代码之家 › 专栏 › 技术社区 › jerH

从ggplot bar plot中省略一些数据标签

ggplot2 r

jerH · 技术社区 · 2 年前

我有一些代码可以从CDCs网站下载新冠肺炎疫苗接种数据,进行一些操作,最终生成这样的条形图

你会注意到马列底部的零。马州未接种疫苗的人数越来越少,今天最终达到0。撇开你是否认为马实际上没有未接种疫苗的人不谈,我可以相信这个数字相当小。。。。

有什么方法可以让ggplot不包括0数据标签吗?

finalBarPlotData <- structure(list(State = structure(c(2L, 3L, 4L, 5L, 6L, 7L, 8L, 
9L, 1L, 10L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 1L, 10L, 2L, 3L, 
4L, 5L, 6L, 7L, 8L, 9L, 1L, 10L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 
9L, 1L, 10L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 1L, 10L), .Label = c("US", 
"CA", "FL", "GA", "MA", "NM", "OH", "OK", "TN", "UT"), class = "factor"), 
    variable = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 
    3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
    4L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L), .Label = c("Boosted", 
    "Eligible", "Ineligible", "Incomplete", "Unvax"), class = "factor"), 
    value = c(10811037.5, 5225168.9, 1825544.6, 2168196.8, 581220.4, 
    2941639.4, 761232.2, 1397638.8, 80651731.4, 624473.9, 16751023.5, 
    8810766.1, 3818756.4, 3144199.2, 864186.6, 3745298.6, 1439699.8, 
    2217344.2, 133078622.6, 1382887.1, 1257568, 470455, 236940, 
    211389, 64755, 192495, 95483, 127987, 8775787, 72985, 4080930, 
    2745163, 1151722, 1382887, 363931, 592129, 553536, 548320, 
    38221889, 258139, 6611664, 4226184, 3584460, 0, 222736, 4217538, 
    1107020, 2537884, 67511493, 867473)), row.names = c(NA, -50L
), class = "data.frame")

以及绘图的代码

stackColors <- c(Boosted = "green", Eligible="blue", Ineligible="yellow2", 
                 Incomplete ="orange", Unvax = "red3")


boosterBar<- ggplot(finalBarPlotData, aes(x=State, y=value,
                                          fill=factor(variable,
                                                      levels = c("Boosted", "Eligible",
                                                                 "Ineligible", "Incomplete",
                                                                 "Unvax")))) +
  geom_bar(stat="identity", position="fill") +   #percent stacked
  labs(x="", y="% of Population", fill="",
       caption="Data: CDC\nNumber in bars represent millions of residents",
       #subtitle = paste("Data as of", format(newestDate, "%A, %B %e, %Y"))) +
  scale_y_continuous(labels = function(x) paste0(x*100, "%")) + # Multiply by 100 & add %  
  theme(plot.title = element_text(size = rel(1), face = "bold"),
        plot.subtitle = element_text(size = rel(0.7)),
        plot.caption = element_text(size = rel(1)),
        axis.text.y = element_text(color='black'),
        axis.title.y = element_text(color='black'),
        axis.text.x = element_text(size=rel(1.25), angle = 45,hjust = 1)) +
  scale_fill_manual(values = stackColors, labels=c("Received Booster","Fully Vax, Booster Eligible","Fully Vax, Booster Ineligible", "First Dose Only", "Unvaccinated")) +
  geom_text(aes(label=round(value/1000000,digits=2)), position=position_fill(vjust=0.5), color="black")


print(boosterBar)

提前感谢。。。。

1 回复 | 直到 2 年前

jared_mamrot 2 年前

在你的情节中有很多事情在发生;也许“最简单”的方法是只打印文本,如果它是>1。

library(tidyverse)

df <- finalBarPlotData <- structure(list(State = structure(c(2L, 3L, 4L, 5L, 6L, 7L, 8L, 
                                                             9L, 1L, 10L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 1L, 10L, 2L, 3L, 
                                                             4L, 5L, 6L, 7L, 8L, 9L, 1L, 10L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 
                                                             9L, 1L, 10L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 1L, 10L), .Label = c("US", 
                                                                                                                               "CA", "FL", "GA", "MA", "NM", "OH", "OK", "TN", "UT"), class = "factor"), 
                                         variable = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
                                                                1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 
                                                                3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
                                                                4L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L), .Label = c("Boosted", 
                                                                                                                        "Eligible", "Ineligible", "Incomplete", "Unvax"), class = "factor"), 
                                         value = c(10811037.5, 5225168.9, 1825544.6, 2168196.8, 581220.4, 
                                                   2941639.4, 761232.2, 1397638.8, 80651731.4, 624473.9, 16751023.5, 
                                                   8810766.1, 3818756.4, 3144199.2, 864186.6, 3745298.6, 1439699.8, 
                                                   2217344.2, 133078622.6, 1382887.1, 1257568, 470455, 236940, 
                                                   211389, 64755, 192495, 95483, 127987, 8775787, 72985, 4080930, 
                                                   2745163, 1151722, 1382887, 363931, 592129, 553536, 548320, 
                                                   38221889, 258139, 6611664, 4226184, 3584460, 0, 222736, 4217538, 
                                                   1107020, 2537884, 67511493, 867473)), row.names = c(NA, -50L
                                                   ), class = "data.frame")

stackColors <- c(Boosted = "green", Eligible="blue", Ineligible="yellow2", 
                 Incomplete ="orange", Unvax = "red3")


boosterBar<- ggplot(finalBarPlotData, aes(x=State, y=value,
                                          fill=factor(variable,
                                                      levels = c("Boosted", "Eligible",
                                                                 "Ineligible", "Incomplete",
                                                                 "Unvax")))) +
  geom_bar(stat="identity", position="fill") +   #percent stacked
  labs(x="", y="% of Population", fill="",
       caption="Data: CDC\nNumber in bars represent millions of residents") +
       #subtitle = paste("Data as of", format(newestDate, "%A, %B %e, %Y"))) +
       scale_y_continuous(labels = function(x) paste0(x*100, "%")) + # Multiply by 100 & add %  
         theme(plot.title = element_text(size = rel(1), face = "bold"),
               plot.subtitle = element_text(size = rel(0.7)),
               plot.caption = element_text(size = rel(1)),
               axis.text.y = element_text(color='black'),
               axis.title.y = element_text(color='black'),
               axis.text.x = element_text(size=rel(1.25), angle = 45,hjust = 1)) +
         scale_fill_manual(values = stackColors, labels=c("Received Booster","Fully Vax, Booster Eligible","Fully Vax, Booster Ineligible", "First Dose Only", "Unvaccinated")) +
         geom_text(aes(label=ifelse(value > 1, round(value/1000000,digits=2), "")), position=position_fill(vjust=0.5), color="black")
       
       
       print(boosterBar)

^{reprex package

(v2.0.1)}