generated from opensafely/research-template
/
project.yaml
210 lines (188 loc) · 7.43 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
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
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
version: '3.0'
expectations:
population_size: 1000
actions:
generate_study_population_1:
run: cohortextractor:latest generate_cohort --study-definition study_definition --index-date-range "2019-09-02 to 2020-01-13 by week" --output-format=csv.gz
outputs:
highly_sensitive:
cohort: output/input_*.csv.gz
generate_study_population_2:
run: cohortextractor:latest generate_cohort --study-definition study_definition --index-date-range "2020-01-20 to 2020-06-01 by week" --output-format=csv.gz
outputs:
highly_sensitive:
cohort: output/input*.csv.gz
generate_study_population_3:
run: cohortextractor:latest generate_cohort --study-definition study_definition --index-date-range "2020-06-08 to 2020-10-19 by week" --output-format=csv.gz
outputs:
highly_sensitive:
cohort: output/inpu*.csv.gz
generate_study_population_4:
run: cohortextractor:latest generate_cohort --study-definition study_definition --index-date-range "2020-10-26 to 2021-03-01 by week" --output-format=csv.gz
outputs:
highly_sensitive:
cohort: output/inp*.csv.gz
generate_study_population_5:
run: cohortextractor:latest generate_cohort --study-definition study_definition --index-date-range "2021-03-08 to 2021-06-14 by week" --output-format=csv.gz
outputs:
highly_sensitive:
cohort: output/in*.csv.gz
generate_study_population_6:
run: cohortextractor:latest generate_cohort --study-definition study_definition --index-date-range "2021-06-21 to 2021-09-27 by week" --output-format=csv.gz
outputs:
highly_sensitive:
cohort: output/i*.csv.gz
generate_measures:
run: cohortextractor:latest generate_measures --study-definition study_definition
needs: [generate_study_population_1, generate_study_population_2, generate_study_population_3, generate_study_population_4, generate_study_population_5, generate_study_population_6]
outputs:
moderately_sensitive:
measure_csv: output/measure_*_rate.csv
subgroup_setup:
run: stata-mp:latest analysis/subgroup_data_setup.do
needs:
- generate_measures
outputs:
highly_sensitive:
subgroup1: output/measure_dvafemale_rate.dta
subgroup2: output/measure_dvamale_rate.dta
subgroup3: output/measure_intdissub14_rate.dta
subgroup4: output/measure_intdisover14_rate.dta
subgroup5: output/measure_rcgpsafeguard_rate.dta
subgroup6: output/measure_alcmisuse_rate.dta
subgroup7: output/measure_drugmisuse_rate.dta
subgroup8: output/measure_opioid_rate.dta
model_alcmisuse:
run: stata-mp:latest analysis/model.do alcmisuse
needs:
- subgroup_setup
outputs:
highly_sensitive:
results1: output/alcmisuse_RR_LD1.dta
results2: output/alcmisuse_RD_LD1.dta
results3: output/alcmisuse_RR_LD2.dta
results4: output/alcmisuse_RD_LD2.dta
moderately_sensitive:
diagnostics1: output/diagnostics/alcmisuse_diagnostics1.svg
diagnostics2: output/diagnostics/alcmisuse_diagnostics2.svg
plot1: output/alcmisuse_plot1.svg
plot2: output/alcmisuse_plot2.svg
model_drugmisuse:
run: stata-mp:latest analysis/model.do drugmisuse
needs:
- subgroup_setup
outputs:
highly_sensitive:
results1: output/drugmisuse_RR_LD1.dta
results2: output/drugmisuse_RD_LD1.dta
results3: output/drugmisuse_RR_LD2.dta
results4: output/drugmisuse_RD_LD2.dta
moderately_sensitive:
