I'm trying to replace the x-axis labels "A0" and "A1" by one "A" which can be placed in the middle of "A0" and "A1". It would be better if there is a method which works like the following question:
grouping of axis labels ggplot2
By that, I mean to redraw the x-axis only for each group, and leave a blank between groups.
Here is the code I'm working on:
y = 1*round(runif(20)*10,1)
x1 = c("A","B")
x2 = c(0,1)
x = expand.grid(x1,x2)
xy = cbind(x,y)
xy$z = paste(xy$Var1,xy$Var2,sep="")
p <- ggplot(xy, aes(x=factor(z), y=y,fill=factor(Var2)))
p + geom_boxplot() + geom_jitter(position=position_jitter(width=.2)) + theme_bw() + xlab("X") + ylab("Y") + scale_fill_discrete(name="Var2",breaks=c(0, 1),labels=c("T", "C"))
Try this. No need for the variable z, just use position="dodge":
p <- ggplot(xy, aes(x=factor(Var1), y=y,fill=factor(Var2)))
p + geom_boxplot(position="dodge") + geom_jitter(position=position_jitter(width=.2)) + theme_bw() + xlab("X") + ylab("Y") + scale_fill_discrete(name="Var2",breaks=c(0, 1),labels=c("T", "C"))
Related
I have a plot like this:
p<-ggplot() +
geom_line(data= myData, aes(x = myData$x , y = myData$y)) +
scale_x_log10()+
scale_y_log10()
My x value is seq(9880000, 12220000, 10000)
There is only one break on the x-axis of the plot, what should I do if to get at least 3 breaks on the plot x-axis?
Here is fully reproducible example of the original poster's problem where a log-scaled plot only displays one break value on the x-axis. I demonstrate three possible solutions below.
library(ggplot2)
# Create a reproducible example data.frame using R functions.
x = seq(9880000, 12220000, 10000)
# Use set.seed() so that anyone who runs this code
# will get the same sequence of 'random' values.
set.seed(31415)
y = cumsum(runif(n=length(x), min=-1e5, max=1e5)) + 1e6
dat = data.frame(x=x, y=y)
# Original poster's plot.
p1 = ggplot(data=dat, aes(x=x, y=y)) +
geom_line() +
scale_x_log10() +
scale_y_log10() +
labs(title="1. Plot has only one x-axis break.")
# Add extra x-axis breaks manually.
x_breaks = c(10^7.0, 10^7.04, 10^7.08)
p2 = ggplot(data=dat, aes(x=x, y=y)) +
geom_line() +
scale_x_log10(breaks=x_breaks) +
scale_y_log10() +
labs(title="2. Add some x-axis breaks manually.")
# Add extra x-axis breaks in semi-automated manner.
x_breaks = 10^pretty(log10(x))
x_labels = formatC(x_breaks, format = "e", digits = 2)
p3 = ggplot(data=dat, aes(x=x, y=y)) +
geom_line() +
scale_x_log10(breaks=x_breaks, labels=x_labels) +
scale_y_log10() +
labs(title="3. Create x-axis breaks with R functions.")
# Skip the log10 scale because the x-values don't span multiple orders of magnitude.
p4 = ggplot(data=dat, aes(x=x, y=y)) +
geom_line() +
scale_y_log10() +
labs(title="4. Check appearance without log10 scale for x-axis.")
library(gridExtra)
ggsave("example.png", plot=arrangeGrob(p1, p2, p3, p4, nrow=2),
width=10, height=5, dpi=150)
I add: scale_x_log10(breaks=seq(9880000, 12220000, 1000000)).
This is my reproducible example:
library(random)
library(ggplot2)
z <- randomStrings(n=235, len=5, digits=TRUE, upperalpha=TRUE, loweralpha=TRUE, unique=TRUE, check=TRUE)
x <- seq(9880000, 12220000, 10000)
y <- randomNumbers(n=235, min=9880000, max=12220000, col=1)
df <- data.frame(z, x, y)
head(df)
V1 x V1.1
1 378VO 9880000 11501626
2 AStRK 9890000 10929705
3 sotp4 9900000 11305700
4 AS4DR 9910000 11302110
5 7iFdk 9920000 11611918
6 HIS7z 9930000 11175074
p<-ggplot() + geom_line(data= df, aes(x = df$x , y = df$V1.1)) + scale_y_log10()
p + scale_x_log10(breaks=seq(9880000, 12220000, 1000000))
Hope it is useful...
