用ggplot2和分位數分割小提琴曲線

Question

為了繪制半密度，我使用了這篇文章中描述的功能： 用ggplot2分割小提琴圖

但是，當我想在密度上繪制分位數時，就像在普通的geom_violin()或geom_boxplot() ，我得到一條錯誤信息。

我也有興趣增加每半密度以上的觀測數量。

這是我想要獲得的一個例子：

data("diamonds")
library(ggplot2)

# Function described in a previous post
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$y))) {
    stopifnot(all(draw_quantiles >= 0), all(draw_quantiles <= 
                                              1))
    quantiles <- create_quantile_segment_frame(data, draw_quantiles)
    aesthetics <- data[rep(1, nrow(quantiles)), setdiff(names(data), c("x", "y")), drop = FALSE]
    aesthetics$alpha <- rep(1, nrow(quantiles))
    both <- cbind(quantiles, aesthetics)
    quantile_grob <- GeomPath$draw_panel(both, ...)
    ggplot2:::ggname("geom_split_violin", grobTree(GeomPolygon$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, ...))
}

tmp <- diamonds[which(diamonds$cut %in% c("Fair", "Good")), ]

# Obtained plot
ggplot(tmp, aes(as.factor(color), carat, fill = cut)) +
  geom_split_violin()

# Error due to internal functions (interleave, ...)
ggplot(tmp, aes(as.factor(color), carat, fill = cut)) +
  geom_split_violin(draw_quantiles = 0.5)

# Function to return number of observation
give_n = function(x, y_up = y_upper) {
  data.frame(y = y_up * 1.06,
             label = paste("n =", length(x))
  )
}

# Code to add number of observations above each half density
new_plot = given_plot +
  # Give back only length of data
  stat_summary(fun.data = give_n, aes(x = as.factor(variable)), geom = "text")

Answer 1

我們可以作進一步的調整由@YAK功能，並添加了一些調整，以create_quantile_segment_frame ：

GeomSplitViolin <- ggproto("GeomSplitViolin", GeomViolin,
  draw_group = function(self, data, ..., draw_quantiles = NULL) {
    # Original function by Jan Gleixner (@jan-glx)
    # Adjustments by Wouter van der Bijl (@Axeman)
    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, ...))
}

然后簡單地繪制：

ggplot(diamonds[which(diamonds$cut %in% c("Fair", "Good")), ],
       aes(as.factor(color), carat, fill = cut)) +
  geom_split_violin(draw_quantiles = c(0.25, 0.5, 0.75))