使用geom_text在geom_point上组织文本 [英] organize text on geom_point using geom_text
问题描述
我有一个线条图,有些时间点难以单独用颜色区分,因此我想标记图上的时间点,但标签重叠(请参见下图)很难阅读标签。
剧情目前看起来像这样,
我想知道是否有办法堆叠标签或某种方式(脚本)可以确保它们不重叠。就像这样, $ b
/ p>
任何帮助将不胜感激。
以下是我用来生成图的代码,
$ p $
require(ggplot2)
require(plyr)
require(reshape)
#create示例数据
set.seed(666)
dfn< - data.frame(
Referral = seq(as.Date(2007-01-15),len = 26,by =23天),
VISIT01 = seq(as.Date(2008-06-15),len = 24,by =15 day)[sample(30,26)],
VISIT02 = seq(as.Date(2008-12-15),len = 24,by =15 day)[sample(30,26)],
VISIT03 = seq(as.Date (2009-01-01),len = 24,by =15 day)[sample(30,26)],
VISIT04 = seq(as.Date(2009-03-30)) ,len = 24,by =60 day)[sample(30,26)],
VISIT05 = seq(as.Date(2010-11-30),len = 24,by =6 (样本(30,26)],
VISIT06 = seq(as.Date(2011-01-30),len = 24,by =6 day)[样本(30,26) )],
Discharge = seq(as.Date(2012-03-30),len = 24,by =30 d ay)[sample(30,26)],
Patient = factor(1:26,labels = LETTERS),
openCase = rep(0:1,100)[sample(100,26) ])
#设置今天的数据,用于没有放电日期的情况
dfn $放电[is.na(dfn $放电)] < - as.Date(2014- (dfn,id = c('Patient','openCase'),variable_name =Visit)
名称(mdfn)[4 ]< - 'Year'#重命名
#通过dfn中的'Referral'命令mdfn中的数据
mdfn $患者< - 因素(mdfn $患者,等级=
(dfn $ Patient [order(dfn $ Referral)]),ordered = TRUE)
#数据集的子集,以避免未关闭的情况出现'Discharge'
mdfn2 < - 子集(mdfn,!(Visit ==Discharge&年份> as.Date(2014-01-01)))
#现在看起来的情节
ggplot(mdfn,aes(Year,Patient))+
geom_blank ()+
geom_line(data = mdfn [mdfn $ openCase == 0,],color =black)+
geom_line(data = mdfn [mdfn $ openCase == 1,],color = gray)+
geom_point(data = mdfn2,aes(color = Visit),size = 4,shape = 124)+
geom_text(data = mdfn2,mapping = aes(x = Year,y =患者,
label = substr(Visit,1,7),color = Visit),size = 2,
vjust = - 。4,hjust = - 。1,angle = 00)
您可以根据数值更改标签的垂直位置
关键是:
y =(as .numeric(Patient)+ 0.25 * as.numeric(Visit)%% 3)-0.12
目前产生:
根据Visit(%% 3)的值,可以增加或减少3个不同级别
每个级别由一个quar ter标签之间的距离(0.25)
第一个标签是0.12,低于水平线
第二个0.12以上
require(ggplot2)
require (plyr)
require(reshape)
#创建示例数据
set.seed(666)
dfn< - data.frame(
Referral = seq(as .Date(2007-01-15),len = 26,by =23 day),
VISIT01 = seq(as.Date(2008-06-15),len = 24,by =15天)[sample(30,26)],
VISIT02 = seq(as.Date(2008-12-15),len = 24,by =15 day)[sample (30,26)],
VISIT03 = seq(as.Date(2009-01-01),len = 24,by =15 day)[sample(30,26)],
VISIT04 = seq(as.Date(2009-03-30),len = 24,by =60 day)[sample(30,26)],
VISIT05 = seq(as.Date 2010-11-30),len = 24,by =6 day)[sample(30,26)],
VISIT06 = seq(as.Date (2011-01-30),len = 24,by =6 day)[sample(30,26)],
Discharge = seq(as.Date(2012-03-30)) ,len = 24,by =30 day)[sample(30,26)],
Patient = factor(1:26,labels = LETTERS),
openCase = rep(0:1, 100)[样本(100,26)])
#设定今日没有出院日期的数据
dfn $出院[出院(dfn $出院)] < ; - as.Date(2014-01-30)
mdfn< - melt(dfn,id = c('Patient','openCase'),variable_name =Visit)
名称(mdfn)[4]< - 'Year'#重命名
#通过dfn中的'Referral'命令mdfn中的数据
mdfn $患者< - 因子(mdfn $ Patient,levels =
(dfn $ Patient [order(dfn $ Referral)]),ordered = TRUE)
#数据集的子集,避免未关闭的病例出现'Discharge'
mdfn2< - subset(mdfn,!(Visit ==Discharge&年份> as.Date(2014-01-01)))
#现在看起来的情节
ggplot(mdfn,aes(Year,Patient))+
geom_blank ()+
geom_line(data = mdfn [mdfn $ openCase == 0,],color =black)+
geom_line(data = mdfn [mdfn $ openCase == 1,],color = gray)+
geom_point(data = mdfn2,aes(color = Visit),size = 4,shape = 124)+
geom_text(data = mdfn2,mapping = aes(x = Year,y =(as.numeric(Patient)+ 0.25 * as.numeric(Visit)%% 3)-0.12,
label = substr(Visit,1,7),color = Visit),size = 2,
hjust = - 。1,angle = 00)
I have a line plot with some time points that are hard to distinguish by the coloring alone and I would therefore like to label the time points on the plot, but the labels overlap (see plot below) in a way where it is hard to read the labels.
