Any tips to remove the zero labels in between the histogram bars?
hist(links$Survey_Duration, breaks = seq(0,50,5), main = "Survey Duration",
labels = TRUE, border = "black",
xlab = "Survey", ylim = c(0, 15), col = "gray", las = 1, xaxt='n')
axis(side=1, at=seq(0,50,5), labels=seq(0,50,5))
abline(v = mean(links$Survey_Duration), col = "royalblue", lwd = 1.5)
abline(v = median(links$Survey_Duration), col = "red", lwd = 1.5)
legend(x = "topright", c("Mean", "Median"), col = c("royalblue","red"),
lwd = c(1.5,1.5))
How about this?
# modify data so there's zero in one of the bins
mtcars$mpg <- ifelse(mtcars$mpg >= 25 & mtcars$mpg <= 30, NA, mtcars$mpg)
# save plot parameters
h <- hist(mtcars$mpg, plot = FALSE)
# produce plot
plot(h, ylim = c(0, 14))
# add labels manually, recoding zeros to nothing
text(h$mids, h$counts + 1, ifelse(h$counts == 0, "", h$counts))
A slightly different answer using the labeling in hist instead of adding text afterwards.
You do not provide your data, so I will use some data that is handy to illustrate.
The labels argument can specify the individual labels
H1 = hist(iris$Sepal.Length, breaks = 3:8, plot=FALSE)
BarLabels = H1$counts
BarLabels[BarLabels == 0] = ""
hist(iris$Sepal.Length, breaks = 3:8, labels = BarLabels)
Thanks #Daniel Anderson, it Ok now (Thumbs Up)
links$Survey_Duration <- ifelse(links$Survey_Duration > 15 &
links$Survey_Duration <= 25,
NA,
links$Survey_Duration)
h <- hist(links$Survey_Duration, breaks = seq(0,50,5), plot = FALSE)
plot(h, ylim = c(0, 14), main = "Survey Duration", xlab = "Time", col = "gray", las = 1)
text(h$mids, h$counts + 1, ifelse(h$counts == 0, "", h$counts))
axis(side=1, at=seq(0,50,5), labels=seq(0,50,5))
abline(v = mean(links$Survey_Duration), col = "royalblue", lwd = 1.5)
abline(v = median(links$Survey_Duration), col = "red", lwd = 1.5)
legend(x = "topright",
c("Mean", "Median"),
col = c("royalblue","red"),
lwd = c(1.5,1.5))
Related
I have a plot that I made using qqmath in the Lattice package (I subset it to only 3 points to make it easier for an example).
table <- data.table(Col1=c(12,3,4), Col2 = c(54,4,6), Col3 = c("Pink", "Pink", "Red"))
PrbGrd <- qnorm(c(0.00001,0.0001,0.001,0.01, 0.05, 0.10,0.20,0.30,0.40,
0.50, 0.60, 0.70,0.80,0.90,0.95,0.99,0.999,0.9999,0.99999))
PrbGrdL<-c("0.001","0.01","0.1","1","5","10","20","30","40","50","60","70","80","90","95","99","99.9","99.99","99.999")
PrbGrdL2<- c("99.999","99.99","99.9","99","95","90","80","70","60","50","40","30","20","10","5","1","0.1","0.01","0.001")
ValGrd<- c(seq(0.001,0.01,0.001),seq(0.01,0.1,0.01),seq(0.1,1,0.1),seq(1,10,1),seq(10,100,10),seq(100,1000,100),seq(1000,10000,1000))
ValGrd<- log10(ValGrd)
ValGrd2 <- c(-2:20)
ProbPlot <- qqmath(~ Col1,
data= table,
distribution = function(p) qnorm(p),
main = "Normal probability plot",
pch=20,
cex=0.5,
xlab="Probability of Lower",
ylab = "Pb",
#xlim = c(max(PrbGrd),min(PrbGrd)),
xlim = c(min(PrbGrd),max(PrbGrd)),
scales=list(y=list(alternating=1),x = list(at = PrbGrd, labels = PrbGrdL, cex = 0.8)),
#yscale.components=yscale.components.log10ticks,
panel=function(x,...){
panel.abline(v=PrbGrd ,col="grey",lty=3)
panel.abline(h=ValGrd2,col="grey",lty=3)
panel.qqmath(x,distribution=qnorm)
}
)
I would like to use the colors that are in the 3rd column of my table (Col3) to change the colors of the respective point on the plot. I can't figure out how to do it within qqmath, this would be simple with the regular plot function... but it doesn't seem as simple with qqmath.
Thank you!
Updated: based on OP's comment.
You can add the col argument, like:
ProbPlot <- qqmath(~ Col1,
data = table,
distribution = function(p) qnorm(p),
main = "Normal probability plot",
pch = 20,
cex = 0.5,
xlab = "Probability of Lower",
ylab = "Pb",
#xlim = c(max(PrbGrd),min(PrbGrd)),
xlim = c(min(PrbGrd),max(PrbGrd)),
scales = list(y = list(alternating = 1),
x = list(at = PrbGrd,
labels = PrbGrdL,
cex = 0.8)),
#yscale.components=yscale.components.log10ticks,
panel = function(x, ...){
panel.abline(v = PrbGrd,
col = "grey",
lty = 3)
panel.abline(h = ValGrd2,
col = "grey",
lty = 3)
panel.qqmath(x,
distribution=qnorm,
col = table$Col3) # add colors for each point
}
)
I can plot the barplot in Excel with decimal points in y-axis limits as shown below.
