv.gz
    outputs:
      highly_sensitive:
        cohort: output/report/i*-01.csv.gz

  join_cohorts_report:
    run: >
      python:latest python analysis/cohort_joiner.py
        --lhs output/report/input_report_20*.csv.gz
        --rhs output/report/input_ethnicity_report.csv.gz
        --output-dir output/report/joined
    needs: [
      generate_study_population_report_monthly_0,
      generate_study_population_report_monthly_1,
      generate_study_population_report_monthly_2,
      generate_study_population_report_monthly_3,
      generate_study_population_report_monthly_4,
      generate_study_population_report_monthly_5,
      generate_study_population_report_ethnicity]
    outputs:
      highly_sensitive:
        cohort: output/report/joined/input_report_20*.csv.gz

  generate_measures_report:
    run: cohortextractor:latest generate_measures
        --study-definition study_definition_report
        --param frequency=monthly
        --output-dir=output/report/joined
    needs: [join_cohorts_report]
    outputs:
      moderately_sensitive:
        measure_csv: output/report/joined/measure_event_*.csv

  join_measures_rounded:
      run: python:latest python analysis/join_and_round.py
           --input-files output/report/joined/measure_event_*_rate.csv
           --input-files output/report/joined/measure_event_*_pcnt.csv
           --exclude-files output/report/joined/measure_*practice*_rate.csv
           --exclude-files output/report/joined/measure_event_code*_rate.csv
           --output-dir output/report/results
           --output-name "measure_rounded.csv"
           --redact
           --redaction-threshold=5
      needs: [generate_measures_report]
      outputs:
        moderately_sensitive:
          # Only output the single summary file
          measure_csv: output/report/results/measure_rounded.csv

  join_measures_unrounded:
      run: python:latest python analysis/join_and_round.py
           --input-files output/report/joined/measure_*practice*_rate.csv
           --input-files output/report/joined/measure_event_code*_rate.csv
           --output-dir output/report/results
           --output-name "measure_unrounded.csv"
           --allow-practice
           --skip-round
      needs: [generate_measures_report]
      outputs:
        moderately_sensitive:
          # Only output the single summary file
          measure_csv: output/report/results/measure_unrounded.csv

  top_5_table_report:
    run: >
      python:latest python analysis/report/top_5_report.py
      --input-file output/report/results/measure_unrounded.csv
      --output-dir output/report/results
      --frequency month
    needs: [join_measures_unrounded]
    outputs:
      moderately_sensitive:
        tables: output/report/results/top_5*.csv
        figures: output/report/results/*top_5_codes_over_time.png
        data: output/report/results/*top_5_codes_over_time.csv

  plot_measure_report:
    run: >
      python:latest python analysis/report/plot_measures_report.py
      --measure-path output/report/results/measure_rounded.csv
      --output-dir output/report/results
    needs: [join_measures_rounded]
    outputs:
      moderately_sensitive:
        measure: output/report/results/*_bar_measures*.jpeg

  panel_plots:
    run: >
      python:latest python analysis/report/create_panels.py
      --input-file output/report/results/measure_rounded.csv
      --practice-file output/report/results/measure_unrounded.csv
      --output-dir output/report/results
      --xtick-frequency 3
    needs: [join_measures_rounded, join_measures_unrounded]
    outputs:
      moderately_sensitive:
        measure: output/report/results/*.png
        deciles_tables: output/report/results/deciles_table*.csv

  panel_plots_stacked_medications:
    run: >
      python:latest python analysis/report/panel_plots.py
      --input-file output/report/results/measure_rounded.csv
      --measures-list "event_amoxicillin_rate"
      --measures-list "event_azithromycin_rate"
      --measures-list "event_clarithromycin_rate"
      --measures-list "event_erythromycin_rate"
      --measures-list "event_phenoxymethylpenicillin_rate"
      --measures-list "event_cefalexin_rate"
      --measures-list "event_co_amoxiclav_rate"
      --measures-list "event_flucloxacillin_rate"
      --output-dir output/report/results
      --output-name "all_medications_by_year"
      --scale "rate"
      --stack-years
    needs: [join_measures_rounded]
    outputs:
      moderately_sensitive:
        measure: output/report/results/all_medications_by_year.png

  panel_plots_stacked_diagnostics:
    run: >
      python:latest python analysis/report/panel_plots.py
      --input-file output/report/results/measure_rounded.csv
      --measures-list "event_scarlet_fever_rate"
      --measures-list "event_sore_throat_tonsillitis_rate"
      --measures-list "event_invasive_strep_a_rate"
      --output-dir output/report/results
      --output-name "all_diagnostics_by_year"
      --scale "rate"
      --stack-years
    needs: [join_measures_rounded]
    outputs:
      moderately_sensitive:
        measure: output/report/results/all_diagnostics_by_year.png

