generated from opensafely/research-template
/
project.yaml
121 lines (102 loc) · 4 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
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
version: "3.0"
expectations:
population_size: 20000
actions:
generate_covid_cohort:
run: cohortextractor:latest generate_cohort --study-definition study_definition_covid
outputs:
highly_sensitive:
cohort: output/input_covid.csv
generate_covid_community_cohort:
run: cohortextractor:latest generate_cohort --study-definition study_definition_covid_community
outputs:
highly_sensitive:
cohort: output/input_covid_community.csv
generate_covid_general_population_cohort:
run: cohortextractor:latest generate_cohort --study-definition study_definition_general_population
outputs:
highly_sensitive:
cohort: output/input_general_population.csv
generate_pneumonia_cohort:
run: cohortextractor:latest generate_cohort --study-definition study_definition_pneumonia
outputs:
highly_sensitive:
cohort: output/input_pneumonia.csv
matching:
run: python:latest python analysis/match_running.py
needs: [generate_covid_cohort, generate_covid_general_population_cohort]
outputs:
moderately_sensitive:
matching_report: output/matching_report_general_population.txt
highly_sensitive:
combined: output/matched_combined_general_population.csv
covid_rates_cohort:
run: stata-mp:latest analysis/000_cr_define_covariates_simple_rates.do "covid"
needs: [generate_covid_cohort]
outputs:
highly_sensitive:
analysis_dataset: output/cohort_rates_covid.dta
covid_community_rates_cohort:
run: stata-mp:latest analysis/000_cr_define_covariates_simple_rates.do "covid_community"
needs: [generate_covid_community_cohort]
outputs:
highly_sensitive:
analysis_dataset: output/cohort_rates_covid_community.dta
pneumonia_rates_cohort:
run: stata-mp:latest analysis/000_cr_define_covariates_simple_rates.do "pneumonia"
needs: [generate_pneumonia_cohort]
outputs:
highly_sensitive:
analysis_dataset: output/cohort_rates_pneumonia.dta
gen_pop_rates_cohort:
run: stata-mp:latest analysis/000_cr_define_covariates_simple_rates.do "matched_combined_general_population"
needs: [matching]
outputs:
highly_sensitive:
analysis_dataset: output/cohort_rates_gen_population.dta
covid_rates:
run: stata-mp:latest analysis/201_cr_simple_rates.do "covid"
needs: [covid_rates_cohort]
outputs:
moderately_sensitive:
rates: output/tabfig/rates_summary_covid.csv
covid_comm_rates:
run: stata-mp:latest analysis/201_cr_simple_rates.do "covid_community"
needs: [covid_community_rates_cohort]
outputs:
moderately_sensitive:
rates: output/tabfig/rates_summary_covid_community.csv
pneumonia_rates:
run: stata-mp:latest analysis/201_cr_simple_rates.do "pneumonia"
needs: [pneumonia_rates_cohort]
outputs:
moderately_sensitive:
rates: output/tabfig/rates_summary_pneumonia.csv
gen_pop_rates:
run: stata-mp:latest analysis/201_cr_simple_rates.do "gen_population"
needs: [gen_pop_rates_cohort]
outputs:
moderately_sensitive:
rates: output/tabfig/rates_summary_gen_population.csv
baseline_characteristics:
run: stata-mp:latest analysis/400_baseline_characteristics.do
needs: [covid_rates_cohort, covid_community_rates_cohort, pneumonia_rates_cohort, gen_pop_rates_cohort]
outputs:
moderately_sensitive:
tables: output/tabfig/an_descriptiveTable_*.txt
append_cohorts:
run: stata-mp:latest analysis/300_cr_data_management_matching.do
needs: [covid_rates_cohort, pneumonia_rates_cohort, gen_pop_rates_cohort]
outputs:
moderately_sensitive:
log: output/append_cohorts.txt
highly_sensitive:
dataset: output/combined_covid_pneumonia.dta
dataset2: output/combined_covid_gen_population.dta
cox_models:
run: stata-mp:latest analysis/302_cox_models.do
needs: [append_cohorts]
outputs:
moderately_sensitive:
log: output/cox_models.txt
dataset: output/tabfig/cox_model_summary.csv