For the following data set, I would like to plot for each variable and color each 10th observations differently. I can do it using the R base. I want to learn how to do it using the ggplot2?
dput(mydata)
structure(list(beta0_C1 = c(5.90722120539152, 5.89025566996191,
5.88591520258904, 5.86911167649919, 5.93772460437405, 5.92985640353594,
5.89150365752453, 5.99046628686212, 5.91548006074821, 5.91571832976612,
5.88437484241154, 5.92092513223357, 5.98978050584774, 5.91152552752889,
5.91235823292462, 5.87961960044268, 5.84048698713552, 5.85484766204026,
5.94002829943904, 5.8844367778216, 5.90201348639369, 5.91220967575205,
5.90010933186624, 5.9187781795242, 5.85506764080697, 5.90103565341373,
5.88527143992961, 5.90218851192948, 5.90118162849608, 5.93147588185271
), beta1_C1 = c(0.389473200070741, 0.386495525456602, 0.401277295631578,
0.400952009358693, 0.376727640651344, 0.380365338054745, 0.393444927288697,
0.351041363714069, 0.393194356572458, 0.393448101768608, 0.398884551136789,
0.399458966787235, 0.357436746423815, 0.393782316102096, 0.387154169967002,
0.400838223362088, 0.404272252119662, 0.407427775176583, 0.379704250022161,
0.388842664781329, 0.382202010301184, 0.401354531881688, 0.391184010553641,
0.390280828053183, 0.402135923802544, 0.384344141458216, 0.405409447440106,
0.391719398951194, 0.398025625260563, 0.361822915989445), beta2_C1 = c(-0.0214886993465096,
-0.020723519439664, -0.0224612526333316, -0.0218187226687474,
-0.0200324040063121, -0.0208421378685671, -0.0218756660346625,
-0.0182499666400075, -0.0222765863213226, -0.022242845613047,
-0.0222033291270054, -0.0231570312767931, -0.0189429585905841,
-0.0221017468740293, -0.0209327798783444, -0.022409049257, -0.021698958175968,
-0.0225601087054418, -0.020928341508875, -0.0214668830626075,
-0.0205872002686706, -0.0233768022702472, -0.021755967293395,
-0.0218442145294776, -0.0222514480818199, -0.0212195394692002,
-0.0232109717283908, -0.0214814999754984, -0.0225124468437127,
-0.0187033387452614), beta0_C2 = c(6.50537199380546, 6.43626630601952,
6.44460360859128, 6.44788878017196, 6.49678676895955, 6.48474789770674,
6.5459727637079, 6.37593806532098, 6.39492158034295, 6.44497331914909,
6.3888816168562, 6.49660574813212, 6.45922901141938, 6.40080765767324,
6.37918638201668, 6.49354321098856, 6.47057962920788, 6.55699741431025,
6.56617313133218, 6.54271932949381, 6.44608000042182, 6.45333777656105,
6.67458442747556, 6.48420983182487, 6.59919337271637, 6.46645685814734,
6.46171236062657, 6.52625058117578, 6.51177045919728, 6.49897849935538
), beta1_C2 = c(-0.370455826326915, -0.338852275811034, -0.340671118342601,
-0.339888681238265, -0.36934391822867, -0.357194169746804, -0.415966150286963,
-0.349051278947586, -0.358209379291251, -0.371785518417424, -0.349725822847608,
-0.368220986471866, -0.327425879655177, -0.336993142255552, -0.328859493371605,
-0.347764105375218, -0.329761787134926, -0.37935820670654, -0.400211161919931,
-0.408699321227288, -0.357590345066542, -0.376548827126353, -0.44672514669147,
-0.353840422053319, -0.421912098450693, -0.371491468175642, -0.354864346664247,
-0.39139246919467, -0.379006372881295, -0.372492936183765), beta2_C2 = c(0.039728365796445,
0.0368393936404604, 0.0375019672690036, 0.0375019364609944, 0.0403444583999664,
