在ggplot中使用多个大小的比例

时间:2013-02-01 13:51:41

标签: r ggplot2 data-visualization

我正在尝试构建一个显示从一个类到另一个类的转换的图。我想让圆圈代表根据类属性调整的每个类,以及从一个类到另一个类的箭头,根据从一个类到另一个类的转换数量来确定。

举个例子:

library(ggplot2)
points <- data.frame( x=runif(10), y=runif(10),class=1:10, size=runif(10,min=1000,max=100000) )
trans <- data.frame( from=rep(1:10,times=10), to=rep(1:10,each=10), amount=runif(100)^3 )
trans <- merge( trans, points, by.x="from", by.y="class" )
trans <- merge( trans, points, by.x="to", by.y="class", suffixes=c(".to",".from") )
ggplot( points, aes( x=x, y=y ) ) + geom_point(aes(size=size),color="red") + 
    scale_size_continuous(range=c(4,20)) + 
    geom_segment( data=trans, aes( x=x.from, y=y.from, xend=x.to, yend=y.to, size=amount ),lineend="round",arrow=arrow(),alpha=0.5)

Example image

我希望能够将不同比例的箭头缩放到圆圈。理想情况下,我想要一个有两个音阶的传奇,但我知道这可能是不可能的(using two scale colour gradients on one ggplot

除了对基础数据应用任意缩放之外,还有更优雅的方法吗?

1 个答案:

答案 0 :(得分:1)

一个不错的选择是将类的周长生成为一系列点,根据您的数据调整比例(直径)。然后将圆圈绘制为路径或多边形。

遵循一些示例代码。 circleFun由@joran在previous post中分享。这有用吗?我认为你应该根据你的真实数据调整圆形比例。

  

重要提示:
  此外,通过使用arrow而未附加grid,我认为您尚未更新ggplot2。我更改了该代码以使用我的设置,并尝试不包含任何可能导致向后兼容性问题的ggplot2代码。

# Load packages
library(package=ggplot2)  # You should update ggplot2
library(package=plyr)     # To proccess each class separately


# Your data generating code
points <- data.frame(x=runif(10), y=runif(10),class=1:10,
                     size=runif(10,min=1000,max=100000) )
trans <- data.frame(from=rep(1:10,times=10), to=rep(1:10,each=10),
                    amount=runif(100)^3 )
trans <- merge(trans, points, by.x="from", by.y="class" )
trans <- merge(trans, points, by.x="to", by.y="class", suffixes=c(".to",".from") )


# Generate a set of points in a circumference
# Originally posted by @joran in
# https://stackoverflow.com/questions/6862742/draw-a-circle-with-ggplot2
circleFun <- function(center = c(0,0), diameter = 1, npoints = 100){
    r = diameter / 2
    tt <- seq(0,2*pi,length.out = npoints)
    xx <- center[1] + r * cos(tt)
    yy <- center[2] + r * sin(tt)
    return(data.frame(x = xx, y = yy))
}


# Get max and min sizes and min distances to estimate circle scales
min_size <- min(points$size, na.rm=TRUE)
max_size <- max(points$size, na.rm=TRUE)
xs <- apply(X=combn(x=points$x, m=2), MARGIN=2, diff, na.rm=TRUE)
ys <- apply(X=combn(x=points$y, m=2), MARGIN=2, diff, na.rm=TRUE)
min_dist <- min(abs(c(xs, ys)))  # Seems too small
mean_dist <- mean(abs(c(xs, ys)))

# Adjust sizes
points$fit_size <- points$size * (mean_dist/max_size)


# Generate the circles based on the points
circles <- ddply(.data=points, .variables='class',
                 .fun=function(class){
                    with(class,
                    circleFun(center = c(x, y), diameter=fit_size))
                 })
circles <- merge(circles, points[, c('class', 'size', 'fit_size')])


# Plot
ggplot(data=circles, aes(x=x, y=y)) +
    geom_polygon(aes(group=factor(class), fill=size)) + 
    geom_segment(data=trans,
                 aes(x=x.from, y=y.from, xend=x.to, yend=y.to, size=amount),
                 alpha=0.6, lineend="round", arrow=grid::arrow()) +
    coord_equal()