How to add text annotation over each boxplot of grouped data in facet_grids in ggplot2

tidyverse
,
1

I tried adding annotations over individual boxplots created using following data and code.

> dput(pans)
structure(list(trt = c("SP", "SP", "SP", "SP", "SP", "SP", "SP", 
"OF", "OF", "OF", "OF", "OF", "OF", "OF", "CF", "CF", "CF", "CF", 
"CF", "CF", "CF", "SP", "SP", "SP", "SP", "SP", "SP", "SP", "OF", 
"OF", "OF", "OF", "OF", "OF", "OF", "CF", "CF", "CF", "CF", "CF", 
"CF", "CF", "SP", "SP", "SP", "SP", "SP", "SP", "SP", "OF", "OF", 
"OF", "OF", "OF", "OF", "OF", "CF", "CF", "CF", "CF", "CF", "CF", 
"CF", "SP", "SP", "SP", "SP", "SP", "SP", "SP", "OF", "OF", "OF", 
"OF", "OF", "OF", "OF", "CF", "CF", "CF", "CF", "CF", "CF", "CF"
), rep = c(1, 2, 3, 4, 5, 6, 7, 1, 2, 3, 4, 5, 6, 7, 1, 2, 3, 
4, 5, 6, 7, 1, 2, 3, 4, 5, 6, 7, 1, 2, 3, 4, 5, 6, 7, 1, 2, 3, 
4, 5, 6, 7, 1, 2, 3, 4, 5, 6, 7, 1, 2, 3, 4, 5, 6, 7, 1, 2, 3, 
4, 5, 6, 7, 1, 2, 3, 4, 5, 6, 7, 1, 2, 3, 4, 5, 6, 7, 1, 2, 3, 
4, 5, 6, 7), yr = c(2018, 2018, 2018, 2018, 2018, 2018, 2018, 
2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 
2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 
2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 
2018, 2018, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 
2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 
2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 
2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019
), st = c("b", "b", "b", "b", "b", "b", "b", "b", "b", "b", "b", 
"b", "b", "b", "b", "b", "b", "b", "b", "b", "b", "h", "h", "h", 
"h", "h", "h", "h", "h", "h", "h", "h", "h", "h", "h", "h", "h", 
"h", "h", "h", "h", "h", "b", "b", "b", "b", "b", "b", "b", "b", 
"b", "b", "b", "b", "b", "b", "b", "b", "b", "b", "b", "b", "b", 
"h", "h", "h", "h", "h", "h", "h", "h", "h", "h", "h", "h", "h", 
"h", "h", "h", "h", "h", "h", "h", "h"), act = c(39, 41, 45, 
36, 33, 40, 41, 31, 28, 32, 36, 41, 30, 34, 30, 34, 25, 28, 27, 
32, 27, 49, 42, 41, 48, 36, 46, 45, 33, 39, 41, 36, 32, 36, 39, 
32, 33, 26, 27, 30, 31, 27, 43, 48, 42, 45, 41, 46, 44, 35, 31, 
33, 29, 36, 33, 31, 25, 35, 24, 27, 28, 30, 26, 45, 50, 52, 47, 
48, 50, 48, 31, 37, 33, 38, 35, 34, 36, 32, 28, 34, 26, 23, 30, 
30)), class = c("spec_tbl_df", "tbl_df", "tbl", "data.frame"), row.names = c(NA, 
-84L), spec = structure(list(cols = list(trt = structure(list(), class = c("collector_character", 
"collector")), rep = structure(list(), class = c("collector_double", 
"collector")), yr = structure(list(), class = c("collector_double", 
"collector")), st = structure(list(), class = c("collector_character", 
"collector")), act = structure(list(), class = c("collector_double", 
"collector"))), default = structure(list(), class = c("collector_guess", 
"collector")), skip = 1), class = "col_spec"))

rep <- factor(pans$rep)
trt <- factor(pans$trt)
yr <- factor(pans$yr)
st <- factor(pans$st)
p <- ggplot(pans, aes(x = st, y = act))
q<-p + geom_boxplot(aes(fill = trt), position = position_dodge(0.8)) + 
  stat_summary(fun = mean, geom = "point", shape=5, size=1.5,
               aes(group = trt), position = position_dodge(0.8)) +
  scale_fill_manual(name="System", values = c("grey50","grey90", "grey100")) + 
  facet_grid(. ~ yr)+
  theme_bw()
plot<-q + scale_x_discrete(breaks=c("b","h"), labels=c("BS", "AH"))
plot2<-plot + theme(axis.title.x = element_blank())
plot2

