R 中的 ggplot2：geom_segment 显示与 geom_line 不同的行
ggplo2 in R: geom_segment displays different line than geom_line
假设我有这个数据框：
treatment <- c(rep("A",6),rep("B",6),rep("C",6),rep("D",6),rep("E",6),rep("F",6))
year <- as.numeric(c(1999:2004,1999:2004,2005:2010,2005:2010,2005:2010,2005:2010))
variable <- c(runif(6,4,5),runif(6,5,6),runif(6,3,4),runif(6,4,5),runif(6,5,6),runif(6,6,7))
se <- c(runif(6,0.2,0.5),runif(6,0.2,0.5),runif(6,0.2,0.5),runif(6,0.2,0.5),runif(6,0.2,0.5),runif(6,0.2,0.5))
id <- 1:36
df1 <- as.data.table(cbind(id,treatment,year,variable,se))
df1$year <- as.numeric(df1$year)
df1$variable <- as.numeric(df1$variable)
df1$se <- as.numeric(df1$se)
正如我在上一个问题 (draw two lines with the same origin using ggplot2 in R) 中提到的，我想使用 ggplot2 以特定方式显示我的数据。
我使用以下脚本设法做到了这一点：
y1 <- df1[df1$treatment=='A'&df1$year==2004,]$variable
y2 <- df1[df1$treatment=='B'&df1$year==2004,]$variable
y3 <- df1[df1$treatment=='C'&df1$year==2005,]$variable
y4 <- df1[df1$treatment=='D'&df1$year==2005,]$variable
y5 <- df1[df1$treatment=='E'&df1$year==2005,]$variable
y5 <- df1[df1$treatment=='E'&df1$year==2005,]$variable
y6 <- df1[df1$treatment=='F'&df1$year==2005,]$variable
p <- ggplot(df1,aes(x=year,y=variable,group=treatment,color=treatment))+
geom_line(aes(y = variable, group = treatment, linetype = treatment, color = treatment),size=1.5,lineend = "round") +
scale_linetype_manual(values=c('solid','solid','solid','dashed','solid','dashed')) +
geom_point(aes(colour=factor(treatment)),size=4)+
geom_errorbar(aes(ymin=variable-se,ymax=variable+se),width=0.2,size=1.5)+
guides(colour = guide_legend(override.aes = list(shape=NA,linetype = c("solid", "solid",'solid','dashed','solid','dashed'))))
p+labs(title="Title", x="years", y = "Variable 1")+
theme_classic() +
scale_x_continuous(breaks=c(1998:2010), labels=c(1998:2010),limits=c(1998.5,2010.5))+
geom_segment(aes(x=2004, y=y1, xend=2005, yend=y3),colour='blue1',size=1.5,linetype='solid')+
geom_segment(aes(x=2004, y=y1, xend=2005, yend=y4),colour='blue1',size=1.5,linetype='dashed')+
geom_segment(aes(x=2004, y=y2, xend=2005, yend=y5),colour='red3',size=1.5,linetype='solid')+
geom_segment(aes(x=2004, y=y2, xend=2005, yend=y6),colour='red3',size=1.5,linetype='dashed')+
scale_color_manual(values=c('blue1','red3','blue1','blue1','red3','red3'))+
theme(text = element_text(size=12))
如您所见，我同时使用了 geom_line 和 geom_segment 来显示图表的线条。
它几乎是完美的，但如果你仔细观察，绘制的线段（2004 年和 2005 年之间）不会显示相同的线宽，即使我在脚本中使用了相同的参数值（即 size=1.5 和 linetype='solid' 或 dashed).
当然我可以手动更改线段的大小以获得相似的线条，但是当我这样做时，线段不如使用 geom_line 的线条平滑。
此外，通过在 aes() 参数中包含 size 或 linetype 参数，我得到了同样的问题（不同的线条形状）。
您是否知道造成这种差异的原因以及如何为线段和线获得完全相同的形状？
这似乎是 geom_segment 的抗锯齿问题，但这似乎是一种开始时有点麻烦的方法。我想我已经通过在原始数据框中复制 A 和 B 处理方式解决了您的问题。
# First we are going to duplicate and rename the 'shared' treatments
library(dplyr)
library(ggplot2)
df1 %>%
filter(treatment %in% c("A", "B")) %>%
mutate(treatment = ifelse(treatment == "A",
"AA", "BB")) %>%
bind_rows(df1) %>% # This rejoins with the original data
# Now we create `treatment_group` and `line_type` variables
mutate(treatment_group = ifelse(treatment %in% c("A", "C", "D", "AA"),
"treatment1",
"treatment2"), # This variable will denote color
line_type = ifelse(treatment %in% c("AA", "BB", "D", "F"),
"type1",
"type2")) %>% # And this variable denotes the line type
# Now pipe into ggplot
ggplot(aes(x = year, y = variable,
group = interaction(treatment_group, line_type), # grouping by both linetype and color
color = treatment_group)) +
geom_line(aes(x = year, y = variable, linetype = line_type),
size = 1.5, lineend = "round") +
geom_point(size=4) +
# The rest here is more or less the same as what you had
geom_errorbar(aes(ymin = variable-se, ymax = variable+se),
width = 0.2, size = 1.5) +
scale_color_manual(values=c('blue1','red3')) +
scale_linetype_manual(values = c('dashed', 'solid')) +
labs(title = "Title", x = "Years", y = "Variable 1") +
scale_x_continuous(breaks = c(1998:2010),
limits = c(1998.5, 2010.5))+
theme_classic() +
theme(text = element_text(size=12))
这会给你以下内容
我的号码不同，因为它们是随机生成的。
然后您可以根据自己的喜好修改图例，但我的建议是使用类似 geom_label 的内容，然后一定要设置 check_overlap = TRUE.
