I have a matrix with the following entries:
dput(MilDis[1:200,])
structure(list(hhDomMil = c("HED", "ETB", "HED", "ETB", "PER",
"BUM", "EXP", "TRA", "TRA", "PMA", "MAT", "MAT", "KON", "ETB",
"PMA", "PMA", "HED", "BUM", "BUM", "HED", "PMA", "PMA", "HED",
"TRA", "BUM", "EXP", "BUM", "PMA", "ETB", "MAT", "ETB", "ETB",
"KON", "MAT", "TRA", "BUM", "BUM", "TRA", "TRA", "PMA", "PMA",
"PMA", "MAT", "ETB", "TRA", "BUM", "TRA", "MAT", "BUM", "ETB",
"TRA", "TRA", "BUM", "KON", "ETB", "ETB", "ETB", "BUM", "KON",
"ETB", "ETB", "PMA", "TRA", "PER", "PER", "MAT", "HED", "KON",
"TRA", "TRA", "TRA", "EXP", "TRA", "BUM", "MAT", "MAT", "TRA",
"PMA", "HED", "PER", "TRA", "PER", "EXP", "PER", "BUM", "KON",
"BUM", "ETB", "ETB", "TRA", "PER", "ETB", "KON", "KON", "BUM",
"ETB", "BUM", "MAT", "BUM", "KON", "KON", "ETB", "MAT", "KON",
"PER", "ETB", "ETB", "KON", "PMA", "PER", "HED", "HED", "PMA",
"MAT", "PMA", "PER", "PMA", "TRA", "TRA", "MAT", "BUM", "BUM",
"KON", "ETB", "ETB", "ETB", "PMA", "TRA", "TRA", "PMA", "PER",
"KON", "PER", "BUM", "KON", "ETB", "ETB", "BUM", "TRA", "ETB",
"PMA", "HED", "MAT", "TRA", "BUM", "PMA", "BUM", "ETB", "TRA",
"TRA", "TRA", "PER", "EXP", "HED", "BUM", "EXP", "HED", "BUM",
"MAT", "DDR", "BUM", "MAT", "KON", "HED", "HED", "TRA", "BUM",
"PMA", "PMA", "PMA", "KON", "KON", "MAT", "ETB", "MAT", "TRA",
"MAT", "ETB", "ETB", "TRA", "MAT", "ETB", "TRA", "HED", "BUM",
"MAT", "TRA", "PMA", "BUM", "BUM", "EXP", "ETB", "EXP", "EXP",
"MAT", "TRA", "KON", "BUM", "BUM", "HED"), kclust = c(1L, 2L,
15L, 4L, 5L, 6L, 5L, 7L, 8L, 5L, 6L, 5L, 11L, 6L, 5L, 1L, 9L,
10L, 2L, 1L, 9L, 8L, 4L, 11L, 14L, 5L, 8L, 11L, 12L, 5L, 5L,
14L, 15L, 2L, 10L, 6L, 8L, 4L, 6L, 8L, 14L, 14L, 16L, 10L, 5L,
1L, 12L, 17L, 12L, 16L, 16L, 5L, 10L, 14L, 8L, 19L, 5L, 4L, 4L,
14L, 2L, 14L, 9L, 7L, 1L, 14L, 4L, 15L, 18L, 16L, 9L, 14L, 6L,
14L, 12L, 11L, 4L, 7L, 8L, 12L, 9L, 16L, 2L, 6L, 15L, 1L, 1L,
3L, 14L, 5L, 5L, 9L, 14L, 6L, 5L, 14L, 15L, 2L, 14L, 2L, 1L,
8L, 5L, 10L, 1L, 1L, 16L, 5L, 2L, 9L, 9L, 1L, 12L, 10L, 1L, 4L,
1L, 9L, 8L, 8L, 5L, 10L, 1L, 10L, 2L, 6L, 15L, 2L, 2L, 10L, 5L,
6L, 10L, 19L, 19L, 6L, 5L, 6L, 7L, 7L, 8L, 5L, 16L, 5L, 6L, 6L,
1L, 10L, 12L, 4L, 7L, 19L, 7L, 8L, 16L, 10L, 5L, 16L, 12L, 7L,
7L, 19L, 4L, 6L, 1L, 15L, 7L, 8L, 16L, 4L, 10L, 15L, 11L, 10L,
1L, 10L, 17L, 1L, 2L, 1L, 14L, 8L, 8L, 14L, 10L, 8L, 6L, 6L,
8L, 5L, 7L, 5L, 1L, 5L, 7L, 9L, 2L, 1L, 9L, 14L), order = c(9,
1, 9, 1, 3, 7, 10, 5, 5, 2, 8, 8, 4, 1, 2, 2, 9, 7, 7, 9, 2,
2, 9, 5, 7, 10, 7, 2, 1, 8, 1, 1, 4, 8, 5, 7, 7, 5, 5, 2, 2,
2, 8, 1, 5, 7, 5, 8, 7, 1, 5, 5, 7, 4, 1, 1, 1, 7, 4, 1, 1, 2,
