r - ggplot2（R）数据周围的密度阴影

Question

我试图在下图的背景上有 2 个“阴影”。这些阴影应该分别代表橙色和蓝色点的密度。是否有意义？

这是要改进的ggplot：在此处输入图像描述

df这是我用来创建此图的代码和数据（矩阵）：

                         PC1           PC2 aa
A_akallopisos    0.043272525  0.0151023307  2
A_akindynos     -0.020707141 -0.0158198405  1
A_allardi       -0.020277664 -0.0221016281  2
A_barberi       -0.023165596  0.0389906701  2
A_bicinctus     -0.025354572 -0.0059122384  2
A_chrysogaster   0.012608835 -0.0339330213  2
A_chrysopterus  -0.022402365 -0.0092476009  1
A_clarkii       -0.014474658 -0.0127024469  1
A_ephippium     -0.016859412  0.0320034231  2
A_frenatus      -0.024190876  0.0238499714  2
A_latezonatus   -0.010718845 -0.0289904165  1
A_latifasciatus -0.005645811 -0.0183202248  2
A_mccullochi    -0.031664307 -0.0096059126  2
A_melanopus     -0.026915545  0.0308399009  2
A_nigripes       0.023420045  0.0293801537  2
A_ocellaris      0.052042539  0.0126144250  2
A_omanensis     -0.020387101  0.0010944998  2
A_pacificus      0.042406273 -0.0260308092  2
A_percula        0.034591721  0.0071153133  2
A_perideraion    0.052830132  0.0064495142  2
A_polymnus       0.030902254 -0.0005091421  2
A_rubrocinctus  -0.033318659  0.0474995722  2
A_sandaracinos   0.055839755  0.0093724082  2
A_sebae          0.021767793 -0.0218640814  2
A_tricinctus    -0.016230301 -0.0018526482  1
P_biaculeatus   -0.014466403  0.0024864574  2



 ggplot(data=df,aes(x=PC1, y=PC2, color=factor(aa), label=rownames(df))) + ggtitle(paste('Site n° ',Sites_names[j],sep='')) +geom_smooth(se=F, method='lm')+ geom_point() + scale_color_manual(name='mutation', values = c("darkorange2","cornflowerblue"), labels = c("A","S")) + geom_text(hjust=0.5, vjust=-1 ,size=3) + xlim(-0.05,0.07)

score 6 · Accepted Answer

以下是一些使用stat_density2d()withgeom="polygon"和映射或设置alpha密度填充区域透明度的可能方法。如果您愿意尝试一些参数，我认为您可以获得一些非常有用的图。具体来说，您可能需要调整以下内容：

n控制密度多边形的平滑度。
h是密度估计的带宽。
bins控制密度级别的数量。

在此处输入图像描述

df = read.table(header=TRUE, text=
"                         PC1           PC2 aa
A_akallopisos    0.043272525  0.0151023307  2
A_akindynos     -0.020707141 -0.0158198405  1
A_allardi       -0.020277664 -0.0221016281  2
A_barberi       -0.023165596  0.0389906701  2
A_bicinctus     -0.025354572 -0.0059122384  2
A_chrysogaster   0.012608835 -0.0339330213  2
A_chrysopterus  -0.022402365 -0.0092476009  1
A_clarkii       -0.014474658 -0.0127024469  1
A_ephippium     -0.016859412  0.0320034231  2
A_frenatus      -0.024190876  0.0238499714  2
A_latezonatus   -0.010718845 -0.0289904165  1
A_latifasciatus -0.005645811 -0.0183202248  2
A_mccullochi    -0.031664307 -0.0096059126  2
A_melanopus     -0.026915545  0.0308399009  2
A_nigripes       0.023420045  0.0293801537  2
A_ocellaris      0.052042539  0.0126144250  2
A_omanensis     -0.020387101  0.0010944998  2
A_pacificus      0.042406273 -0.0260308092  2
A_percula        0.034591721  0.0071153133  2
A_perideraion    0.052830132  0.0064495142  2
A_polymnus       0.030902254 -0.0005091421  2
A_rubrocinctus  -0.033318659  0.0474995722  2
A_sandaracinos   0.055839755  0.0093724082  2
A_sebae          0.021767793 -0.0218640814  2
A_tricinctus    -0.016230301 -0.0018526482  1
P_biaculeatus   -0.014466403  0.0024864574  2")


