generated from opensafely/research-template
-
Notifications
You must be signed in to change notification settings - Fork 0
/
imm_comb.R
155 lines (135 loc) · 5.51 KB
/
imm_comb.R
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
# # # # # # # # # # # # # # # # # # # # #
# This script creates an upset plot for immunosuppression subgroups
# # # # # # # # # # # # # # # # # # # # #
# Import libraries
library(tidyverse)
library(here)
library(glue)
library(dplyr)
library(gt)
library(gtsummary)
library(reshape2)
# Select wave and subgroup based on input arguments
args <- commandArgs(trailingOnly=TRUE)
if(length(args)==0){
wave <- "wave4"
} else {
wave <- args[[1]]
}
# Import filtered data
d <- read_rds(here::here("output", "filtered", paste0("input_",wave,".rds")))
## Broad categories
# Create text coding for each group
d = d %>%
mutate(
any_transplant_alt = if_else(any_transplant == 1, "Tx", "0"),
any_bone_marrow_alt = if_else(any_bone_marrow == 1, "HC", "0"),
radio_chemo_alt = if_else(radio_chemo == 1, "RC", "0"),
immunosuppression_medication_alt = if_else(immunosuppression_medication == 1, "IMM", "0"),
immunosuppression_diagnosis_alt = if_else(immunosuppression_diagnosis == 1, "IMD", "0")
)
# Combine text coding
d$immuno_combined = paste0(
d$any_transplant_alt,"-",
d$any_bone_marrow_alt,"-",
d$radio_chemo_alt,"-",
d$immunosuppression_medication_alt,"-",
d$immunosuppression_diagnosis_alt
)
# Summarise set sizes
sets = data.frame("Group" = c("Tx", "HC", "IMD", "IMM", "RC"),
"Count" = c(
plyr::round_any(sum(d$any_transplant), 5),
plyr::round_any(sum(d$any_bone_marrow), 5),
plyr::round_any(sum(d$immunosuppression_diagnosis), 5),
plyr::round_any(sum(d$immunosuppression_medication), 5),
plyr::round_any(sum(d$radio_chemo), 5)
),
"Type" = "Set"
)
# Collate combinations
collated = data.frame(table(d$immuno_combined)) %>% arrange(-Freq)
names(collated) = c("Group", "Count")
# Group counts of <500 as 'Other'
collated_other = data.frame("Group" = "Other",
"Count" = sum(collated$Count[collated$Count<500]))
collated_final = rbind(collated[collated$Count>=500,], collated_other) %>%
mutate(Count = plyr::round_any(Count, 5),
Type = "Combo")
# Collate sets and combinations
collated_final = rbind(sets, collated_final)
## Save as csv
output_dir <- here("output", "imm_comb")
fs::dir_create(output_dir)
write_csv(collated_final, here::here("output", "imm_comb", paste0("imm_comb_",wave,"_broad.csv")))
## Narrow categories
# Create text coding for each group
d = d %>%
mutate(
any_transplant_alt = case_when(
any_transplant_type == "Kidney transplant" ~ "Tx (KT)",
any_transplant_type == "Other transplant" ~ "Tx (OT)",
TRUE ~ "0"
),
bone_marrow_alt = case_when(
any_bone_marrow_type == "Tx (BM)" ~ "Tx (BM)",
any_bone_marrow_type == "HC no Tx (BM)" ~ "HC (Tx-)",
TRUE ~ "0"
),
radio_chemo_alt = case_when(
radio_chemo_cat == ">6 months" ~ "RC (>6m)",
radio_chemo_cat == "<=6 months" ~ "RC (<=6m)",
TRUE ~ "0"
),
immunosuppression_medication_alt = case_when(
immunosuppression_medication_cat == ">3 months" ~ "IMM (>3m)",
immunosuppression_medication_cat == "<=3 months" ~ "IMM (<=3m)",
TRUE ~ "0"
),
immunosuppression_diagnosis_alt = case_when(
immunosuppression_diagnosis_cat == ">1 year" ~ "IMD (>1y)",
immunosuppression_diagnosis_cat == "<=1 year" ~ "IMD (<=1y)",
TRUE ~ "0"
)
)
# Combine text coding
d$immuno_combined = paste0(
d$any_transplant_alt,"-",
d$bone_marrow_alt,"-",
d$radio_chemo_alt,"-",
d$immunosuppression_medication_alt,"-",
d$immunosuppression_diagnosis_alt
)
# Summarise set sizes
sets = data.frame("Group" = c("Tx (KT)", "Tx (OT)",
"Tx (BM)", "HC (Tx-)",
"RC (>6m)", "RC (<=6m)",
"IMM (>3m)", "IMM (<=3m)",
"IMD (>1y)", "IMD (<=1y)"),
"Count" = c(
plyr::round_any(sum(d$any_transplant_type=="Kidney transplant", na.rm=T), 5),
plyr::round_any(sum(d$any_transplant_type=="Other transplant", na.rm=T), 5),
plyr::round_any(sum(d$any_bone_marrow_type=="Tx (BM)", na.rm=T), 5),
plyr::round_any(sum(d$any_bone_marrow_type=="HC no Tx (BM)", na.rm=T), 5),
plyr::round_any(sum(d$radio_chemo_cat==">6 months", na.rm=T), 5),
plyr::round_any(sum(d$radio_chemo_cat=="<=6 months", na.rm=T), 5),
plyr::round_any(sum(d$immunosuppression_medication_cat==">3 months", na.rm=T), 5),
plyr::round_any(sum(d$immunosuppression_medication_cat=="<=3 months", na.rm=T), 5),
plyr::round_any(sum(d$immunosuppression_diagnosis_cat==">1 year", na.rm=T), 5),
plyr::round_any(sum(d$immunosuppression_diagnosis_cat=="<=1 year", na.rm=T), 5)
),
"Type" = "Set"
)
# Collate combinations
collated = data.frame(table(d$immuno_combined)) %>% arrange(-Freq)
names(collated) = c("Group", "Count")
# Group counts of <100 as 'Other'
collated_other = data.frame("Group" = "Other",
"Count" = sum(collated$Count[collated$Count<500]))
collated_final = rbind(collated[collated$Count>=500,], collated_other) %>%
mutate(Count = plyr::round_any(Count, 5),
Type = "Combo")
# Collate sets and combinations
collated_final = rbind(sets, collated_final)
## Save as csv
write_csv(collated_final, here::here("output", "imm_comb", paste0("imm_comb_",wave,"_narrow.csv")))