0.0378627636833333, 0.0446717245407897, 0.0377538641609231, 0.039662572899695,
0.0408055348533836, 0.0386737104573771, 0.0397794302159846, 0.0352739962796708,
0.0376756204317514, 0.0370614500426065, 0.0374731659969108, 0.035366001926832,
0.0397165124506166, 0.0414814320660011, 0.0431083057931525, 0.0388672853038453,
0.0403590048367136, 0.0461540000449275, 0.0379315295246309, 0.0440664419193363,
0.0404593732981113, 0.0387390924290065, 0.0417832766420881, 0.0409598003097311,
0.0394548129358408)), row.names = c(NA, 30L), class = "data.frame")
R base code
par(mfrow=c(3,3))
col.set=c("green","blue","purple","deeppink","darkorchid","darkmagenta","black","khaki")
loop.vector=1:ncol(mydata)
for(b in loop.vector) {
x.beta<-mydata[,b]
beta <- substr(sub("^beta", '', names(mydata)[b]),1,1)
Cn <- substr(sub("^beta", '',names(mydata)[b]),3,4)
plot(x.beta, type = "n", ylab="", xlab="",
main=bquote(beta[.(beta)]~.(Cn)),
cex.main=1)
mtext("plots of betas",line=-1.5, cex=1, outer = TRUE)
for (k in 1:3){
beta_k=mydata[((nrow(mydata)/3)*k-((nrow(mydata)/3)-1)):
((nrow(mydata)/3)*k),b]
lines(((nrow(mydata)/3)*k-((nrow(mydata)/3)-1)):
((nrow(mydata)/3)*k),beta_k,
col=col.set[k])
legend("topleft", bg="transparent",inset=0.05,legend=paste0("chain_",1:3),
col=col.set, lty=1,box.lty=0, cex=0.8)
}
}
I want the same main title for each plot and one main titile for all plots.
how can I do it using the ggplot2 package?
ggplot2 works best with a long data frame containing variables for x, y, color, etc. This makes a long data frame:
library(tidyverse)
long_data = my_data %>%
mutate(n=1:nrow(my_data), chain=paste0('Chain ', rep(1:3, each=nrow(my_data)/3))) %>%
pivot_longer(cols=c(-n, -chain)) %>%
mutate(name=str_replace(name, '(\\d)_', '[\\1]~~'))
This makes the plot.
ggplot(long_data, aes(n, value, color=chain)) +
geom_line() +
facet_wrap(~name, scales='free_y', ncol=3, dir='v',
labeller=label_parsed) +
scale_color_manual('', values=c('Chain 1'='green', 'Chain 2'='blue', 'Chain 3'='purple')) +
theme_minimal()
Quite similar to #KentJohnson's answer but adding expression labelling of your facets, centered title and using scale_color_manual function to edit color labeling:
library(ggplot2)
library(dplyr)
library(tidyr)
df %>% mutate(Group = rep(c("A","B","C"), each = 10),
Position = 1:30) %>%
pivot_longer(-c(Group,Position), names_to = "Var",values_to = "val") %>%
mutate(Var = factor(Var, levels = c("beta0_C1","beta1_C1","beta2_C1","beta0_C2","beta1_C2","beta2_C2"),
labels = c(expression(beta[0]*"C1"),
expression(beta[1]*"C1"),
expression(beta[2]*"C1"),
expression(beta[0]*"C2"),
expression(beta[1]*"C2"),
expression(beta[2]*"C2")))) %>%
ggplot(aes(x = Position, y = val, color = Group))+
geom_line()+
facet_wrap(.~Var, scales = "free", labeller = label_parsed)+
labs(x = "", y ="", title = "Plots of Betas", color = "")+
scale_color_manual(values = c("green","blue","purple"), labels = c("Chain 1","Chain 2","Chain 3"))+
theme_minimal()+
theme(plot.title = element_text(hjust = 0.5))
Related
Given this R script:
library(glue)
library(ggplot2)
ir.data <- read.csv(file="~/apps/mine/cajueiro_weather_station/sensor_data/temperature_data.csv", header = F)
ir.data$V1 <- as.POSIXct(ir.data$V1, format = "%Y-%m-%dT%H:%M:%S", tz = "UTC")