library(ggplot2)

p1 = ggplot(data=df, aes(x=PC1, y=PC2, color=factor(aa), label=rownames(df))) + 
     ggtitle(paste('Site n° ',sep='')) +
     stat_density2d(aes(fill=factor(aa), alpha = ..level..), 
                    geom="polygon", color=NA, n=200, h=0.03, bins=4) + 
     geom_smooth(se=F, method='lm') + 
     geom_point() + 
     scale_color_manual(name='mutation', 
                        values = c("darkorange2","cornflowerblue"), 
                        labels = c("A","S")) + 
     scale_fill_manual( name='mutation', 
                        values = c("darkorange2","cornflowerblue"), 
                        labels = c("A","S")) + 
     geom_text(hjust=0.5, vjust=-1 ,size=3, color="black") + 
     scale_x_continuous(expand=c(0.3, 0)) + # Zooms out so that density polygons
     scale_y_continuous(expand=c(0.3, 0)) + # don't reach edges of plot.
     coord_cartesian(xlim=c(-0.05, 0.07),
                     ylim=c(-0.04, 0.05)) # Zooms back in for the final plot.


p2 = ggplot(data=df, aes(x=PC1, y=PC2, color=factor(aa), label=rownames(df))) + 
     ggtitle(paste('Site n° ',sep='')) +
     stat_density2d(aes(fill=factor(aa)), alpha=0.2,
                    geom="polygon", color=NA, n=200, h=0.045, bins=2) + 
     geom_smooth(se=F, method='lm', size=1) + 
     geom_point(size=2) + 
     scale_color_manual(name='mutation', 
                        values = c("darkorange2","cornflowerblue"), 
                        labels = c("A","S")) + 
     scale_fill_manual( name='mutation', 
                        values = c("darkorange2","cornflowerblue"), 
                        labels = c("A","S")) + 
     geom_text(hjust=0.5, vjust=-1 ,size=3) + 
     scale_x_continuous(expand=c(0.3, 0)) + # Zooms out so that density polygons
     scale_y_continuous(expand=c(0.3, 0)) + # don't reach edges of plot.
     coord_cartesian(xlim=c(-0.05, 0.07),
                     ylim=c(-0.04, 0.05)) # Zooms back in for the final plot.

library(gridExtra)
ggsave("plots.png", plot=arrangeGrob(p1, p2, ncol=1), width=8, height=11, dpi=120)

score 2 · Accepted Answer

这是我的建议。当您叠加两种颜色和密度时，使用阴影或多边形会变得非常难看。等高线图可能会更好看，当然也更容易使用。

我创建了一些随机数据作为可重现的示例，并使用了一个简单的密度函数，该函数使用最近 5 个点的平均距离。

df <- data.frame(PC1 = runif(20),
            PC2 = runif(20),
            aa = rbinom(20,1,0.5))


point.density <- function(row){
  points <- df[df$aa == row[[3]],]
  x.dist <- (points$PC1 - row[[1]])^2
  y.dist <- (points$PC2 - row[[2]])^2
  x <- x.dist[order(x.dist)[1:5]]
  y <- y.dist[order(y.dist)[1:5]]
  1/mean(sqrt(x + y))
}

# you need to calculate the density for the whole grid.
res <- c(1:100)/100 # this is the resolution, so gives a 100x100 grid

plot.data0 <- data.frame(x.val = rep(res,each = length(res)),
                        y.val = rep(res, length(res)),
                        type = rep(0,length(res)^2))

plot.data1 <- data.frame(x.val = rep(res,each = length(res)),
                         y.val = rep(res, length(res)),
                         type = rep(1,length(res)^2))

plot.data <- rbind(plot.data0,plot.data1)

# we need a density value for each point type, so 2 grids
densities <- apply(plot.data,1,point.density)
plot.data <- cbind(plot.data, z.val = densities)

library(ggplot2)

# use stat_contour to draw the densities. Be careful to specify which dataset you're using
ggplot() +  stat_contour(data = plot.data, aes(x=x.val, y=y.val, z=z.val, colour =    factor(type)), bins = 20, alpha = 0.4) + geom_point(data = df, aes(x=PC1,y=PC2,colour = factor(aa)))

等高线图 http://img34.imageshack.us/img34/6215/1yvb.png

r 轮廓 ggplot2

r - ggplot2（R）数据周围的密度阴影

2 回答 2

Related

Reference