Here is my sample data:
Singer <- c("A","B","C","A","B","C")
Rank <- c(1,2,3,3,2,1)
Episode <- c(1,1,1,2,2,2)
Votes <- c(0.3,0.28,0.11,0.14,0.29,0.38)
data <- data_frame(Episode,Singer,Rank,Votes)
data$Episode <- as.character(data$Episode)
I would like to make a line graph to show the performance of each singer.
I tried to use ggplot2 like below:
ggplot(data,aes(x=Episode,y=Votes,group = Singer)) + geom_line()
I have two questions:
How can I format the y-axis as percentage?
How can I label each dot in this line graph as the values of "Rank", which allows me to show rank and votes in the same graph?
To label each point use:
geom_label(aes(label = Rank))
# or
geom_text(aes(label = Rank), nudge_y = .01, nudge_x = 0)
To format the axis labels use:
scale_y_continuous(labels = scales::percent_format())
# or without package(scales):
scale_y_continuous(breaks = (seq(0, .4, .2)), labels = sprintf("%1.f%%", 100 * seq(0, .4, .2)), limits = c(0,.4))
Complete code:
library(ggplot2)
library(scales)
ggplot(data, aes(x = factor(Episode), y = Votes, group = Singer)) +
geom_line() +
geom_label(aes(label = Rank)) +
scale_y_continuous(labels = scales::percent_format())
Data:
Singer <- c("A","B","C","A","B","C")
Rank <- c(1,2,3,3,2,1)
Episode <- c(1,1,1,2,2,2)
Votes <- c(0.3,0.28,0.11,0.14,0.29,0.38)
data <- data_frame(Episode,Singer,Rank,Votes)
# no need to transform to character bc we use factor(Episode) in aes(x=..)
Related
I'm trying to plot box plots with normal distribution of the underlying data next to the plots in a vertical format like this:
This is what I currently have graphed from an excel sheet uploaded to R:
And the code associated with them:
set.seed(12345)
library(ggplot2)
library(ggthemes)
library(ggbeeswarm)
#graphing boxplot and quasirandom scatterplot together
ggplot(X8_17_20_R_20_60, aes(Type, Diameter)) +
geom_quasirandom(shape=20, fill="gray", color = "gray") +
geom_boxplot(fill="NA", color = c("red4", "orchid4", "dark green", "blue"),
outlier.color = "NA") +
theme_hc()
Is this possible in ggplot2 or R in general? Or is the only way this would be feasible is through something like OrignLab (where the first picture came from)?
You can do something similar to your example plot with the gghalves package:
library(gghalves)
n=0.02
ggplot(iris, aes(Species, Sepal.Length)) +
geom_half_boxplot(center=TRUE, errorbar.draw=FALSE,
width=0.5, nudge=n) +
geom_half_violin(side="r", nudge=n) +
geom_half_dotplot(dotsize=0.5, alpha=0.3, fill="red",
position=position_nudge(x=n, y=0)) +
theme_hc()
There are a few ways to do this. To gain full control over the look of the plot, I would just calculate the curves and plot them. Here's some sample data that's close to your own and shares the same names, so it should be directly applicable:
set.seed(12345)
X8_17_20_R_20_60 <- data.frame(
Diameter = rnorm(4000, rep(c(41, 40, 42, 40), each = 1000), sd = 6),
Type = rep(c("AvgFeret", "CalcDiameter", "Feret", "MinFeret"), each = 1000))
Now we create a little data frame of normal distributions based on the parameters taken from each group:
df <- do.call(rbind, mapply( function(d, n) {
y <- seq(min(d), max(d), length.out = 1000)
data.frame(x = n - 5 * dnorm(y, mean(d), sd(d)) - 0.15, y = y, z = n)
}, with(X8_17_20_R_20_60, split(Diameter, Type)), 1:4, SIMPLIFY = FALSE))
Finally, we draw your plot and add a geom_path with the new data.
library(ggplot2)
library(ggthemes)
library(ggbeeswarm)
ggplot(X8_17_20_R_20_60, aes(Type, Diameter)) +
geom_quasirandom(shape = 20, fill = "gray", color = "gray") +
geom_boxplot(fill="NA", aes(color = Type), outlier.color = "NA") +
scale_color_manual(values = c("red4", "orchid4", "dark green", "blue")) +
geom_path(data = df, aes(x = x, y = y, group = z), size = 1) +
theme_hc()
Created on 2020-08-21 by the reprex package (v0.3.0)
I'm working with stock prices and trying to plot the price difference.
