Box plot with significance notation (*)
cly
2022-08-05
Prepare required packages:
# if(!require(readr)) install.packages("readr")
# if(!require(dplyr)) install.packages("dplyr") #data_frame, %>%, filter, summarise, group_by
# if(!require(emmeans)) install.packages("emmeans") #package to run follow-up comparisons
# if(!require(phia)) install.packages("phia") #testInteractions
# if(!require(tidyr)) install.packages("tidyr") #spread
# if(!require(ARTool)) install.packages("ARTool") #art, artlm
# if(!require(ggplot2)) install.packages("ggplot2") #ggplot, stat_…, geom_…, etc
# if(!require(ggsignif)) install.packages("ggsignif")
# if(!require(tidyverse)) install.packages("tidyverse") # tidyverse for data manipulation and visualization
# if(!require(ggpubr)) install.packages("ggpubr") # ggpubr for creating easily publication ready plots
# if(!require(rstatix)) install.packages("rstatix") # rstatix provides pipe-friendly R functions for easy statistical analyses
# if(!require(lmerTest)) install.packages("lmerTest")
# if(!require(afex)) install.packages("afex") #package to run ANOVAs
# if(!require(plotly)) install.packages("plotly") #creating subplotlibrary(readr)
library(dplyr) #data_frame, %>%, filter, summarise, group_by
library(emmeans) #package to run follow-up comparisons
library(phia) #testInteractions
library(tidyr) #spread
library(ARTool) #art, artlm
library(ggplot2) #ggplot, stat_…, geom_…, etc
library(ggsignif)
library(tidyverse) # tidyverse for data manipulation and visualization
library(ggpubr) # ggpubr for creating easily publication ready plots
library(rstatix) # rstatix provides pipe-friendly R functions for easy statistical analyses
library(lmerTest)
library(afex) #package to run ANOVAs
library(plotly) #creating subplotCreate a pseudo dataset
#== create a dummy dataset as an example
mydata <- data.frame(score = c(45 ,85, 66, 78, 92, 94, 91, 85, 62, 60,
40, 56, 70, 80, 90, 88, 95, 90, 45, 55,
84, 88, 88, 90, 92, 93, 91, 85, 80, 73,
97, 100, 93, 91, 90, 87, 94, 83, 92, 93,
45 ,85, 66, 78, 92, 94, 91, 85, 62, 60,
97, 100, 93, 91, 90, 87, 94, 83, 92, 93),
frequency = c(1 ,2, 3, 1, 2, 4, 1, 5, 2, 6,
1 ,2, 3, 1, 2, 4, 1, 5, 2, 6,
8, 8, 8, 9, 9, 9, 9, 8, 8, 7,
9, 10, 9, 9, 9, 7, 9, 8, 9, 9,
4, 6, 7, 8, 9, 8, 9, 9, 5, 5,
5 ,5, 6, 7, 2, 4, 1, 5, 2, 6),
condition = c(rep('condition1', 20), rep('condition2', 20), rep('condition3', 20)),
version = c(rep('versionA', 30), rep('versionB', 30)))Plot boxplots with the annotation of significant difference
Customize color, font size, box width, outlier size, add mean on boxplot
Add stat significance notation
Customize font size, color, position, comparison test in geom_signif
Check more details about geom_signif here: https://rdrr.io/cran/ggsignif/man/stat_signif.html
Figure 1
### Boxplot ###
score_fig <- ggplot(mydata, aes(x=condition, y=score, fill=condition)) +
geom_boxplot(width=0.3, outlier.size=0.5) + #change width of the box and line
stat_summary(fun = mean, geom = "point", col = "black", shape=17) + # Add points to plot
stat_summary(fun = mean, geom = "text", col = "black", size = 2.7, # Add text to plot
vjust = 3, aes(label = paste("M:", round(..y.., digits = 2)))) +
#xlab("Conditions")+
theme(axis.text.x = element_text(angle = 0, vjust = 0.5, size=8))+
ylab("Score")+
#ylim(1, 7)+
ggtitle("Fig title here")+
theme(legend.position="top", plot.title = element_text(hjust = 0.5, size=10)) +
#scale_fill_brewer(palette="Dark2")+
scale_fill_manual(values=c("#6fa8dc", "#f1c232", "#bcbcbc"))+
# add sig notation
geom_signif(comparisons=list(c("condition1", "condition2")),
test = "wilcox.test",
na.rm = FALSE,
map_signif_level = TRUE,
col = "#5b5b5b",
size = 0.4, #change line size
y_position = 100)+
geom_signif(comparisons=list(c("condition2", "condition3")),
test = "wilcox.test",
na.rm = FALSE,
map_signif_level = TRUE,
col = "#5b5b5b",
textsize = 3, # adjust font size of NS
size = 0.4, #change line size
y_position = 98)+
geom_signif(comparisons=list(c("condition1","condition3")),
test = "wilcox.test",
na.rm = FALSE,
map_signif_level = TRUE,
col = "#5b5b5b",
size = 0.4, #change line size
y_position = 103)
score_fig 
#ggsave(filename="myFig.pdf", plot=score_fig)Figure 2
### Boxplot ###
frequency_fig <- ggplot(mydata, aes(x=version, y=frequency, color=version)) + #change the color of the border
geom_boxplot(width=0.3, outlier.size=0.5) + #change width of the box and line
stat_summary(fun = mean, geom = "point", col = "black", shape=17) + # Add points to plot
stat_summary(fun = mean, geom = "text", col = "black", size = 2.7, # Add text to plot
vjust = 3, aes(label = paste("M:", round(..y.., digits = 2)))) +
#xlab("Conditions")+
theme(axis.text.x = element_text(angle = 0, vjust = 0.5, size=8))+
ylab("Frequency")+
#ylim(1, 7)+
ggtitle("Fig title here")+
theme(legend.position="top", plot.title = element_text(hjust = 0.5, size=10)) +
#scale_fill_brewer(palette="Dark2")+
scale_color_manual(values=c("#6fa8dc", "#f1c232", "#bcbcbc"))+
# add sig notation
geom_signif(comparisons=list(c("versionA", "versionB")),
test = "wilcox.test",
na.rm = FALSE,
map_signif_level = TRUE,
col = "black",
size = 0.4, #change line size
y_position = 10)
frequency_fig 
Combine Fig1 and Fig2 together
Combine multiple plots into one plot
Export the figure as PDF, PNG, etc.
figure <- ggarrange(score_fig, frequency_fig,
labels = c("A", "B"),
ncol = 2, nrow = 2,
common.legend = TRUE, legend = "top",
align = "hv",
font.label = list(size = 10, color = "black", face = "bold", family = NULL, position = "top"))
figure
#ggexport(figure, filename = "myplot.pdf")