-
Notifications
You must be signed in to change notification settings - Fork 0
/
2_data.Rmd
260 lines (219 loc) · 12 KB
/
2_data.Rmd
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
250
251
252
253
254
255
256
257
258
259
260
---
title: "SwiFCoIBMove: Data import and processing"
author: "Cédric Scherer"
date: '`r format(Sys.time(), "%B %d, %Y")`'
output:
html_document:
theme: paper
toc: true
toc_float: true
toc_depth: 3
code_folding: show
link-citations: yes
editor_options:
chunk_output_type: console
---
```{r knitr-setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE, message = FALSE, warning = FALSE)
```
Script to import, process, and subset the simulation results (saved as .csv by running simulations using the "SwiFCoIBM-move.nlogo" file in the model folder).
# Setup
```{r libraries, message = F}
## libraries
library(tidyverse) ## data wrangling
library(magrittr) ## ceci n'est pas une pipe
filedate <- "2019-03-05"
```
# Data
## Load data
```{r load-data}
df_all <- df_raw <- data.table::fread("./simulations/2019-03-05_SwiFCoIBMove_mue4.csv", skip = 6)
```
## Data cosmetics
### rename columns
```{r rename-cols}
rename_map <- c(
'[run number]' = "run",
'case_fatality' = "cfr",
'file' = "scenario",
'roaming' = "roaming",
'mue' = "mue",
'mue_max' = "mue_max_rm",
'q' = "dir_pers",
'run_years' = "run_years_rm",
'seed_setup' = "seed_setup_rm",
'mean_quality' = "quality_rm",
'herd_prop' = "herd_prop_rm",
'release_fct' = "release_fct_rm",
'longevity' = "longevity_rm",
'age_blur' = "age_blur_rm",
'fem_prob' = "fem_prob_rm",
'dist_disp' = "dist_disp_rm",
'year_release' = "year_release_rm",
'fert_red' = "fert_red_rm",
'fetal_inf' = "fetal_inf_rm",
't_anti' = "t_anti_rm",
't_trans' = "t_trans_rm",
'b_within' = "beta_within",
'b_between' = "beta_between_rm",
'b_move' = "beta_move",
'[step]' = "week",
'seed' = "seed",
'count turtles' = "ind_all",
'count turtles with [epi_stat = \"\"esSusc\"\"]' = "ind_susc",
'count turtles with [epi_stat = \"\"esTrans\"\"]' = "ind_trans",
'count turtles with [epi_stat = \"\"esLeth\"\"]' = "ind_leth",
'count turtles with [dem_stat = \"\"dsRoaming\"\"]' = "roam_all",
'count turtles with [dem_stat = \"\"dsRoaming\"\" AND epi_stat = \"\"esSusc\"\"]' = "roam_susc",
'count turtles with [dem_stat = \"\"dsRoaming\"\" AND epi_stat = \"\"esTrans\"\"]' = "roam_trans",
'count turtles with [dem_stat = \"\"dsRoaming\"\" AND epi_stat = \"\"esLeth\"\"]' = "roam_leth",
'new_trans' = "new_trans",
'new_leth' = "new_leth",
'contacts_avg' = "contacts_avg",
'contacts_med' = "contacts_med",
'contacts_lwr' = "contacts_lwr",
'contacts_upr' = "contacts_upr",
'contacts_max' = "contacts_max",
'contacts_var' = "contacts_var",
'contacts_1' = "contacts_1",
'contacts_2' = "contacts_2",
'contacts_3' = "contacts_3",
'contacts_4' = "contacts_4",
'contacts_5' = "contacts_5",
'contacts_6' = "contacts_6",
'contacts_7' = "contacts_7",
'contacts_8' = "contacts_8",
'contacts_9' = "contacts_9",
'trans_w' = "trans_w",
'trans_b' = "trans_b",
'trans_g' = "trans_g",
'patches_0' = "patches_0",
'patches_1' = "patches_1",
'patches_2' = "patches_2",
'patches_3' = "patches_3",
'patches_4' = "patches_4",
'patches_5' = "patches_5",
'patches_6' = "patches_6",
'patches_7' = "patches_7",
'patches_8' = "patches_8",
'patches_9' = "patches_9",
'count patches with [is_infected = 1]' = "cell_infected",
'count patches with [is_infectious = 1]' = "cell_infectious",