But I would not be able to change the y-axis limits in R.
Here is my code in R.
par(mfrow=c(1, 1), mar=c(7, 4, 5, 6))
mydata <- data.frame(Algorithm1=c(95.85, 96.94), Algorithm2=c(96.04, 96.84), Algorithm3=c(95, 95.30))
barplot(as.matrix(mydata), main="Precision", ylim=range(0:100),
beside=T, col=c("red", "blue"), las=1, border = 0, cex.lab=1, cex.axis=1, font=1,col.axis="black", ylab = "Percentage",
legend.text = c("X1", "X2"),
args.legend = list(x ='topright', bty='n', inset=c(-0.20,0)))
Thanks in advance for your answer.
You can also use ggplot2 and scales.
library(dplyr)
library(ggplot2)
library(scales)
mydata <- data.frame(Algorithm = rep(c('Algorithm1','Algorithm2','Algorithm3'), each=2),
variable_x = rep(c('X1','X2'),3),
values=c(0.9585, 0.9694,0.9604, 0.9684, 0.95, 0.9530))
mydata %>%
ggplot(aes(x=Algorithm,y=values,fill=variable_x))+
geom_bar(stat='identity', position='dodge')+
scale_y_continuous(labels = scales::percent, limits = c(0.94,0.975), oob = rescale_none)+
scale_fill_manual(values= c(X1='red',X2='blue'))
Set the limit of y and xpd = FALSE.
FALSE : all plotting is clipped to the plot region
TRUE : all plotting is clipped to the figure region
NA : all plotting is clipped to the device region
library(RColorBrewer)
color <- brewer.pal(3, "Set1")[2:1]
plot.new()
plot.window(xlim = c(0, 10), ylim = c(94, 97.5), yaxs = "i")
abline(h = seq(94, 97.5, 0.5), col = 8)
barplot(as.matrix(mydata), beside = T, col = color,
border = NA, legend.text = c("X1", "X2"),
args.legend = list(x = 'topright', bty = "n"), xpd = F, add = T)
You could do:
tickPoints <- 20 * (0:5)
par(mfrow = c(1, 1), mar = c(7, 4, 5, 6))
mydata <- data.frame(
Algorithm1 = c(95.85, 96.94),
Algorithm2 = c(96.04, 96.84),
Algorithm3 = c(95, 95.30)
)
barplot(
as.matrix(mydata), main = "Precision", beside = T, col = c("red", "blue"),
las = 1, border = 0, cex.lab = 1, cex.axis = 1, font = 1, col.axis = "black",
ylab = "Percentage", legend.text = c("X1", "X2"),
args.legend = list(x = 'topright', bty = 'n',inset = c(-0.20, 0)),
axes = FALSE,
ylim = range(tickPoints)
)
axis(side = 2, at = tickPoints, labels = sprintf("%0.1f", tickPoints))
Note the axes = FALSE in the call to barplot
I have found multiple ways to create a secondary y-axis in plot but I couldn't find a way to create a secondary y-axis in histogram.
Here is a sample code:
a <- sample(90:110, 50, replace=TRUE)
b <- runif(50, min=0, max=1)
hist(a)
lines(b)
b is too small to show in hist(a) so is there any way that I can see both in the histogram?
Technically a solution may be quite an identical to the approach proposed for the plots in this answer. The idea is to use overlapping of two plots as proposed by #r2evans.
It makes sense to use color coding:
# set color rules
col_a <- "red"
col_b <- "darkblue"
col_common <- "black"
Then let's draw the histogram and the plot:
# draw a histogram first
par(mar = c(5, 5, 5, 5) + 0.3)
hist(a, col = col_a, axes = FALSE, xlab = "", ylab = "", main = "")
# add both axes with the labels
axis(side = 1, xlim = seq(along.with = b), col = col_a, col.axis = col_a)
mtext(side = 1, text = "a_value", col = col_a, line = 2.5)
axis(side = 2, col = col_a, col.axis = col_a, ylab = "")
mtext(side = 2, text = "a_Frequency", col = col_a, line = 2.5)
# ... and add an overlaying plot
par(new=TRUE)
plot(b, ylim = c(0, 1), axes = FALSE, col = col_b, type = "l", xlab = "", ylab = "")
points(b, col = col_b, pch = 20, xlab = "", ylab = "")
axis(side = 3, xlim = seq(along.with = b), col = col_b, col.axis = col_b)
mtext(side = 3, text = "b_index", col = col_b, line = 2.5)
axis(side = 4, ylim = c(0, 1), col = col_b, col.axis = col_b)
mtext(side = 4, text = "b_value", col = col_b, line = 2.5)
box(col = col_common)
For a customer I'm trying to do a combined barplot and lineplot (with points) with two y axis.
