資料:《Statistical Analysis of Network Data with R》
語(yǔ)言R常見(jiàn)的網(wǎng)絡(luò)分析包:
- 基礎(chǔ)網(wǎng)絡(luò)操作誉结、可視化于特征化: igraph命雀、network型凳、sna
- 網(wǎng)絡(luò)建模:igraph寥枝、eigenmodel峰尝、ergm冒嫡、mixer
- 網(wǎng)絡(luò)建模:glasso、huge
網(wǎng)絡(luò)分析研究大部分是描述性的工作。
網(wǎng)絡(luò)的可視化 即是一門(mén)藝術(shù)纲缓,也是一門(mén)科學(xué)。
聚類系數(shù) Clustering cofficient
三元閉包體現(xiàn)了社會(huì)網(wǎng)絡(luò)的“傳遞性”(transitivity)罗侯,枚舉所有節(jié)點(diǎn)三元組中構(gòu)成三角形的比值來(lái)表征依痊。
網(wǎng)絡(luò)的可視化和數(shù)值特征化是網(wǎng)絡(luò)分析的首要步驟之一性宏。
網(wǎng)絡(luò)可視化視圖將數(shù)據(jù)的多個(gè)重要反面整合在一個(gè)圖表中群井。
同配性 assortativity
該節(jié)點(diǎn)在多大程度上會(huì)與同類型或者不同類型的其他節(jié)點(diǎn)進(jìn)行匹配,可以通過(guò)一種相關(guān)性統(tǒng)計(jì)量(所謂的同配系數(shù))進(jìn)行量化毫胜。
將復(fù)雜系統(tǒng)中感興趣的問(wèn)題與合適的網(wǎng)絡(luò)概括性度量匹配起來(lái)蝌借,是網(wǎng)絡(luò)特征化方法起作用的關(guān)鍵所在。
模體 motif
網(wǎng)絡(luò)中的頻繁子圖模式
網(wǎng)絡(luò)聚類系數(shù)的分布,用來(lái)檢驗(yàn)社會(huì)網(wǎng)路的聚集性上
sand安裝包
網(wǎng)絡(luò)數(shù)據(jù)統(tǒng)計(jì)分析 statistical analysis of network data
在CRAN上
install.packages("sand")
# 安裝包statistical analysis of network data 網(wǎng)絡(luò)數(shù)據(jù)統(tǒng)計(jì)分析
install.packages("igraph")
library(igraph)
library(igraphdata)
library(sand)
install_sand_packages()
?sand
第2章 操作網(wǎng)絡(luò)數(shù)據(jù)
G=(V,E)
節(jié)點(diǎn) :vertices 或者 nodes
邊:edges 或者 links
節(jié)點(diǎn)數(shù)量:圖的階數(shù) order
邊的數(shù)量:圖的規(guī)模 size
同構(gòu)圖 isomorphic
無(wú)向 undirected
有向 directed graph 或者 digraph
邊:有向邊 directed edges 或 弧 arcs
雙向 mutual
小的圖形用 formulate來(lái)創(chuàng)建
# 2.1
library(igraph) # 載入igraph包
# 創(chuàng)建一個(gè)圖對(duì)象g指蚁,包含Nv=7個(gè)節(jié)點(diǎn)
g <- graph.formula(1-2, 1-3, 2-3, 2-4, 3-5, 4-5, 4-6, 4-7, 5-6, 6-7)
# 2.2
## 節(jié)點(diǎn)系列:Vertex sequence
V(g)
# 2.3
## 邊序列:Edge squence
E(g)
# 2.4
## 顯示圖的結(jié)構(gòu)
str(g)
# 2.5
## 可視化圖
plot(g)
# 2.6
## 有向圖的創(chuàng)建
dg <- graph.formula(1-+2, 1-+3, 2++3)
plot(dg)
# 2.7
## 1,2,3,...,n的編號(hào)是默認(rèn)給定的標(biāo)簽,也可以自己給定標(biāo)簽
dg2 <- graph.formula(Sam-+Mary, Sam-+Tom, Mary++Tom)
str(dg2)
summary(dg2)
str(dg2) # 屬性調(diào)用不清楚
?str()
# 2.8
## 通過(guò)節(jié)點(diǎn)的name屬性進(jìn)行修改自晰。
V(dg)$name <- c("小明", "小藍(lán)", "小西")
plot(dg)
三種表示圖的格式:鄰接列表凝化、邊列表、領(lǐng)接矩陣
-
鄰接列表 adjacency list
邊列表 edge list
E(dg)
+ 4/4 edges from 2ec3d7f (vertex names):
[1] 小明->小藍(lán) 小明->小西 小藍(lán)->小西 小西->小藍(lán)
- 領(lǐng)接矩陣 adjacency matrix 數(shù)據(jù) 0 和1
# 2.10
## 鄰接矩陣
get.adjacency(g)
7 x 7 sparse Matrix of class "dgCMatrix"
1 2 3 4 5 6 7
1 . 1 1 . . . .
