Question

我有一个带有标准id，variable和value列的融合数据框。变量有4个级别。

我想使用ggplot使用每个因子的值绘制散点图

来说明

data.frame(id= gl(4,1,labels=paste("id",1:4,sep="")), variable=gl(4,4,labels=LETTERS[1:4]),value=rnorm(16))

        id variable        value
1  id1        A -0.494270766
2  id2        A  0.189400188
3  id3        A -0.550961030
4  id4        A -1.046945450
5  id1        B -0.525552660
6  id2        B -0.293601677
7  id3        B  0.009664513
8  id4        B -0.214687215
9  id1        C  1.253551926
10 id2        C -1.241847326
11 id3        C -0.307036508
12 id4        C -0.228632605
13 id1        D -1.683798512
14 id2        D -0.419295267
15 id3        D -0.154469178
16 id4        D -0.763460558

我想为每对变量A对B，A对C，A对D，B对C等生成ggplot散点图，然后对它们进行平滑处理。

干杯，戴维

Answer 1

以下是 ggplot2 中plotmatrix的略微修改版本：

dat <- data.frame(id= gl(4,1,labels=paste("id",1:4,sep="")), variable=gl(4,4,labels=LETTERS[1:4]),value=rnorm(16))

require(reshape2)
dat <- dcast(dat,id~variable)

plotmatrix <- function (data, mapping = aes(), colour = "black") 
{
    grid <- expand.grid(x = 1:ncol(data), y = 1:ncol(data))
    grid <- subset(grid, x != y)
    all <- do.call("rbind", lapply(1:nrow(grid), function(i) {
        xcol <- grid[i, "x"]
        ycol <- grid[i, "y"]
        data.frame(xvar = names(data)[ycol], yvar = names(data)[xcol], 
            x = data[, xcol], y = data[, ycol], data)
    }))
    all$xvar <- factor(all$xvar, levels = names(data))
    all$yvar <- factor(all$yvar, levels = names(data))
    densities <- do.call("rbind", lapply(1:ncol(data), function(i) {
        data.frame(xvar = names(data)[i], yvar = names(data)[i], 
            x = data[, i])
    }))
    densities$xvar <- factor(densities$xvar, levels = names(data))
    densities$yvar <- factor(densities$yvar, levels = names(data))
    mapping <- defaults(mapping, aes_string(x = "x", y = "y"))
    class(mapping) <- "uneval"
    ggplot(all, mapping) + 
        facet_grid(xvar ~ yvar, scales = "free") + 
        geom_point(colour = colour, na.rm = TRUE) + 
        stat_density(aes(x = x,y = ..scaled.. * diff(range(x)) + min(x)), 
            data = densities,position = "identity", colour = "grey20", geom = "line") + 
        geom_smooth(se = FALSE,method = "lm",colour = "blue")
}

plotmatrix(dat[,-1])

enter image description here

Answer 2

试试这个，

library(ggplot2)
library(reshape2)
library(plyr)

d <- data.frame(id= gl(4,1,labels=paste("id",1:4,sep="")), variable=gl(4,4,labels=LETTERS[1:4]),value=rnorm(16))


plot_pair <- function(pair=c("A","B"), d){
  m <- cast(d, ...~variable, subset=(variable %in% pair))
   ggplot(m, aes_string(x=pair[1], y=pair[2])) +
     geom_point() +
       geom_smooth()

}

pdf("allpairs.pdf")
a_ply(combn(levels(d$variable), 2), 2, plot_pair, d=d, .print=TRUE)
dev.off()

Answer 3

遵循@Dason的建议尝试GGally包并使用@ baptise的重塑代码......

    library(ggplot2)
    library(reshape2)
    library(plyr)
    library(GGally)
    #
    n <- 100   # number of observations
    i <- 4     # number of variables, cannot exceed 26 since letters are used as labels
    #
    # create data, following @Davy
    d <- data.frame(id= gl(n, 1, labels, paste("id", 1:n,sep="")), 
                    variable=gl(i, n, labels=LETTERS[1:i]),value=rnorm(n*i))
    #
    # reshape for plotting, from @baptise
    group <- unique(d$variable)
    m <- dcast(d, ...~variable, subset=.(variable %in% group))
    #
    # make scatterplot matrix using GGally package
    # as suggested by @Dason
    ggpairs(m[,2:ncol(m)], 
           lower = list(continuous = "smooth"),
           axisLabels="show")
    # done!

结果是对角线上方的方框中的网格线有点忙（但毫无疑问它们可以关闭），在此之前需要进行一些其他的最后润色才能进入黄金时段。

enter image description here

但ggplot2方法通常是正确的（如果需要，可以删除更平滑的方法）。 GGally代码位于github。

值得注意的是，有一些奇妙的散点图矩阵的例子（包括代码）可以在R的RomainFrançois'R Graph Gallery中完成。 This one与上面的完全类似。

使用同一列中的值绘制折线图

3 个答案: