将 P 值添加到组内比较箱线图

我正在尝试创建一个箱线图，它仅显示箱线图中每个条形的组内的显着 p 值。例如，它会比较 I1 和 SI2 的“一般”、“良好”、“非常好”等

我尝试使用以下代码来实现上面的情节

library(ggplot2)
library(dplyr)
data("diamonds")

labeldat <- diamonds %>%
  group_by(cut, clarity) %>%
  dplyr::summarise(labels = paste(n(), n_distinct(color), sep = "\n"))


Comparisons = list(c("I1","SI2"),c("I1","SI1"),c("I1","VS2"),c("I1","VS1"),c("I1","VVS2"),c("I1","VVS1"),c("I1","IF"),
                   c("SI2","SI1"),c("SI2","VS2"),c("SI2","VS1"),c("SI2","VVS2"),c("SI2","VVS1"),c("SI2","IF"),
                   c("SI1","VS2"),c("SI1","VS1"),c("SI1","VVS2"),c("SI1","VVS1"),c("SI1","IF"),
                   c("VS2","VS1"),c("VS2","VVS2"),c("VS2","VVS1"),c("VS2","IF"),
                   c("VS1","VVS2"),c("VS1","VVS1"),c("VS1","IF"),
                   c("VVS2","VVS1"),c("VVS2","IF"),
                   c("VVS1","IF"))



ggplot(diamonds, aes(x=cut, y=price)) +
  geom_boxplot(aes(fill=clarity), position = position_dodge2(width=0.75)) + 
  theme_bw() + 
  geom_text(data = labeldat, aes(x = cut, y = -250, label = labels), hjust = 0.5, position = position_dodge2(width = .75))+
  stat_compare_means(aes(group=clarity), label = "p.signif", method="t.test", comparisons = Comparisons)

不幸的是，使用比较参数似乎存在计算错误，我无法弄清楚如何解决： 警告信息： 计算失败于stat_signif(): 需要 TRUE/FALSE 时缺少值

我尝试在没有比较的情况下运行它，但它似乎只是给了我一个总体分数

您可以使用 ggsignif 来实现这一点。它允许手动注释，因此您可以单独计算 p 值，并创建带有过滤比较的注释数据框。例子：

library(ggplot2)
library(ggsignif)
library(dplyr)
library(data.table)

dm <- split(diamonds, diamonds$cut)
getp <- function(y, pval=.05){
    a <- stats::pairwise.wilcox.test(x=y$price, g=y$clarity,
        p.adjust.method="none", paired=FALSE)
    return(as.data.table(as.table(a$p.value))[!is.na(N) & N < pval])
}
dmp <- data.table::rbindlist(lapply(dm, getp), idcol = "cut")
data.table::setnames(dmp, c("cut", "start", "end", "label"))
dmp$label <- formatC(
    signif(dmp$label, digits = 3),
    digits = 3,
    format = "g",
    flag = "#"
)
dmp[, y := (0:(.N-1)) * (2E4/.N)+2e4, by=cut]
data.table::setDF(dmp)

ggplot(diamonds, aes(x=clarity, y=price)) +
    geom_boxplot(aes(fill=clarity), position = position_dodge2(width=0.75)) + 
    facet_wrap(~ cut)+
    ggsignif::geom_signif(data=dmp,
        aes(xmin=start, xmax=end, annotations=label, y_position=y),
        textsize = 2, vjust = -0.2,
        manual=TRUE) + 
    ylim(NA, 4E4) +
    theme_bw() +
    theme(axis.text.x = element_blank())