5, 3, 3, 8, 9, 4, 5, 5, 5, 10, 5, 7, 8, 8, 5, 2, 9, 3, 5, 3,
10, 3, 7, 4, 7, 1, 1, 5, 3, 1, 4, 4, 7, 1, 7, 8, 7, 4, 4, 1,
8, 4, 3, 1, 1, 4, 2, 3, 9, 9, 2, 8, 2, 3, 2, 5, 5, 8, 7, 7, 4,
1, 1, 1, 2, 5, 5, 2, 3, 4, 3, 7, 4, 1, 1, 7, 5, 1, 2, 9, 8, 5,
7, 2, 7, 1, 5, 5, 5, 3, 10, 9, 7, 10, 9, 7, 8, 6, 7, 8, 4, 9,
9, 5, 7, 2, 2, 2, 4, 4, 8, 1, 8, 5, 8, 1, 1, 5, 8, 1, 5, 9, 7,
8, 5, 2, 7, 7, 10, 1, 10, 10, 8, 5, 4, 7, 7, 9)), .Names = c("hhDomMil",
"kclust", "order"), row.names = c(NA, 200L), class = "data.frame")
I want to create a stacked bar plot like this one .
The only problem is, that I would like to have the order of the stacks to fit this (ETB,PMA,PER,KON,TRA,DDR,BUM,MAT,HED,EXP) - the order numbers in the matrix and I have also some aesthetic problems. I searched for a solution here but none of the ordering suggestions worked for me... :-\
Thanks a lot for your help! Dominik
UPDATE
Here is the code I used to draw my plot:
mycols <- c('#FFFD00', '#97CB00', '#3168FF', '#FF0200', '#FB02FE', \
'#CCFCCC', '#FE9900', '#98CBF8', '#00CCFF', '#00FD03') # Set milieu colors
ggplot(MilDis) +
geom_bar(aes(kclust, fill=factor(hhDomMil), \
colour=mycols), position='fill', binwidth=1, colour='white') +
scale_fill_manual(values = mycols)
UPDATE 2:
That's how I did it now:
mycols <- c('#3168FF', '#00CCFF', '#98CBF8', '#CCFCCC', '#00FD03',\
'#97CB00', '#FFFD00', '#FE9900', '#FB02FE', '#FF0200') # Set milieu colors
ggplot(MilDis) +
geom_bar(aes(factor(kclust), fill=reorder(hhDomMil,order)),\
position='fill') +
scale_fill_manual(values = mycols)
With this result:
Thank you all for your help!
The answer to this is easily solved by getting your data formatted correctly before passing it to ggplot()
. The key is to explicitly set the levels of the hhDomMil
factor. Assuming your data are in dat
:
dat <- transform(dat, hhDomMil = factor(hhDomMil,
levels = c("ETB", "PMA", "PER", "KON",
"TRA", "DDR", "BUM", "MAT",
"HED", "EXP")))
That fixes hhDomMil
as a factor in place inside dat
, and sets the levels to be in the order you wanted:
> head(dat$hhDomMil)
[1] HED ETB HED ETB PER BUM
Levels: ETB PMA PER KON TRA DDR BUM MAT HED EXP
Notice what is happing when R coerces hhDomMil
to a factor:
> head(factor(as.character(dat$hhDomMil)))
[1] HED ETB HED ETB PER BUM
Levels: BUM DDR ETB EXP HED KON MAT PER PMA TRA
The default is to sort the levels alphabetically, which is why the plot is coming out as you show.
The best advice I can give, is to get your data correctly formatted first and only then try to plot it - don't rely on automatic or on-the-fly conversion to get this right for you; inevitably it won't be what you want.