ir.data$size <- (ir.data$V2 - ir.data$V3)
ggplot(ir.data, aes(x=V1)) +
labs(title = "IR-radiation-based sky temperature monitoring.",
subtitle = glue("Samples from {ir.data$V1[1]}h to {tail(ir.data$V1, n=1)}h UTC-3."),
caption = "Cajueiro Weather Station - fschuindt.githhub.io/blog/weather") +
geom_line(aes(y = V2), color = "#6163c2") +
geom_line(aes(y = V3), color = "#ad1fa2") +
scale_color_discrete(name = "Labels", labels = c("Ambient temperature.", "Sky temperature.")) +
xlab("Timestamp") +
ylab("Measured temperature in °Celcius")
And this .csv data sample:
2022-04-30T19:47:00,28.03,28.05
2022-04-30T19:47:02,27.99,28.01
2022-04-30T19:47:04,28.07,28.01
2022-04-30T19:47:06,28.05,28.05
2022-04-30T19:47:08,28.05,28.01
2022-04-30T19:47:10,28.03,28.01
2022-04-30T19:47:12,28.05,27.99
2022-04-30T19:47:14,28.07,28.01
2022-04-30T19:47:16,28.07,28.05
2022-04-30T19:47:18,28.05,28.05
2022-04-30T19:47:20,28.09,28.07
That's the plot output (the .csv data is bigger than the example):
Why the labels described at scale_color_discrete(name = "Labels", labels = c("Ambient temperature.", "Sky temperature.")) are not being displayed?
It's not recognising those values in an aes call to colour. Reshape data to put all y values in a single column, pass a grouping variable to aes(colour = ...) and use scale_colour_manual to set colours instead:
library(tidyverse)
ir.data <- read_csv(
"2022-04-30T19:47:00,28.03,28.05
2022-04-30T19:47:02,27.99,28.01
2022-04-30T19:47:04,28.07,28.01
2022-04-30T19:47:06,28.05,28.05
2022-04-30T19:47:08,28.05,28.01
2022-04-30T19:47:10,28.03,28.01
2022-04-30T19:47:12,28.05,27.99
2022-04-30T19:47:14,28.07,28.01
2022-04-30T19:47:16,28.07,28.05
2022-04-30T19:47:18,28.05,28.05
2022-04-30T19:47:20,28.09,28.07",
col_names = c("V1", "V2", "V3")
)
ir.data %>%
pivot_longer(-V1, names_to = "Labels", values_to = "V") %>%
ggplot(aes(x = V1, y = V, colour = Labels)) +
labs(
title = "IR-radiation-based sky temperature monitoring.",
subtitle = glue::glue(
"Samples from {ir.data$V1[1]}h to {tail(ir.data$V1, n=1)}h UTC-3."
),
caption = "Cajueiro Weather Station - fschuindt.githhub.io/blog/weather"
) +
geom_line(size = 1) +
scale_color_manual(
name = "Labels",
,
values = c("#6163c2", "#ad1fa2"),
limits = c("V2", "V3"),
labels = c("Ambient temperature.", "Sky temperature."),
) +
xlab("Timestamp") +
ylab("Measured temperature in °Celcius")
Created on 2022-05-06 by the reprex package (v2.0.1)
To make the plots more comparable, I would like to set the limits of all fill- and symbol size axes to the same size. Is this possible? Also the legends for "size" and "fill" are swapping places in the last two plots, which I would like to prevent as well.
Thanks in advance!!!
ggballonplot chart
Some code as an example
library(ggplot2)
library(ggpubr)
plot4 <- ggballoonplot(data_matrix_comb, x = "Time", y = "Depth",
size = "mean_percentage_of_indivuals",
fill = "mean_variance", facet.by = "Stage",
ggtheme = theme_bw()) + scale_fill_viridis_c(option = "C") +
labs(title "Autumn")
library(gridExtra)
grid.arrange(plot1, plot2, plot3, plot4, ncol=2, nrow = 2)
You can use ggarrange() from ggpubr(),I would suggest a common legend since it doesn't make sense to have it 4 times.