2 1 . 1 1 . . .
3 1 1 . . 1 . .
4 . 1 . . 1 1 1
5 . . 1 1 . 1 .
6 . . . 1 1 . 1
7 . . . 1 . 1 .
子圖 subgraph
導(dǎo)出子圖 induced subgraph
# 2.11
## 導(dǎo)出子圖
h <- induced.subgraph(g, 1:5)
plot(h)
## 導(dǎo)出子圖 刪除節(jié)點(diǎn)6和節(jié)點(diǎn)7
h1 <- g - vertices(c(6,7))
plot(h1)
# 2.13
# 給h1增加兩個(gè)新節(jié)點(diǎn)酬荞,然后在增加邊
h1 <- h1 + vertices(c(6,7))
plot(h1)
g <- h1 + edges(c(4,5), c(4,7), c(5,6), c(6,7))
plot(g)
# 圖的合并
h1 <- h
h2 <- graph.formula(4-6, 4-7, 5-6, 6-7)
g <- graph.union(h1, h2)
plot(g)
2.3 網(wǎng)絡(luò)的修飾
> library(sand)
載入需要的程輯包:igraphdata
Statistical Analysis of Network Data with R
Type in C2 (+ENTER) to start with Chapter 2.
> g.lazega <- graph.data.frame(elist.lazega, directed = "FALSE", vertices = v.attr.lazega)
> g.lazega$name <- "Lazega Lawyers" # 給圖命名
>
> vcount(g.lazega) # 節(jié)點(diǎn)個(gè)數(shù)
[1] 36
> ecount(g.lazega) # 邊的個(gè)數(shù)
[1] 115
>
> list.vertex.attributes(g.lazega) # 節(jié)點(diǎn)的屬性
[1] "name" "Seniority" "Status" "Gender" "Office" "Years"
[7] "Age" "Practice" "School"
> is.simple(g) # 判斷是否是簡(jiǎn)答圖
[1] TRUE
> E(mg)$weight <- 1 # 給所有的邊賦值為1
> wg2 <- simplify(mg)
> is.simple(wg2)
[1] TRUE
> E(wg2)$weight
[1] 1 1 2 1 1 1 1 1 1 1
plot(mg)
plot(wg2)
把mg轉(zhuǎn)化為wg2
> # 圖g中節(jié)點(diǎn)5的鄰居
> neighbors(g,5)
+ 3/7 vertices, named, from bb8e27b:
[1] 3 4 6
>
> degree(g)
1 2 3 4 5 6 7
2 3 3 4 3 3 2
>
> degree(dg, mode = "in") # 有向圖搓劫,入度數(shù)
小明 小藍(lán) 小西
0 2 2
> degree(dg, mode = "out") # 無(wú)向圖瞧哟,出度數(shù)
小明 小藍(lán) 小西
2 1 1
g.full <- graph.full(7)
g.ring <- graph.ring(7)
g.tree <- graph.tree(7, children = 2, mode = "undirected")
g.star <- graph.star(7, mode = "undirected")
par(mfrow=c(2,2))
plot(g.full)
plot(g.ring)
plot(g.tree)
plot(g.star)
# 二部圖
g.bip <- graph.formula(actor1:actor2:actor3, movie1:movie2,
actor1:actor2-movie1, actor2:actor3 - movie2)
V(g.bip)$type <- grepl("^movie", V(g.bip)$name)
plot(g.bip)
3 網(wǎng)絡(luò)數(shù)據(jù)可視化
# 3.1
library(sand)
## 數(shù)據(jù)一:5x5x5的網(wǎng)格(3D)
g.l <- graph.lattice(c(5, 5, 5))
# 3.2
## 數(shù)據(jù)二:博客網(wǎng)絡(luò) 數(shù)據(jù)記錄了146個(gè)獨(dú)立博客之間的引用關(guān)系
data(aidsblog)
summary(aidsblog)
str(aidsblog)
# 這個(gè)函數(shù)不能用就調(diào)用基礎(chǔ)的api
vcount(aidsblog) # 節(jié)點(diǎn)個(gè)數(shù)
ecount(aidsblog) # 邊的個(gè)數(shù)
## 節(jié)點(diǎn)系列:Vertex sequence
V(aidsblog)
## 邊序列:Edge squence
E(aidsblog)
