R语言ggalluvia包优雅的绘制桑基图

桑基图通常用于表示能量、物料、资本等数据从一个地方流入另一个地方。左边代表留出点，右边代表流入点，中间带宽表示流入量的大小，因此，我们通过桑基图清晰的看到两个节点的数据流动。今天介绍一下ggalluvia包绘制桑基图，ggalluvia包的特点是相对操作简单，容易上手。

先导入数据和R包

library(foreign)
library(ggplot2)
library(ggalluvial)
library(networkD3)
bc <- read.spss("E:/r/test/tree_car.sav",
                use.value.labels=F, to.data.frame=T)

我们来看下数据，car就是汽车售价，age是年龄，gender是性别，inccat是收入，这里分成4个等级，ed是教育程度。（公众号回复：汽车销售，可以获得该数据）。
我们处理一下数据，把分类变量转换成因子，然后加上一个标签。

bc$ed<-factor(bc$ed,levels=c(1:5),labels=c("小学","初中","高中","大学","博士"))
bc$inccat<-factor(bc$inccat,levels=c(1:4),labels=c("低收入","中低收入","中等收入","富裕"))
bc$gender<-ifelse(bc$gender=="m",1,0)
bc$gender<-factor(bc$gender,levels = c(0,1),labels=c("女性","男性"))
bc$marital<-factor(bc$marital,levels = c(0,1),labels=c("未婚","已婚"))

这数据比较大，我们取其中一部分来绘制

bc<-bc[1:100,]

ggalluvial包绘制桑基图还是比较简单的，我们先要设置axis1流出节点，和axis2流入节点
假设我们想知道不同收入人群购车费用在不同性别的流动（演示而已，不具有实际意义），

ggplot(bc,aes(y = car, axis1 = inccat, axis2 =ed)) +
  geom_alluvium(aes(fill = gender))

这样一个最简单的桑基图就画好了，我们给它进一步设置宽度，加个方框和字体，fill这里表示方框的颜色

ggplot(bc,aes(y = car, axis1 = inccat, axis2 =ed)) +
  geom_alluvium(aes(fill = gender)) +
  geom_stratum(width = 1/6, fill = "black", color = "grey") +
  geom_label(stat = "stratum", aes(label = after_stat(stratum)))

还可以对X轴进一步设置

ggplot(bc,aes(y = car, axis1 = inccat, axis2 =ed)) +
  geom_alluvium(aes(fill = gender)) +
  geom_stratum(width = 1/6, fill = "black", color = "grey") +
  geom_label(stat = "stratum", aes(label = after_stat(stratum))) +
  scale_x_discrete(limits = c("收入层次", "教育程度"), expand = c(.05, .05)) +
  scale_fill_brewer(type = "qual", palette = "Set1") +
  ggtitle("收入和购买汽车关系")

在scale_fill_brewer中set可以对风格进一步设置

ggplot(bc,aes(y = car, axis1 = inccat, axis2 =ed)) +
  geom_alluvium(aes(fill = gender)) +
  geom_stratum(width = 1/6, fill = "black", color = "grey") +
  geom_label(stat = "stratum", aes(label = after_stat(stratum))) +
  scale_x_discrete(limits = c("收入层次", "教育程度"), expand = c(.05, .05)) +
  scale_fill_brewer(type = "qual", palette = "Set3") +
  ggtitle("收入和购买汽车关系")

我们还可以进一步增加中间的节点

ggplot(bc,aes(y = car, axis1 = inccat, axis2 =ed,axis3 = marital)) +
  geom_alluvium(aes(fill = gender)) +
  geom_stratum(width = 1/6, fill = "black", color = "grey") +
  geom_label(stat = "stratum", aes(label = after_stat(stratum))) +
  scale_x_discrete(limits = c("Gender", "Dept"), expand = c(.05, .05)) +
  scale_fill_brewer(type = "qual", palette = "Set3") +
  ggtitle("收入和购买汽车关系")

我们可以使用coord_flip()函数把它倒置过来

ggplot(bc,aes(y = car,
              axis1 = inccat, axis2 = ed, axis3 = marital)) +
  geom_alluvium(aes(fill = gender),
                width = 1/8, knot.pos = 0, reverse = FALSE) +
  scale_fill_manual(values = c("男性"= "blue", "女性" = "red")) +
  guides(fill = "none") +
  geom_stratum(alpha = .4, width = 1/8, reverse = FALSE) +
  geom_text(stat = "stratum", aes(label = after_stat(stratum)),
            reverse = FALSE) +
  scale_x_continuous(breaks = 1:3, labels = c("inccat", "ed", "marital")) +
  coord_flip() +
  ggtitle("收入和购买汽车关系")

倒置后也可以进一步更换风格

ggplot(bc,aes(y = car,
              axis1 = inccat, axis2 = ed, axis3 = marital)) +
  geom_alluvium(aes(fill = gender),
                width = 1/8, knot.pos = 0, reverse = FALSE) +
  scale_fill_manual(values = c("男性"= "blue", "女性" = "red")) +
  guides(fill = "none") +
  geom_stratum(alpha = .4, width = 1/8, reverse = FALSE) +
  geom_text(stat = "stratum", aes(label = after_stat(stratum)),
            reverse = FALSE) +
  scale_fill_brewer(type = "qual", palette = "Set3")+
  scale_x_continuous(breaks = 1:3, labels = c("inccat", "ed", "marital")) +
  coord_flip() +
  ggtitle("收入和购买汽车关系")

下期再介绍使用networkD3包绘制桑基图。