I simulated some data since you did not provide (please do so in the future!).
Also slight variation from what you did, I placed all the data.frames inside a list, and if possible, you should try that so that you don't run the same code multiple times.. (i.e avoid copy-paste code):
library(ggplot2)
library(ggpubr)
library(dplyr)
set.seed(111)
dat = data.frame(Time=rep(c("day","night"),12),
Depth=rep(c("aphotic","euphotic"),each=2,times=6),
Stage = rep(c("adult","juvenil"),each=4),
mean_percentage_of_indivuals=100*runif(24),
mean_variance = rnbinom(24,mu=100,size=0.5))
dat_all = dat %>% group_by(Time,Depth,Stage) %>% summarize_all(mean)
dat_spring = dat[1:8,]
dat_summer = dat[9:16,]
dat_autumn = dat[17:24,]
dat_list = list("All Seasons"=dat_all,"Spring"=dat_spring,
"Summer"=dat_summer,"Autumn"=dat_autumn)
plts = lapply(names(dat_list),function(i){
p <- ggballoonplot(dat_list[[i]], x = "Time", y = "Depth",
size = "mean_percentage_of_indivuals",
fill = "mean_variance", facet.by = "Stage",
ggtheme = theme_bw()) +
scale_fill_viridis_c(option = "C") +
labs(title=i)
return(p)
})
ggarrange(plotlist =plts,ncol=2, nrow=2, common.legend = TRUE)
For the following data set, I would like to plot for each variable and color each 10th observations differently. I can do it using the R base. I want to learn how to do it using the ggplot2?
dput(mydata)
structure(list(beta0_C1 = c(5.90722120539152, 5.89025566996191,
5.88591520258904, 5.86911167649919, 5.93772460437405, 5.92985640353594,
5.89150365752453, 5.99046628686212, 5.91548006074821, 5.91571832976612,
5.88437484241154, 5.92092513223357, 5.98978050584774, 5.91152552752889,
5.91235823292462, 5.87961960044268, 5.84048698713552, 5.85484766204026,
5.94002829943904, 5.8844367778216, 5.90201348639369, 5.91220967575205,
5.90010933186624, 5.9187781795242, 5.85506764080697, 5.90103565341373,
5.88527143992961, 5.90218851192948, 5.90118162849608, 5.93147588185271
), beta1_C1 = c(0.389473200070741, 0.386495525456602, 0.401277295631578,
0.400952009358693, 0.376727640651344, 0.380365338054745, 0.393444927288697,
0.351041363714069, 0.393194356572458, 0.393448101768608, 0.398884551136789,
0.399458966787235, 0.357436746423815, 0.393782316102096, 0.387154169967002,
0.400838223362088, 0.404272252119662, 0.407427775176583, 0.379704250022161,
0.388842664781329, 0.382202010301184, 0.401354531881688, 0.391184010553641,
0.390280828053183, 0.402135923802544, 0.384344141458216, 0.405409447440106,
0.391719398951194, 0.398025625260563, 0.361822915989445), beta2_C1 = c(-0.0214886993465096,
-0.020723519439664, -0.0224612526333316, -0.0218187226687474,
-0.0200324040063121, -0.0208421378685671, -0.0218756660346625,
-0.0182499666400075, -0.0222765863213226, -0.022242845613047,
-0.0222033291270054, -0.0231570312767931, -0.0189429585905841,
-0.0221017468740293, -0.0209327798783444, -0.022409049257, -0.021698958175968,
-0.0225601087054418, -0.020928341508875, -0.0214668830626075,
-0.0205872002686706, -0.0233768022702472, -0.021755967293395,
-0.0218442145294776, -0.0222514480818199, -0.0212195394692002,
-0.0232109717283908, -0.0214814999754984, -0.0225124468437127,
