horizontal dendrogram in R with labels
这是代码:
labs = paste("sta_",1:50,sep="") #new labels
rownames(USArrests)<-labs #set new row names
hc <- hclust(dist(USArrests), "ave")
library(ggplot2)
library(ggdendro)
#convert cluster object to use with ggplot
dendr <- dendro_data(hc, type="rectangle")
#your own labels are supplied in geom_text() and label=label
ggplot() +
geom_segment(data=segment(dendr), aes(x=x, y=y, xend=xend, yend=yend)) +
geom_text(data=label(dendr), aes(x=x, y=y, label=label, hjust=0), size=3) +
coord_flip() + scale_y_reverse(expand=c(0.2, 0)) +
theme(axis.line.y=element_blank(),
axis.ticks.y=element_blank(),
axis.text.y=element_blank(),
axis.title.y=element_blank(),
panel.background=element_rect(fill="white"),
panel.grid=element_blank())
有谁知道,如何着色不同的群集?例如,您想要将2个群集(k = 2)着色?
答案 0 :(得分:17)
解决方法是使用plot()
绘制群集对象,然后使用函数rect.hclust()
绘制群集周围的边界(群集的nunber使用参数k=
设置)。如果将rect.hclust()
的结果保存为对象,则会生成观察列表,其中每个列表元素包含属于每个集群的观察值。
plot(hc)
gg<-rect.hclust(hc,k=2)
现在可以将此列表转换为数据框,其中列clust
包含集群的名称(在此示例中为两个组) - 根据列表元素的长度重复名称。
clust.gr<-data.frame(num=unlist(gg),
clust=rep(c("Clust1","Clust2"),times=sapply(gg,length)))
head(clust.gr)
num clust
sta_1 1 Clust1
sta_2 2 Clust1
sta_3 3 Clust1
sta_5 5 Clust1
sta_8 8 Clust1
sta_9 9 Clust1
新数据框与label()
对象(dendr
结果)的dendro_data()
信息合并。
text.df<-merge(label(dendr),clust.gr,by.x="label",by.y="row.names")
head(text.df)
label x y num clust
1 sta_1 8 0 1 Clust1
2 sta_10 28 0 10 Clust2
3 sta_11 41 0 11 Clust2
4 sta_12 31 0 12 Clust2
5 sta_13 10 0 13 Clust1
6 sta_14 37 0 14 Clust2
绘制树状图时,使用text.df
添加带有geom_text()
的标签,并使用列clust
获取颜色。
ggplot() +
geom_segment(data=segment(dendr), aes(x=x, y=y, xend=xend, yend=yend)) +
geom_text(data=text.df, aes(x=x, y=y, label=label, hjust=0,color=clust), size=3) +
coord_flip() + scale_y_reverse(expand=c(0.2, 0)) +
theme(axis.line.y=element_blank(),
axis.ticks.y=element_blank(),
axis.text.y=element_blank(),
axis.title.y=element_blank(),
panel.background=element_rect(fill="white"),
panel.grid=element_blank())
答案 1 :(得分:17)
这种方法与@ DidzisElferts非常相似,只是更简单一点。
df <- USArrests # really bad idea to muck up internal datasets
labs <- paste("sta_",1:50,sep="") # new labels
rownames(df) <- labs # set new row names
library(ggplot2)
library(ggdendro)
hc <- hclust(dist(df), "ave") # heirarchal clustering
dendr <- dendro_data(hc, type="rectangle") # convert for ggplot
clust <- cutree(hc,k=2) # find 2 clusters
clust.df <- data.frame(label=names(clust), cluster=factor(clust))
# dendr[["labels"]] has the labels, merge with clust.df based on label column
dendr[["labels"]] <- merge(dendr[["labels"]],clust.df, by="label")