Add this between your parenthesis: breaks=seq(specify, breaks, here)
For example, if you wanted a break at 0, 10, 100:
scale_x_log10((breaks=seq(0,10,100))
Thi is my data:
x <- c("22-01-16","26-01-16","28-01-16","01-02-16","05-02-16","16-02-16","17-03-16","18-03-16","04-04-16","05-04-16","06-04-16","08-04-16")
y <- c(97.14,75,54.44,70.45,110.56,66.3,178.76,171.90,419.41,424,518.63,242.17)
z <- c("ADCP","ADCP","ADCP","ADCP","ADCP","ADCP","ADCP","ADCP","ADCP","ADCP","ADCP","ADCP")
So I make the dataframe
Datos <- data.frame(x)
Datos$Caudal <- y
Datos$Tipo <- z
Datos$Fecha <- as.Date(Datos$x, "%d-%m-%y")
and plot using ggplot2
Serie_Caudal <-
ggplot(Datos, aes(Fecha, Caudal)) +
geom_line(size=1, colour="red") +
geom_point(shape=23,size=1, colour="blue",fill = "blue") +
scale_x_date(date_breaks = "1 week",labels = date_format("%d/%b"))+
xlab("Fecha") + ylab(bquote('Caudal ('*m^3~s^-1*')')) +
ggtitle("Caudales Diarios (01-06/2016)")
Serie_Caudal
I try to plot a legend but i can´t the way, i try use Melt but my data change in a way i can´t plot. Also try scale_fill_manual but the legend don´t show up. I want to know if there is a way to put a legend manualy.
The legend must show a blue point and ADCP
This shows only a blue dot.
ggplot(aes(Fecha, Caudal, colour = "ADCP"), data = Datos) +
geom_point() +
geom_point(shape=23,size=1,color="blue",fill = "blue") +
scale_color_manual(values = c("ADCP"="blue"),name = "") +
geom_line(color="red", size=1) +
scale_x_date(date_breaks = "1 week",labels = date_format("%d/%b")) +
xlab("Fecha") + ylab(bquote('Caudal ('*m^3~s^-1*')')) +
ggtitle("Caudales Diarios (01-06/2016)")
I have this kind of table:
dt <- data.table(titles=c('B','C','A','C'),
labs =c('b','c','a','c'),
values=c( 3, 2, 3, 4))
In order to plot the points without collapsing and re-ordering, I had to do the following trick with ggplot(): instead of aes(x=titles, y=values) I use aes(x=seq_len(nrow(dt)), y=values):
ggplot(data = dt,
aes(x=seq_len(nrow(dt)), y=values)) +
geom_point() +
geom_text(aes(label=labs)) +
scale_x_discrete(labels=dt$titles) + xlab('titles')
Now I want to have labels not for all points but only for a subset of them (for example, where values>2). This call doesn't work:
ggplot(data = dt,
aes(x=seq_len(nrow(dt)), y=values)) +
geom_point() +
geom_text(data=subset(dt, values>2), aes(label=labs)) +
scale_x_discrete(labels=dt$titles) + xlab('titles')
# Error: Aesthetics must be either length 1 or the same as the data (2): label, x, y
How to call geom_text() in this case?
I think you are looking for the inherit.aes=F option:
dt2 <- subset(dt, values>2)
ggplot(data = dt,
aes(x=seq_len(nrow(dt)), y=values)) +
geom_point() +
geom_text(data=dt2, aes(x=values, y=values, label=labs), inherit.aes=F) +
scale_x_discrete(labels=dt$titles) + xlab('titles')
I am trying to create a Cleveland Dot Plot given for two categories in this case J and K. The problem is the elements A,B,C are in both categories so R keeps farting. I have made a simple example:
x <- c(LETTERS[1:10],LETTERS[1:3],LETTERS[11:17])
type <- c(rep("J",10),rep("K",10))
y <- rnorm(n=20,10,2)
data <- data.frame(x,y,type)
data
data$type <- as.factor(data$type)
nameorder <- data$x[order(data$type,data$y)]
data$x <- factor(data$x,levels=nameorder)
ggplot(data, aes(x=y, y=x)) +
geom_segment(aes(yend=x), xend=0, colour="grey50") +
geom_point(size=3, aes(colour=type)) +
scale_colour_brewer(palette="Set1", limits=c("J","K"), guide=FALSE) +
theme_bw() +
theme(panel.grid.major.y = element_blank()) +
facet_grid(type ~ ., scales="free_y", space="free_y")
Ideally, I would want a dot plot for both categories(J,K) individually with each factor(vector x) decreasing with respect to the y vector. What ends up happening is that both categories aren't going from biggest to smallest and are erratic at the end instead. Please help!