The plotted chart is given below
pans

Then I tried adding annotation using geom_text using code

pans2 = distinct(pans, yr, st, trt) %>%
  arrange(yr, st, trt)
pans2$yloc = max(pans$act) + .05
pans2$label = c("a", "b", "a", "b", "b", "b", "a", "b", "a", "b", "b", "b")
plot2 + geom_text(data = pans2, aes(y = yloc, label = label), 
          position = position_dodge(width = .75))

However, I am getting the following error:
Don't know how to automatically pick scale for object of type function. Defaulting to continuous. Error: Aesthetics must be valid data columns. Problematic aesthetic(s): label = label. Did you mistype the name of a data column or forget to add after_stat()? Run rlang::last_error() to see where the error occurred.

Kindly help me in creating a graph with text annotations over each boxplot

thanks

2

Your code works for me. The original code did not place the labels in the last plot correctly because there is no aesthetic in geom_text for dodge to work with. I added color just to get it to work. Iam sure you will want to modify that.

pans <- structure(list(trt = c("SP", "SP", "SP", "SP", "SP", "SP", "SP", 
                       "OF", "OF", "OF", "OF", "OF", "OF", "OF", "CF", "CF", "CF", "CF", 
                       "CF", "CF", "CF", "SP", "SP", "SP", "SP", "SP", "SP", "SP", "OF", 
                       "OF", "OF", "OF", "OF", "OF", "OF", "CF", "CF", "CF", "CF", "CF", 
                       "CF", "CF", "SP", "SP", "SP", "SP", "SP", "SP", "SP", "OF", "OF", 
                       "OF", "OF", "OF", "OF", "OF", "CF", "CF", "CF", "CF", "CF", "CF", 
                       "CF", "SP", "SP", "SP", "SP", "SP", "SP", "SP", "OF", "OF", "OF", 
                       "OF", "OF", "OF", "OF", "CF", "CF", "CF", "CF", "CF", "CF", "CF"
), rep = c(1, 2, 3, 4, 5, 6, 7, 1, 2, 3, 4, 5, 6, 7, 1, 2, 3, 
           4, 5, 6, 7, 1, 2, 3, 4, 5, 6, 7, 1, 2, 3, 4, 5, 6, 7, 1, 2, 3, 
           4, 5, 6, 7, 1, 2, 3, 4, 5, 6, 7, 1, 2, 3, 4, 5, 6, 7, 1, 2, 3, 
           4, 5, 6, 7, 1, 2, 3, 4, 5, 6, 7, 1, 2, 3, 4, 5, 6, 7, 1, 2, 3, 
           4, 5, 6, 7), yr = c(2018, 2018, 2018, 2018, 2018, 2018, 2018, 
                               2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 
                               2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 
                               2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 2018, 
                               2018, 2018, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 
                               2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 
                               2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 
                               2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019
           ), st = c("b", "b", "b", "b", "b", "b", "b", "b", "b", "b", "b", 
                     "b", "b", "b", "b", "b", "b", "b", "b", "b", "b", "h", "h", "h", 
                     "h", "h", "h", "h", "h", "h", "h", "h", "h", "h", "h", "h", "h", 
                     "h", "h", "h", "h", "h", "b", "b", "b", "b", "b", "b", "b", "b", 
                     "b", "b", "b", "b", "b", "b", "b", "b", "b", "b", "b", "b", "b", 
                     "h", "h", "h", "h", "h", "h", "h", "h", "h", "h", "h", "h", "h", 
                     "h", "h", "h", "h", "h", "h", "h", "h"), act = c(39, 41, 45, 
                                                                      36, 33, 40, 41, 31, 28, 32, 36, 41, 30, 34, 30, 34, 25, 28, 27, 
                                                                      32, 27, 49, 42, 41, 48, 36, 46, 45, 33, 39, 41, 36, 32, 36, 39, 
                                                                      32, 33, 26, 27, 30, 31, 27, 43, 48, 42, 45, 41, 46, 44, 35, 31, 
                                                                      33, 29, 36, 33, 31, 25, 35, 24, 27, 28, 30, 26, 45, 50, 52, 47, 
                                                                      48, 50, 48, 31, 37, 33, 38, 35, 34, 36, 32, 28, 34, 26, 23, 30, 
                                                                      30)), class = c("spec_tbl_df", "tbl_df", "tbl", "data.frame"), row.names = c(NA, 
                                                                                                                                                   -84L), spec = structure(list(cols = list(trt = structure(list(), class = c("collector_character", 
                                                                                                                                                                                                                              "collector")), rep = structure(list(), class = c("collector_double", 
                                                                                                                                                                                                                                                                               "collector")), yr = structure(list(), class = c("collector_double", 
                                                                                                                                                                                                                                                                                                                               "collector")), st = structure(list(), class = c("collector_character", 
                                                                                                                                                                                                                                                                                                                                                                               "collector")), act = structure(list(), class = c("collector_double", 
                                                                                                                                                                                                                                                                                                                                                                                                                                "collector"))), default = structure(list(), class = c("collector_guess", 
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      "collector")), skip = 1), class = "col_spec"))