The plot currently look like this,
I wonder if there is a way to 'stack' the labels or some way (script) that can ensure they do not overlap. Something like this,
Any help would be appreciated.
Here is the code I used to produce the plot,
require(ggplot2)
require(plyr)
require(reshape)
# create sample data
set.seed(666)
dfn <- data.frame(
Referral = seq(as.Date("2007-01-15"), len= 26, by="23 day"),
VISIT01 = seq(as.Date("2008-06-15"), len= 24, by="15 day")[sample(30, 26)],
VISIT02 = seq(as.Date("2008-12-15"), len= 24, by="15 day")[sample(30, 26)],
VISIT03 = seq(as.Date("2009-01-01"), len= 24, by="15 day")[sample(30, 26)],
VISIT04 = seq(as.Date("2009-03-30"), len= 24, by="60 day")[sample(30, 26)],
VISIT05 = seq(as.Date("2010-11-30"), len= 24, by="6 day")[sample(30, 26)],
VISIT06 = seq(as.Date("2011-01-30"), len= 24, by="6 day")[sample(30, 26)],
Discharge = seq(as.Date("2012-03-30"), len= 24, by="30 day")[sample(30, 26)],
Patient = factor(1:26, labels = LETTERS),
openCase = rep(0:1, 100)[sample(100, 26)])
# set today's data for cases that do not have an Discharge date
dfn$Discharge[ is.na(dfn$Discharge) ] <- as.Date("2014-01-30")
mdfn <- melt(dfn, id=c('Patient', 'openCase'), variable_name = "Visit")
names(mdfn)[4] <- 'Year' # rename
# order data in mdfn by 'Referral' in dfn
mdfn$Patient <- factor(mdfn$Patient,levels =
(dfn$Patient[order(dfn$Referral)]),ordered = TRUE)
# subset a dataset to avoid 'Discharge' for cases that are not closed
mdfn2 <- subset(mdfn,!(Visit=="Discharge" & Year > as.Date("2014-01-01")))
# the plot as it looks now
ggplot(mdfn, aes(Year, Patient)) +
geom_blank() +
geom_line(data = mdfn[mdfn$openCase == 0,], colour = "black") +
geom_line(data = mdfn[mdfn$openCase == 1,], colour = "grey") +
geom_point(data = mdfn2, aes(colour = Visit), size = 4, shape = 124) +
geom_text(data=mdfn2, mapping=aes(x=Year, y=Patient,
label=substr(Visit, 1, 7), colour=Visit), size=2,
vjust=-.4, hjust=-.1, angle = 00)
You can change the vertical location of the label according to the numeric value of Visit.
The key is:
y=(as.numeric(Patient)+0.25*as.numeric(Visit)%%3)-0.12
This currently produces:
3 different levels according to values of Visit (%%3), which you can increase or decrease
each level is separated by a quarter of the distance between y labels (0.25)
the first label is 0.12 below the horizontal line
the second is 0.12 above
require(ggplot2)
require(plyr)
require(reshape)
# create sample data
set.seed(666)
dfn <- data.frame(
Referral = seq(as.Date("2007-01-15"), len= 26, by="23 day"),
VISIT01 = seq(as.Date("2008-06-15"), len= 24, by="15 day")[sample(30, 26)],
VISIT02 = seq(as.Date("2008-12-15"), len= 24, by="15 day")[sample(30, 26)],
VISIT03 = seq(as.Date("2009-01-01"), len= 24, by="15 day")[sample(30, 26)],
VISIT04 = seq(as.Date("2009-03-30"), len= 24, by="60 day")[sample(30, 26)],
VISIT05 = seq(as.Date("2010-11-30"), len= 24, by="6 day")[sample(30, 26)],
VISIT06 = seq(as.Date("2011-01-30"), len= 24, by="6 day")[sample(30, 26)],
Discharge = seq(as.Date("2012-03-30"), len= 24, by="30 day")[sample(30, 26)],
Patient = factor(1:26, labels = LETTERS),
openCase = rep(0:1, 100)[sample(100, 26)])
# set today's data for cases that do not have an Discharge date
dfn$Discharge[ is.na(dfn$Discharge) ] <- as.Date("2014-01-30")
mdfn <- melt(dfn, id=c('Patient', 'openCase'), variable_name = "Visit")
names(mdfn)[4] <- 'Year' # rename
# order data in mdfn by 'Referral' in dfn
mdfn$Patient <- factor(mdfn$Patient,levels =
(dfn$Patient[order(dfn$Referral)]),ordered = TRUE)
# subset a dataset to avoid 'Discharge' for cases that are not closed
mdfn2 <- subset(mdfn,!(Visit=="Discharge" & Year > as.Date("2014-01-01")))
# the plot as it looks now
ggplot(mdfn, aes(Year, Patient)) +
geom_blank() +
geom_line(data = mdfn[mdfn$openCase == 0,], colour = "black") +
geom_line(data = mdfn[mdfn$openCase == 1,], colour = "grey") +
geom_point(data = mdfn2, aes(colour = Visit), size = 4, shape = 124) +
geom_text(data=mdfn2, mapping=aes(x=Year, y=(as.numeric(Patient)+0.25*as.numeric(Visit)%%3)-0.12,
label=substr(Visit, 1, 7), colour=Visit), size=2,
hjust=-.1, angle = 00)
这篇关于使用geom_text在geom_point上组织文本的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!