r - 将 ggplot2 对象中的图例名称从小到大排序

问题描述

我有下面的数据框，我想将图例名称的顺序设置为从小到大。Cases这些值可能是字符，但它们与我认为可能有用的列对应，因为数据集是动态的。

Cum<-structure(list(Age.group = c("00-04", "00-04", "05-14", "05-14", 
                                  "15-24", "15-24", "25-49", "25-49", "50-64", "50-64", "65-79", 
                                  "65-79", "80+", "80+"), Gender = c("Female", "Male", "Female", 
                                                                     "Male", "Female", "Male", "Female", "Male", "Female", "Male", 
                                                                     "Female", "Male", "Female", "Male"), Cases = c(64578, 70518, 
                                                                                                                    187568, 197015, 414405, 388138, 1342394, 1206168, 792180, 742744, 
                                                                                                                    400232, 414613, 282268, 198026), lab = c("64,578", "70,518", 
                                                                                                                                                             "187,568", "197,015", "414,405", "388,138", "1,342,394", "1,206,168", 
                                                                                                                                                             "792,180", "742,744", "400,232", "414,613", "282,268", "198,026"
                                                                                                                    ), Age.group.Sum = c(135096, 135096, 384583, 384583, 802543, 
                                                                                                                                         802543, 2548562, 2548562, 1534924, 1534924, 814845, 814845, 480294, 
                                                                                                                                         480294), lab2 = c("135,096", "135,096", "384,583", "384,583", 
                                                                                                                                                           "802,543", "802,543", "2,548,562", "2,548,562", "1,534,924", 
                                                                                                                                                           "1,534,924", "814,845", "814,845", "480,294", "480,294"), color = c("#4285f4", 
                                                                                                                                                                                                                               "#4285f4", "#90a9e0", "#90a9e0", "#dd9e5f", "#dd9e5f", "#b45f06", 
                                                                                                                                                                                                                               "#b45f06", "#b45f06", "#b45f06", "#dd9e5f", "#dd9e5f", "#aebbd6", 
                                                                                                                                                                                                                               "#90a9e0"), Range = c("LESS THAN 74.5K", "LESS THAN 74.5K", "148.9K - 223.4K", 
                                                                                                                                                                                                                                                     "148.9K - 223.4K", "372.3K - 446.7K", "372.3K - 446.7K", "MORE THAN 670.1K", 
                                                                                                                                                                                                                                                     "MORE THAN 670.1K", "MORE THAN 670.1K", "MORE THAN 670.1K", "372.3K - 446.7K", 
                                                                                                                                                                                                                                                     "372.3K - 446.7K", "223.4K - 297.8K", "148.9K - 223.4K")), class = "data.frame", row.names = c(NA, 
                                                                                                                                                                                                                                                                                                                                                    -14L))

names(mycols) <- mycols
ylab <- c(0.5,1,1.5,2,2.5)
lbls <- setNames(unique(Cum$color), unique(Cum$Range))
                                                                                                    
                                                                                                                                                                                                                                                                                                                                                
ggplot_obj <- ggplot(data = Cum, aes(x = `Age.group`, y = Cases, group = Gender,fill = Range)) +
  geom_bar(aes(
   
    text = paste("<b>Gender:</b>", Gender, "<br><b>Age:</b>", `Age.group` ,
                 "<br><b>Cases:</b>", lab, "<br><b>Total cases in age group:</b>",
                 lab2)), 
    position = "dodge", stat = "identity") +
  geom_text(aes(y = Cases + 10000, label = Gender), vjust = 1,
            position = position_dodge(width=0.9),size=2) +
  scale_fill_manual(values = lbls) +
  coord_cartesian(ylim = c(0, max(Cum$Cases)*1.1), expand = FALSE) +
  theme_bw()+ theme(
    # remove the vertical grid lines
    panel.grid.major.x = element_blank(),
    panel.border = element_blank(), axis.line.x = element_line()
  ) +
  scale_y_continuous(labels = unit_format(unit = "M", scale = 1e-6))+
  xlab("Age group")

标签： rggplot2plotly

解决方案

我们可以将列转换为自定义顺序中指定factor的levels

Cum$Range <- factor(Cum$Range, levels = c("LESS THAN 74.5K" , "148.9K - 223.4K" , "223.4K - 297.8K", "372.3K - 446.7K" ,  "MORE THAN 670.1K"))
ylab <- c(0.5,1,1.5,2,2.5)
lbls <- setNames(Cum$color[match(levels(Cum$Range), Cum$Range)], levels(Cum$Range))

ggplot用OP 的代码构建绘图

-输出

更新

如果“范围”值是动态的（假设单位相同），则使用提取数字部分parse_number，order并获取unique值

lvls <- as.character(unique(Cum$Range[order(readr::parse_number(as.character(Cum$Range)))]))
Cum$Range <- factor(Cum$Range, levels = lvls)

或者另一种选择是arrange通过“案例”并设置“范围”的级别

library(dplyr)
Cum <-  Cum %>% 
         arrange(Cases, Age.group) %>%
         mutate(Range = factor(Range, levels = unique(Range)))
lbls <- setNames(Cum$color[match(levels(Cum$Range), Cum$Range)], levels(Cum$Range))

r - 将 ggplot2 对象中的图例名称从小到大排序

问题描述

解决方案

更新

推荐阅读