Problem: My bars and points are not aligned.
Background: We have several machines and are measuring their number of on/of switches and the amount of time that each machine is running. We want both information together in one plot to save space, because we have several machines.
The data is aggregated by day or hour. Here's some sample data:
date <- seq(as.Date("2016-10-01"), as.Date("2016-10-10"), "day")
counts <- c(390, 377, 444, NA, NA, NA, NA, 162, 166, 145)
runtime <- c(56.8, 59.4, 51.0, NA, NA, NA, NA, 38.5, 40.9, 43.4)
df <- data.frame(date = date, counts = counts, runtime = runtime)
Here's what I tried so far:
par(mar = c(3,4,4,4) + 0.3)
barplot(df$runtime, col = "palegreen2", border = "NA", ylab = "runtime in [%]",
ylim = c(0,100), font.lab = 2)
par(new = TRUE)
ymax <- max(df$counts, na.rm = TRUE) * 1.05
plot(df$date, df$counts, type = "n", xlab = "", ylab = "", yaxt = "n",
main = "Machine 1", ylim = c(0, ymax))
abline(v = date, col = "red", lwd = 2.5)
lines(df$date, df$counts, col = "blue", lwd = 2)
points(df$date, df$counts, pch = 19, cex = 1.5)
axis(4)
mtext("Number of switching operations", side = 4, line = 3, font = 2)
I found some inspiration for two axis here: http://robjhyndman.com/hyndsight/r-graph-with-two-y-axes/
What can I do to get bars with their middle aligned with the points of the lineplot?
The problem you are running into is the call to the second plot function after the barplot. This is shifting/resizing the plotting canvas which is causing the shift in the subsequent points.
Here is a quick work-around that just rescales the points and lines onto the barplot. It saves the barplot as an object, which stores x-axis locations for the mid-points of the bars. Then, when you plot the abline, lines and points using 'bp' as the x-axis variable, they will be correctly aligned.
ymax <- max(df$counts, na.rm = TRUE) * 1.05
par(mar=c(4.1,5.1,2.1,5.1))
bp <- barplot(df$runtime, col = "palegreen2", border = "NA", ylab = "runtime in [%]",
ylim = c(0,100), font.lab = 2, xlim=c(0.2,12), )
barplot(df$runtime, col = "palegreen2", ylab = "runtime in [%]", border="NA",
ylim = c(0,100), font.lab = 2)
abline(v = bp, col = "red", lwd = 2.5)
lines(bp, df$counts/ymax*100, col = "blue", lwd = 2)
points(bp, df$counts/ymax*100, pch = 19, cex = 1.5)
axis(4,at=c(0,20,40,60,80,100), labels=c("0","100","200","300","400","500"))
mtext("Number of switching operations", side = 4, line = 3, font = 2)
axis(1, at=bp, labels=df$date)
#emilliman: Thank you for your patience and input! Your plot is not completely correct, because the scaling of the second y-axis does not fit the points' values, but your idea helped me to find a solution!
Here's my new code:
library(plyr)
ymax <- max(df$counts, na.rm = TRUE)
ymax_up <- round_any(ymax, 100, f = ceiling)
ylab <- ymax_up/5 * c(0:5)
par(mar = c(3,4,4,4) + 0.3)
bp <- barplot(df$runtime, col = "palegreen2", border = "NA", ylab = "runtime in [%]",
ylim = c(0,100), font.lab = 2, main = "Machine 1")
abline(v = bp, col = "red", lwd = 2.5)
lines(bp, 100/ymax_up * df$counts, col = "blue", lwd = 2)
points(bp, 100/ymax_up * df$counts, pch = 19, cex = 1.5)
axis(4,at=c(0,20,40,60,80,100), labels= as.character(ylab))
mtext("Number of switching operations", side = 4, line = 3, font = 2)
xlab <- as.character(df$date, format = "%b %d")
axis(1, at=bp, labels = xlab)
abline(h = c(0,100))
(http://i.imgur.com/9YtYGSD.png)
Maybe this is helpful for others who run into this problem.
Does anyone know how to extract the 'y' off the y-axis while preserving the variable names in the following plot:
par(mar = c(5,7,4,2) +.01)
matrix <- matrix(rnorm(100) ,ncol = 2, nrow =6)
y <- 1:6
par(mar = c(5,7,4,2) +.01)
plot(matrix[,1], y, cex = .8, pch = 20, xlab = "Standardized Mean Differences", col = "darkblue", main = "Balance Assessment", yaxt = "n")
points(matrix[,2], y, cex = .8, pch = 20, col ="cyan")
abline(v = 0, col = "gray50", lty =2)
text(y =1:6, par("usr")[1], labels = c("Var1", "Var2", "Var3", "Var4", "Var5", "Var6"), pos = 2, xpd = TRUE, srt = 0, cex = .8, font = 1, col = "blue")
It's minor, but it's driving me crazy. Thanks!
Just set ylab='' to remove it.