generated from opensafely/research-template
/
project.yaml
97 lines (88 loc) · 3.75 KB
/
project.yaml
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
version: '3.0'
expectations:
population_size: 1000
actions:
generate_ethnicity:
run: cohortextractor:latest generate_cohort --study-definition study_definition_ethnicity --output-format=feather
outputs:
highly_sensitive:
cohort: output/input_ethnicity.feather
generate_study_population:
run: cohortextractor:latest generate_cohort --study-definition study_definition
outputs:
highly_sensitive:
cohort: output/input.csv
generate_rates_1:
run: cohortextractor:latest generate_cohort --study-definition study_definition_rates --index-date-range "2015-01-01 to 2018-12-01 by month" --skip-existing --output-dir=output --output-format=feather
outputs:
highly_sensitive:
cohort: output/measures/inpu*.feather
generate_rates_2:
run: cohortextractor:latest generate_cohort --study-definition study_definition_rates --index-date-range "2019-01-01 to 2022-12-01 by month" --skip-existing --output-dir=output --output-format=feather
outputs:
highly_sensitive:
cohort: output/measures/inp*.feather
join_ethnicity:
run: python:latest python analysis/join_ethnicity.py
needs:
[
generate_rates_1,
generate_rates_2,
generate_ethnicity,
]
outputs:
highly_sensitive:
cohort: output/measures/in*.feather
generate_measures:
run: cohortextractor:latest generate_measures --study-definition study_definition_rates --skip-existing --output-dir=output/measures
needs:
[
generate_rates_1,
generate_rates_2,
join_ethnicity,
]
outputs:
moderately_sensitive:
measure_csv1: output/measures/measure_prevalence*_rate.csv
measure_csv2: output/measures/measure_prevalencebyRegion*_rate.csv
measure_csv3: output/measures/measure_prevalencebyIMD*_rate.csv
measure_csv4: output/measures/measure_prevalencebyEthnicity*_rate.csv
measure_csv5: output/measures/measure_prevalencebyAge*_rate.csv
measure_csv6: output/measures/measure_incidence*_rate.csv
measure_csv7: output/measures/measure_incidencebyRegion*_rate.csv
measure_csv8: output/measures/measure_incidencebyIMD*_rate.csv
measure_csv9: output/measures/measure_incidencebyEthnicity*_rate.csv
measure_csv10: output/measures/measure_incidencebyAge*_rate.csv
measure_csv11: output/measures/measure_mortality*_rate.csv
describe_trends:
run: r:latest analysis/Descriptive_trends.R
needs:
[
generate_measures,
generate_study_population
]
outputs:
moderately_sensitive:
Fig1: output/incidence.png
Fig2: output/prevalence.png
Fig3: output/died_prostate.png
Fig4: output/incidence_by_age_group.png
Fig5: output/incidence_by_ethnicity.png
Fig6: output/incidence_by_imd_cat.png
Fig7: output/incidence_by_region.png
Fig8: output/prevalenc_by_age_group.png
Fig9: output/prevalenc_by_ethnicity.png
Fig10: output/prevalenc_by_imd_cat.png
Fig11: output/prevalenc_by_region.png
csv1: output/Rates_rounded_prevalence.csv
csv2: output/Rates_rounded_prevalence_by_region.csv
csv3: output/Rates_rounded_prevalence_by_imd_cat.csv
csv4: output/Rates_rounded_prevalence_by_ethnicity.csv
csv5: output/Rates_rounded_prevalence_by_age_group.csv
csv6: output/Rates_rounded_incidence.csv
csv7: output/Rates_rounded_incidence_by_region.csv
csv8: output/Rates_rounded_incidence_by_imd_cat.csv
csv9: output/Rates_rounded_incidence_by_ethnicity.csv
csv10: output/Rates_rounded_incidence_by_age_group.csv
csv11: output/Rates_rounded_died_prostate.csv
csv12: output/Table1.csv