希望对您有所帮助！
假设我有这个数据框：
treatment <- c(rep("A",6),rep("B",6),rep("C",6),rep("D",6),rep("E",6),rep("F",6))
year <- as.numeric(c(1999:2004,1999:2004,2005:2010,2005:2010,2005:2010,2005:2010))
variable <- c(runif(6,4,5),runif(6,5,6),runif(6,3,4),runif(6,4,5),runif(6,5,6),runif(6,6,7))
se <- c(runif(6,0.2,0.5),runif(6,0.2,0.5),runif(6,0.2,0.5),runif(6,0.2,0.5),runif(6,0.2,0.5),runif(6,0.2,0.5))
id <- 1:36
df1 <- as.data.table(cbind(id,treatment,year,variable,se))
df1$year <- as.numeric(df1$year)
df1$variable <- as.numeric(df1$variable)
df1$se <- as.numeric(df1$se)
正如我在上一个问题 (draw two lines with the same origin using ggplot2 in R) 中提到的，我想使用 ggplot2 以特定方式显示我的数据。
我使用以下脚本设法做到了这一点：
y1 <- df1[df1$treatment=='A'&df1$year==2004,]$variable
y2 <- df1[df1$treatment=='B'&df1$year==2004,]$variable
y3 <- df1[df1$treatment=='C'&df1$year==2005,]$variable
y4 <- df1[df1$treatment=='D'&df1$year==2005,]$variable
y5 <- df1[df1$treatment=='E'&df1$year==2005,]$variable
y5 <- df1[df1$treatment=='E'&df1$year==2005,]$variable
y6 <- df1[df1$treatment=='F'&df1$year==2005,]$variable
p <- ggplot(df1,aes(x=year,y=variable,group=treatment,color=treatment))+
geom_line(aes(y = variable, group = treatment, linetype = treatment, color = treatment),size=1.5,lineend = "round") +
scale_linetype_manual(values=c('solid','solid','solid','dashed','solid','dashed')) +
geom_point(aes(colour=factor(treatment)),size=4)+
geom_errorbar(aes(ymin=variable-se,ymax=variable+se),width=0.2,size=1.5)+
guides(colour = guide_legend(override.aes = list(shape=NA,linetype = c("solid", "solid",'solid','dashed','solid','dashed'))))
p+labs(title="Title", x="years", y = "Variable 1")+
theme_classic() +
scale_x_continuous(breaks=c(1998:2010), labels=c(1998:2010),limits=c(1998.5,2010.5))+
geom_segment(aes(x=2004, y=y1, xend=2005, yend=y3),colour='blue1',size=1.5,linetype='solid')+
geom_segment(aes(x=2004, y=y1, xend=2005, yend=y4),colour='blue1',size=1.5,linetype='dashed')+
geom_segment(aes(x=2004, y=y2, xend=2005, yend=y5),colour='red3',size=1.5,linetype='solid')+
geom_segment(aes(x=2004, y=y2, xend=2005, yend=y6),colour='red3',size=1.5,linetype='dashed')+
scale_color_manual(values=c('blue1','red3','blue1','blue1','red3','red3'))+
theme(text = element_text(size=12))
如您所见，我同时使用了 geom_line 和 geom_segment 来显示图表的线条。
它几乎是完美的，但如果你仔细观察，绘制的线段（2004 年和 2005 年之间）不会显示相同的线宽，即使我在脚本中使用了相同的参数值（即 size=1.5 和 linetype='solid' 或 dashed).
当然我可以手动更改线段的大小以获得相似的线条，但是当我这样做时，线段不如使用 geom_line 的线条平滑。
此外，通过在 aes() 参数中包含 size 或 linetype 参数，我得到了同样的问题（不同的线条形状）。
您是否知道造成这种差异的原因以及如何为线段和线获得完全相同的形状？
这似乎是 geom_segment 的抗锯齿问题，但这似乎是一种开始时有点麻烦的方法。我想我已经通过在原始数据框中复制 A 和 B 处理方式解决了您的问题。
# First we are going to duplicate and rename the 'shared' treatments
library(dplyr)
library(ggplot2)
df1 %>%
filter(treatment %in% c("A", "B")) %>%
mutate(treatment = ifelse(treatment == "A",
"AA", "BB")) %>%
bind_rows(df1) %>% # This rejoins with the original data
# Now we create `treatment_group` and `line_type` variables
mutate(treatment_group = ifelse(treatment %in% c("A", "C", "D", "AA"),
"treatment1",
"treatment2"), # This variable will denote color
line_type = ifelse(treatment %in% c("AA", "BB", "D", "F"),
"type1",
"type2")) %>% # And this variable denotes the line type
# Now pipe into ggplot
ggplot(aes(x = year, y = variable,
group = interaction(treatment_group, line_type), # grouping by both linetype and color
color = treatment_group)) +
geom_line(aes(x = year, y = variable, linetype = line_type),
size = 1.5, lineend = "round") +
geom_point(size=4) +
# The rest here is more or less the same as what you had
geom_errorbar(aes(ymin = variable-se, ymax = variable+se),
width = 0.2, size = 1.5) +
scale_color_manual(values=c('blue1','red3')) +
scale_linetype_manual(values = c('dashed', 'solid')) +
labs(title = "Title", x = "Years", y = "Variable 1") +
scale_x_continuous(breaks = c(1998:2010),
limits = c(1998.5, 2010.5))+
theme_classic() +
theme(text = element_text(size=12))
这会给你以下内容
我的号码不同，因为它们是随机生成的。
然后您可以根据自己的喜好修改图例，但我的建议是使用类似 geom_label 的内容，然后一定要设置 check_overlap = TRUE.
希望对您有所帮助！