  event_counts_medication:
    run: >
      python:latest python analysis/report/tables.py
      --input-file output/report/results/measure_rounded.csv
      --output-dir output/report/results
      --output-name "event_counts_medication.csv"
      --measures-list "event_amoxicillin_rate"
      --measures-list "event_azithromycin_rate"
      --measures-list "event_clarithromycin_rate"
      --measures-list "event_erythromycin_rate"
      --measures-list "event_phenoxymethylpenicillin_rate"
      --measures-list "event_flucloxacillin_rate"
      --measures-list "event_cefalexin_rate"
      --measures-list "event_co_amoxiclav_rate"
    needs: [join_measures_rounded]
    outputs:
      moderately_sensitive:
        measure: output/report/results/event_counts_medication.csv

  event_counts_clinical:
    run: >
      python:latest python analysis/report/tables.py
      --input-file output/report/results/measure_rounded.csv
      --output-dir output/report/results
      --output-name "event_counts_clinical.csv"
      --measures-list "event_scarlet_fever_rate"
      --measures-list "event_sore_throat_tonsillitis_rate"
      --measures-list "event_invasive_strep_a_rate"
    needs: [join_measures_rounded]
    outputs:
      moderately_sensitive:
        measure: output/report/results/event_counts_clinical.csv


### WEEKLY ###
  generate_study_population_report_weekly_1:
    run: cohortextractor:latest generate_cohort
      --study-definition study_definition_report
      --index-date-range "2022-09-01 to 2022-11-09 by week"
      --param frequency=weekly
      --output-dir=output/report/weekly
      --output-format=csv.gz
    outputs:
      highly_sensitive:
        cohort: output/report/weekly/input_*.csv.gz

  generate_study_population_report_weekly_2:
    run: cohortextractor:latest generate_cohort
      --study-definition study_definition_report
      --index-date-range "2022-11-10 to 2023-01-25 by week"
      --param frequency=weekly
      --output-dir=output/report/weekly
      --output-format=csv.gz
    outputs:
      highly_sensitive:
        cohort: output/report/weekly/input*.csv.gz

  generate_study_population_report_weekly_3:
    run: cohortextractor:latest generate_cohort
      --study-definition study_definition_report
      --index-date-range "2023-01-26 to 2023-02-22 by week"
      --param frequency=weekly
      --output-dir=output/report/weekly
      --output-format=csv.gz
    outputs:
      highly_sensitive:
        cohort: output/report/weekly/inpu*.csv.gz

  generate_measures_report_weekly:
    run: cohortextractor:latest generate_measures
      --study-definition study_definition_report
      --param frequency=weekly
      --output-dir=output/report/weekly
    needs: [generate_study_population_report_weekly_1, generate_study_population_report_weekly_2, generate_study_population_report_weekly_3]
    outputs:
      moderately_sensitive:
        measure_csv: output/report/weekly/measure_event_*_rate.csv

  join_measures_rounded_weekly:
      run: python:latest python analysis/join_and_round.py
           --input-files output/report/weekly/joined/measure_*_rate.csv
           --input-files output/report/weekly/measure_*_rate.csv
           --exclude-files output/report/weekly/joined/measure_*practice*_rate.csv
           --exclude-files output/report/weekly/joined/measure_event_code*_rate.csv
           --exclude-files output/report/weekly/measure_*practice*_rate.csv
           --exclude-files output/report/weekly/measure_event_code*_rate.csv
           --output-dir output/report/weekly/results
           --output-name "measure_rounded_weekly.csv"
           --redact
           --redaction-threshold=5
      needs: [generate_measures_report_weekly]
      outputs:
        moderately_sensitive:
          # Only output the single summary file
          measure_csv: output/report/weekly/results/measure_rounded_weekly.csv

  join_measures_unrounded_weekly:
      run: python:latest python analysis/join_and_round.py
           --input-files output/report/weekly/joined/measure_*practice*_rate.csv
           --input-files output/report/weekly/joined/measure_event_code*_rate.csv
           --input-files output/report/weekly/measure_*practice*_rate.csv
           --input-files output/report/weekly/measure_event_code*_rate.csv
           --output-dir output/report/weekly/results
           --output-name "measure_unrounded_weekly.csv"
           --allow-practice
           --skip-round
      needs: [generate_measures_report_weekly]
      outputs:
        moderately_sensitive:
          # Only output the single summary file
          measure_csv: output/report/weekly/results/measure_unrounded_weekly.csv

