Load the data
combined <- import(here::here("data", "clean", "backup", "linelist_combined_20141201.rds"))
Simple epidemic curve,
default setting
## simple epidemic curve, default setting
ggplot( # open the plot
data = combined, # open the database
mapping = aes(
x = date_onset # chose variable(s) to include
)) +
geom_histogram() # choose the geometry histogram
Simple epidemic curve,
binwidth = 1 (each bar = 1 day)
## simple epidemic curve, binwidth = 1 (each bar = 1 day)
ggplot(
data = combined,
mapping = aes(
x = date_onset
)) +
geom_histogram(binwidth = 1) # specify the bin width
Simple epidemic curve,
binwidth = 7 (each bar = 7 days)
## simple epidemic curve, binwidth = 7 (each bar = 7 days)
# but... we don't know when start the bin
ggplot(
data = combined,
mapping = aes(
x = date_onset
))+
geom_histogram(binwidth = 7) # specify the bin width
Simple epidemic curve,
using parameter breaks to define the break points for the histogram
bins
Create the break
points for the histogram bins
# first date of onset
min(combined$date_onset, na.rm = T)
## [1] "2014-05-06"
# last date of onset
max(combined$date_onset, na.rm = T)
## [1] "2014-11-28"
# first day of the week of the week of the first date of onset
floor_date(min(combined$date_onset, na.rm = T),
unit = "week",
week_start = 1)
## [1] "2014-05-05"
# first day of the week of the following week of the last date of onset
ceiling_date(max(combined$date_onset, na.rm = T),
unit = "week",
week_start = 1)
## [1] "2014-12-01"
# break points for the histogram bin
# => sequence of dates with first day of the week of all weeks from the week with the first date of onset to the week with the last date of onset
ebola_weeks <-
seq.Date(
from = floor_date(min(combined$date_onset, na.rm = T),
unit = "week",
week_start = 1),
to = ceiling_date(max(combined$date_onset, na.rm = T),
unit = "week",
week_start = 1),
by = "weeks"
)
ebola_weeks
## [1] "2014-05-05" "2014-05-12" "2014-05-19" "2014-05-26" "2014-06-02"
## [6] "2014-06-09" "2014-06-16" "2014-06-23" "2014-06-30" "2014-07-07"
## [11] "2014-07-14" "2014-07-21" "2014-07-28" "2014-08-04" "2014-08-11"
## [16] "2014-08-18" "2014-08-25" "2014-09-01" "2014-09-08" "2014-09-15"
## [21] "2014-09-22" "2014-09-29" "2014-10-06" "2014-10-13" "2014-10-20"
## [26] "2014-10-27" "2014-11-03" "2014-11-10" "2014-11-17" "2014-11-24"
## [31] "2014-12-01"
Making the
epicurve
ggplot(
data = combined,
mapping = aes(
x = date_onset
))+
geom_histogram(
breaks = ebola_weeks # specify the break points for the histogram bins
)
Simple epidemic curve
with break points and x-axis with month using scale_x_date
ggplot(
data = combined,
mapping = aes(
x = date_onset
))+
geom_histogram(
breaks = ebola_weeks
) +
scale_x_date(
date_breaks = "1 months") # specify the labels on the x axis (date), appears every month
simple epidemic curve
with break points and x-axis with month using scale_x_date
## simple epidemic curve with break points and x-axis with month using scale_x_date
ggplot(
data = combined,
mapping = aes(
x = date_onset
))+
geom_histogram(
breaks = ebola_weeks
) +
scale_x_date(
date_breaks = "1 months", # specify the labels on the x axis (date): a label every month
date_labels = "%B") # specify the format of the labels : month name
Simple epidemic curve
with break points and x-axis with weeks using scale_x_date and
label_date_short
## simple epidemic curve with break points and x-axis with weeks using scale_x_date and label_date_short
ggplot(
data = combined,
mapping = aes(
x = date_onset
))+
geom_histogram(
breaks = ebola_weeks
) +
scale_x_date(
date_breaks = "1 week", # specify the labels on the x axis (date): a label every week
labels = scales::label_date_short() # automatically constructs a short format string sufficient to uniquely identify labels
)
Same as previous
changing color of lines around bars and color of fill within bars
## same as previous changing color of lines around bars and color of fill within bars
ggplot(
data = combined,
mapping = aes(
x = date_onset
))+
geom_histogram(
breaks = ebola_weeks,
color = "darkblue", # color of lines around bars
fill = "lightblue" # color of fill within bars
) +
scale_x_date(
date_breaks = "1 months",
labels = scales::label_date_short()
)
Same as previous
adding labels for titles
## same as previous adding labels for titles
ggplot(
data = combined,
mapping = aes(
x = date_onset
))+
geom_histogram(
breaks = ebola_weeks,
color = "darkblue", # color of lines around bars
fill = "lightblue" # color of fill within bars
) +
scale_x_date(
date_breaks = "1 months",
labels = scales::label_date_short()
) +
labs(x = "Date", # title of x-axis
y = "Cases (n)", # title of y-axis
title = "Cases by week of onset", # graphic title
subtitle = str_glue("Source: MSF data from {Sys.Date()}")) # graphic sub-title
Same as previous with
simplify plot background using theme_bw()
## same as previous with simplify plot background using theme_bw()
ggplot(
data = combined,
mapping = aes(
x = date_onset
))+
geom_histogram(
breaks = ebola_weeks,
color = "darkblue", # color of lines around bars
fill = "lightblue" # color of fill within bars
) +
scale_x_date(
date_breaks = "2 weeks",
labels = scales::label_date_short()
) +
labs(x = "Date", # title of x-axis
y = "Cases (n)", # title of y-axis
title = "Cases by week of onset", # graphic title
subtitle = str_glue("Source: MSF data from {Sys.Date()}"))+ # graphic sub-title
theme_bw() # simplify plot background
