Grouped bar chart using ggplot2 - r

I have some data structured in the same way as the following:
structure(list(respectfromsuperior = structure(c(1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L,
1L, 1L, 1L, NA, 2L, 1L, 1L, 1L, 1L, 2L), .Label = c("agree",
"disagree"), class = "factor"), respectideserve = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
2L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 2L), .Label = c("agree",
"disagree"), class = "factor"), undesirablechange = structure(c(2L,
2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 2L, 1L, NA, 2L, 2L,
2L, 2L, 2L, 1L, 1L, NA, 1L, 2L, 1L, 2L, 2L, 2L), .Label = c("agree",
"disagree"), class = "factor"), jobsecuritypoor = structure(c(2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L,
2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("agree",
"disagree"), class = "factor"), promotionprospectsadequate = structure(c(2L,
1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L,
2L, 1L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L), .Label = c("agree",
"disagree"), class = "factor"), salaryadequate = structure(c(2L,
1L, 1L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L,
2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("agree",
"disagree"), class = "factor"), branch = structure(c(1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("Edinburgh",
"Head Office", "Manchester"), class = "factor")), .Names = c("respectfromsuperior",
"respectideserve", "undesirablechange", "jobsecuritypoor", "promotionprospectsadequate",
"salaryadequate", "branch"), class = "data.frame", row.names = c(1L,
2L, 4L, 6L, 10L, 11L, 13L, 15L, 16L, 17L, 19L, 20L, 22L, 23L,
25L, 27L, 29L, 30L, 32L, 33L, 34L, 35L, 39L, 40L, 41L, 42L, 43L,
44L, 45L))
I would like to use ggplot 2 to plot a bar graph with the following features:
the bars representing percentage of respondents who agree with
statements in columns 2:6 of the data (disagree not plotted). Percentage calculated as a
percentage of branch members (not as percentage of total
respondents)
bars grouped by branch on the x axis
the questions (columns 2:6) are used as the 'Fill' argument
I've tried playing around with the code below but not able to work it out:
data.r <- melt(rewitemsbr, id.vars='branch')
ggplot(data=data.r, aes(x=value, fill=variable)) +
geom_bar(stat="count", position=position_dodge())
this is the best I've come up with:
Any help very much appreciated thank you.


You can try following.
# get the stats using aggregate
res <- aggregate(d[,1:6], list(d$branch), function(x) sum(x=="agree", na.rm = T)/length(x))
res
Group.1 respectfromsuperior respectideserve undesirablechange jobsecuritypoor promotionprospectsadequate salaryadequate
1 Edinburgh 1.0 0.8888889 0.1111111 0.0 0.6666667 0.4444444
2 Head Office 0.7 0.3000000 0.4000000 0.2 0.2000000 0.0000000
3 Manchester 0.8 0.8000000 0.2000000 0.1 0.6000000 0.2000000
# to long format
library(reshape2)
res_long <- melt(res, id.vars='Group.1')
# plot
ggplot(data=res_long, aes(x=Group.1, y=value, fill=variable)) +
geom_bar(stat="identity", position=position_dodge())