  top_5_table_report_weekly:
    run: >
      python:latest python analysis/report/top_5_report.py
      --input-file output/report/weekly/results/measure_unrounded_weekly.csv
      --output-dir output/report/weekly/results
      --frequency week
    needs: [join_measures_unrounded_weekly]
    outputs:
      moderately_sensitive:
        tables: output/report/weekly/results/top_5*.csv
        figures: output/report/weekly/results/*top_5_codes_over_time.png
        data: output/report/weekly/results/*top_5_codes_over_time.csv

  plot_measure_report_weekly:
    run: >
      python:latest python analysis/report/plot_measures_report.py
      --measure-path output/report/weekly/results/measure_rounded_weekly.csv
      --output-dir output/report/weekly/results
      --frequency week
    needs: [join_measures_rounded_weekly]
    outputs:
      moderately_sensitive:
        measure: output/report/weekly/results/*_bar_measures*.jpeg

  panel_plots_weekly:
    run: >
      python:latest python analysis/report/create_panels.py
      --input-file output/report/weekly/results/measure_rounded_weekly.csv
      --practice-file output/report/weekly/results/measure_unrounded_weekly.csv
      --output-dir output/report/weekly/results
      --frequency week
    needs: [join_measures_rounded_weekly, join_measures_unrounded_weekly]
    outputs:
      moderately_sensitive:
        measure: output/report/weekly/results/*.png
        deciles_tables: output/report/weekly/results/deciles_t*.csv

  event_counts_medication_weekly:
    run: >
      python:latest python analysis/report/tables.py
      --input-file output/report/weekly/results/measure_rounded_weekly.csv
      --output-dir output/report/weekly/results
      --output-name "event_counts_medication.csv"
      --measures-list "event_amoxicillin_rate"
      --measures-list "event_azithromycin_rate"
      --measures-list "event_clarithromycin_rate"
      --measures-list "event_erythromycin_rate"
      --measures-list "event_phenoxymethylpenicillin_rate"
      --measures-list "event_flucloxacillin_rate"
      --measures-list "event_cefalexin_rate"
      --measures-list "event_co_amoxiclav_rate"
    needs: [join_measures_rounded_weekly]
    outputs:
      moderately_sensitive:
        measure: output/report/weekly/results/event_counts_medication.csv

  event_counts_clinical_weekly:
    run: >
      python:latest python analysis/report/tables.py
      --input-file output/report/weekly/results/measure_rounded_weekly.csv
      --output-dir output/report/weekly/results
      --output-name "event_counts_clinical.csv"
      --measures-list "event_scarlet_fever_rate"
      --measures-list "event_sore_throat_tonsillitis_rate"
      --measures-list "event_invasive_strep_a_rate"
    needs: [join_measures_rounded_weekly]
    outputs:
      moderately_sensitive:
        measure: output/report/weekly/results/event_counts_clinical.csv

  generate_notebook:
    run: jupyter:latest jupyter nbconvert /workspace/analysis/report/report.ipynb --execute --to html --output-dir=/workspace/output/report --ExecutePreprocessor.timeout=86400 --no-input
    needs: [
      event_counts_medication,
      event_counts_clinical,
      top_5_table_report,
      plot_measure_report,
      panel_plots,
      panel_plots_stacked_medications,
      panel_plots_stacked_diagnostics
      ]
    outputs:
      moderately_sensitive:
        notebook: output/report/report.html

  generate_notebook_weekly:
    run: jupyter:latest jupyter nbconvert /workspace/analysis/report/report_weekly.ipynb --execute --to html --output-dir=/workspace/output/report --ExecutePreprocessor.timeout=86400 --no-input
    needs: [
      event_counts_medication_weekly,
      event_counts_clinical_weekly,
      top_5_table_report_weekly,
      plot_measure_report_weekly,
      panel_plots_weekly,
      ]
    outputs:
      moderately_sensitive:
        notebook: output/report/report_weekly.html

Timeline

  • Created:

  • Started:

  • Finished:

  • Runtime: 13:51:01

These timestamps are generated and stored using the UTC timezone on the TPP backend.

Job information

Status
Succeeded
Backend
TPP
Workspace
strepa_scarlet
Requested by
Christine Cunningham
Branch
main
Force run dependencies
No
Git commit hash
a40f56c
Requested actions
  • generate_measures_report
  • join_measures_rounded
  • join_measures_unrounded
  • top_5_table_report
  • plot_measure_report
  • panel_plots
  • panel_plots_stacked_medications
  • panel_plots_stacked_diagnostics
  • event_counts_medication
  • event_counts_clinical
  • generate_notebook