Overview
This take-home exercise aims to reveal the daily routines of two selected participant of the city of Engagement, Ohio USA by using use ViSIElse and other appropriate visual analytics methods.
Importing Packages
In this take-home exercise, the following R packages will be used: - sf, an R package specially designed to handle geospatial data in simple feature objects.
packages = c('lubridate', 'tidyverse',
'readr','tmap','sf','sftime',
'clock','rmarkdown','ViSiElse',
'fastDummies','ggplot2')
for (p in packages){
if(!require(p, character.only = T)){
install.packages(p)
}
library(p,character.only = T)
}
Importing data
logs_fread <- list.files(path = "Data/ActivityLogs/",
pattern = "*.csv",
full.names = T) %>%
map_df(~fread(.))
buildings <- read_sf("Data/Buildings.csv",
options = "GEOM_POSSIBLE_NAMES=location")
Data preparation
Create label date, time, and hours.
logs_fread$month <- factor(month(logs_fread$`timestamp`),
levels=1:12,
labels=month.abb,
ordered=TRUE)
logs_March <- logs_fread %>% filter(month == 'Mar')
logs_March$date <- as_date(logs_March$`timestamp`)
logs_March$time <- format(logs_March$timestamp, format = "%H:%M:%S")
logs_March$hour <-hour(logs_March$`timestamp`)
Change the time into numerical value - number of minutes
Calculate their daily average balance.
Balance comparison
The line chart below presents the available balance for participant 4 and 16 throughout March 2022.
balance_comparison <- merge(participant4_balance,participant16_balance,
by="date")
ggplot(balance_comparison, aes(date)) +
geom_line(aes(y = Balance.x, colour = "participant 4")) +
geom_line(aes(y = Balance.y, colour = "participant 16"))
Daily routine comparison
grouped4 <- log_participant4 %>%
count(hour,currentMode) %>%
ungroup() %>%
na.omit()
ggplot(grouped4,
aes(hour,currentMode,
fill = n)) +
geom_tile(color = "white",
size = 0.1) +
coord_equal() +
scale_fill_gradient(name = "Frequencies",
low = "sky blue",
high = "dark blue") +
labs(x = 'Hour',
y = NULL,
title = "Monthly routine for participant 4") +
theme(axis.ticks = element_blank(),
plot.title = element_text(hjust = 0.5),
legend.title = element_text(size = 4),
legend.text = element_text(size = 3) )
grouped16 <- log_participant16 %>%
count(hour,currentMode) %>%
ungroup() %>%
na.omit()
ggplot(grouped16,
aes(hour,currentMode,
fill = n)) +
geom_tile(color = "white",
size = 0.1) +
coord_equal() +
scale_fill_gradient(name = "Frequencies",
low = "sky blue",
high = "dark blue") +
labs(x = 'Hour',
y = NULL,
title = "Monthly routine for participant 16") +
theme(axis.ticks = element_blank(),
plot.title = element_text(hjust = 0.5),
legend.title = element_text(size = 4),
legend.text = element_text(size = 3) )
get_home_time4 <- (log_participant4%>%
filter(currentMode == 'AtHome'))[, c('date','time')]%>%
group_by(date) %>%
summarize(get_home = min(time))
leave_home_time4 <- (log_participant4%>%
filter(currentMode == 'AtHome'))[, c('date','time')]%>%
group_by(date) %>%
summarize(leave_home = max(time))
start_travel_time4 <- (log_participant4%>%
filter(currentMode == 'Transport'))[, c('date','time')]%>%
group_by(date) %>%
summarize(start_travel = min(time))
end_travel_time4 <-(log_participant4%>%
filter(currentMode == 'Transport'))[, c('date','time')]%>%
group_by(date) %>%
summarize(end_travel = max(time))
start_work_time4 <- (log_participant4%>%
filter(currentMode == 'AtWork'))[, c('date','time')]%>%
group_by(date) %>%
summarize(start_work = min(time))
end_work_time4 <- (log_participant4%>%
filter(currentMode == 'AtWork'))[, c('date','time')]%>%
group_by(date) %>%
summarize(end_work = max(time))
get_restaurant_time4 <- (log_participant4%>%
filter(currentMode == 'AtRestaurant'))[, c('date','time')]%>%
group_by(date) %>%
summarize(get_restaurant = min(time))
