isaric-exploration/project.yaml at main · opensafely/isaric-exploration · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
################################################################################
#
# Description: This script defines the project pipeline - it specifys the
#              execution orders for all the code in this repo using a series of
#              actions.
#
# Author(s): M Green
# Date last updated: 07/08/2023
#
################################################################################

version: '3.0'

expectations:
  population_size: 1000

actions:

  # Extract isaric data (ehrQL) ----
  extract_first_isaric_admission:
    run: >
      ehrql:v0 generate-dataset analysis/dataset_definition_isaric.py
      --output 'output/admissions/isaric_admission1.csv.gz'
    outputs:
      highly_sensitive:
        csv: output/admissions/isaric_admission1.csv.gz


  # Extract sus data (ehrQL)----
  extract_first_sus_admission_methodA_ehrQL:
    run: >
      ehrql:v0
        generate-dataset analysis/dataset_definition_sus.py
        --output output/admissions/sus_methodA_admission1_ehrQL.csv.gz
        --
        --admission_method A
    outputs:
      highly_sensitive:
        cohort: output/admissions/sus_methodA_admission1_ehrQL.csv.gz

  extract_first_sus_admission_methodB_ehrQL:
    run: >
      ehrql:v0
        generate-dataset analysis/dataset_definition_sus.py
        --output output/admissions/sus_methodB_admission1_ehrQL.csv.gz
        --
        --admission_method B
    outputs:
      highly_sensitive:
        cohort: output/admissions/sus_methodB_admission1_ehrQL.csv.gz

  extract_first_sus_admission_methodC_ehrQL:
    run: >
      ehrql:v0
        generate-dataset analysis/dataset_definition_sus.py
        --output output/admissions/sus_methodC_admission1_ehrQL.csv.gz
        --
        --admission_method C
    outputs:
      highly_sensitive:
        cohort: output/admissions/sus_methodC_admission1_ehrQL.csv.gz


  # Extract sus data (cohortextractor)----
  extract_sus_methodA_admission1_cohortextractor:
    run: >
      cohortextractor:latest generate_cohort
      --study-definition study_definition_sus
      --output-file output/admissions/sus_methodA_admission1_cohortextractor.csv.gz
      --param admission_number=1
      --param admission_method=A
    outputs:
      highly_sensitive:
        csv: output/admissions/sus_methodA_admission1_cohortextractor.csv.gz

  extract_sus_methodB_admission1_cohortextractor:
    run: >
      cohortextractor:latest generate_cohort
      --study-definition study_definition_sus
      --output-file output/admissions/sus_methodB_admission1_cohortextractor.csv.gz
      --param admission_number=1
      --param admission_method=B
    outputs:
      highly_sensitive:
        csv: output/admissions/sus_methodB_admission1_cohortextractor.csv.gz

  extract_sus_methodC_admission1_cohortextractor:
    run: >
      cohortextractor:latest generate_cohort
      --study-definition study_definition_sus
      --output-file output/admissions/sus_methodC_admission1_cohortextractor.csv.gz
      --param admission_number=1
      --param admission_method=C
    outputs:
      highly_sensitive:
        csv: output/admissions/sus_methodC_admission1_cohortextractor.csv.gz


  # Data properties ----
  data_properties:
    run: >
      r:latest
        analysis/rcode/descriptive/data_properties.R
        output/admissions/isaric_admission1.csv.gz
        output/admissions/sus_methodA_admission1_cohortextractor.csv.gz
        output/admissions/sus_methodA_admission1_ehrQL.csv.gz
        output/data_properties
    needs: [extract_first_isaric_admission, extract_sus_methodA_admission1_cohortextractor, extract_first_sus_admission_methodA_ehrQL]
    outputs:
      moderately_sensitive:
        txt1: output/data_properties/*.txt


  # ehrQL vs cohortextractor ----
  ehrQL_vs_cohortextractor_comparison:
    run: >
      r:latest
        analysis/rcode/translation/ehrQL_vs_cohortextractor_comparison.R
    needs: [extract_first_sus_admission_methodA_ehrQL, extract_first_sus_admission_methodB_ehrQL, extract_first_sus_admission_methodC_ehrQL, extract_sus_methodA_admission1_cohortextractor, extract_sus_methodB_admission1_cohortextractor, extract_sus_methodC_admission1_cohortextractor]
    outputs:
      moderately_sensitive:
        csv: output/translation/ehrQL_vs_cohortextractor_comparison.csv


  # Data processing ----
  data_process:
    run: >
      r:latest
        analysis/rcode/process/process_data.R
    needs: [extract_first_isaric_admission, extract_first_sus_admission_methodA_ehrQL, extract_first_sus_admission_methodB_ehrQL, extract_first_sus_admission_methodC_ehrQL]
    outputs:
      highly_sensitive:
        rds: output/admissions/processed_*.rds

  # Resuts for preliminary report ----
  validation_report_data:
    run: >
      r:latest
        analysis/rcode/validation/validation_report_data.R
    needs: [data_process]
    outputs:
      moderately_sensitive:
        redacted_tables: output/validation/table_*.csv
  #      unredacted_tables: output/validation/for-checks/table_*.csv

  # # Preliminary report ----
  # validation_report:
  #   run: r:latest -e 'rmarkdown::render("analysis/rcode/validation/validation_report.Rmd", knit_root_dir = "/workspace", output_dir="/workspace/output/reports")'
  #   needs: [data_process]
  #   outputs:
  #     moderately_sensitive:
  #       html: output/reports/validation_report.html