Related

Running ggplot inside foreach is slower than running it with just a for loop

I am making a map of a dataset with 20 million data points in ggplot. A single map (with facetting) takes 10-15 mins, so I checked if using multiple cores in parallel mode would work better. Using foreach, maps took more time to make. Some foreach runs were running for 30min-1 hour without producing any results. I know that the answer to this question (Why is the parallel package slower than just using apply?) shows that in parallel computation, sometimes it takes more time to combine the result from the separate parallel processes than running the task itself. But I saw some run examples when I was searching that minute-runs can be improved. Do you think it is possible?
Due to the sheer amount of data I have, I sampled my dataset:
structure(list(lat = c(46.791667, 52.958333, 57.375, 62.625,
74.041667, 60.208333, 30.208333, 56.791667, 57.375, 40.958333,
56.541667, 38.958333, 35.291667, 43.625, 71.375, 66.875, 74.375,
66.458333, 47.791667, 48.041667, 41.541667, 40.875, 57.208333,
64.375, 42.625, 43.958333, 69.958333, 72.375, 36.875, 66.958333,
39.791667, 36.625, 52.625, 65.708333, 42.208333, 53.708333, 35.458333,
58.625, 34.875, 57.291667, 59.708333, 61.708333, 72.041667, 59.958333,
32.208333, 43.625, 39.541667, 62.625, 41.208333, 32.291667, 48.958333,
47.291667, 60.375, 49.458333, 37.208333, 65.708333, 57.958333,
31.041667, 63.875, 43.625, 54.541667, 55.541667, 45.458333, 72.375,
54.708333, 37.958333, 32.375, 60.125, 59.041667, 37.875, 42.958333,
44.375, 59.791667, 49.208333, 34.375, 53.208333, 59.458333, 53.375,
45.458333, 72.125, 66.208333, 60.958333, 47.625, 60.291667, 41.125,
67.541667, 54.625, 55.541667, 37.541667, 44.291667, 44.458333,
40.041667, 49.458333, 39.625, 73.375, 41.458333, 71.375, 31.041667,
66.791667, 42.541667), lon = c(-6.125, -19.541667, -29.291667,
-9.2083333, -11.541667, -6.625, -25.708333, -14.458333, -48.291667,
-63.541667, -41.291667, -12.541667, -48.291667, -58.708333, 6.625,
-2.7083333, -69.375, -19.291667, -27.208333, -36.625, -17.791667,
-50.541667, -38.708333, 9.375, -56.208333, -44.958333, -59.041667,
8.875, -21.125, -24.791667, -40.375, -26.208333, -31.875, -11.875,
-60.958333, -39.125, -32.458333, -54.791667, -44.541667, -37.958333,
-48.625, -10.541667, 3.5416667, -17.791667, -16.041667, -9.9583333,
-32.708333, 0.875, -18.625, -54.208333, -63.125, -56.458333,
-55.125, -22.708333, -40.958333, -56.208333, -33.625, -69.125,
-58.125, -17.541667, -23.541667, -17.041667, -18.458333, -64.791667,
-25.208333, -35.875, -44.791667, -11.291667, -58.291667, -46.208333,
-41.208333, -5.0416667, -38.208333, -13.875, -55.291667, -17.291667,
-48.625, -38.791667, -59.375, -19.291667, 5.5416667, -19.625,
-41.375, -66.291667, -17.625, -14.208333, -39.291667, -48.875,
-16.541667, -21.375, -46.375, 2.625, -60.291667, -40.375, 2.4583333,
-16.458333, 4.875, -66.291667, -4.2916667, -36.458333), entity = structure(c(2L,
2L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 2L,
2L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 2L,
1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 2L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L,
2L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 1L,
2L, 1L, 1L), .Label = c("Cc", "Li"), class = "factor"), watcon = structure(c(1L,
2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 1L,
1L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
1L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 1L,
2L, 2L, 2L), .Label = c("calm", "stormy"), class = "factor"),
step = structure(c(1L, 3L, 2L, 4L, 4L, 2L, 3L, 3L, 3L, 4L,
2L, 2L, 3L, 2L, 1L, 3L, 3L, 3L, 4L, 4L, 4L, 1L, 1L, 1L, 2L,
4L, 1L, 2L, 2L, 4L, 2L, 4L, 4L, 3L, 4L, 2L, 2L, 1L, 2L, 2L,
1L, 4L, 3L, 2L, 3L, 3L, 2L, 4L, 1L, 3L, 2L, 2L, 3L, 4L, 4L,
2L, 2L, 3L, 4L, 1L, 3L, 2L, 1L, 4L, 2L, 3L, 1L, 3L, 1L, 2L,
1L, 4L, 4L, 3L, 1L, 1L, 1L, 3L, 1L, 2L, 2L, 4L, 3L, 4L, 4L,
4L, 1L, 2L, 1L, 4L, 3L, 4L, 2L, 4L, 1L, 4L, 1L, 2L, 2L, 4L
), .Label = c("abundance", "enccomb", "adscomb", "infcomb"
), class = "factor")), row.names = c(NA, -100L), class = "data.frame")
The code I am using is:
library(oceanmap)
library(sf)
library(ggmap)
library(rnaturalearth)
library(rnaturalearthdata)
library(rgeos)
library(tidyverse)
world <- ne_countries(scale = "medium", returnclass = "sf")
library(doParallel)
library(foreach)
cl <- makeCluster(5)
doParallel::registerDoParallel(cl)
entities <- unique(sample$entity)
foreach(i=1:length(entities), .packages = c("tidyverse", "dplyr")) %dopar% {
ggplot (data=world) + geom_sf(color="white", fill="white") + coord_sf(xlim = c(-34,-30), ylim = c(53,62) , expand = FALSE) + geom_point(subset(sample, sample$entity==entities[i]), mapping=aes(x = lon, y = lat, color = log10(value))) + facet_grid(watcon~step2) +
ggtitle(entities[i])
ggsave(filename = paste0(i,".png"))
}
stopCluster(cl)
P.S. I am using ggplot because of the opportunities for editing the map itself. Lattice is faster but lacks the customization that I am looking for.
Any help on how to improve my foreach code or if it's even possible is greatly appreciated!