leave_restaurant_time4 <- (log_participant4%>%
filter(currentMode == 'AtRestaurant'))[, c('date','time')]%>%
group_by(date) %>%
summarize(leave_restaurant = max(time))
start_recreation_time4 <- (log_participant4%>%
filter(currentMode == 'AtRecreation'))[, c('date','time')]%>%
group_by(date) %>%
summarize(start_recreation = min(time))
end_recreation_time4 <- (log_participant4%>%
filter(currentMode == 'AtRecreation'))[, c('date','time')]%>%
group_by(date) %>%
summarize(end_recreation = max(time))
get_home_time16 <- (log_participant16%>%
filter(currentMode == 'AtHome'))[, c('date','time')]%>%
group_by(date) %>%
summarize(get_home = min(time))
leave_home_time16 <- (log_participant16%>%
filter(currentMode == 'AtHome'))[, c('date','time')]%>%
group_by(date) %>%
summarize(leave_home = max(time))
start_travel_time16 <- (log_participant16%>%
filter(currentMode == 'Transport'))[, c('date','time')]%>%
group_by(date) %>%
summarize(start_travel = min(time))
end_travel_time16 <-(log_participant16%>%
filter(currentMode == 'Transport'))[, c('date','time')]%>%
group_by(date) %>%
summarize(end_travel = max(time))
start_work_time16 <- (log_participant16%>%
filter(currentMode == 'AtWork'))[, c('date','time')]%>%
group_by(date) %>%
summarize(start_work = min(time))
end_work_time16 <- (log_participant16%>%
filter(currentMode == 'AtWork'))[, c('date','time')]%>%
group_by(date) %>%
summarize(end_work = max(time))
get_restaurant_time16 <- (log_participant16%>%
filter(currentMode == 'AtRestaurant'))[, c('date','time')]%>%
group_by(date) %>%
summarize(get_restaurant = min(time))
leave_restaurant_time16 <- (log_participant16%>%
filter(currentMode == 'AtRestaurant'))[, c('date','time')]%>%
group_by(date) %>%
summarize(leave_restaurant = max(time))
start_recreation_time16 <- (log_participant16%>%
filter(currentMode == 'AtRecreation'))[, c('date','time')]%>%
group_by(date) %>%
summarize(start_recreation = min(time))
end_recreation_time16 <- (log_participant16%>%
filter(currentMode == 'AtRecreation'))[, c('date','time')]%>%
group_by(date) %>%
summarize(end_recreation = max(time))
participant4_list <- list(get_home_time4, leave_home_time4,
start_travel_time4,end_travel_time4,
start_work_time4,end_work_time4,
get_restaurant_time4,leave_restaurant_time4,
start_recreation_time4,end_recreation_time4)
participant4_routine <- participant4_list %>% reduce(full_join, by='date')
participant16_list <- list(get_home_time16, leave_home_time16,
start_travel_time16,end_travel_time16,
start_work_time16,end_work_time16,
get_restaurant_time16,leave_restaurant_time16,
start_recreation_time16,end_recreation_time16)
participant16_routine <- participant16_list %>% reduce(full_join, by='date')
visielse(participant4_routine)
-parameters
method : global
grwithin :
quantity : N
informer : median
tests : FALSE
threshold.test : 0.01
pixel : 20
t_0 : 0
-MATp : 10 x 74 sparse Matrix of class "dgCMatrix"
-L : 0 x 0 data.frame
-idsort : 0 x 0 matrix
-MATpsup : 0 x 0 sparse Matrix of class "dgCMatrix"
-idsup : length 0 vector
-Lsup : 0 x 0 data.frame
-colvect : 1 x 1 matrix
-BZL : 0 x 0 sparse Matrix of class "dgCMatrix"
-book : 10 x 6 ViSibook
-group : length 0 factor
-vect_tps : length 74 vector
-testsP : length 0 vector
-informers : 3 x 10 matrix visielse(participant16_routine)
-parameters
method : global
grwithin :
quantity : N
informer : median
tests : FALSE
threshold.test : 0.01
pixel : 20
t_0 : 0
-MATp : 10 x 74 sparse Matrix of class "dgCMatrix"
-L : 0 x 0 data.frame
-idsort : 0 x 0 matrix
-MATpsup : 0 x 0 sparse Matrix of class "dgCMatrix"
-idsup : length 0 vector
-Lsup : 0 x 0 data.frame
-colvect : 1 x 1 matrix
-BZL : 0 x 0 sparse Matrix of class "dgCMatrix"
-book : 10 x 6 ViSibook
-group : length 0 factor
-vect_tps : length 74 vector
-testsP : length 0 vector
-informers : 3 x 10 matrix