generated from opensafely/research-template
-
Notifications
You must be signed in to change notification settings - Fork 0
/
project.yaml
150 lines (136 loc) · 5.11 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
version: '3.0'
expectations:
population_size: 10000
actions:
generate_dataset:
run: ehrql:v1 generate-dataset analysis/dataset_definition.py
--output output/dataset_definition.csv
outputs:
highly_sensitive:
cohort: output/dataset_definition.csv
measures_dataset_2016:
run: ehrql:v1 generate-measures analysis/dataset_definition_measures.py
--output output/measures/measures_dataset_2016.csv
--
--start-date "2016-04-01"
--intervals 12
needs: [generate_dataset]
outputs:
highly_sensitive:
measure_csv: output/measures/measures_dataset_2016.csv
measures_dataset_2017:
run: ehrql:v1 generate-measures analysis/dataset_definition_measures.py
--output output/measures/measures_dataset_2017.csv
--
--start-date "2017-04-01"
--intervals 12
needs: [generate_dataset]
outputs:
highly_sensitive:
measure_csv: output/measures/measures_dataset_2017.csv
measures_dataset_2018:
run: ehrql:v1 generate-measures analysis/dataset_definition_measures.py
--output output/measures/measures_dataset_2018.csv
--
--start-date "2018-04-01"
--intervals 12
needs: [generate_dataset]
outputs:
highly_sensitive:
measure_csv: output/measures/measures_dataset_2018.csv
measures_dataset_2019:
run: ehrql:v1 generate-measures analysis/dataset_definition_measures.py
--output output/measures/measures_dataset_2019.csv
--
--start-date "2019-04-01"
--intervals 12
needs: [generate_dataset]
outputs:
highly_sensitive:
measure_csv: output/measures/measures_dataset_2019.csv
measures_dataset_2020:
run: ehrql:v1 generate-measures analysis/dataset_definition_measures.py
--output output/measures/measures_dataset_2020.csv
--
--start-date "2020-04-01"
--intervals 12
needs: [generate_dataset]
outputs:
highly_sensitive:
measure_csv: output/measures/measures_dataset_2020.csv
measures_dataset_2021:
run: ehrql:v1 generate-measures analysis/dataset_definition_measures.py
--output output/measures/measures_dataset_2021.csv
--
--start-date "2021-04-01"
--intervals 12
needs: [generate_dataset]
outputs:
highly_sensitive:
measure_csv: output/measures/measures_dataset_2021.csv
measures_dataset_2022:
run: ehrql:v1 generate-measures analysis/dataset_definition_measures.py
--output output/measures/measures_dataset_2022.csv
--
--start-date "2022-04-01"
--intervals 12
needs: [generate_dataset]
outputs:
highly_sensitive:
measure_csv: output/measures/measures_dataset_2022.csv
measures_dataset_2023:
run: ehrql:v1 generate-measures analysis/dataset_definition_measures.py
--output output/measures/measures_dataset_2023.csv
--
--start-date "2023-04-01"
--intervals 12
needs: [generate_dataset]
outputs:
highly_sensitive:
measure_csv: output/measures/measures_dataset_2023.csv
measures_dataset_2024:
run: ehrql:v1 generate-measures analysis/dataset_definition_measures.py
--output output/measures/measures_dataset_2024.csv
--
--start-date "2024-04-01"
--intervals 6
needs: [generate_dataset]
outputs:
highly_sensitive:
measure_csv: output/measures/measures_dataset_2024.csv
run_incidence_graphs:
run: stata-mp:latest analysis/100_incidence_graphs.do
needs: [generate_dataset, measures_dataset_2016, measures_dataset_2017, measures_dataset_2018, measures_dataset_2019, measures_dataset_2020, measures_dataset_2021, measures_dataset_2022, measures_dataset_2023, measures_dataset_2024]
outputs:
moderately_sensitive:
log1: logs/descriptive_tables.log
figure1: output/figures/incidence_*.svg
figure2: output/figures/prevalence_*.svg
figure3: output/figures/inc_comp_*.svg
figure4: output/figures/prev_comp_*.svg
figure5: output/figures/inc_adj_*.svg
figure6: output/figures/inc_ma_sex_*.svg
figure7: output/figures/prev_adj_*.svg
figure8: output/figures/inc_adj_ma_*.svg
figure9: output/figures/inc_adj_ma2_*.svg
figure10: output/figures/adj_ma_sex_*.svg
figure11: output/figures/adj_ma_sex2_*.svg
figure12: output/figures/adj_ma_age_*.svg
data1: output/data/arima_nonstandardised.csv
run_sarima:
run: r:latest analysis/200_sarima.R
needs: [run_incidence_graphs]
outputs:
moderately_sensitive:
log1: logs/sarima_log.txt
figure1: output/figures/observed_*.svg
figure2: output/figures/raw_pre_covid_*.svg
figure3: output/figures/differenced_pre_covid_*.svg
figure4: output/figures/seasonal_pre_covid_*.svg
figure5: output/figures/raw_acf_*.svg
figure6: output/figures/differenced_acf_*.svg
figure7: output/figures/seasonal_acf_*.svg
figure8: output/figures/auto_residuals_*.svg
figure9: output/figures/obs_pred_*.svg
table1: output/tables/change_incidence_byyear.csv
table2: output/tables/values_*.csv