Stacked barplot using ggplot2 - data visualisation

I have very little experience with R and am trying to make a stacked barplot using ggplot2.
I have 2 groups - control and experimental, and 2 choices - red and green. I'm not sure how to organise my data.
There were 80 animals in my trial (control n=40, experimental n=40) and they were given the choice of red and green substrate, I noted which substrate they chose, and that's the data I'm trying to plot.
I would essentially want 'Experimental' and 'Control on the x-axis, and the number of choices on the y-axis (e.g. Control, Red n=20, Control, Green = 12 etc).
Any help would be appreciated!
Edited to add:
This is the graph it's outputting
This is the code I'm using (including suggested adjustments):
df <- data.frame(group = rep(c("control", "experimental"), each = 40),
substrate = sample (c("red","green"), 80, TRUE))
ggplot(df, aes(x = group, y = substrate, fill = substrate)) +
geom_bar(stat = "identity") +
scale_fill_manual(values = c("red", "green"))
This is the output:
structure(list(group = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("control", "experimental"
), class = "factor"), substrate = structure(c(1L, 2L, 1L, 2L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 1L,
2L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 1L,
2L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L,
1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L,
1L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 2L), .Label = c("green",
"red"), class = "factor")), class = "data.frame", row.names = c(NA,
-80L))
output from df(behaviour) - original dataframe
structure(list(group = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("Control", "Experimental"
), class = "factor"), substrate = structure(c(1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("Green",
"Red"), class = "factor")), class = "data.frame", row.names = c(NA,
-80L))

Your data:
behaviour=structure(list(group = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("Control", "Experimental"
), class = "factor"), substrate = structure(c(1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("Green",
"Red"), class = "factor")), class = "data.frame", row.names = c(NA,
-80L))
We can tabulate your data:
table(behaviour$group,behaviour$substrate)
Green Red
Control 10 30
Experimental 27 13
So you can only specify fill or y with geom_bar. In your case, you specify the fill, the geom_bar() function will do the counting for you:
ggplot(behaviour,aes(x=group,fill=substrate))+
geom_bar() + scale_fill_manual(values=c("#29c7ac","#c02739"))

You could have your data like this, with one row for each observation (i.e. each animal), with the group and the substrate recorded for each:
df <- data.frame(group = rep(c("control", "experimental"), each = 40),
substrate = rep(c("green", "red", "green", "red"), c(10, 30, 27, 13)))
Now define your plot using ggplot, specifying group as your x axis, and ..count.. as your y axis. Use geom_bar to get the stacked bars you are looking for, and finally use scale_fill_manual to set the colours:
library(ggplot2)
ggplot(df, aes(x = group, y = ..count.., fill = substrate)) +
geom_bar(colour = "black") +
scale_fill_manual(values = c("green", "red"))

