forked from majaliindberg/Touch_com_asd
-
Notifications
You must be signed in to change notification settings - Fork 0
/
2_describe-dataset.R
251 lines (184 loc) · 7.18 KB
/
2_describe-dataset.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
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
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
library(tidyverse)
library(summarytools)
library(ggplot2)
library(patchwork)
# source all .R files in the Rfunctions directory
sapply(list.files("Rfunctions", full.names = TRUE), source)
# folder paths ####
PROCESSED_DATA_FOLDER <- "Data/processed/"
TABLES_FOLDER <- "Tables/"
FIGURES_FOLDER <- "Figures/"
REPORTS_FOLDER <- "Data/reports/"
# read data ####
demog <- read_csv(
paste0(PROCESSED_DATA_FOLDER, "demographics-data.csv"),
col_types = "cccccccccc"
)
questionnaires <- read_csv(
paste0(PROCESSED_DATA_FOLDER, 'questionnaire-data.csv'),
col_types = "cccccnnnnnnnnnnnnnn"
)
#. summary table ####
demog %>%
select(-c(PID, `Age Cohort`)) %>%
dfSummary(varnumbers = FALSE, valid.col = FALSE, na.col = FALSE) %>%
# freq_table() %>%
view(file = paste0(TABLES_FOLDER,"table1_demographics.html"))
# check that qualtrics assigned even numbers to different tasks ####
print_prop_xtab(xtabs(~ group + task, filter(demog, experiment == "viewed touch")))
# a bit uneven, perhaps due to dropouts for the free text task?
# forced choice task ####
demog_forced <- filter(demog, task == "forced choice")
questionnaires_forced <- filter(questionnaires, task == "forced choice")
print_prop_xtab(xtabs(~ group + Language + experiment, demog_forced))
print_prop_xtab(xtabs(~ group + `Country of Residence` + experiment, demog_forced))
print_prop_xtab(xtabs(~ group + Gender + experiment, demog_forced))
print_prop_xtab(xtabs(~ group + `Age Group` + experiment, demog_forced))
#. summary table ####
demog_forced %>%
group_by(experiment, group) %>%
select(-c(PID, task, `Age Cohort`)) %>%
freq_table() %>%
view(file = paste0(TABLES_FOLDER,"table1_demographics_forced-choice.html"))
#. autism grouping vs. questionnaires ####
questionnaires_forced %>%
group_by(experiment, group) %>%
select(-c(PID, task, Experimenter)) %>%
freq_table() %>%
view(file = paste0(TABLES_FOLDER,"table1_questionnaires_forced-choice.html"))
questionnaires %>%
questionnaire_plot_combined("AQ_total", "AQ score")
ggsave(paste0(FIGURES_FOLDER,"AQ by group.svg"), width = 6, height = 4)
questionnaires %>%
questionnaire_plot_combined("BAPQ_total", "BAPQ score")
ggsave(paste0(FIGURES_FOLDER,"BAPQ by group.svg"), width = 6, height = 4)
questionnaires %>%
questionnaire_plot_combined("STQ_total", "STQ score")
ggsave(paste0(FIGURES_FOLDER,"STQ by group.svg"), width = 6, height = 4)
questionnaires %>%
questionnaire_plot_combined("TAS_total", "TAS score")
ggsave(paste0(FIGURES_FOLDER,"TAS by group.svg"), width = 6, height = 4)
#. subset for comparable demographics ####
#.. felt touch subset ####
# Swedish-speaking, only experimenters 1 & 3
demog_felt_strict <- filter(
demog_forced,
experiment == "felt touch" &
Language == "Swedish" &
Experimenter != "2"
)
demog_felt_strict %>%
group_by(group) %>%
select(-c(PID, task, experiment, `Age Cohort`)) %>%
freq_table() %>%
view(file = paste0(TABLES_FOLDER,"tableS1_demographics_felt-touch_strict.html"))
#.. viewed touch subset ####
demog_viewed_reduced <- filter(
demog_forced,
experiment == "viewed touch" &
`Country of Residence` == "Sweden" &
Language == "Swedish",
Gender == "Female"
)
# viewed touch select control group
# numbers matched to ASD group
# 1 from 21-25
# 4 from 26-30
# 4 from 31-35
# 5 from 36-40
# https://stackoverflow.com/questions/66476142/sample-from-a-data-frame-using-group-specific-sample-sizes
set.seed(09032023)