diagnostics1: output/diagnostics/drugmisuse_diagnostics1.svg
diagnostics2: output/diagnostics/drugmisuse_diagnostics2.svg
plot1: output/drugmisuse_plot1.svg
plot2: output/drugmisuse_plot2.svg
model_opioid:
run: stata-mp:latest analysis/model.do opioid
needs:
- subgroup_setup
outputs:
highly_sensitive:
results1: output/opioid_RR_LD1.dta
results2: output/opioid_RD_LD1.dta
results3: output/opioid_RR_LD2.dta
results4: output/opioid_RD_LD2.dta
moderately_sensitive:
diagnostics1: output/diagnostics/opioid_diagnostics1.svg
diagnostics2: output/diagnostics/opioid_diagnostics2.svg
plot1: output/opioid_plot1.svg
plot2: output/opioid_plot2.svg
model_dvafemale:
run: stata-mp:latest analysis/model.do dvafemale
needs:
- subgroup_setup
outputs:
highly_sensitive:
results1: output/dvafemale_RR_LD1.dta
results2: output/dvafemale_RD_LD1.dta
results3: output/dvafemale_RR_LD2.dta
results4: output/dvafemale_RD_LD2.dta
moderately_sensitive:
diagnostics1: output/diagnostics/dvafemale_diagnostics1.svg
diagnostics2: output/diagnostics/dvafemale_diagnostics2.svg
plot1: output/dvafemale_plot1.svg
plot2: output/dvafemale_plot2.svg
model_dvamale:
run: stata-mp:latest analysis/model.do dvamale
needs:
- subgroup_setup
outputs:
highly_sensitive:
results1: output/dvamale_RR_LD1.dta
results2: output/dvamale_RD_LD1.dta
results3: output/dvamale_RR_LD2.dta
results4: output/dvamale_RD_LD2.dta
moderately_sensitive:
diagnostics1: output/diagnostics/dvamale_diagnostics1.svg
diagnostics2: output/diagnostics/dvamale_diagnostics2.svg
plot1: output/dvamale_plot1.svg
plot2: output/dvamale_plot2.svg
model_intdissub14:
run: stata-mp:latest analysis/model.do intdissub14
needs:
- subgroup_setup
outputs:
highly_sensitive:
results1: output/intdissub14_RR_LD1.dta
results2: output/intdissub14_RD_LD1.dta
results3: output/intdissub14_RR_LD2.dta
results4: output/intdissub14_RD_LD2.dta
moderately_sensitive:
diagnostics1: output/diagnostics/intdissub14_diagnostics1.svg
diagnostics2: output/diagnostics/intdissub14_diagnostics2.svg
plot1: output/intdissub14_plot1.svg
plot2: output/intdissub14_plot2.svg
model_intdisover14:
run: stata-mp:latest analysis/model.do intdisover14
needs:
- subgroup_setup
outputs:
highly_sensitive:
results1: output/intdisover14_RR_LD1.dta
results2: output/intdisover14_RD_LD1.dta
results3: output/intdisover14_RR_LD2.dta
results4: output/intdisover14_RD_LD2.dta
moderately_sensitive:
diagnostics1: output/diagnostics/intdisover14_diagnostics1.svg
diagnostics2: output/diagnostics/intdisover14_diagnostics2.svg
plot1: output/intdisover14_plot1.svg
plot2: output/intdisover14_plot2.svg
model_rcgpsafeguard:
run: stata-mp:latest analysis/model.do rcgpsafeguard
needs:
- subgroup_setup
outputs:
highly_sensitive:
results1: output/rcgpsafeguard_RR_LD1.dta
results2: output/rcgpsafeguard_RD_LD1.dta
results3: output/rcgpsafeguard_RR_LD2.dta
results4: output/rcgpsafeguard_RD_LD2.dta
moderately_sensitive:
diagnostics1: output/diagnostics/rcgpsafeguard_diagnostics1.svg
diagnostics2: output/diagnostics/rcgpsafeguard_diagnostics2.svg
plot1: output/rcgpsafeguard_plot1.svg
plot2: output/rcgpsafeguard_plot2.svg
combine_results:
run: stata-mp:latest analysis/combine_results.do
needs:
- model_alcmisuse
- model_drugmisuse
- model_opioid
- model_dvafemale
- model_dvamale
- model_intdissub14
- model_intdisover14
- model_rcgpsafeguard
outputs:
moderately_sensitive:
results: output/CITS_results.csv