-0.0187033387452614), beta0_C2 = c(6.50537199380546, 6.43626630601952,
6.44460360859128, 6.44788878017196, 6.49678676895955, 6.48474789770674,
6.5459727637079, 6.37593806532098, 6.39492158034295, 6.44497331914909,
6.3888816168562, 6.49660574813212, 6.45922901141938, 6.40080765767324,
6.37918638201668, 6.49354321098856, 6.47057962920788, 6.55699741431025,
6.56617313133218, 6.54271932949381, 6.44608000042182, 6.45333777656105,
6.67458442747556, 6.48420983182487, 6.59919337271637, 6.46645685814734,
6.46171236062657, 6.52625058117578, 6.51177045919728, 6.49897849935538
), beta1_C2 = c(-0.370455826326915, -0.338852275811034, -0.340671118342601,
-0.339888681238265, -0.36934391822867, -0.357194169746804, -0.415966150286963,
-0.349051278947586, -0.358209379291251, -0.371785518417424, -0.349725822847608,
-0.368220986471866, -0.327425879655177, -0.336993142255552, -0.328859493371605,
-0.347764105375218, -0.329761787134926, -0.37935820670654, -0.400211161919931,
-0.408699321227288, -0.357590345066542, -0.376548827126353, -0.44672514669147,
-0.353840422053319, -0.421912098450693, -0.371491468175642, -0.354864346664247,
-0.39139246919467, -0.379006372881295, -0.372492936183765), beta2_C2 = c(0.039728365796445,
0.0368393936404604, 0.0375019672690036, 0.0375019364609944, 0.0403444583999664,
0.0378627636833333, 0.0446717245407897, 0.0377538641609231, 0.039662572899695,
0.0408055348533836, 0.0386737104573771, 0.0397794302159846, 0.0352739962796708,
0.0376756204317514, 0.0370614500426065, 0.0374731659969108, 0.035366001926832,
0.0397165124506166, 0.0414814320660011, 0.0431083057931525, 0.0388672853038453,
0.0403590048367136, 0.0461540000449275, 0.0379315295246309, 0.0440664419193363,
0.0404593732981113, 0.0387390924290065, 0.0417832766420881, 0.0409598003097311,
0.0394548129358408)), row.names = c(NA, 30L), class = "data.frame")
R base code
par(mfrow=c(3,3))
col.set=c("green","blue","purple","deeppink","darkorchid","darkmagenta","black","khaki")
loop.vector=1:ncol(mydata)
for(b in loop.vector) {
x.beta<-mydata[,b]
beta <- substr(sub("^beta", '', names(mydata)[b]),1,1)
Cn <- substr(sub("^beta", '',names(mydata)[b]),3,4)
plot(x.beta, type = "n", ylab="", xlab="",
main=bquote(beta[.(beta)]~.(Cn)),
cex.main=1)
mtext("plots of betas",line=-1.5, cex=1, outer = TRUE)
for (k in 1:3){
beta_k=mydata[((nrow(mydata)/3)*k-((nrow(mydata)/3)-1)):
((nrow(mydata)/3)*k),b]
lines(((nrow(mydata)/3)*k-((nrow(mydata)/3)-1)):
((nrow(mydata)/3)*k),beta_k,
col=col.set[k])
legend("topleft", bg="transparent",inset=0.05,legend=paste0("chain_",1:3),
col=col.set, lty=1,box.lty=0, cex=0.8)
}
}
I want the same main title for each plot and one main titile for all plots.
how can I do it using the ggplot2 package?
ggplot2 works best with a long data frame containing variables for x, y, color, etc. This makes a long data frame:
library(tidyverse)
long_data = my_data %>%
mutate(n=1:nrow(my_data), chain=paste0('Chain ', rep(1:3, each=nrow(my_data)/3))) %>%
pivot_longer(cols=c(-n, -chain)) %>%
mutate(name=str_replace(name, '(\\d)_', '[\\1]~~'))
This makes the plot.