# 3.3
igraph.options(vertex.size=3, vertex.label=NA, edge.arrow.size=0.5)
par(mfrow=c(1, 2))
plot(g.l, layout=layout.circle)
title("5x5x5 Lattice")
plot(aidsblog, layout=layout.circle)
title("Blog Network")
# 3.4
plot(g.l, layout=layout.fruchterman.reingold)
title("5x5x5 Lattice")
plot(aidsblog, layout=layout.fruchterman.reingold)
title("Blog Network")
# 3.5
plot(g.l, layout=layout.kamada.kawai)
title("5x5x5 Lattice")
plot(aidsblog, layout=layout.kamada.kawai)
title("Blog Network")
# 3.7 二部圖的可視化
plot(g.bip, layout=-layout.bipartite(g.bip)[,2:1],
vertex.size=30, vertex.shapes=ifelse(V(g.bip)$type,
"rectangle", "circlr"),
vertex.color=ifelse(ifelse(V(g.bip)$type, "red", "cyan")))
Zachary 空手道俱樂(lè)部網(wǎng)絡(luò) (karate club network)
數(shù)據(jù)集合實(shí)際上只存在兩個(gè)社團(tuán),分別以教練為中心和以主管為中心枪向。
# 3.8
library(igraphdata)
data(karate)
# 可重復(fù)的布局
set.seed(42)
l <- layout.kamada.kawai(karate)
# 首先回執(zhí)未修飾的圖
igraph.options(vertex.size=10)
par(mfrow = c(1,1))
plot(karate, layout=1, vertex.label=V(karate))
# 修飾圖勤揩,首先設(shè)定標(biāo)簽
V(karate)$label <- sub("Actor", "", V(karate)$name)
# 兩個(gè)領(lǐng)導(dǎo)者與其他俱樂(lè)部成員的節(jié)點(diǎn)形狀不同
V(karate)$shape <- "circle"
V(karate)[c("Mr Hi", "John A")]$shape <- "rectangle"
# 使用顏色區(qū)分不同的派別
V(karate)[Faction == 1]$color <- "red"
V(karate)[Faction == 2]$color <- "dodgerblue"
# 節(jié)點(diǎn)面積正比于節(jié)點(diǎn)強(qiáng)弱(即所關(guān)聯(lián)邊的權(quán)重值之和)
V(karate)$size <- 4 * sqrt(graph.strength(karate))
V(karate)$size <- v(karate)$size * .5
# 將共同活動(dòng)的數(shù)量設(shè)定為邊的權(quán)重(粗細(xì))
E(karate)$width <- E(karate)$weight
# 使用顏色區(qū)分派別內(nèi)部和派別之間的邊
F1 <- V(karate)[Faction == 1]
F2 <- V(karate)[Faction == 2]
E(karate)[F1 %--% F1]$color <- "pink"
E(Karate)[F2 %--% F2]$color <- "lightblue"
E(karate)[F1 %--% F2]$color <- "yellow"
#這樣可以看出R語(yǔ)言繪圖確實(shí)有很多優(yōu)勢(shì)
# 較小節(jié)點(diǎn)的標(biāo)簽位置偏移量(初始為 0)
V(karate)$label.dist <- ifelse(V(karate)$size >= 10, 0, 0.75)
# 使用相同布局繪制修飾后的圖
plot(karate, layout=l)
Lazega律師網(wǎng)絡(luò)可視化
# 3.9
library(sand)
data(lazega)
# 使用顏色表示辦公地點(diǎn)
colbar <- c("red", "dodgerblue", "goldenrod")
v.colors <- colbar[V(lazega)$Office]
# 使用形狀表示執(zhí)業(yè)類型
v.shapes <- c("circle", "square")[V(lazega)$Practice]
# 節(jié)點(diǎn)大小正比于在公司工作了幾年
v.size <- 3.5 * sqrt(V(lazega)$Years)
# 節(jié)點(diǎn)標(biāo)簽為個(gè)人的資歷
v.label <- V(lazega)$Seniority
# 可重復(fù)布局
set.seed(42)
l <- layout.fruchterman.reingold(lazega)
