Add a line from different result to boxplot graph in ggplot2

Question

I have a dataframe (df1) that contains 3 columns (y1, y2, x). I managed to plot a boxplot graph between y1, x and y2, x. I have another dataframe (df2) which contains two columns A, x. I want to plot a line graph (A,x) and add it to the boxplot. Note the variable x in both dataframes is the axis access, however, it has different values. I tried to combine and reshape both dataframes and plot based on the factor(x)... I got 3 boxplots in one graph. I need to plot df2 as line and df1 as boxplot in one graph.

df1 <- structure(list(Y1 = c(905L, 941L, 744L, 590L, 533L, 345L, 202L, 
369L, 200L, 80L, 200L, 80L, 50L, 30L, 60L, 20L, 30L, 30L), Y2 = c(774L, 
823L, 687L, 545L, 423L, 375L, 249L, 134L, 45L, 58L, 160L, 60L, 
20L, 40L, 20L, 26L, 19L, 27L), x = c(10L, 10L, 10L, 20L, 20L, 
20L, 40L, 40L, 40L, 50L, 50L, 50L, 70L, 70L, 70L, 90L, 90L, 90L
 )), .Names = c("Y1", "Y2", "x"), row.names = c(NA, -18L), class = "data.frame")

df2 <- structure(list(Y3Line = c(384L, 717L, 914L, 359L, 241L, 265L, 
240L, 174L, 114L, 165L, 184L, 96L, 59L, 60L, 127L, 54L, 31L, 
44L), x = c(36L, 36L, 36L, 56L, 56L, 56L, 65L, 65L, 65L, 75L, 
75L, 75L, 85L, 85L, 85L, 99L, 99L, 99L)), .Names = c("A", 
"x"), row.names = c(NA, -18L), class = "data.frame")

df_l <- melt(df1, id.vars = "x")

ggplot(df_l, aes(x = factor(x), y =value, fill=variable  )) +
geom_boxplot()+
#  here I'trying to add the line graph from df2
geom_line(data = df2, aes(x = x, y=A))

Any suggestions?

Answer 1

In the second dataset you have three y values per x value, do you want to draw seperate lines per x value or the mean per x value? Both are shown below. The trick is to first change the x variables in both datasets to factors that contain all the levels of both variables.

df1 <-structure(list(Y1 = c(905L, 941L, 744L, 590L, 533L, 345L, 202L, 
369L, 200L, 80L, 200L, 80L, 50L, 30L, 60L, 20L, 30L, 30L), Y2 = c(774L, 
823L, 687L, 545L, 423L, 375L, 249L, 134L, 45L, 58L, 160L, 60L, 
20L, 40L, 20L, 26L, 19L, 27L), x = c(10L, 10L, 10L, 20L, 20L, 
20L, 40L, 40L, 40L, 50L, 50L, 50L, 70L, 70L, 70L, 90L, 90L, 90L
)), .Names = c("Y1", "Y2", "x"), row.names = c(NA, -18L), class = "data.frame")

df2 <- structure(list(Y3Line = c(384L, 717L, 914L, 359L, 241L, 265L, 
240L, 174L, 114L, 165L, 184L, 96L, 59L, 60L, 127L, 54L, 31L, 
44L), x = c(36L, 36L, 36L, 56L, 56L, 56L, 65L, 65L, 65L, 75L, 
75L, 75L, 85L, 85L, 85L, 99L, 99L, 99L)), .Names = c("A", 
"x"), row.names = c(NA, -18L), class = "data.frame")

library(ggplot2)
library(reshape2)

df_l <- melt(df1, id.vars = "x")

allLevels <- levels(factor(c(df_l$x,df2$x)))
df_l$x <- factor(df_l$x,levels=(allLevels))
df2$x <- factor(df2$x,levels=(allLevels))

Line per x category:

ggplot(data=df_l,aes(x = x, y =value))+geom_line(data=df2,aes(x = factor(x), y =A))  + 
geom_boxplot(aes(fill=variable )) 

Connected means of x categories:

ggplot(data=df2,aes(x = factor(x), y =A)) + 
stat_summary(fun.y=mean, geom="line", aes(group=1))  + 
geom_boxplot(data=df_l,aes(x = x, y =value,fill=variable ))