Article Directory
- Reproduce picture
- Set the working path and load related R packages
- Read the data set
- data visualization
- Calculate mean and standard deviation
- Visualization process
Follow the “Nature” official publication to learn graphing, and today I reproduce a dual-axis graph in the Nature article – a grouped histogram on the left and a line scatter graph on the right.
Reproduce image
A in the picture is what we are going to reproduce today. This picture is a dual-axis chart that combines a histogram and a scatter chart.
Set the working path and load related R packages
rm(list = ls()) # Clear the current environment variables
setwd("C:/Users/Zz/Desktop/Official Account SES") # Set the working path
# Load R package
library(ggplot2)
library(tidyverse)
Read data set
cData <- read_csv("cData.csv")
head(cData)
# Weeks Type lfValue rgValue
# <dbl> <chr> <dbl> <dbl>
# 1 20 By week of testing 2500 1.3
# 2 20 By week of testing 2550 1.5
# 3 20 By week of testing 2450 1.45
# 4 21 By week of testing 2750 1.2
# 5 21 By week of testing 2780 1.25
# 6 21 By week of testing 2680 1.18
Data visualization
# Species composition stacked area chart
library(ggplot2)
library(ggalluvial)
ggplot(data = top10,
aes(x = Depth, y = Abundance, fill = reorder(Phylum, -Abundance),
color = reorder(Phylum, -Abundance),
stratum = reorder(Phylum, -Abundance) ,
alluvium = reorder(Phylum, -Abundance))) +
geom_alluvium(aes(fill = reorder(Phylum, -Abundance)),
alpha = 0.7, decreasing = FALSE) +
geom_stratum(aes(fill = reorder(Phylum, Abundance)),
width = 0.3, size = 0.1, color = "black") +
scale_y_continuous(expand = c(0, 0)) +
theme_bw() +
facet_grid(. ~ Treat, scales = "fixed") +
scale_fill_manual(values = c("#EB7369", "#CF8B0B", "#9D9F20", "#2BB077", "#2BB077",
"#1BB3B7", "#29A4DE", "#8989C1", "#B174AD",
"#DE66A1"), name = "Phylum") +
scale_color_manual(values = c("#EB7369", "#CF8B0B", "#9D9F20", "#2BB077", "#2BB077",
"#1BB3B7", "#29A4DE", "#8989C1", "#B174AD",
"#DE66A1")) +
guides(color = "none") +
theme(
panel.grid=element_blank(),
panel.spacing.x = unit(0, units = "cm"),
strip.background = element_rect(
color = "white", fill = "white",
linetype = "solid", size = 1),
strip.placement = "outside",
axis.line.y.left = element_line(color = "black", size = 0.7),
axis.line.x.bottom = element_line(color = "black", size = 0.7),
strip.text.x = element_text(size = 14, face = "bold"),
axis.text = element_text(face = "bold",
size = 12, color = "black"),
axis.title = element_text(face = "bold",
size = 14, color = "black"),
legend.title = element_text(face = "bold",
size = 12, color = "black"),
legend.text = element_text(face = "bold", size = 12, color = "black"),
axis.ticks.x = element_line(size = 1),
axis.ticks.y = element_line(size = 1),
) +
labs(x = "Depth",y= "Relative Abundance of Phylum (%)")
The data includes the following indicators: 2 (left and right) numerical variables, 2 categorical variables.
Before visualizing, we need to first think about the elements in the picture and what they are composed of.
- Calculate the mean and standard deviation for each group or treatment;
Calculate mean and standard deviation
cData_summary <- cData %>%
group_by(Weeks, Type) %>%
summarize(
avg_lfValue = mean(lfValue),
sd_lfValue = sd(lfValue),
avg_rgValue = mean(rgValue),
sd_rgValue = sd(rgValue),
)
cData_summary
# Weeks Type avg_lfValue sd_lfValue avg_rgValue sd_rgValue
# <dbl> <chr> <dbl> <dbl> <dbl> <dbl>
# 1 20 By week of onset 2623. 25.2 1.98 0.0764
# 2 20 By week of testing 2500 50 1.42 0.104
# 3 21 By week of onset 3543. 40.4 1.74 0.0361
# 4 21 By week of testing 2737. 51.3 1.21 0.0361
# 5 22 By week of onset 2770 26.5 1.28 0.0300
# 6 22 By week of testing 2160 60 1.10 0.0839
# 7 23 By week of onset 2143. 40.4 1.31 0.0208
# 8 23 By week of testing 1777. 75.1 1.02 0.0153
# 9 24 By week of onset 1823. 25.2 1.15 0.0300
# 10 24 By week of testing 1667. 61.1 1.07 0.0265
# 11 25 By week of onset 1690 36.1 1.23 0.0208
# 12 25 By week of testing 1610 36.1 1.2 0.0300
# 13 26 By week of onset 1607. 30.6 1.18 0.0252
# 14 26 By week of testing 1673. 30.6 1.16 0.0361
Visualization process
ggplot() +
geom_bar(
data = cData_summary %>%
mutate(Type = factor(Type, levels = c("By week of testing","By week of onset"))),
aes(x = Weeks, y = avg_lfValue, fill = Type),
alpha = 0.5, stat = "identity", position = position_dodge(0.75), width = 0.75
) +
geom_errorbar(
data = cData_summary %>%
mutate(Type = factor(Type, levels = c("By week of testing","By week of onset"))),
aes(x = Weeks, y = avg_lfValue,
ymin = avg_lfValue - sd_lfValue, ymax = avg_lfValue + sd_lfValue,
group = Type), color = "black",
position = position_dodge(0.75), width = 0.2
) +
geom_line(
data = cData_summary %>%
mutate(Type = factor(Type, levels = c("By week of testing","By week of onset"))),
aes(x = Weeks, avg_rgValue*1950, group = Type, color = Type),
position = position_dodge(0.75), linewidth = 0.8
) +
geom_point(
data = cData_summary %>%
mutate(Type = factor(Type, levels = c("By week of testing","By week of onset"))),
aes(x = Weeks, y = avg_rgValue*1950, color = Type),
position = position_dodge(0.75), size = 2.5
) +
scale_x_continuous(
breaks = seq(20, 26, 1)
) +
scale_y_continuous(name = c("Number of laboratory-confirmed\\
sympotomatic cases"),
sec.axis = sec_axis(~ ./1950,
name = c("Test positivity rate (%)"),
breaks = seq(0, 2, 1)),
limits = c(0, 4000),
breaks = seq(0, 4000, 500),
expand = c(0, 0)) +
scale_color_manual(
values = c("#FE8F3C", "#1E899A")
) +
scale_fill_manual(
values = c("#FE8F3C", "#1E899A")
) +
theme_bw() +
theme(
legend.position = c(0.9, 0.9),
legend.background = element_blank(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
axis.text.x.bottom = element_text(color = "black", size = 12),
axis.text.y.left = element_text(color = "black", size = 12),
axis.text.y.right = element_text(color = "#44909A", size = 12),
axis.title.y.right = element_text(color = "#44909A", size = 12, angle = 90),
axis.line.y.right = element_line(color = "#44909A"),
axis.ticks.y.right = element_line(color = "#44909A"),
axis.title = element_text(color = "black", size = 12)
) +
labs(
x = "Week",
color = "",
fill = ""
)
The reproduction effect is relatively perfect. For details, you can refer to the code in the article. If you have any questions, you can leave a message for discussion~