demog_viewed_strict_control <- demog_viewed_reduced %>%
filter(group == "Control" & `Age Group` != "16 - 20") %>%
group_split(`Age Group`) %>%
map2_dfr(c(1,4,4,5), ~ slice_sample(.x, n = .y))
demog_viewed_strict <- full_join(
filter(demog_viewed_reduced, group == "ASD"),
demog_viewed_strict_control
)
print_prop_xtab(xtabs(~ group + `Age Group` + experiment, demog_viewed_strict))
demog_viewed_strict %>%
group_by(group) %>%
select(-c(PID, task, experiment, Experimenter, `Age Cohort`)) %>%
freq_table() %>%
view(file = paste0(TABLES_FOLDER,"tableS2_demographics_viewed-touch_strict.html"))
#.. felt vs. seen touch subset ####
demog_forced_reduced <- filter(
demog_forced,
Gender == "Female"
)
print_prop_xtab(xtabs(~ experiment + `Age Group` + group, demog_forced_reduced))
# forced choice select ASD felt touch group
# reduce 16-20 to more closely resemble ASD viewed touch group
# 7 from 16-20
# 5 from 21-25
# 3 from 26-30
# 1 from 31-35
# 0 from 36-40
set.seed(24032023)
demog_forced_strict_felt_asd <- demog_forced_reduced %>%
filter(experiment == "felt touch", group == "ASD" & `Age Group` != "36 - 40") %>%
group_split(`Age Group`) %>%
map2_dfr(c(7,5,3,1), ~ slice_sample(.x, n = .y))
# forced choice select control viewed touch group
# select to match age deomgraphics of felt touch control group
# 3 from 16-20
# 13 from 21-25
# 2 from 26-30
# 1 from 31-35
# 2 from 36-40
set.seed(24032023)
demog_forced_strict_viewed_control <- demog_forced_reduced %>%
filter(experiment == "viewed touch", group == "Control") %>%
group_split(`Age Group`) %>%
map2_dfr(c(3,13,2,1,2), ~ slice_sample(.x, n = .y))
demog_forced_strict <- full_join(
filter(demog_forced_reduced, experiment == "felt touch" & group == "Control"),
filter(demog_forced_reduced, experiment == "viewed touch" & group == "ASD")
) %>%
full_join(demog_forced_strict_felt_asd) %>%
full_join(demog_forced_strict_viewed_control)
print_prop_xtab(xtabs(~ experiment + `Age Group` + group, demog_forced_strict))
demog_forced_strict %>%
group_by(group, experiment) %>%
select(-c(PID, task, Experimenter, `Age Cohort`)) %>%
freq_table() %>%
view(file = paste0(TABLES_FOLDER,"tableS3_demographics_felt-vs-viewed_strict.html"))
#.. save PIDs for strict subsets ####
demog_forced %>%
select(experiment, group, PID) %>%
mutate(
felt_touch = PID %in% demog_felt_strict$PID,
viewed_touch = PID %in% demog_viewed_strict$PID,
felt_vs_viewed = PID %in% demog_forced_strict$PID
) %>%
write_csv(paste0(PROCESSED_DATA_FOLDER, "PIDs-included-in-strict-subsets.csv"))
# free text task ####
demog_free <- filter(demog, task == "free text")
print_prop_xtab(xtabs(~ group + Language, demog_free))
print_prop_xtab(xtabs(~ group + `Country of Residence`, demog_free))
print_prop_xtab(xtabs(~ group + Gender, demog_free))
print_prop_xtab(xtabs(~ group + `Age Group`, demog_free))
#. summary table ####
demog_free %>%
group_by(group) %>%
select(-c(PID, Experimenter, experiment, task, `Age Cohort`)) %>%
freq_table() %>%
view(file = paste0(TABLES_FOLDER,"tableS4_demographics_free-text.html"))
# missing questionnaire responses ####
questionnaires %>%
group_by(group,AQ_n_missing) %>% tally()
questionnaires %>%
group_by(group,BAPQ_n_missing) %>% tally()
questionnaires %>%
group_by(group,STQ_n_missing) %>% tally()
questionnaires %>%
group_by(group, TAS_n_missing) %>% tally()
full_join(demog, questionnaires) %>%
select(PID, group,Language, `Country of Residence`, contains("n_missing")) %>%
rowwise() %>%
mutate(total_n_missing = sum(c_across(contains("n_missing")))) %>%
filter(total_n_missing > 0) %>%
select(-total_n_missing) %>%
arrange(group, -across(contains("n_missing"))) %>%
write_path_csv("Data/reports/", "online_missing_questionnaire_responses.csv")