add one legend with all variables for combined graphs

Question

I'm trying to plot two graphs side-by-side with one common legend that incorporates all the variables between both graphs (some vars are different between the graphs).

Here's a mock example of what I've been attempting:

#make relative abundance values for n rows
  makeData <- function(n){
  n <- n
  x <- runif(n, 0, 1)
  y <- x / sum(x)
}

#make random matrices filled with relative abundance values
makeDF <- function(col, rw){
  df <- matrix(ncol=col, nrow=rw)
  for(i in 1:ncol(df)){
    df[,i] <- makeData(nrow(df))
  }
  return(df)
}

#create df1 and assign col names
df1 <- makeDF(4, 5)
colSums(df1) #verify relative abundance values = 1
df1 <- as.data.frame(df1)
colnames(df1) <- c("taxa","s1", "s2", "s3")
df1$taxa <- c("ASV1", "ASV2", "ASV3", "ASV4", "ASV5")

#repeat for df2
df2 <- makeDF(4,5)
df2 <- as.data.frame(df2)
colnames(df2) <- c("taxa","s1", "s2", "s3")
df2$taxa <- c("ASV1", "ASV5", "ASV6", "ASV7", "ASV8")

# convert wide data format to long format -- for plotting
library(reshape2)
makeLong <- function(df){
  df.long <- melt(df, id.vars="taxa",
                  measure.vars=grep("s\\d+", names(df), val=T),
                  variable.name="sample",
                  value.name="value")
  return(df.long)
}
df1 <- makeLong(df1)
df2 <- makeLong(df2)

#generate distinct colours for each asv
taxas <- union(df1$taxa, df2$taxa)
library("RColorBrewer")
qual_col_pals = brewer.pal.info[brewer.pal.info$category == 'qual',]
colpals <- qual_col_pals[c("Set1", "Dark2", "Set3"),] #select colour palettes
col_vector = unlist(mapply(brewer.pal, colpals$maxcolors, rownames(colpals)))
taxa.col=sample(col_vector, length(taxas))
names(taxa.col) <- taxas

# plot using ggplot
library(ggplot2)
plotdf2 <- ggplot(df2, aes(x=sample, y=value, fill=taxa)) + 
  geom_bar(stat="identity")+
  scale_fill_manual("ASV", values = taxa.col)

plotdf1 <- ggplot(df1, aes(x=sample, y=value, fill=taxa)) + 
  geom_bar(stat="identity")+
  scale_fill_manual("ASV", values = taxa.col)

#combine plots to one figure and merge legend
library(ggpubr)
ggpubr::ggarrange(plotdf1, plotdf2, ncol=2, nrow=1, common.legend = T, legend="bottom")

(if you have suggestions on how to generate better mock data, by all means!)

When I run my code, I am able to get the two graphs in one figure, but the legend does not incorporate all variables from both plots:

I ideally would like to avoid having repeat variables in the legend, such as:

From what I've searched online, the legend only works when the variables are the same between graphs, but in my case I have similar and different variables.

Thanks for any help!

Answer 1

Maybe this is what you are looking for:

1. Convert your taxa variables to factor with the levels equal to your taxas variable, i.e. to include all levels from both datasets.

2. Add argument drop=FALSE to both scale_fill_manual to prevent dropping of unused factor levels.

Note: I only added the relevant parts of the code and set the seed to 42 at the beginning of the script.

set.seed(42)

df1$taxa <- factor(df1$taxa, taxas)
df2$taxa <- factor(df2$taxa, taxas)

# plot using ggplot
library(ggplot2)
plotdf2 <- ggplot(df2, aes(x=sample, y=value, fill=taxa)) + 
  geom_bar(stat="identity") +
  scale_fill_manual("ASV", values = taxa.col, drop = FALSE)

plotdf1 <- ggplot(df1, aes(x=sample, y=value, fill=taxa)) + 
  geom_bar(stat="identity")+
  scale_fill_manual("ASV", values = taxa.col, drop = FALSE)

#combine plots to one figure and merge legend
library(ggpubr)
ggpubr::ggarrange(plotdf1, plotdf2, ncol=2, nrow=1, common.legend = T, legend="bottom")