plot(lazega, layout=l, vertex.color=v.colors, vertex.shape=v.shapes,
vertex.size=v.size, vertex.label=v.label)
大型網(wǎng)絡(luò)可視化
srt() 不能用使用 upgrade_graph()d代替
library(sand)
summary(fblog)
upgrade_graph(fblog)
# upgrade_graph(fblog) = summary(fblog) + str(fblog)
# 新api 舊api
library(sand)
summary(fblog)
upgrade_graph(fblog)
# upgrade_graph(fblog) = summary(fblog) + str(fblog)
# 新api 舊api
list.vertex.attributes(fblog) # 節(jié)點(diǎn)的屬性
party.names <- sort(unique(V(fblog)$PolParty))
party.names
set.seed(42) # 設(shè)定隨機(jī)數(shù)種子,一個(gè)特定的種子可以產(chǎn)生一個(gè)特定的偽隨機(jī)序列秘蛔,
l = layout.kamada.kawai(fblog)
party.nums.f <- as.factor(V(fblog)$PolParty)
party.nums <- as.numeric(party.names.f)
plot(fblog, layout=l, vertex.color=party.nums,
vertex.size=3, vertex.label=NA)
DrL算法陨亡,針對(duì)大型網(wǎng)絡(luò)可視化設(shè)計(jì)的布局算法。
set.seed(42) # 設(shè)定隨機(jī)數(shù)種子深员,一個(gè)特定的種子可以產(chǎn)生一個(gè)特定的偽隨機(jī)序列
l <- layout.drl(fblog)
plot(fblog, layout=l, vertex.size=5, vertex.label=NA, vertex.color=party.nums)
元節(jié)點(diǎn)繪制
節(jié)點(diǎn)的節(jié)點(diǎn)负蠕,即社區(qū)節(jié)點(diǎn)(主題節(jié)點(diǎn))
fblog.c <- contract.vertices(fblog, party.nums)
E(fblog.c)$weight <- 1
fblog.c <- simplify(fblog.c)
party.size <- as.vector(table(V(fblog)$PolParty))
plot(fblog.c, vertex.size=5*sqrt(party.size),
vertex.label=party.names,vertex.color=V(fblog.c),
edge.width=sqrt(E(fblog.c)$weight),
vertex.label.dist=1.5,edge.arrow.size=0)
個(gè)體中心網(wǎng)(egocentric network)
即一個(gè)中心節(jié)點(diǎn),一其直接相連的鄰居倦畅,以及這些節(jié)點(diǎn)至今的邊遮糖。
data("karate")
k.nbhds <- graph.neighborhood(karate, order = 1)
# k.nbhds形成了不同的圖
# 教練(Mr Hi, 節(jié)點(diǎn)1) 和 主管(John A叠赐,節(jié)點(diǎn)34)的鄰居規(guī)模最大
sapply(k.nbhds, vcount) # 函數(shù)vcount 節(jié)點(diǎn)計(jì)數(shù)
# 提取連個(gè)最大的子網(wǎng)絡(luò)并繪制網(wǎng)絡(luò)
k.1 <- k.nbhds[[1]]
k.34 <- k.nbhds[[34]]
par(mfrow = c(1,2))
plot(k.1, vertex.label=NA,
vertex.color=c("red", rep("lightblue", 16)))
plot(k.34, vertex.label=NA,
vertex.color=c(rep("lightblue", 17),"red"))
第四章 網(wǎng)絡(luò)圖特征的描述性分析
4.2節(jié)點(diǎn)和邊
度分布
library(igraph)
library(sand)
data(karate)
hist(degree(karate), col="lightblue", xlim = c(0,50),
xlab = "Vertex Degree", ylab = "Frequency", main="")
節(jié)點(diǎn)強(qiáng)度分布
- 強(qiáng)度strength 即與某個(gè)節(jié)點(diǎn)相連的邊的權(quán)重之和
hist(graph.strength(karate), col="pink",
xlab = "Vertex Strength", ylab = "Frequency", main="")
