使用 geom_text 在填充条形图中居中标签

Question

我是 ggplot2 （和 R）的新手，我正在尝试制作一个填充条形图，每个框中都有标签，指示组成该块的百分比。

这是我当前图形的示例，我想向其中添加标签：

##ggplot figure 
library(gpplot2)
library(scales) 

#specify order I want in plots
ZIU$Affinity=factor(ZIU$Affinity, levels=c("High", "Het", "Low"))
ZIU$Group=factor(ZIU$Group, levels=c("ZUM", "ZUF", "ZIM", "ZIF"))

ggplot(ZIU, aes(x=Group))+
geom_bar(aes(fill=Affinity), position="fill", width=1, color="black")+
scale_y_continuous(labels=percent_format())+
scale_fill_manual("Affinity", values=c("High"="blue", "Het"="lightblue", "Low"="gray"))+
labs(x="Group", y="Percent Genotype within Group")+
ggtitle("Genotype Distribution", "by Group")

我想添加以每个框为中心的标签以及该框代表的百分比

我尝试使用此代码添加标签，但它不断生成错误消息“错误：geom_text 需要以下缺失的美学：y”，但我的图没有 y 美学，这是否意味着我不能使用 geom_text？（另外，我不确定一旦 y 美学问题得到解决，geom_text 语句的其余部分是否能够实现我想要的效果，即每个框中居中的白色标签。）

ggplot(ZIU, aes(x=Group)) +
geom_bar(aes(fill=Affinity), position="fill", width=1, color="black")+
geom_text(aes(label=paste0(sprintf("%.0f", ZIU$Affinity),"%")),
    position=position_fill(vjust=0.5), color="white")+
scale_y_continuous(labels=percent_format())+
scale_fill_manual("Affinity", values=c("High"="blue", "Het"="lightblue", "Low"="gray"))+
labs(x="Group", y="Percent Genotype within Group")+
ggtitle("Genotype Distribution", "by Group")

另外，如果有人有消除 NA 值的建议，我们将不胜感激！我试过

geom_bar(aes(fill=na.omit(Affinity)), position="fill", width=1, color="black")

但收到错误“错误：美学必须是长度 1 或与数据 (403) 相同：填充，x”

 dput(sample)
 structure(list(Group = structure(c(3L, 3L, 3L, 3L, 3L, 3L, 3L, 
 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 1L, 1L, 1L, 
 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
 2L), .Label = c("ZUM", "ZUF", "ZIM", "ZIF"), class = "factor"), 
StudyCode = c(1, 2, 3, 4, 5, 6, 20, 21, 22, 23, 143, 144, 
145, 191, 192, 193, 194, 195, 196, 197, 10, 24, 25, 26, 27, 
28, 71, 72, 73, 74, 274, 275, 276, 277, 278, 279, 280, 290, 
291, 292), Affinity = structure(c(3L, 2L, 1L, 2L, 3L, 1L, 
1L, 2L, 2L, 2L, 2L, 2L, 3L, 2L, 3L, 2L, 3L, 1L, 1L, 1L, 3L, 
2L, 1L, 2L, 2L, 1L, 2L, 2L, 3L, 3L, 2L, 1L, 3L, 2L, 1L, 3L, 
3L, 2L, 2L, 2L), .Label = c("High", "Het", "Low"), class = "factor")), .Names = c("Group", 
"StudyCode", "Affinity"), row.names = c(NA, 40L), class = c("tbl_df", 
"tbl", "data.frame"))

太感谢了！

Answer 1

链接的示例具有y美感，因为数据是预先汇总的，而不是让 ggplot 在内部进行计数。对于您的数据，类似的方法是：

library(scales) 
library(tidyverse)

# Summarize data to get counts and percentages
ZIU %>% group_by(Group, Affinity) %>%
  tally %>%
  mutate(percent=n/sum(n)) %>%   # Pipe summarized data into ggplot
  ggplot(aes(x=Group, y=percent, fill=Affinity)) +
   geom_bar(stat="identity", width=1, color="black") +
   geom_text(aes(label=paste0(sprintf("%1.1f", percent*100),"%")), 
             position=position_stack(vjust=0.5), colour="white") +
   scale_y_continuous(labels=percent_format()) +
   scale_fill_manual("Affinity", values=c("High"="blue", "Het"="lightblue", "Low"="gray")) +
   labs(x="Group", y="Percent Genotype within Group") +
   ggtitle("Genotype Distribution", "by Group")

另一种选择是使用线图，这可能会使相对值更加清晰。假设这些Group值不形成自然序列，这些线只是作为区分Affinity不同 值之间的值的指南Group。

ZIU %>% group_by(Group, Affinity) %>%
  tally %>%
  mutate(percent=n/sum(n)) %>%   # Pipe summarized data into ggplot
  ggplot(aes(x=Group, y=percent, colour=Affinity, group=Affinity)) +
  geom_line(alpha=0.4) +
  geom_text(aes(label=paste0(sprintf("%1.1f", percent*100),"%")), show.legend=FALSE) +
  scale_y_continuous(labels=percent_format(), limits=c(0,1)) +
  labs(x="Group", y="Percent Genotype within Group") +
  ggtitle("Genotype Distribution", "by Group") +
  guides(colour=guide_legend(override.aes=list(alpha=1, size=1))) +
  theme_classic()