I created one using autoplot.zoo(), my question is, how can I manage to change the point shapes to triangles when they are above the upper threshold and to circles when they are below the lower threshold. I understand that when using the basic plot() function you can do these by calling the points() function, wondering how I can do this but with ggplot2.
Here is the code for the plot:
p<-autoplot.zoo(data, geom = "line")+
geom_hline(yintercept = threshold, color="red")+
geom_hline(yintercept = -threshold, color="red")+
ggtitle("AAPL vs. SPY out of sample")
p+geom_point()
We can't fully replicate without your data, but here's an attempt with some sample generated data that should be similar enough that you can adapt for your purposes.
# Sample data
data = data.frame(date = c(2001:2020),
spread = runif(20, -10,10))
# Upper and lower threshold
thresh <- 4
You can create an additional variable that determines the shape, based on the relationship in the data itself, and pass that as an argument into ggplot.
# Create conditional data
data$outlier[data$spread > thresh] <- "Above"
data$outlier[data$spread < -thresh] <- "Below"
data$outlier[is.na(data$outlier)] <- "In Range"
library(ggplot2)
ggplot(data, aes(x = date, y = spread, shape = outlier, group = 1)) +
geom_line() +
geom_point() +
geom_hline(yintercept = c(thresh, -thresh), color = "red") +
scale_shape_manual(values = c(17,16,15))
# If you want points just above and below# Sample data
data = data.frame(date = c(2001:2020),
spread = runif(20, -10,10))
thresh <- 4
data$outlier[data$spread > thresh] <- "Above"
data$outlier[data$spread < -thresh] <- "Below"
ggplot(data, aes(x = date, y = spread, shape = outlier, group = 1)) +
geom_line() +
geom_point() +
geom_hline(yintercept = c(thresh, -thresh), color = "red") +
scale_shape_manual(values = c(17,16))
Alternatively, you can just add the points above and below the threshold as individual layers with manually specified shapes, like this. The pch argument points to shape type.
# Another way of doing this
data = data.frame(date = c(2001:2020),
spread = runif(20, -10,10))
# Upper and lower threshold
thresh <- 4
ggplot(data, aes(x = date, y = spread, group = 1)) +
geom_line() +
geom_point(data = data[data$spread>thresh,], pch = 17) +
geom_point(data = data[data$spread< (-thresh),], pch = 16) +
geom_hline(yintercept = c(thresh, -thresh), color = "red") +
scale_shape_manual(values = c(17,16))
How do I stop the Y-axis changing during an animation?
The graph I made is at http://i.imgur.com/EKx6Tw8.gif
The idea is to make an animated heatmap of population and income each year. The problem is the y axis jumps to include 0 or not include the highest value sometime. How do you solidly set the axis values? I know this must be a common issue but I can't find the answer
The code to recreate it is
library(gapminder)
library(ggplot2)
library(devtools)
install_github("dgrtwo/gganimate")
library(gganimate)
library(dplyr)
mydata <- dplyr::select(gapminder, country,continent,year,lifeExp,pop,gdpPercap)
#bin years into 5 year bins
mydata$lifeExp2 <- as.integer(round((mydata$lifeExp-2)/5)*5)
mydata$income <- cut(mydata$gdpPercap, breaks=c(0,250,500,750,1000,1500,2000,2500,3000,3500,4500,5500,6500,7500,9000,11000,21000,31000,41000, 191000),
labels=c(0,250,500,750,1000,1500,2000,2500,3000,3500,4500,5500,6500,7500,9000,11000,21000,31000,41000))
sizePer <- mydata%>%
group_by(lifeExp2, income, year)%>%
mutate(popLikeThis = sum(pop))%>%
group_by(year)%>%
mutate(totalPop = sum(as.numeric(pop)))%>%
mutate(per = (popLikeThis/totalPop)*100)
sizePer$percent <- cut(sizePer$per, breaks=c(0,.1,.3,1,2,3,5,10,20,Inf),
labels=c(0,.1,.3,1,2.0,3,5,10,20))
saveGIF({
for(i in c(1997,2002,2007)){
print(ggplot(sizePer %>% filter(year == i),
aes(x = lifeExp2, y = income)) +
geom_tile(aes(fill = percent)) +
theme_bw()+
theme(legend.position="top", plot.title = element_text(size=30, face="bold",hjust = 0.5))+
coord_cartesian(xlim = c(20,85), ylim = c(0,21)) +
scale_fill_manual("%",values = c("#ffffcc","#ffeda0","#fed976","#feb24c","#fd8d3c","#fc4e2a","#e31a1c","#bd0026","#800026"),drop=FALSE)+
annotate(x=80, y=3, geom="text", label=i, size = 6) +
annotate(x=80, y=1, geom="text", label="#iamreddave", size = 5) +
ylab("Income") + # Remove x-axis label
xlab("Life Expenctancy")+
ggtitle("Worldwide Life Expectancy and Income")
)}
}, interval=0.7,ani.width = 900, ani.height = 600)
Solution:
Adding scale_y_discrete(drop = F) to the ggplot call. Answered by #bdemarest in comments.
