ggplot(data=dat, aes(x=time, y=total_bill, fill=time)) +
geom_bar(colour="black", fill="#DD8888", width=.8, stat="identity") +
guides(fill=FALSE) +
xlab("Time of day") + ylab("Total bill") +
ggtitle("Average bill for 2 people")
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
1.5、資料集計數條形圖
library(reshape2)
# Look at fist several rows
head(tips)#對如下資料集day計數繪圖
total_bill tip sex smoker day time size
1 16.99 1.01 Female No Sun Dinner 2
2 10.34 1.66 Male No Sun Dinner 3
3 21.01 3.50 Male No Sun Dinner 3
4 23.68 3.31 Male No Sun Dinner 2
5 24.59 3.61 Female No Sun Dinner 4
6 25.29 4.71 Male No Sun Dinner 4
#繪圖
ggplot(data=tips, aes(x=day)) +
geom_bar(stat="count")
ggplot(data=dat1, aes(x=time, y=total_bill, fill=sex)) +
geom_bar(colour="black", stat="identity",
position=position_dodge(),
size=.3) + # Thinner lines
scale_fill_hue(name="Sex of payer") + # Set legend title
xlab("Time of day") + ylab("Total bill") + # Set axis labels
ggtitle("Average bill for 2 people") + # Set title
theme_bw()
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
18、完美的線性圖
ggplot(data=dat1, aes(x=time, y=total_bill, group=sex, shape=sex, colour=sex)) +
geom_line(aes(linetype=sex), size=1) + # Set linetype by sex
geom_point(size=3, fill="white") + # Use larger points, fill with white
expand_limits(y=0) + # Set y range to include 0
scale_colour_hue(name="Sex of payer", # Set legend title
l=30) + # Use darker colors (lightness=30)
scale_shape_manual(name="Sex of payer",
values=c(22,21)) + # Use points with a fill color
scale_linetype_discrete(name="Sex of payer") +
xlab("Time of day") + ylab("Total bill") + # Set axis labels
ggtitle("Average bill for 2 people") + # Set title
theme_bw() +
theme(legend.position=c(.7, .4)) # Position legend inside
# This must go after theme_bw
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
2、ggplot2添加誤差棒和均值（means and error bars）
2.1、預設添加折線圖誤差棒
#準備資料
tg <- ToothGrowth
head(tg)
# summarySE provides the standard deviation, standard error of the mean, and a (default 95%) confidence interval
summarySE <- function(data=NULL, measurevar, groupvars=NULL, na.rm=FALSE,
conf.interval=.95, .drop=TRUE) {
library(plyr)
# New version of length which can handle NA's: if na.rm==T, don't count them
length2 <- function (x, na.rm=FALSE) {
if (na.rm) sum(!is.na(x))
else length(x)
}
# This does the summary. For each group's data frame, return a vector with
# N, mean, and sd
datac <- ddply(data, groupvars, .drop=.drop,
.fun = function(xx, col) {
c(N = length2(xx[[col]], na.rm=na.rm),
mean = mean (xx[[col]], na.rm=na.rm),
sd = sd (xx[[col]], na.rm=na.rm)
)
},
measurevar
)
# Rename the "mean" column
datac <- rename(datac, c("mean" = measurevar))
datac$se <- datac$sd / sqrt(datac$N) # Calculate standard error of the mean
# Confidence interval multiplier for standard error
# Calculate t-statistic for confidence interval:
# e.g., if conf.interval is .95, use .975 (above/below), and use df=N-1
ciMult <- qt(conf.interval/2 + .5, datac$N-1)
datac$ci <- datac$se * ciMult
return(datac)
}
tgc <- summarySE(tg, measurevar="len", groupvars=c("supp","dose"))
tgc
ggplot(tgc, aes(x=dose, y=len, colour=supp)) +
geom_errorbar(aes(ymin=len-se, ymax=len+se), width=.1) +
geom_line() +
geom_point()
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
2.2、折線圖誤差棒防重疊
pd <- position_dodge(0.1) # move them .05 to the left and right
ggplot(tgc, aes(x=dose, y=len, colour=supp)) +
geom_errorbar(aes(ymin=len-se, ymax=len+se), width=.1, position=pd) +
geom_line(position=pd) +
geom_point(position=pd)
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
2.3、按照95%置信區間添加折線圖誤差棒
# Use 95% confidence interval instead of SEM
ggplot(tgc, aes(x=dose, y=len, colour=supp)) +
geom_errorbar(aes(ymin=len-ci, ymax=len+ci), width=.1, position=pd) +
geom_line(position=pd) +
geom_point(position=pd)
set.seed(1234)