Difference between densityPlot and geom_density

I am plotting the same data with both geom_density and base R's densityPlot:
head(df)
min_dist iteration
<dbl> <fct>
1 -79277 1
2 -68987 1
3 -98661 1
4 -98145 1
5 -222408 1
6 -217409 1
geom_density:
ggplot(df) + geom_density(aes(min_dist)) + xlim(c(-1e4, 1e4)) + geom_rug(aes(min_dist))
densityPlot:
densityPlot(df$min_dist, xlim = c(-1e4, 1e4))
And they are strikingly different!
I was under the impression that geom_density was a wrapper for stat_density.
Is this just a matter of different adjust values?
df <- structure(list(min_dist = c(-79277, -68987, -98661, -98145, -222408,
-217409, -10759, -10363, 48034, 48525, 617038, 617069, -19656,
-17396, -479, -333, -48721, -47691, -19761, 380, 31429, 33953,
-9220, -61971, -609, -560, 6228, 13082, -217137, -216639, 99268,
102365, -119574, -53795, -329407, -111401, 1018733, -559898,
-1346, -15, -71577, -2883, 19490, -12321, -12240, -8470, -29804,
28724, 40673, -57818, -41421, -39126, 136783, 165727, -52989,
-51058, 58995, -12226, 8057, 44217, 13280, 16828, -80410, 11324,
975, 2630, 14250, 17108, -29341, -27033, -79277, -68987, -98661,
-98145, -222408, -217409, -10759, -10363, 48034, 48525, 617038,
617069, -19656, -17396, -479, -333, -48721, -47691, -19761, 380,
31429, 33953, -9220, -61971, -609, -560, 6228, 13082, -217137,
-216639, 99268, 102365, -119574, -53795, -329407, -111401, 1018733,
-559898, -1346, -15, -71577, -2883, 19490, -12321, -12240, -8470,
-29804, 28724, 40673, -57818, -41421, -39126, 136783, 165727,
-52989, -51058, 58995, -12226, 8057, 44217, 13280, 16828, -80410,
11324, 975, 2630, 14250, 17108, -29341, -27033), iteration = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("1",
"2"), class = "factor")), row.names = c(NA, -140L), class = c("tbl_df",
"tbl", "data.frame"))

Geom Bar Plot, sum of count not visible

I have a dataframe tag, with 51X5 structure
structure(list(Tagging = structure(c(1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("CIRCLE CAMPIAGN",
"NATIONAL CAMPIAGN"), class = "factor"), Status = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L), .Label = c("Negative", "Positive"), class = "factor"),
Month = structure(c(1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L,
3L, 3L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L,
3L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 1L, 1L,
1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 3L), .Label = c("JUL",
"JUN", "MAY"), class = "factor"), Category = structure(c(1L,
4L, 6L, 1L, 2L, 4L, 6L, 1L, 2L, 4L, 5L, 6L, 1L, 2L, 4L, 5L,
6L, 1L, 2L, 4L, 5L, 6L, 1L, 2L, 4L, 6L, 1L, 4L, 6L, 2L, 3L,
4L, 6L, 1L, 2L, 3L, 4L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L,
3L, 4L, 5L, 6L, 6L), .Label = c("Data", "Other", "Roaming",
"Unlimited", "VAS", "Voice"), class = "factor"), count = c(3L,
2L, 1L, 4L, 5L, 2L, 1L, 2L, 6L, 7L, 2L, 3L, 4L, 9L, 6L, 2L,
3L, 3L, 3L, 10L, 2L, 5L, 5L, 5L, 4L, 3L, 1L, 1L, 1L, 2L,
1L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 4L, 1L, 1L, 3L, 3L, 2L,
1L, 1L, 1L, 3L, 4L, 2L)), class = "data.frame", row.names = c(NA,
-51L))
I want to create a bar plot (ggplot) to show bar graph with label on bar as sum of count of category month wise I am using below code
ggplot(data = tag, aes(x = Tagging, y = count, fill = Status)) +
geom_col() +
labs(x = "Tagging", y = "Count", title = "FlyTxt ROI", subtitle = "Statistics") +
geom_text(aes(label = count), color = "white", size = 3, position = position_stack(vjust = 0.5)) +
theme_minimal()+facet_wrap(~Month)
But I am getting split count values:
Help as I want only sum of count for each status