I have a dataframe in R like this:
dat = data.frame(Sample = c(1,1,2,2,3), Start = c(100,300,150,200,160), Stop = c(180,320,190,220,170))
And I would like to plot it such that the x-axis is the position and the y-axis is the number of samples at that position, with each sample in a different colour. So in the above example you would have some positions with height 1, some with height 2 and one area with height 3. The aim being to find regions where there are a large number of samples and what samples are in that region.
i.e. something like:
&
---
********- -- **
where * = Sample 1, - = Sample 2 and & = Sample 3
My first try:
dat$Sample = factor(dat$Sample)
ggplot(aes(x = Start, y = Sample, xend = Stop, yend = Sample, color = Sample), data = dat) +
geom_segment(size = 2) +
geom_segment(aes(x = Start, y = 0, xend = Stop, yend = 0), size = 2, alpha = 0.2, color = "black")
I combine two segment geometries here. One draws the colored vertical bars. These show where Samples have been measured. The second geometry draws the grey bar below where the density of the samples is shown. Any comments to improve on this quick hack?
This hack may be what you're looking for, however I've greatly increased the size of the dataframe in order to take advantage of stacking by geom_histogram.
library(ggplot2)
dat = data.frame(Sample = c(1,1,2,2,3),
Start = c(100,300,150,200,160),
Stop = c(180,320,190,220,170))
# Reformat the data for plotting with geom_histogram.
dat2 = matrix(ncol=2, nrow=0, dimnames=list(NULL, c("Sample", "Position")))
for (i in seq(nrow(dat))) {
Position = seq(dat[i, "Start"], dat[i, "Stop"])
Sample = rep(dat[i, "Sample"], length(Position))
dat2 = rbind(dat2, cbind(Sample, Position))
}
dat2 = as.data.frame(dat2)
dat2$Sample = factor(dat2$Sample)
plot_1 = ggplot(dat2, aes(x=Position, fill=Sample)) +
theme_bw() +
opts(panel.grid.minor=theme_blank(), panel.grid.major=theme_blank()) +
geom_hline(yintercept=seq(0, 20), colour="grey80", size=0.15) +
geom_hline(yintercept=3, linetype=2) +
geom_histogram(binwidth=1) +
ylim(c(0, 20)) +
ylab("Count") +
opts(axis.title.x=theme_text(size=11, vjust=0.5)) +
opts(axis.title.y=theme_text(size=11, angle=90)) +
opts(title="Segment Plot")
png("plot_1.png", height=200, width=650)
print(plot_1)
dev.off()
Note that the way I've reformatted the dataframe is a bit ugly, and will not scale well (e.g. if you have millions of segments and/or large start and stop positions).
I am building charts that have two lines in the axis text. The first line contains the group name, the second line contains that group population. I build my axis labels as a single character string with the format "LINE1 \n LINE2". Is it possible to assign different font faces and sizes to LINE1 and LINE2, even though they are contained within a single character string? I would like LINE1 to be large and bolded, and LINE2 to be small and unbolded.
