r - 使用 ggplot2 分割 fiddle 图

Question

我想使用 ggplot 创建一个分割 fiddle 密度图，就像 this page 上的第四个示例一样。 Seaborn 文档。

这是一些数据:

set.seed(20160229)

my_data = data.frame(
    y=c(rnorm(1000), rnorm(1000, 0.5), rnorm(1000, 1), rnorm(1000, 1.5)),
    x=c(rep('a', 2000), rep('b', 2000)),
    m=c(rep('i', 1000), rep('j', 2000), rep('i', 1000))
)

我可以像这样绘制躲避的 fiddle :

library('ggplot2')

ggplot(my_data, aes(x, y, fill=m)) +
  geom_violin()

但是很难直观地比较并排分布中不同点的宽度。我在 ggplot 中找不到任何拆分 fiddle 的示例 - 这可能吗？

我找到了base R graphics solution但该函数相当长，我想突出显示分布模式，这些模式很容易在 ggplot 中添加为附加层，但如果我需要弄清楚如何编辑该函数，则会更难。

Answer 1

或者，为了避免摆弄密度，您可以扩展 ggplot2's GeomViolin像这样:

GeomSplitViolin <- ggproto("GeomSplitViolin", GeomViolin, 
                           draw_group = function(self, data, ..., draw_quantiles = NULL) {
  data <- transform(data, xminv = x - violinwidth * (x - xmin), xmaxv = x + violinwidth * (xmax - x))
  grp <- data[1, "group"]
  newdata <- plyr::arrange(transform(data, x = if (grp %% 2 == 1) xminv else xmaxv), if (grp %% 2 == 1) y else -y)
  newdata <- rbind(newdata[1, ], newdata, newdata[nrow(newdata), ], newdata[1, ])
  newdata[c(1, nrow(newdata) - 1, nrow(newdata)), "x"] <- round(newdata[1, "x"])

  if (length(draw_quantiles) > 0 & !scales::zero_range(range(data$y))) {
    stopifnot(all(draw_quantiles >= 0), all(draw_quantiles <=
      1))
    quantiles <- ggplot2:::create_quantile_segment_frame(data, draw_quantiles)
    aesthetics <- data[rep(1, nrow(quantiles)), setdiff(names(data), c("x", "y")), drop = FALSE]
    aesthetics$alpha <- rep(1, nrow(quantiles))
    both <- cbind(quantiles, aesthetics)
    quantile_grob <- GeomPath$draw_panel(both, ...)
    ggplot2:::ggname("geom_split_violin", grid::grobTree(GeomPolygon$draw_panel(newdata, ...), quantile_grob))
  }
  else {
    ggplot2:::ggname("geom_split_violin", GeomPolygon$draw_panel(newdata, ...))
  }
})

geom_split_violin <- function(mapping = NULL, data = NULL, stat = "ydensity", position = "identity", ..., 
                              draw_quantiles = NULL, trim = TRUE, scale = "area", na.rm = FALSE, 
                              show.legend = NA, inherit.aes = TRUE) {
  layer(data = data, mapping = mapping, stat = stat, geom = GeomSplitViolin, 
        position = position, show.legend = show.legend, inherit.aes = inherit.aes, 
        params = list(trim = trim, scale = scale, draw_quantiles = draw_quantiles, na.rm = na.rm, ...))
}

并使用新的geom_split_violin，如下所示:

ggplot(my_data, aes(x, y, fill = m)) + geom_split_violin()