ggplot(long_data, aes(n, value, color=chain)) +
geom_line() +
facet_wrap(~name, scales='free_y', ncol=3, dir='v',
labeller=label_parsed) +
scale_color_manual('', values=c('Chain 1'='green', 'Chain 2'='blue', 'Chain 3'='purple')) +
theme_minimal()
Quite similar to #KentJohnson's answer but adding expression labelling of your facets, centered title and using scale_color_manual function to edit color labeling:
library(ggplot2)
library(dplyr)
library(tidyr)
df %>% mutate(Group = rep(c("A","B","C"), each = 10),
Position = 1:30) %>%
pivot_longer(-c(Group,Position), names_to = "Var",values_to = "val") %>%
mutate(Var = factor(Var, levels = c("beta0_C1","beta1_C1","beta2_C1","beta0_C2","beta1_C2","beta2_C2"),
labels = c(expression(beta[0]*"C1"),
expression(beta[1]*"C1"),
expression(beta[2]*"C1"),
expression(beta[0]*"C2"),
expression(beta[1]*"C2"),
expression(beta[2]*"C2")))) %>%
ggplot(aes(x = Position, y = val, color = Group))+
geom_line()+
facet_wrap(.~Var, scales = "free", labeller = label_parsed)+
labs(x = "", y ="", title = "Plots of Betas", color = "")+
scale_color_manual(values = c("green","blue","purple"), labels = c("Chain 1","Chain 2","Chain 3"))+
theme_minimal()+
theme(plot.title = element_text(hjust = 0.5))
I am trying to produce a heatmap with ggplot2 or plotly in R, where the values associated with a block or tile are used as labels in the respective tile. This was not so difficult, but I have removed the legend and would like to change the colours of the labels conditional on their values to increase their visibility.
Here a reproducible examples to show what I mean.
Data (using data.table and dplyr):
sig <- rep(c("sig1", "sig2", "sig3"), 100, replace = TRUE, prob = c(0.4, 0.35, 0.25))
date <- c("2019-11-01", "2019-11-02", "2019-11-03")
another <- as.data.table(expand.grid(sig, date))
test_dat_numerics <- another[, number_ok := sample(0:100, 900, replace = TRUE)]
setnames(test_dat_numerics, c("Var1", "Var2"), c("sig", "date"))
test_dat_numerics <- test_dat_numerics[, avg := mean(number_ok), by = .(date, sig)] %>%
dplyr::select(-number_ok) %>%
dplyr::rename(number_ok = avg) %>%
dplyr::mutate(prop = ifelse(number_ok > 50, 1, 0))
dplyr::distinct()
The heatmap (with ggplot2):
ggp <- ggplot(test_dat_numerics, aes(date, sig, fill = number_ok)) +
geom_tile() +
geom_text(aes(label = test_dat_numerics$number_ok)) +
theme(legend.position="none")
This results in
The darker a block becomes the less visible the text becomes. To prevent this, my intention is to make the text white when a value is below 50 and black otherwise. This is the part where I failed both with ggplot2 and plotly until now and would be grateful for help.
With plotly:
p <- test_dat_numerics %>%
plot_ly(type = "heatmap",
x = ~date,
y = ~sig,
z = ~number_ok,
# zmax = 100,
# zmin = 0,
showscale = FALSE,
colorscale = "Blues") %>%
add_annotations(text = as.character(test_dat_numerics$number_ok),
showarrow = FALSE,
color = list(if (test_dat_numerics$number_ok[i] > 50) {"black"} else {"white"})) %>%
layout(title = "Test Heatmap",
# titlefont = t,
xaxis = list(title = "Datum"), yaxis = list(title = "Signal")
)
I found a great plotly example here, but I couldn't manage to get to work for my case. Here the annotation part of my code:
ann <- list()
for (i in 1:length(unique(test_dat_numerics$sig))) {
for (j in 1:length(unique(test_dat_numerics$date))) {
for (k in 1:(length(unique(test_dat_numerics$sig))*length(unique(test_dat_numerics$date)))) {
ann[[k]] <- list(
x = i,
y = j,
font = list(color = if (test_dat_numerics$number_ok[i] > 50) {"black"} else {"white"}),
text = as.character(test_dat_numerics$number_ok[[k]]),
xref = "x",
yref = "y",
showarrow = FALSE )
}
}
}
p_test_num_heat <- layout(p, annotations = ann)
Here, one of numerous attempts with ggplot2:
ggp <- ggplot(test_dat_numerics, aes(date, sig, fill = number_ok)) +
geom_tile() +
geom_text(aes(label = test_dat_numerics$number_ok)) +
geom_label(aes(colour = factor(test_dat_numerics$prop))) +
theme(legend.position="none")
(This code produces the plot in the image above if the second to last line is removed.)
