R ggplot- na.rm is not removing the record

Question

I am not sure why "na.rm=TRUE" in ggplot() and geom_col() don't remove the missing. Here is the input file (file name in the code is dat.csv ):

br,tr,obs,ee,dd
UU,RRR,228,0.38895,0.33691
BB,RRR,591,0.37254,0.40899
GG,RRR,702,0.36163,0.38155
UU,AAA,229,0.31594,0.32768
BB,AAA,591,0.18185,0.23339
GG,AAA,702,0.37287,0.40218
UU,BBB,228,0.16561,0.32313
BB,BBB,591,0.22578,0.41145
GG,BBB,702,0.28103,0.46357
UU,LLL,1,.,.
UU,TTT,107,-0.01136,0.2265
BB,TTT,33,-0.34362,0.07749
GG,TTT,54,0.00905,-0.07037

Here is the code

library("data.table")
library(conflicted)
library(tidyverse)
library(ggplot2)

ee <- fread("dat.csv", select = c("br","tr","obs","ee"))
ee_r <- data.frame(a = 1:nrow(ee), Method = "OLD")
ee <- cbind(rename(ee, Acc = ee), ee_r)

dd <- fread("dat.csv", select = c("br","tr","obs","dd"))
dd_r <- data.frame(a = 1:nrow(dd), Method = "NEW")
dd <- cbind(rename(dd, Acc = dd), dd_r)

dat <- rbind(ee,dd)
dat <- subset(dat, select = -c(a))

dat$Acc[dat$Acc=="."] <- NA

br_nbs <- paste(dat$br, dat$obs, sep = "\n")
br_nbs

#data <- subset(dat, !is.na(Acc)) This command gives me error

ggplot(dat, aes(x = br_nbs, y = Acc, fill = Method), na.rm=TRUE)+
  geom_col(colour="black",width=1, position=position_dodge(0.7), na.rm=TRUE) +
  facet_wrap(~tr, strip.position = "top", labeller = "label_value", scales = "free_x")

And here is the plot with NAs in the red box:

I appreciate any comments.

Thanks.

Answer 1

Like @r2evans, I am unsure what your input data actually is. I think it might be this:

dput(dat)
structure(list(br = c("UU", "BB", "GG", "UU", "BB", "GG", "UU", 
"BB", "GG", "UU", "UU", "BB", "GG", "UU", "BB", "GG", "UU", "BB", 
"GG", "UU", "BB", "GG", "UU", "UU", "BB", "GG"), tr = c("RRR", 
"RRR", "RRR", "AAA", "AAA", "AAA", "BBB", "BBB", "BBB", "LLL", 
"TTT", "TTT", "TTT", "RRR", "RRR", "RRR", "AAA", "AAA", "AAA", 
"BBB", "BBB", "BBB", "LLL", "TTT", "TTT", "TTT"), obs = c(228L, 
591L, 702L, 229L, 591L, 702L, 228L, 591L, 702L, 1L, 107L, 33L, 
54L, 228L, 591L, 702L, 229L, 591L, 702L, 228L, 591L, 702L, 1L, 
107L, 33L, 54L), Acc = c("0.38895", "0.37254", "0.36163", "0.31594", 
"0.18185", "0.37287", "0.16561", "0.22578", "0.28103", ".", "-0.01136", 
"-0.34362", "0.00905", "0.33691", "0.40899", "0.38155", "0.32768", 
"0.23339", "0.40218", "0.32313", "0.41145", "0.46357", ".", "0.2265", 
"0.07749", "-0.07037"), Method = c("OLD", "OLD", "OLD", "OLD", 
"OLD", "OLD", "OLD", "OLD", "OLD", "OLD", "OLD", "OLD", "OLD", 
"NEW", "NEW", "NEW", "NEW", "NEW", "NEW", "NEW", "NEW", "NEW", 
"NEW", "NEW", "NEW", "NEW")), row.names = c(NA, 26L), class = "data.frame")

Now, finish off your data wranging and, critically, add br_nbs to the data frame.

dat$br_nbs <- paste(dat$br, dat$obs, sep = "\n")
dat$Acc[dat$Acc=="."] <- NA

And plot the data, with minor modifications to your code.

ggplot(dat %>% filter(!is.na(Acc)), aes(x = br_nbs, y = Acc, fill = Method))+
  geom_col(colour="black",width=1, position=position_dodge(0.7)) +
  facet_wrap(~tr, strip.position = "top", labeller = "label_value", scales = "free_x")

Giving