The problem is, that the information you show in the bar is accumulated by geom_col over all categories but the geom_text doesn't do that.
On option is to pre-summarize the data (to get rid of the category split) and then plot the graph.
library(tidyverse)
tag_sum <- tag %>%
group_by(Tagging, Status, Month) %>%
summarise(count_sm = sum(count))
ggplot(data = tag_sum, aes(x = Tagging, y = count_sm, fill = Status)) +
geom_col() +
geom_text(aes(label = count_sm), color = "white", size = 3,
position = position_stack(vjust = 0.5)) +
facet_wrap(~Month) +
labs(x = "Tagging", y = "Count", title = "FlyTxt ROI", subtitle = "Statistics") +
theme_minimal()

Bar chart for factorial designs in R

I'm currently trying to create a clustered bar chart using ggplot2. It's basically just mean response times for a 2x2x2 factorial design. The three factors are load, compatibility and salience. I'm having a hard time jamming the third factor (salience) in there though. It shouldn't be a stacked graph though
This is what I currently have
bar+stat_summary(fun.y = mean, geom = "bar", position = "dodge") +
+ stat_summary(fun.data = mean_cl_normal, geom = "errorbar", position = position_dodge(width = 0.90), width = 0.2)+
+ labs(x = "Compatibility", y = "Mean RT", fill = "Load")
Here's a small sample of the data I'm trying to graph:
ID load comp sal rt
1 1 High Incompatible Non_Salient 787
2 1 Low Compatible Salient 754
3 2 High Incompatible Salient 654
I've seen graphs like these numerous times before but I have no idea how to get ggplot2 to display three independent variables at the same time.
I've tried splitting the graphs by adding
+ facet_wrap( ~ sal)
but that doesn't work either. It just says "Invalid argument to unary operator"
Any help would be appreciated.

Is this the kind of plot you are looking for?
I used the Wii data from the book "Discovering Statistics Using R", which is in a similar format to yours.
structure(list(athlete = structure(c(1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L), .Label = c("Athlete", "Non-Athlete"), class = "factor"),
stretch = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L), .Label = c("No Stretching", "Stretching"
), class = "factor"), wii = structure(c(1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("Playing Wii",
"Watching Wii"), class = "factor"), injury = c(2L, 2L, 1L,
2L, 0L, 1L, 2L, 0L, 2L, 2L, 2L, 1L, 4L, 2L, 2L, 0L, 0L, 3L,
3L, 3L, 2L, 1L, 0L, 2L, 2L, 3L, 2L, 2L, 3L, 1L, 2L, 4L, 1L,
2L, 2L, 2L, 1L, 4L, 4L, 1L, 2L, 3L, 3L, 3L, 3L, 2L, 3L, 2L,
2L, 2L, 1L, 0L, 3L, 3L, 2L, 1L, 2L, 4L, 1L, 2L, 5L, 5L, 3L,
6L, 4L, 3L, 4L, 5L, 5L, 2L, 6L, 4L, 4L, 4L, 3L, 4L, 3L, 2L,
1L, 4L, 3L, 2L, 2L, 1L, 3L, 1L, 1L, 3L, 4L, 2L, 7L, 8L, 6L,
9L, 4L, 7L, 5L, 9L, 6L, 4L, 8L, 5L, 4L, 7L, 10L, 1L, 3L,
2L, 1L, 3L, 3L, 2L, 3L, 4L, 2L, 0L, 1L, 3L, 2L, 0L)),
.Names = c("athlete", "stretch", "wii", "injury"),
class = "data.frame", row.names = c(NA, -120L))
Here is how to produce the plot.
library(ggplot2)
library(Hmisc)
ggplot(data=Wii, aes(x=stretch, y=injury, fill=wii)) +
facet_wrap(~athlete) +
stat_summary(fun.y = mean, geom = "bar", position = "dodge") +
stat_summary(fun.data = mean_cl_normal, geom = "errorbar", position = position_dodge(width = 0.90), width = 0.2)

Resources