library(igraphdata)
data(yeast)
# 邊的數(shù)量
ecount(yeast)
# 節(jié)點(diǎn)的數(shù)量
vcount(yeast)
d.yeast <- degree(yeast)
par(mfrow = c(1,2))
# 節(jié)點(diǎn)度分布的異質(zhì)性很強(qiáng)
hist(d.yeast, col="blue",
xlab="Degree",ylab="Frequency",
main="Degree Distribution")
#度的分布遞減欲账,采用雙對(duì)數(shù)坐標(biāo)表達(dá)度的信息更為有效
dd.yeast <- degree.distribution(yeast)
d <- 1:max(d.yeast)-1
ind <- (dd.yeast != 0)
plot(d[ind], dd.yeast[ind], log="xy", col="blue",
xlab=c("Log-Degree"), ylab=c("Log-Intensity"),
mian="Log-Log Degree Distribution")
度值不同的節(jié)點(diǎn)以何種方式彼此連接
a.nn.deg.yeast <- graph.knn(yeast, V(yeast))$knn
plot(d.yeast, a.nn.deg.yeast, log="xy",
col="goldenrod", xlab = c("Log Vertex Degree"),
ylab = c("Log Average Neighbor Degree"))
節(jié)點(diǎn)中心性(centrality)
- 接近中心性 closeness centrality
l <- layout.kamada.kawai(aidsblog)
par(mfrow=c(1,2))
plot(aidsblog, layout=l, mian="Hubs",
vertex.label="", vertex.size=10 *
sqrt(hub.score(aidsblog)$vector))
plot(aidsblog, layout=l, mian="Authorities",
vertex.label="", vertex.size=10 *
sqrt(authority.score(aidsblog)$vector))
4.3 子圖,完全子圖
library(igraphdata)
library(igraph)
data(karate)
# cliques 團(tuán) 完全子圖
table(sapply(cliques(karate), length))
cliques(karate)[sapply(cliques(karate), length) == 5]
data(yeast)
clique.number(yeast)
cores <- graph.coreness(karate)
sna::gplot.target(g, cores, circ.lab = FALSE,
circ.col = "skyblue", userrow = FALSE,
vertex.col = cores, edge.col="darkgray")
detach("package:network")
detach("package:sna")
plot(aidsblog)
aidsblog <- simplify(aidsblog)
> dyad.census(aidsblog)
$`mut`
[1] 3
$asym
[1] 177
$null
[1] 10405
圖的密度
> ego.instr <- induced.subgraph(karate,
+ neighborhood(karate, 1, 1)[[1]])
>
> ego.admin <- induced.subgraph(karate,
+ neighborhood(karate, 1, 34)[[1]])
>
> graph.density(karate)
[1] 0.1390374
>
> graph.density(ego.instr)
[1] 0.25
>
> graph.density(ego.admin)
[1] 0.2091503
全局聚類系數(shù)
> transitivity(karate)
[1] 0.2556818
局部聚類系數(shù)
> transitivity(karate, "local", vids = c(1,34))
[1] 0.1500000 0.1102941
互惠性 reciprocity
二元組普查
> reciprocity(aidsblog, mode = "default")
[1] 0.03278689
>
> reciprocity(aidsblog, mode="ratio")
[1] 0.01666667
連通芭概,割與流
> is.connected(yeast)
[1] FALSE
plot(yeast, vertex.label=NA, vertex.size=3,edge.arrow.size=1)
plot(yeast, layout=layout.kamada.kawai,vertex.label=NA, vertex.size=3,edge.arrow.size=1)