dat <- data.frame(cond = factor(rep(c("A","B"), each=200)),
rating = c(rnorm(200),rnorm(200, mean=.8)))
# View first few rows
head(dat)
ggplot(dat, aes(x=rating)) + geom_histogram(binwidth=.5)
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
3.2、輪廓直方圖
# Draw with black outline, white fill
ggplot(dat, aes(x=rating)) +
geom_histogram(binwidth=.5, colour="black", fill="white")
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
3.3、核密度圖
# Density curve
ggplot(dat, aes(x=rating)) + geom_density()
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
3.4、核密度圖結合直方圖
# Histogram overlaid with kernel density curve
ggplot(dat, aes(x=rating)) +
geom_histogram(aes(y=..density..), # Histogram with density instead of count on y-axis
binwidth=.5,
colour="black", fill="white") +
geom_density(alpha=.2, fill="#FF6666") # Overlay with transparent density plot
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
3.5、直方圖添加均值線
ggplot(dat, aes(x=rating)) +
geom_histogram(binwidth=.5, colour="black", fill="white") +
geom_vline(aes(xintercept=mean(rating, na.rm=T)), # Ignore NA values for mean
color="red", linetype="dashed", size=1)
# Density plots
ggplot(dat, aes(x=rating, colour=cond)) + geom_density()
# Density plots with semi-transparent fill
ggplot(dat, aes(x=rating, fill=cond)) + geom_density(alpha=.3)
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
3.11、多組資料直方圖添加均值線
# Find the mean of each group
library(plyr)
cdat <- ddply(dat, "cond", summarise, rating.mean=mean(rating))
cdat
#> cond rating.mean
#> 1 A -0.05775928
#> 2 B 0.87324927
# Overlaid histograms with means
ggplot(dat, aes(x=rating, fill=cond)) +
geom_histogram(binwidth=.5, alpha=.5, position="identity") +
geom_vline(data=cdat, aes(xintercept=rating.mean, colour=cond),
linetype="dashed", size=1)
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
3.12、多組資料直方圖添加均值線
# Density plots with means
ggplot(dat, aes(x=rating, colour=cond)) +
geom_density() +
geom_vline(data=cdat, aes(xintercept=rating.mean, colour=cond),
linetype="dashed", size=1)
ggplot(dat, aes(x=xvar, y=yvar, color=cond)) +
geom_point(shape=1) +
scale_colour_hue(l=50) + # Use a slightly darker palette than normal
geom_smooth(method=lm, # Add linear regression lines
se=FALSE) # Don't add shaded confidence region
library(ggplot2)
bp <- ggplot(PlantGrowth, aes(x=group, y=weight)) +
geom_boxplot()
bp + scale_x_discrete(limits=c("trt1","trt2","ctrl"))#設定順序
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
6.2、設定刻度标簽名稱
bp + scale_x_discrete(breaks=c("ctrl", "trt1", "trt2"),
labels=c("Control", "Treat 1", "Treat 2"))
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
6.3、隐藏網格線、刻度标簽、短标記線
# Hide x tick marks, labels, and grid lines
bp + scale_x_discrete(breaks=NULL)
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
6.4、設定刻度範圍
# 刻度包含0
bp + expand_limits(y=0)
# 刻度包含0和8
bp + expand_limits(y=c(0,8))
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
#刻度範圍為5到7.5
bp + ylim(5, 7.5)
# Using coord_cartesian "zooms" into the area
bp + coord_cartesian(ylim=c(5, 7.5))
# 刻度步長設定
bp + coord_cartesian(ylim=c(5, 7.5)) +
scale_y_continuous(breaks=seq(0, 10, 0.25)) # Ticks from 0-10, every .25
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
6.5、tick markers隐藏
bp + scale_y_continuous(breaks=seq(1,10,1/4))
# The breaks can be spaced unevenly
bp + scale_y_continuous(breaks=c(4, 4.25, 4.5, 5, 6,8))
# Suppress ticks and gridlines
bp + scale_y_continuous(breaks=NULL)
# Hide tick marks and labels (on Y axis), but keep the gridlines
bp + theme(axis.ticks = element_blank(), axis.text.y = element_blank())
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
6.6、刻度機關轉換為對數, 指數、開方等
set.seed(201)
n <- 100
dat <- data.frame(
xval = (1:n+rnorm(n,sd=5))/20,
yval = 2*2^((1:n+rnorm(n,sd=5))/20)
)
# A scatterplot with regular (linear) axis scaling
sp <- ggplot(dat, aes(xval, yval)) + geom_point()