Unfortunately factors can only have one set of levels. The only way i've found to do this is actually to create two separate data.frames from your data and re-level the factor in each. For example
data <- data.frame(
x = c(LETTERS[1:10],LETTERS[1:3],LETTERS[11:17]),
y = rnorm(n=20,10,2),
type= c(rep("J",10),rep("K",10))
)
data$type <- as.factor(data$type)
J<-subset(data, type=="J")
J$x <- reorder(J$x, J$y, max)
K<-subset(data, type=="K")
K$x <- reorder(K$x, K$y, max)
Now we can plot them with
ggplot(mapping = aes(x=y, y=x, xend=0, yend=x)) +
geom_segment(data=J, colour="grey50") +
geom_point(data=J, size=3, aes(colour=type)) +
geom_segment(data=K, colour="grey50") +
geom_point(data=K, size=3, aes(colour=type)) +
theme_bw() +
theme(panel.grid.major.y = element_blank()) +
facet_grid(type ~ ., scales="free_y", space="free_y")
which results in
I have data where I look at the difference in growth between a monoculture and a mixed culture for two different species. Additionally, I made a graph to make my data clear.
I want a barplot with error bars, the whole dataset is of course bigger, but for this graph this is the data.frame with the means for the barplot.
plant species means
Mixed culture Elytrigia 0.886625
Monoculture Elytrigia 1.022667
Monoculture Festuca 0.314375
Mixed culture Festuca 0.078125
With this data I made a graph in ggplot2, where plant is on the x-axis and means on the y-axis, and I used a facet to divide the species.
This is my code:
limits <- aes(ymax = meansS$means + eS$se, ymin=meansS$means - eS$se)
dodge <- position_dodge(width=0.9)
myplot <- ggplot(data=meansS, aes(x=plant, y=means, fill=plant)) + facet_grid(. ~ species)
myplot <- myplot + geom_bar(position=dodge) + geom_errorbar(limits, position=dodge, width=0.25)
myplot <- myplot + scale_fill_manual(values=c("#6495ED","#FF7F50"))
myplot <- myplot + labs(x = "Plant treatment", y = "Shoot biomass (gr)")
myplot <- myplot + opts(title="Plant competition")
myplot <- myplot + opts(legend.position = "none")
myplot <- myplot + opts(panel.grid.minor=theme_blank(), panel.grid.major=theme_blank())
So far it is fine. However, I want to add two different horizontal lines in the two facets. For that, I used this code:
hline.data <- data.frame(z = c(0.511,0.157), species = c("Elytrigia","Festuca"))
myplot <- myplot + geom_hline(aes(yintercept = z), hline.data)
However if I do that, I get a plot were there are two extra facets, where the two horizontal lines are plotted. Instead, I want the horizontal lines to be plotted in the facets with the bars, not to make two new facets. Anyone a idea how to solve this.
I think it makes it clearer if I put the graph I create now:
Make sure that the variable species is identical in both datasets. If it a factor in one on them, then it must be a factor in the other too
library(ggplot2)
dummy1 <- expand.grid(X = factor(c("A", "B")), Y = rnorm(10))
dummy1$D <- rnorm(nrow(dummy1))
dummy2 <- data.frame(X = c("A", "B"), Z = c(1, 0))
ggplot(dummy1, aes(x = D, y = Y)) + geom_point() + facet_grid(~X) +
geom_hline(data = dummy2, aes(yintercept = Z))
dummy2$X <- factor(dummy2$X)
ggplot(dummy1, aes(x = D, y = Y)) + geom_point() + facet_grid(~X) +
geom_hline(data = dummy2, aes(yintercept = Z))