library(ggplot2)
library(dplyr)
#> 
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#> 
#>     filter, lag
#> The following objects are masked from 'package:base':
#> 
#>     intersect, setdiff, setequal, union
rep <- factor(pans$rep)
trt <- factor(pans$trt)
yr <- factor(pans$yr)
st <- factor(pans$st)
p <- ggplot(pans, aes(x = st, y = act))
q<-p + geom_boxplot(aes(fill = trt), position = position_dodge(0.8)) + 
  stat_summary(fun = mean, geom = "point", shape=5, size=1.5,
               aes(group = trt), position = position_dodge(0.8)) +
  scale_fill_manual(name="System", values = c("grey50","grey90", "grey100")) + 
  facet_grid(. ~ yr)+
  theme_bw()
plot<-q + scale_x_discrete(breaks=c("b","h"), labels=c("BS", "AH"))
plot2<-plot + theme(axis.title.x = element_blank())
plot2


pans2 = distinct(pans, yr, st, trt) %>%
  arrange(yr, st, trt)
pans2$yloc = max(pans$act) + .05
pans2$label = c("a", "b", "a", "b", "b", "b", "a", "b", "a", "b", "b", "b")
plot2 + geom_text(data = pans2, aes(y = yloc, label = label,color=trt), 
                  position = position_dodge(width = .75))

Created on 2021-01-23 by the reprex package (v0.3.0)

1 Like
3

Thanks FJCC for the solution.
Is there a way out to position the labels just near to the boxplots as in the image below
pans copy

4

This is not perfect but I hope it shows you one possible approach. I hand calculated the position of the whisker of each box plot and use that to place the y position of the labels.

plot<-q + scale_x_discrete(breaks=c("b","h"), labels=c("BS", "AH"))
plot2<-plot + theme(axis.title.x = element_blank())
plot2

STATS = pans %>% group_by(yr,st, trt) %>% 
  summarize(Q75 = quantile(act, probs = 0.75),
            Q25 = quantile(act, probs = 0.25),
            MaxVal = max(act), .groups = "keep") %>% 
  mutate(WhiskUp = 1.05* (Q75 + 1.5 * (Q75 - Q25)))

pans2 = distinct(pans, yr, st, trt) %>%
  arrange(yr, st, trt) %>% 
  inner_join(STATS, by = c("yr", "st", "trt"))

#pans2$yloc = max(pans$act) + .05
pans2$label = c("a", "b", "a", "b", "b", "b", "a", "b", "a", "b", "b", "b")
plot2 + geom_text(data = pans2, aes(y = WhiskUp, label = label,color=trt), 
                  position = position_dodge(width = .75))
1 Like
5

Thanks a lot. It'll surely help.

6

This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.