# Change font options:
# X-axis label: bold, red, and 20 points
# X-axis tick marks: rotate 90 degrees CCW, move to the left a bit (using vjust,
# since the labels are rotated), and 16 points
bp + theme(axis.title.x = element_text(, colour="#990000", size=20),
axis.text.x = element_text(angle=90, vjust=0.5, size=16))
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
library(scales) # Need the scales package
bp + scale_y_continuous(labels=percent) +
scale_x_discrete(labels=abbreviate) # In this particular case, it has no effect
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
7、ggplot2圖例設定
7.1、預設圖例
library(ggplot2)
bp <- ggplot(data=PlantGrowth, aes(x=group, y=weight, fill=group)) + geom_boxplot()
bp
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
7.2、三種方法不顯示圖例
# Remove legend for a particular aesthetic (fill)
bp + guides(fill=FALSE)
# It can also be done when specifying the scale
bp + scale_fill_discrete(guide=FALSE)
# This removes all legends
bp + theme(legend.position="none")
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
7.3、修改圖例顯示順序
bp + scale_fill_discrete(breaks=c("trt1","ctrl","trt2"))
df1 <- data.frame(
sex = factor(c("Female","Female","Male","Male")),
time = factor(c("Lunch","Dinner","Lunch","Dinner"), levels=c("Lunch","Dinner")),
total_bill = c(13.53, 16.81, 16.24, 17.42)
)
lp1 <- ggplot(data=df1, aes(x=time, y=total_bill, group=sex, shape=sex, colour=sex)) + geom_line() + geom_point()
# Here's what happens if you just specify colour
lp1 + scale_colour_discrete(name ="Payer",
breaks=c("Female", "Male"),
labels=c("Woman", "Man"))
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
7.7、圖例标題字号、顔色設定
# Title appearance
bp + theme(legend.title = element_text(colour="blue", size=16, ))
# Label appearance
bp + theme(legend.text = element_text(colour="blue", size = 16, face = "bold"))
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
7.8、圖例添加背景色
bp + theme(legend.background = element_rect(fill="gray90", size=.5, linetype="dotted"))
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
7.9、圖例位置
bp + theme(legend.position="top")
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
# Position legend in graph, where x,y is 0,0 (bottom left) to 1,1 (top right)
bp + theme(legend.position=c(.5, .5))
# Set the "anchoring point" of the legend (bottom-left is 0,0; top-right is 1,1)
# Put bottom-left corner of legend box in bottom-left corner of graph
bp + theme(legend.justification=c(0,0), legend.position=c(0,0))
# Put bottom-right corner of legend box in bottom-right corner of graph
bp + theme(legend.justification=c(1,0), legend.position=c(1,0))
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
8、ggplot2添加輔助線
8.1、所有柱子添加水準直線
# Some sample data
dat <- read.table(header=TRUE, text='
cond result
control 10
treatment 11.5
')
library(ggplot2)
bp <- ggplot(dat, aes(x=cond, y=result)) +
geom_bar(position=position_dodge(), stat="identity")
# Make the line red and dashed
bp + geom_hline(aes(yintercept=12), colour="#990000", linetype="dashed")
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
dat <- read.table(header=TRUE, text='
cond group result hline
control A 10 9
treatment A 11.5 12
control B 12 9
treatment B 14 12
')
# Define basic bar plot
bp <- ggplot(dat, aes(x=cond, y=result, fill=group)) +
geom_bar(position=position_dodge(), stat="identity")
# The error bars get plotted over one another -- there are four but it looks
# like two
bp + geom_errorbar(aes(ymax=hline, ymin=hline), linetype="dashed")
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
8.2、每個柱子各自添加輔助線
# Draw separate hlines for each bar. First add another column to dat
dat$hline <- c(9,12)
# Can get the same result, even if we get the hline values from a second data frame
# Define data frame with hline
dat_hlines <- data.frame(cond=c("control","treatment"), hline=c(9,12))
d
