5

我有以下数据集：

df <- data.frame(dens = rnorm(5000),
             split = as.factor(sample(1:2, 5000, replace = T)),
             method = as.factor(sample(c("A","B"), 5000, replace = T)),
             counts = sample(c(1, 10, 100, 1000, 10000), 5000, replace = T))

对于每个计数，我在 A 组和 B 组中的拆分 1 和 2 有以下拆分小提琴图。我们为每个设置有四个组，但它有一个嵌套方面：

library(ggplot2)
GeomSplitViolin <- ggproto("GeomSplitViolin", GeomViolin, 
                           draw_group = function(self, data, ..., draw_quantiles = NULL){
                               ## By @YAK: https://stackoverflow.com/questions/35717353/split-violin-plot-with-ggplot2
                               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$y))) {
                                   stopifnot(all(draw_quantiles >= 0), all(draw_quantiles <= 1))
                                   quantiles <- create_quantile_segment_frame(data, draw_quantiles, split = TRUE, grp = grp)
                                   aesthetics <- data[rep(1, nrow(quantiles)), setdiff(names(data), c("x", "y")), drop = FALSE]
                                   aesthetics$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, ...))
                               }
                           }
                           )

create_quantile_segment_frame <- function (data, draw_quantiles, split = FALSE, grp = NULL) {
    dens <- cumsum(data$density)/sum(data$density)
    ecdf <- stats::approxfun(dens, data$y)
    ys <- ecdf(draw_quantiles)
    violin.xminvs <- (stats::approxfun(data$y, data$xminv))(ys)
    violin.xmaxvs <- (stats::approxfun(data$y, data$xmaxv))(ys)
    violin.xs <- (stats::approxfun(data$y, data$x))(ys)
    if (grp %% 2 == 0) {
        data.frame(x = ggplot2:::interleave(violin.xs, violin.xmaxvs), 
                   y = rep(ys, each = 2), group = rep(ys, each = 2)) 
    } else {
        data.frame(x = ggplot2:::interleave(violin.xminvs, violin.xs), 
                   y = rep(ys, each = 2), group = rep(ys, each = 2)) 
    }
}

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, ...))
}



df$key <- factor(paste(df$split, df$method))

levels(df$split) <- factor(0:2)
library(ggplot2)
ggplot(df, aes(x = interaction(split, counts), y = dens, fill = key)) +geom_split_violin(draw_quantiles = c(0.25, 0.5, 0.75)) +scale_fill_manual(values=RColorBrewer::brewer.pal(name="Paired",n=4)) + theme_light() + theme(legend.position="bottom") + scale_x_discrete(limits=levels(interaction(df$split,df$counts))[-length(levels(interaction(df$split,df$counts)))],drop = FALSE, name = "Counts")

我得到以下信息：

在此处输入图像描述

这很好，除了我只想在 x 轴上以及蓝色和绿色小提琴图之间有计数 1、10、100、1000、10000 的标签。因此，在第一个蓝色和绿色小提琴图之间标记 1，在第二个蓝色和绿色小提琴图之间标记 10，在第二个蓝色和绿色小提琴图之间标记 100，依此类推。

感谢您提供有关如何执行此操作的任何建议。

4

2 回答 2

3

您可以尝试将文本层添加到绘图本身，而不是更改离散比例的断点，它能够接受离散比例位置的非整数值：

ggplot(df,
       aes(x = x, y = dens, fill = key)) + 
  geom_split_violin(draw_quantiles = c(0.25, 0.5, 0.75)) +

  # annotate layer with non-integer positions
  annotate(geom = "text", x = c(1.5, 4.5, 7.5, 10.5, 13.5), y = -3.75,
           label = c("1", "10", "100", "1000", "10000")) +
  scale_fill_manual(values=RColorBrewer::brewer.pal(name="Paired", n=4)) + 
  scale_x_discrete(name = "Counts", drop = FALSE) +
  theme_minimal() + 

  # hide the actual discrete labels / ticks
  theme(legend.position="bottom",
        axis.ticks.x = element_blank(),
        axis.text.x = element_blank())

阴谋

于 2018-03-09T05:26:28.097 回答
3

我通常用刻面解决这些问题，然后将条带格式化为轴标签。theme(panel.spacing = .....)这也自然地使两对更靠近，没有任何技巧，如果需要，您可以通过更改来更改距离。例如：

ggplot(df, aes(x = split, y = dens, fill = key)) +
  geom_split_violin(draw_quantiles = c(0.25, 0.5, 0.75)) +
  scale_fill_manual(values=RColorBrewer::brewer.pal(name="Paired",n=4)) + 
  xlab('count') +
  facet_grid(~counts, scales = 'free_x', switch = 'x') +
  theme_light() + 
  theme(legend.position = "bottom", axis.text.x = element_blank(), axis.ticks.x = element_blank(),
        strip.background = element_blank(), strip.text = element_text(color = 'black'))

在此处输入图像描述

或具有不太明显方面的不同主题：

ggplot(df, aes(x = split, y = dens, fill = key)) +
  geom_split_violin(draw_quantiles = c(0.25, 0.5, 0.75)) +
  scale_fill_manual(values=RColorBrewer::brewer.pal(name="Paired",n=4)) + 
  xlab('count') +
  facet_grid(~counts, scales = 'free_x', switch = 'x') +
  theme_minimal() + 
  theme(legend.position = "bottom", axis.text.x = element_blank(), axis.ticks.x = element_blank())

在此处输入图像描述

于 2018-03-12T10:10:34.917 回答