# plot the dendrogram; note use of color=cluster in geom_text(...)
ggplot() +
geom_segment(data=segment(dendr), aes(x=x, y=y, xend=xend, yend=yend)) +
geom_text(data=label(dendr), aes(x, y, label=label, hjust=0, color=cluster),
size=3) +
coord_flip() + scale_y_reverse(expand=c(0.2, 0)) +
theme(axis.line.y=element_blank(),
axis.ticks.y=element_blank(),
axis.text.y=element_blank(),
axis.title.y=element_blank(),
panel.background=element_rect(fill="white"),
panel.grid=element_blank())
答案 2 :(得分:12)
添加到@DidzisElferts'和@ jlhoward的代码,树形图本身可以着色。
library(ggplot2)
library(ggdendro)
library(plyr)
library(zoo)
df <- USArrests # really bad idea to muck up internal datasets
labs <- paste("sta_", 1:50, sep = "") # new labels
rownames(df) <- labs # set new row names
cut <- 4 # Number of clusters
hc <- hclust(dist(df), "ave") # hierarchical clustering
dendr <- dendro_data(hc, type = "rectangle")
clust <- cutree(hc, k = cut) # find 'cut' clusters
clust.df <- data.frame(label = names(clust), cluster = clust)
# Split dendrogram into upper grey section and lower coloured section
height <- unique(dendr$segments$y)[order(unique(dendr$segments$y), decreasing = TRUE)]
cut.height <- mean(c(height[cut], height[cut-1]))
dendr$segments$line <- ifelse(dendr$segments$y == dendr$segments$yend &
dendr$segments$y > cut.height, 1, 2)
dendr$segments$line <- ifelse(dendr$segments$yend > cut.height, 1, dendr$segments$line)
# Number the clusters
dendr$segments$cluster <- c(-1, diff(dendr$segments$line))
change <- which(dendr$segments$cluster == 1)
for (i in 1:cut) dendr$segments$cluster[change[i]] = i + 1
dendr$segments$cluster <- ifelse(dendr$segments$line == 1, 1,
ifelse(dendr$segments$cluster == 0, NA, dendr$segments$cluster))
dendr$segments$cluster <- na.locf(dendr$segments$cluster)
# Consistent numbering between segment$cluster and label$cluster
clust.df$label <- factor(clust.df$label, levels = levels(dendr$labels$label))
clust.df <- arrange(clust.df, label)
clust.df$cluster <- factor((clust.df$cluster), levels = unique(clust.df$cluster), labels = (1:cut) + 1)
dendr[["labels"]] <- merge(dendr[["labels"]], clust.df, by = "label")
# Positions for cluster labels
n.rle <- rle(dendr$segments$cluster)
N <- cumsum(n.rle$lengths)
N <- N[seq(1, length(N), 2)] + 1
N.df <- dendr$segments[N, ]
N.df$cluster <- N.df$cluster - 1
# Plot the dendrogram
ggplot() +
geom_segment(data = segment(dendr),
aes(x=x, y=y, xend=xend, yend=yend, size=factor(line), colour=factor(cluster)),
lineend = "square", show.legend = FALSE) +
scale_colour_manual(values = c("grey60", rainbow(cut))) +
scale_size_manual(values = c(.1, 1)) +
geom_text(data = N.df, aes(x = x, y = y, label = factor(cluster), colour = factor(cluster + 1)),
hjust = 1.5, show.legend = FALSE) +
geom_text(data = label(dendr), aes(x, y, label = label, colour = factor(cluster)),
hjust = -0.2, size = 3, show.legend = FALSE) +
scale_y_reverse(expand = c(0.2, 0)) +
labs(x = NULL, y = NULL) +
coord_flip() +
theme(axis.line.y = element_blank(),
axis.ticks.y = element_blank(),
axis.text.y = element_blank(),
axis.title.y = element_blank(),
panel.background = element_rect(fill = "white"),
panel.grid = element_blank())
2集群和4集群解决方案:
答案 3 :(得分:4)
获得类似结果的一个简短方法是使用包dendextend
(从这个不错的overview派生而来)。
df <- USArrests # really bad idea to muck up internal datasets
labs <- paste("sta_",1:50,sep="") # new labels
rownames(df) <- labs # set new row names
require(magittr)
require(ggplot)
require(dendextend)
dend <- df %>% dist %>%
hclust %>% as.dendrogram %>%
set("branches_k_color", k = 4) %>% set("branches_lwd", 0.7) %>%
set("labels_cex", 0.6) %>% set("labels_colors", k = 4) %>%
set("leaves_pch", 19) %>% set("leaves_cex", 0.5)
ggd1 <- as.ggdend(dend)
ggplot(ggd1, horiz = TRUE)
注意:状态的顺序与上面的顺序略有不同 - 虽然没有真正改变解释。
答案 4 :(得分:-1)
对于那些仍在寻找一种方便的方法来执行此操作的人,您可以使用我的包 ggdendroplot (https://github.com/NicolasH2/ggdendroplot)。
如果您有来自已发布示例的数据:
labs = paste("sta_",1:50,sep="") #new labels
rownames(USArrests)<-labs #set new row names
hc <- hclust(dist(USArrests), "ave")
...您可以使用 ggdendroplot 和 ggplot 来获得彩色树状图:
devtools::install_github("NicolasH2/ggdendroplot")
library(ggdendroplot)
library(ggplot2)
ggplot() + geom_dendro(hc, dendrocut = 30)
您可以将其向侧面和头部等方向转动。它基本上只是一个 ggplot 图层,因此您可以根据需要进一步修改图形并将其添加到其他 ggplot 中。查看 github page 以了解您可以使用 ggdendroplot 做什么。