I'm pretty stuck on this one... Thanks in advance for any advice!
With ggplot2, you can use colour in the aes of geom_text (+ scale_colour_manual):
ggplot(test_dat_numerics, aes(date, sig, fill = number_ok)) +
geom_tile() +
geom_text(aes(label = number_ok, colour =ifelse(number_ok>50, "black", "white"))) +
scale_colour_manual(values=c("white"="white", "black"="black")) +
theme(legend.position="none")
# I am trying to combine a horizontal beside barplot with the table
# with the values in it.
# E.g. original table, including sample_ids
df = data.frame(
sample_id=c("s01","s02","s03","s04","s05","s06","s07","s08","s09","s10"),
one=runif(10,0,10),
two=runif(10,0,10),
three=runif(10,0,10),
four=runif(10,0,10)
)
# I created a mydata that I then do barplot as matrix
mydata = data.frame(
one=df$one,
two=df$two,
three=df$three,
four=df$four
)
# Plotted, using rainbow colouring, with a legend in the top right
barplot(as.matrix(mydata),horiz=TRUE,beside=TRUE,col=rainbow(length(df$sample_id)), legend=paste(df$sample_id), args.legend = list(x = "topright", bty = "n"),xlim=c(0,20))
# Now I would like the grid.table to be on the bottom right, ideally with the same order and colouring as the legend
library(gridExtra)
grid.table(df)
# Any ideas?
# EDIT: also tried addtable2plot from plotrix, with no much success
bp = barplot(as.matrix(mydata),horiz=TRUE,beside=TRUE,col=rainbow(length(df$sample_id)), legend=paste(df$sample_id), args.legend = list(x = "topright", bty = "n"),xlim=c(0,20))
library(plotrix)
addtable2plot(bp, y=0, df,cex=0.3)
The other option would be to turn the barplot into a ggplot geom_bar, but I struggled to do it for more than 2 columns.
Here's one way to do it using addtable2plot of plotrix package. It allows you to use the legend positions such as "bottomright"
df = data.frame(
sample_id=c("s01","s02","s03","s04","s05","s06","s07","s08","s09","s10"),
one=runif(10,0,10),
two=runif(10,0,10),
three=runif(10,0,10),
four=runif(10,0,10)
)
mydata = data.frame(
one=df$one,
two=df$two,
three=df$three,
four=df$four
)
library(plotrix)
dev.off()
windows(width = 8, height = 6)
df$one = round(df$one,2)
df$two = round(df$two,2)
df$three = round(df$three,2)
df$four = round(df$four,2)
barplot(as.matrix(mydata),horiz=TRUE,beside=TRUE,col=rainbow(length(df$sample_id)),
legend=paste(df$sample_id),
args.legend = list(x = "topright", bty = "n", cex = 1),
xlim=c(0,20))
addtable2plot("bottomright",table = df, cex = .9, bty = "o",
bg = c("white","grey"), vlines = TRUE, xpad = .25)
If you want to make the barplot in ggplot2, you need to reshape your data into long format. Based on your example data, the following code:
library(ggplot2)
library(gridExtra)
library(reshape2)
bp <- ggplot(melt(df, id.vars = 1),
aes(x = variable, y = value, fill = sample_id)) +
geom_bar(stat = 'identity', position = 'dodge') +
scale_fill_manual(values = rainbow(10)) +
labs(x = NULL, y = NULL) +
coord_flip() +
theme_minimal(base_size = 14)
gt <- tableGrob(df, rows = NULL, theme = ttheme_minimal())
grid.arrange(bp, gt, ncol = 2, widths = c(2.5,2))
which gives the following result: