在保留悬停信息的同时,将多边形添加到散点图中

Question

我有5个x,y数据集,我正在使用R的plotly.

以下是数据:

set.seed(1)
df <- do.call(rbind,lapply(seq(1,20,4),function(i) data.frame(x=rnorm(50,mean=i,sd=1),y=rnorm(50,mean=i,sd=1),cluster=i)))

这是他们的plotly散点图:

library(plotly)
clusters.plot <- plot_ly(marker=list(size=10),type='scatter',mode="markers",x=~df$x,y=~df$y,color=~df$cluster,data=df) %>% hide_colorbar() %>% layout(xaxis=list(title="X",zeroline=F),yaxis=list(title="Y",zeroline=F))

这使:

然后,按照@Marco Sandri的回答,我使用以下代码添加限制这些集群的多边形:

多边形代码:

library(data.table)
library(grDevices)

splinesPolygon <- function(xy,vertices,k=3, ...)
{
  # Assert: xy is an n by 2 matrix with n >= k.
  # Wrap k vertices around each end.
  n <- dim(xy)[1]
  if (k >= 1) {
    data <- rbind(xy[(n-k+1):n,], xy, xy[1:k, ])
  } else {
    data <- xy
  }
  # Spline the x and y coordinates.
  data.spline <- spline(1:(n+2*k), data[,1], n=vertices, ...)
  x <- data.spline$x
  x1 <- data.spline$y
  x2 <- spline(1:(n+2*k), data[,2], n=vertices, ...)$y
  # Retain only the middle part.
  cbind(x1, x2)[k < x & x <= n+k, ]
}

clustersPolygon <- function(df)
{
  dt <- data.table::data.table(df)
  hull <- dt[,.SD[chull(x,y)]]
  spline.hull <- splinesPolygon(cbind(hull$x,hull$y),100)
  return(data.frame(x=spline.hull[,1],y=spline.hull[,2],stringsAsFactors=F))
}

library(dplyr)
polygons.df <- do.call(rbind,lapply(unique(df$cluster),function(l)
  clustersPolygon(df=dplyr::filter(df,cluster == l)) %>%
    dplyr::rename(polygon.x=x,polygon.y=y) %>%
    dplyr::mutate(cluster=l)))

现在添加多边形:

clusters <- unique(df$cluster)

for(l in clusters) clusters.plot <- clusters.plot %>% 
 add_polygons(x=dplyr::filter(polygons.df,cluster == l)$polygon.x,
              y=dplyr::filter(polygons.df,cluster == l)$polygon.y,
              line=list(width=2,color="black"),
              fillcolor='transparent', inherit = FALSE)

这使:

虽然这很有用,但遗憾的是它消除了hoverinfo添加多边形之前存在的现象,现在只是每个多边形的轨迹.

改变inherit来自FALSE于TRUE与我写的错误结果在该职位.所以我的问题是如何在不改变hoverinfo原始图的情况下添加多边形.

Answer 1

我认为这里的部分问题是当你开始混合和匹配跟踪类型时,colorbarin plotly有一些奇怪的行为和副作用.

解决此问题的最简单方法(由于您按群集着色而不是连续变量似乎是合适的)是将聚类列的类更改为带表达式的有序因子df$cluster <- ordered(as.factor(df$cluster)).(我相信这也可能是一个dplyr mutate声明.)

包和数据生成功能

library(data.table)
library(grDevices)
library(dplyr)
library(plotly)

## Function Definitions 
splinesPolygon <- function(xy,vertices,k=3, ...) {
  # Assert: xy is an n by 2 matrix with n >= k.
  # Wrap k vertices around each end.
  n <- dim(xy)[1]
  if (k >= 1) {
    data <- rbind(xy[(n-k+1):n,], xy, xy[1:k, ])
  } else {
    data <- xy
  }
  # Spline the x and y coordinates.
  data.spline <- spline(1:(n+2*k), data[,1], n=vertices, ...)
  x <- data.spline$x
  x1 <- data.spline$y
  x2 <- spline(1:(n+2*k), data[,2], n=vertices, ...)$y
  # Retain only the middle part.
  cbind(x1, x2)[k < x & x <= n+k, ]
}

clustersPolygon <- function(df) {
  dt <- data.table::data.table(df)
  hull <- dt[,.SD[chull(x,y)]]
  spline.hull <- splinesPolygon(cbind(hull$x,hull$y),100)
  return(data.frame(x=spline.hull[,1],y=spline.hull[,2],stringsAsFactors=F))
}

生成数据

这里的一个关键区别是将您的集群定义为有序因子,以防止它被视为将调用colorbar古怪的连续变量.

set.seed(1)
df <- do.call(rbind,lapply(seq(1,20,4),function(i) data.frame(x=rnorm(50,mean=i,sd=1),y=rnorm(50,mean=i,sd=1),cluster=i)))

## Critical Step here: Make cluster an ordered factor so it will
## be plotted with the sequential viridis scale, but will not 
## be treated as a continuous spectrum that gets the colorbar involved
df$cluster <- ordered(as.factor(df$cluster))

## Make hull polygons
polygons.df <- do.call(rbind,lapply(unique(df$cluster),function(l) clustersPolygon(df=dplyr::filter(df,cluster == l)) %>% dplyr::rename(polygon.x=x,polygon.y=y) %>% dplyr::mutate(cluster=l)))
clusters <- unique(df$cluster)
clustersPolygon(df=dplyr::filter(df,cluster == l)) %>% dplyr::rename(polygon.x=x,polygon.y=y) %>% dplyr::mutate(cluster=l)))

构建一个plotly对象

这里大致相同,但首先初始化一个空的绘图对象,然后在原始数据点之前添加船体多边形.

## Initialize an empty plotly object so that the hulls can be added first
clusters.plot <- plot_ly()

## Add hull polygons sequentially
for(l in clusters) clusters.plot <- clusters.plot %>% 
  add_polygons(x=dplyr::filter(polygons.df,cluster == l)$polygon.x,
               y=dplyr::filter(polygons.df,cluster == l)$polygon.y,
               name = paste0("Cluster ",l),
               line=list(width=2,color="black"),
               fillcolor='transparent', 
               hoverinfo = "none",
               showlegend = FALSE,
               inherit = FALSE)  

## Add the raw data trace
clusters.plot <- clusters.plot %>% 
  add_trace(data=df, x= ~x,y= ~y,color= ~cluster,
            type='scatter',mode="markers",
            marker=list(size=10)) %>% 
  layout(xaxis=list(title="X",
                    zeroline=F),
         yaxis=list(title="Y",
                    zeroline=F))
## Print the output
clusters.plot

给出以下输出