R语言绘制桑吉图
KJY
2019-10-11
快速入门
需要使用networkD3这个包
networkD3是基于D3JS的R包交互式绘图工具，用于转换R语言生成的图为交互式网页嵌套图。目前支持网络图，桑基图，树枝图等。
networkD3包基于D3.JS(最流行的可视化库之一)构建，还可以和R中常见的网络可视化包例如network、igraph等连用，支持管道操作符%>%(dplyr中常用，读者可自行学习)和ggplot2语法，是一个非常灵活的网络可视化包
桑吉图(sankey diagram)使用来研究同一个变量在其不同分类中的比例或者说是流动的.实体(或者说是节点,node)一般使用长方形或者文字来表示.箭头和弧线用来表示在他们之间的流动.
library(networkD3)
library(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──## ✓ ggplot2 3.3.3 ✓ purrr 0.3.4
## ✓ tibble 3.1.1 ✓ dplyr 1.0.5
## ✓ tidyr 1.1.3 ✓ stringr 1.4.0
## ✓ readr 1.4.0 ✓ forcats 0.5.1## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()## create a dataframe with 10 nodes
nodes = data.frame("name" = c("Node_0", "Node_1", "Node_2", "Node_3", "Node_4", "Node_5",
"Node_6", "Node_7", "Node_8", "Node_9"))
## create edges with weights
links = as.data.frame(matrix(c(0, 5, 2, # node 0 -> node 5 with weight 2
0, 6, 1, # node 0 -> node 6 with weight 1
1, 7, 3, # node 1 -> node 7 with weight 3
2, 8, 2, # node 2 -> node 8 with weight 2
2, 9, 3, # node 2 -> node 9 with weight 3
3, 5, 1, # node 3 -> node 5 with weight 1
3, 9, 5, # node 3 -> node 9 with weight 5
4, 9, 2 # node 4 -> node 9 with weight 2
), byrow = TRUE, ncol = 3))
## set column names for links
names(links) = c("source", "target", "value")
links## source target value
## 1 0 5 2
## 2 0 6 1
## 3 1 7 3
## 4 2 8 2
## 5 2 9 3
## 6 3 5 1
## 7 3 9 5
## 8 4 9 2## Draw Sankey Diagram
p = sankeyNetwork(Links = links, Nodes = nodes,
Source = "source", Target = "target",
Value = "value", NodeID = "name",
fontSize = 16, nodeWidth = 40)
p另外一个例子
links <- data.frame(
source = c("group_A","group_A", "group_B", "group_C", "group_C", "group_E"),
target = c("group_C","group_D", "group_E", "group_F", "group_G", "group_H"),
value = c(2,3, 2, 3, 1, 3)
)
head(links)## source target value
## 1 group_A group_C 2
## 2 group_A group_D 3
## 3 group_B group_E 2
## 4 group_C group_F 3
## 5 group_C group_G 1
## 6 group_E group_H 3##构建connection data frame中所有nodes的data frame
nodes <- data.frame(
name = c(as.character(links$source),
as.character(links$target)) %>% unique()
)
nodes## name
## 1 group_A
## 2 group_B
## 3 group_C
## 4 group_E
## 5 group_D
## 6 group_F
## 7 group_G
## 8 group_H#然后我们需要将每个node的名字代替为其在node data frame中的位置index,注意是要从哦开始计算.
links$IDsource <- match(links$source, nodes$name) - 1
links$IDtarget <- match(links$target, nodes$name) - 1
links## source target value IDsource IDtarget
## 1 group_A group_C 2 0 2
## 2 group_A group_D 3 0 4
## 3 group_B group_E 2 1 3
## 4 group_C group_F 3 2 5
## 5 group_C group_G 1 2 6
## 6 group_E group_H 3 3 7#开始创建桑吉图
p <- networkD3::sankeyNetwork(
Links = links,
Nodes = nodes,
Source = "IDsource",
Target = "IDtarget",
Value = "value",
NodeID = "name",
sinksRight = FALSE
)
p改变node颜色
library(networkD3)
## create a dataframe with 10 nodes
nodes = data.frame("name" = c("Node_0", "Node_1", "Node_2", "Node_3", "Node_4", "Node_5",
"Node_6", "Node_7", "Node_8", "Node_9"))
## create edges with weights
links = as.data.frame(matrix(c(0, 5, 2, # node 0 -> node 5 with weight 2
0, 6, 1, # node 0 -> node 6 with weight 1
1, 7, 3, # node 1 -> node 7 with weight 3
2, 8, 2, # node 2 -> node 8 with weight 2
2, 9, 3, # node 2 -> node 9 with weight 3
3, 5, 1, # node 3 -> node 5 with weight 1
3, 9, 5, # node 3 -> node 9 with weight 5
4, 9, 2 # node 4 -> node 9 with weight 2
), byrow = TRUE, ncol = 3))
## set column names for links
names(links) = c("source", "target", "value")
## Create custom color list using d3 for each node
node_color <- 'd3.scaleOrdinal() .domain(["Node_0", "Node_1", "Node_2", "Node_3", "Node_4",
"Node_5", "Node_6", "Node_7", "Node_8", "Node_9"]) .range(["red", "blue", "orange" ,
"yellow", "cyan", "green", "magenta", "dodgerblue", "pink", "black"])'
## Draw Sankey Diagram
p = sankeyNetwork(Links = links, Nodes = nodes,
Source = "source", Target = "target",
Value = "value", NodeID = "name",
fontSize = 16, nodeWidth = 40,
colourScale = node_color)
p改变node和edge的颜色
library(networkD3)
## create a dataframe with 10 nodes
nodes = data.frame("name" = c("Node_0", "Node_1", "Node_2", "Node_3", "Node_4", "Node_5",
"Node_6", "Node_7", "Node_8", "Node_9"))
## create edges with weights
links = as.data.frame(matrix(c(0, 5, 2, # node 0 -> node 5 with weight 2
0, 6, 1, # node 0 -> node 6 with weight 1
1, 7, 3, # node 1 -> node 7 with weight 3
2, 8, 2, # node 2 -> node 8 with weight 2
2, 9, 3, # node 2 -> node 9 with weight 3
3, 5, 1, # node 3 -> node 5 with weight 1
3, 9, 5, # node 3 -> node 9 with weight 5
4, 9, 2 # node 4 -> node 9 with weight 2
), byrow = TRUE, ncol = 3))
## set column names for links
names(links) = c("source", "target", "value")
## add edge types for coloring purpose
links$group = c("type_0",
"type_0",
"type_1",
"type_2",
"type_2",
"type_3",
"type_3",
"type_4")
## Create custom color list using d3 for each node
node_color <- 'd3.scaleOrdinal() .domain(["Node_0", "Node_1", "Node_2", "Node_3", "Node_4",
"Node_5", "Node_6", "Node_7", "Node_8", "Node_9", "type_0", "type_1", "type_2",
"type_3", "type_4"]) .range(["red", "blue", "orange" , "yellow", "cyan", "green", "magenta",
"dodgerblue", "pink", "black", "red", "blue", "orange" , "yellow", "cyan"])'
## Draw Sankey Diagram
p = sankeyNetwork(Links = links, Nodes = nodes,
Source = "source", Target = "target",
Value = "value", NodeID = "name",
fontSize = 16, nodeWidth = 40,
colourScale = node_color,
LinkGroup="group")
p最后一次修改于 2019-10-11