Here's some sample code:
Treatment <- rep(c('T','C'),each=2)
Gender <- rep(c('Male','Female'),2)
Response <- sample(1:100,4)
test_df <- data.frame(Treatment, Gender, Response)
xbreaks <- levels(test_df$Gender)
xlabels <- paste(xbreaks,'\n',c('POP1','POP2'))
hist <- ggplot(test_df, aes(x=Gender, y=Response, fill=Treatment, stat="identity"))
hist + geom_bar(position = "dodge") + scale_y_continuous(limits = c(0,
100), name = "") + scale_x_discrete(labels=xlabels, breaks = xbreaks) +
opts(
axis.text.x = theme_text(face='bold',size=12)
)
I tried this, but the result was one large, bolded entry, and one small, unbolded entry:
hist + geom_bar(position = "dodge") + scale_y_continuous(limits = c(0,
100), name = "") + scale_x_discrete(labels=xlabels, breaks = xbreaks) +
opts(
axis.text.x = theme_text(face=c('bold','plain'),size=c('15','10'))
)
Another possible solution is to create separate chart elements, but I don't think that ggplot2 has a 'sub-axis label' element available...
Any help would be very much appreciated.
Cheers,
Aaron
I also think that I could not to make the graph by only using ggplot2 features.
I would use grid.text and grid.gedit.
require(ggplot2)
Treatment <- rep(c('T','C'), each=2)
Gender <- rep(c('Male','Female'), 2)
Response <- sample(1:100, 4)
test_df <- data.frame(Treatment, Gender, Response)
xbreaks <- levels(test_df$Gender)
xlabels <- paste(xbreaks,'\n',c('',''))
hist <- ggplot(test_df, aes(x=Gender, y=Response, fill=Treatment,
stat="identity"))
hist + geom_bar(position = "dodge") +
scale_y_continuous(limits = c(0, 100), name = "") +
scale_x_discrete(labels=xlabels, breaks = xbreaks) +
opts(axis.text.x = theme_text(face='bold', size=12))
grid.text(label="POP1", x = 0.29, y = 0.06)
grid.text(label="POP2", x = 0.645, y = 0.06)
grid.gedit("GRID.text", gp=gpar(fontsize=8))
Please try to tune a code upon according to your environment (e.g. the position of sub-axis labels and the fontsize).
I found another simple solution below:
require(ggplot2)
Treatment <- rep(c('T','C'),each=2)
Gender <- rep(c('Male','Female'),2)
Response <- sample(1:100,4)
test_df <- data.frame(Treatment, Gender, Response)
xbreaks <- levels(test_df$Gender)
xlabels[1] <- expression(atop(bold(Female), scriptstyle("POP1")))
xlabels[2] <- expression(atop(bold(Male), scriptstyle("POP2")))
hist <- ggplot(test_df, aes(x=Gender, y=Response, fill=Treatment,
stat="identity"))
hist +
geom_bar(position = "dodge") +
scale_y_continuous(limits = c(0, 100), name = "") +
scale_x_discrete(label = xlabels, breaks = xbreaks) +
opts(
axis.text.x = theme_text(size = 12)
)
All,
Using Triad's cheat this is the closest I was able to get to solution on this one. Let me know if you have any questions:
library(ggplot2)
spacing <- 0 #We can adjust how much blank space we have beneath the chart here
labels1= paste('Group',c('A','B','C','D'))
labels2 = rep(paste(rep('\n',spacing),collapse=''),length(labels1))
labels <- paste(labels1,labels2)
qplot(1:4,1:4, geom="blank") +
scale_x_continuous(breaks=1:length(labels), labels=labels) + xlab("")+
opts(plot.margin = unit(c(1, 1, 3, 0.5), "lines"),
axis.text.x = theme_text(face='bold', size=14))
xseq <- seq(0.15,0.9,length.out=length(labels)) #Assume for now that 0.15 and 0.9 are constant plot boundaries
sample_df <- data.frame(group=rep(labels1,each=2),subgroup=rep(c('a','b'),4),pop=sample(1:10,8))
popLabs <- by(sample_df,sample_df$group,function(subData){
paste(paste(subData$subgroup,' [n = ', subData$pop,']',sep=''),collapse='\n')
})
gridText <- paste("grid.text(label='\n",popLabs,"',x=",xseq,',y=0.1)',sep='')
sapply(gridText, function(x){ #Evaluate parsed character string for each element of gridText
eval(parse(text=x))
})
grid.gedit("GRID.text", gp=gpar(fontsize=12))
Cheers,
Aaron