# The bars are from dat, but the lines are from dat_hlines
bp + geom_errorbar(data=dat_hlines, aes(y=NULL, ymax=hline, ymin=hline), colour="#AA0000")
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
dat <- read.table(header=TRUE, text='
cond group result hline
control A 10 11
treatment A 11.5 12
control B 12 12.5
treatment B 14 15
')
# Define basic bar plot
bp <- ggplot(dat, aes(x=cond, y=result, fill=group)) +
geom_bar(position=position_dodge(), stat="identity")
bp
bp + geom_errorbar(aes(ymax=hline, ymin=hline), linetype="dashed",
position=position_dodge())
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
8.3、分面圖中添加輔助線
dat <- read.table(header=TRUE, text='
cond xval yval
control 11.5 10.8
control 9.3 12.9
control 8.0 9.9
control 11.5 10.1
control 8.6 8.3
control 9.9 9.5
control 8.8 8.7
control 11.7 10.1
control 9.7 9.3
control 9.8 12.0
treatment 10.4 10.6
treatment 12.1 8.6
treatment 11.2 11.0
treatment 10.0 8.8
treatment 12.9 9.5
treatment 9.1 10.0
treatment 13.4 9.6
treatment 11.6 9.8
treatment 11.5 9.8
treatment 12.0 10.6
')
library(ggplot2)
sp <- ggplot(dat, aes(x=xval, y=yval, colour=cond)) + geom_point()
library(dplyr)
lines <- dat %>%
group_by(cond) %>%
summarise(
x = mean(xval),
ymin = min(yval),
ymax = max(yval)
)
dat_vlines <- data.frame(cond=levels(dat$cond), xval=c(10,11.5))
spf <- sp + facet_grid(. ~ cond)
spf + geom_hline(aes(yintercept=10)) +
geom_linerange(aes(x=x, y=NULL, ymin=ymin, ymax=ymax), data=lines)
hp <- ggplot(tips, aes(x=total_bill)) + geom_histogram(binwidth=2,colour="white")
hp + facet_grid(sex ~ smoker, scales="free", space="free")
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
10、ggplot2拼圖
#現在已經有很多拼圖包了，寫這個書的時時間比較早了，這裡整的有點麻煩
multiplot <- function(..., plotlist=NULL, file, cols=1, layout=NULL) {
library(grid)
# Make a list from the ... arguments and plotlist
plots <- c(list(...), plotlist)
numPlots = length(plots)
# If layout is NULL, then use 'cols' to determine layout
if (is.null(layout)) {
# Make the panel
# ncol: Number of columns of plots
# nrow: Number of rows needed, calculated from # of cols
layout <- matrix(seq(1, cols * ceiling(numPlots/cols)),
ncol = cols, nrow = ceiling(numPlots/cols))
}
if (numPlots==1) {
print(plots[[1]])
} else {
# Set up the page
grid.newpage()
pushViewport(viewport(layout = grid.layout(nrow(layout), ncol(layout))))
# Make each plot, in the correct location
for (i in 1:numPlots) {
# Get the i,j matrix positions of the regions that contain this subplot
matchidx <- as.data.frame(which(layout == i, arr.ind = TRUE))
print(plots[[i]], vp = viewport(layout.pos.row = matchidx$row,
layout.pos.col = matchidx$col))
}
}
}
library(ggplot2)
# This example uses the ChickWeight dataset, which comes with ggplot2
# First plot
p1 <- ggplot(ChickWeight, aes(x=Time, y=weight, colour=Diet, group=Chick)) +
geom_line() +
ggtitle("Growth curve for individual chicks")
# Second plot
p2 <- ggplot(ChickWeight, aes(x=Time, y=weight, colour=Diet)) +
geom_point(alpha=.3) +
geom_smooth(alpha=.2, size=1) +
ggtitle("Fitted growth curve per diet")
# Third plot
p3 <- ggplot(subset(ChickWeight, Time==21), aes(x=weight, colour=Diet)) +
geom_density() +
ggtitle("Final weight, by diet")
# Fourth plot
p4 <- ggplot(subset(ChickWeight, Time==21), aes(x=weight, fill=Diet)) +
geom_histogram(colour="black", binwidth=50) +
facet_grid(Diet ~ .) +
ggtitle("Final weight, by diet") +
theme(legend.position="none") # No legend (redundant in this graph)
multiplot(p1, p2, p3, p4, cols=2)
R可視化26|R Graphics Cookbook-ggplot2。。。。。。目錄
11、ggplot2圖形儲存
11.1、R預設儲存方式
# 6x3 inches
pdf("plots.pdf", width=6, height=3)
# 10x6 cm
pdf("plots.pdf", width=10/2.54, height=6/2.54)
plot(...)
plot(...)
dev.off()#dev.off() command to tell R that you are finished plotting; otherwise your graph will not show up.
#eg
pdf("plots.pdf", width=6, height=3)
ggplot(dat, aes(x=rating, fill=cond)) + geom_density(alpha=.3)
dev.off()