'max [id] of patches' = "n_cluster",
'count_init' = "count_init",
'count_init_roaming' = "count_init_roaming",
'dens_var' = "dens_var_all",
'dens_roam_var' = "dens_var_roam",
'dens_inf_group_var' = "dens_var_inf_group",
'dens_inf_roam_var' = "dens_var_inf_roam",
'quality_mean_6' = "qual_mean_6",
'mean [visited] of turtles with [dem_stat = \"\"dsRoaming\"\"]' = "visits_mean",
'F_infectious' = "F_infectious",
'F_infected' = "F_infectected",
'dist_inf' = "dist_inf",
'week_inf_max' = "week_inf_max",
'week_release' = "week_release",
'week_last' = "week_last"
)
names(df_all) <- rename_map[names(df_all)]
rm(rename_map)
```
### select columns used for further analyses and factorize variables
```{r select+factorize}
df_all %<>%
dplyr::select(-ends_with("_rm")) %>%
mutate_at(c(1:2, 5:length(.)), as.numeric)
(lev_roam <- unique(df_all$roaming))
(lev_scen <- unique(df_all$scenario))
df_all %<>%
mutate(
run = factor(run),
cfr = factor(cfr),
roaming = factor(roaming, levels = lev_roam),
scenario = factor(scenario, levels = lev_scen)
)
```
### correct non-logical values, calculate additional parameters and fill up for each measurement if needed
```{r correct+add}
df_all %<>%
group_by(run) %>%
filter(week != 0) %>%
mutate(
ind_immu = ind_all - ind_trans - ind_leth - ind_susc,
ind_inf = ind_trans + ind_leth,
roam_inf = roam_trans + roam_leth,
roam_immu = roam_all - roam_trans - roam_leth - roam_susc,
new_inf = new_trans + new_leth,
week_last = max(week_last),
trans_m = trans_w + trans_b,
trans = trans_g + trans_m,
contacts_avg = na_if(contacts_avg, -999),
contacts_med = na_if(contacts_med, -999),
contacts_lwr = na_if(contacts_lwr, -999),
contacts_upr = na_if(contacts_upr, -999),
contacts_max = na_if(contacts_max, -999),
contacts_var = na_if(contacts_var, -999)
) %>%
filter(week <= week_last + 1) %>%
mutate(
week_ext = if_else(week_last == 624, NA_real_, week_last + 1),
week_pathogen = week - week_release,
week_inf_max = week_inf_max - week_release + 1,
week_inf_max = ifelse(week_inf_max < 1, NA, week_inf_max),
duration_weeks = max(week_pathogen),
duration_quarter = duration_weeks / 13
) %>%
arrange(run, week) %>%
tbl_df()
```
## Save as .Rds
```{r save-proc }
saveRDS(df_all, file = glue::glue("./data/{filedate}_SwiFCoIBMove_all.Rds"))
```
# Subsets
## Create subsets
```{r create-subsets}
## only outbreak weeks
df_inf <- df_all %>%
filter(week >= week_release)
## mean values for time of outbreak
df_infmean <- df_inf %>%
group_by(run) %>%
dplyr::select(-week, -week_pathogen, -week_ext) %>%
summarise_all(funs(if(is.numeric(.)) mean(., na.rm = TRUE) else first(.)))
## sample data for testing
df_sample <- df_all %>%
group_by(roaming, scenario, mue, cfr, dir_pers) %>%
do(sample_n(., 500))
```
## Save subsets as .Rds
```{r save-subsets}
saveRDS(df_inf, file = glue::glue("./data/{filedate}_SwiFCoIBMove_inf.Rds"))
saveRDS(df_infmean, file = glue::glue("./data/{filedate}_SwiFCoIBMove_infmean.Rds"))
```
# Data info
## Check sample size
```{r sample-size}
df_n <- df_infmean %>%
group_by(roaming, cfr, mue, scenario) %>%
summarise(n = n())
length(unique(df_n$n))
```
## Variables
```{r variables}
## number of unique values
df_infmean %>%
keep(is.factor) %>%
map_int(n_distinct)
## unique values of each variable
df_infmean %>%
keep(is.factor) %>%
dplyr::select(-run) %>%
map(unique)
```
***
# Version info
```{r version}
version
sessionInfo()
```