rm(list=ls())

# working directory
setwd("/home/hychang/R_pwd/2026-09-14_R-plots/Box_plots/")

# load packages
library(readxl)
library(ggplot2)

### Step 1. import data, choose one of them to import file
# (1) fill in full path of your file and the sheet name
df1= read_xlsx("/home/hychang/R_pwd/2026-09-14_R-plots/Box_plots/sample1.xlsx", sheet = "Sheet1")

# (2) If you don't know the full path, use file.choose to select your file, 
#     remember fill in the sheet name
df1= read_xlsx(file.choose(), sheet = "Sheet1")


### Step 2. import the multiple comparison result (optional)

df2= read_xlsx("/home/hychang/R_pwd/2026-09-14_R-plots/Box_plots/sample1.xlsx", sheet = "Sheet2")


### Step 3. Inspect data

# dimension
df1; dim(df1)
df2; dim(df2)

# counts of strain
table(df1$"Strain")
table(df1$"Strain", useNA = "always")

# range of value
range(df1$"Value")


### Step 4. setting sample order

# set your ordering in levels
df1$"Strain" = factor(df1$"Strain",
                      levels = c("A", "B", "C"))


### Step 5. plot

# version 1
# all data points using a single, uniform color.
p1= ggplot(data = df1, aes(x= Strain, y= Value))+
  geom_boxplot(width = 0.4, outlier.shape = NA)+
  geom_point(color= "#003175", size= 2,
             position = position_jitter(width = 0.2,height = 0))+
  scale_y_continuous(limits = c(0, NA))+
  labs(x= "Strain", y= "Value")+
  theme_classic()+
  theme(axis.title = element_text(size = 16),
        axis.text = element_text(size = 14))

# show plot
p1


# version 2
# Colors data points by Strain and adds statistical significance group labels at the top.
p2= ggplot(data = df1, aes(x= Strain, y= Value))+
  geom_boxplot(width = 0.4, outlier.shape = NA)+
  geom_point(aes(color= Strain), size = 2,
             position = position_jitter(width = 0.2,height = 0))+
  geom_text(data = df2, aes(x= Strain, y= Inf, label = groups), vjust= "inward")+
  scale_color_manual(values = c("#1B9E77", "#D95F02", "#7570B3"))+
  scale_y_continuous(limits = c(0, NA))+
  labs(x= "Strain", y= "Value")+
  theme_classic()+
  theme(axis.title = element_text(size = 16),
        axis.text = element_text(size = 14))

# show plot
p2


### Step 6. Export

# version 1 PDF export
pdf("simple_boxplot1.pdf")
p1
dev.off()

# version 2 PDF export
pdf("/home/hychang/R_pwd/2026-09-14_R-plots/Box_plots/simple_boxplot2.pdf")
p2
dev.off()

# change the width and height to 6 and 4 in inch
pdf("simple_boxplot1_w6h4.pdf", width = 6, height = 4)
p1
dev.off()

pdf("simple_boxplot2_w6h4.pdf", width = 6, height = 4)
p2
dev.off()


# version 1 PNG export
png("simple_boxplot1.png")
p1
dev.off()

# version 2 PNG export
png("simple_boxplot2.png")
p2
dev.off()

# change width and height to 600 and 400 in pixels
png("simple_boxplot1_w600h400.png", width = 600, height = 400)
p1
dev.off()

png("simple_boxplot2_w600h400.png", width = 600, height = 400)
p2
dev.off()