ggplot2 geom_point,带有分箱x轴,用于二进制数据

Question

我正在尝试为二进制数据创建带有分箱x轴的散点图.当我使用geom_point二进制y时,情节很无用(见图1).如图2所示,我想根据x轴的值对数据进行分类,然后使用geom_point(将每个bin中的obs数量映射到该点的大小)绘制每个bin中的avg x和avg y ).我可以通过聚合数据来做到这一点,但我想知道ggplot是否可以直接进行.我玩过stat_bindot等等,但无法找到解决方案.有任何想法吗？下面是一些代码.

谢谢!

# simulate data
n=1000
y=rbinom(n,1,0.5)
x=runif(n)
data=data.frame(x,y)

# figure 1 - geom_point with binary data, pretty useless!
ggplot(data,aes(x=x,y=y)) + geom_point() + ylim(0,1)

# let's create an aggregated dataset with bins
bin=cut(data$x,seq(0,1,0.05))
# I am sure the aggregation can be done in a better way...
data.bin=aggregate(data,list(bin),function(x) { return(c(mean(x),length(x)))})

# figure 2 - geom_point with binned x-axis, much nicer!
ggplot(data.bin,aes(x=x[,1],y=y[,1],size=x[,2])) + geom_point() + ylim(0,1)

图1和2:

Answer 1

我为此编写了一个新的Stat函数.

这需要nbins,bin_var,bin_fun和summary_fun作为参数,以默认设置所有四个.

• 默认值nbins取决于数据点的数量.
• 默认bin_var值为"x".您也可以将其设置为"y".这指定了馈送到的变量bin_fun.
• bin_fun是分箱功能.默认情况下,这是seq_cut我为此目的而写的.您也可以编写自己的分箱功能.它只需要将数据和nbins作为参数.
• summary_fun是用于聚合分箱的汇总函数.默认情况下,它是mean.您还可以指定单独聚合函数x和y fun.x和fun.y.
• 如果使用GEOM这需要ymin和ymax美学,你还可以指定fun.ymin和fun.ymax.

请注意,如果指定aes(group = your_bins),bin_fun则会被忽略,而是使用分组变量.另请注意,它将创建一个可以作为访问的计数变量..count...

在您的情况下,您使用它像这样:

p <- ggplot(data, aes(x, y)) +
  geom_point(aes(size = ..count..), stat = "binner") +
  ylim(0, 1)

在这种情况下不是很有用(虽然这证明了同方差性,并且方差大约为0.25,因为伯尔尼(0.5)变量的假设)但仅仅是为了示例:

p + geom_linerange(stat = "binner",
                   fun.ymin = function(y) mean(y) - var(y) / 2,
                   fun.ymax = function(y) mean(y) + var(y) / 2)

代码:

library(proto)

stat_binner <- function (mapping = NULL, data = NULL, geom = "point", position = "identity", ...) {
  StatBinner$new(mapping = mapping, data = data, geom = geom, position = position, ...)
}

StatBinner <- proto(ggplot2:::Stat, {
  objname <- "binner"

  default_geom <- function(.) GeomPoint
  required_aes <- c("x", "y")

  calculate_groups <- function(., data, scales, bin_var = "x", nbins = NULL, bin_fun = seq_cut, summary_fun = mean,
                       fun.data = NULL, fun.y = NULL, fun.ymax = NULL, fun.ymin = NULL,
                       fun.x = NULL, fun.xmax = NULL, fun.xmin = NULL, na.rm = FALSE, ...) {
    data <- remove_missing(data, na.rm, c("x", "y"), name = "stat_binner")

    # Same rules as binnedplot in arm package
    n <- nrow(data)
    if (is.null(nbins)) {
      nbins <- if (n >= 100) floor(sqrt(n))
              else if (n > 10 & n < 100) 10
              else floor(n/2)
    }

    if (length(unique(data$group)) == 1) {
      data$group <- bin_fun(data[[bin_var]], nbins)
    }

    if (!missing(fun.data)) {
      # User supplied function that takes complete data frame as input
      fun.data <- match.fun(fun.data)
      fun <- function(df, ...) {
        fun.data(df$y, ...)
      }
    } else {
      if (!is.null(summary_fun)) {
        if (!is.null(fun.x)) message("fun.x overriden by summary_fun")
        if (!is.null(fun.y)) message("fun.y overriden by summary_fun")
        fun.x <- fun.y <- summary_fun
      }

      # User supplied individual vector functions
      fs_x <- compact(list(xmin = fun.x, x = fun.x, xmax = fun.xmax))
      fs_y <- compact(list(ymin = fun.ymin, y = fun.y, ymax = fun.ymax))

      fun <- function(df, ...) {
        res_x <- llply(fs_x, function(f) do.call(f, list(df$x, ...)))
        res_y <- llply(fs_y, function(f) do.call(f, list(df$y, ...)))
        names(res_y) <- names(fs_y)
        names(res_x) <- names(fs_x)
        as.data.frame(c(res_y, res_x))
      }
    }
    summarise_by_x_and_y(data, fun, ...)
  }


})

summarise_by_x_and_y <- function(data, summary, ...) {
  summary <- ddply(data, "group", summary, ...)
  count <- ddply(data, "group", summarize, count = length(y))

  unique <- ddply(data, "group", ggplot2:::uniquecols)
  unique$y <- NULL
  unique$x <- NULL

  res <- merge(merge(summary, unique, by = "group"), count, by = "group")

  # Necessary for, eg, colour aesthetics
  other_cols <- setdiff(names(data), c(names(summary), names(unique)))
  if (length(other_cols) > 0) {
    other <- ddply(data[, c(other_cols, "group")], "group", numcolwise(mean))
    res <- merge(res, other, by = "group")
  }

  res
}


seq_cut <- function(x, nbins) {
  bins <- seq(min(x), max(x), length.out = nbins)
  findInterval(x, bins, rightmost.closed = TRUE)
}