您可以查看“交叉验证”网站的关键字/ 标签。
作为网络分支
一种实现方法是根据关键字之间的关系（它们在同一帖子中重合的频率）将其绘制为网络。
当您使用此sql脚本从（data.stackexchange.com/stats/query/edit/1122036）获取网站的数据时
select Tags from Posts where PostTypeId = 1 and Score >2
然后，您将获得所有得分为2或更高的问题的关键字列表。
您可以通过绘制以下内容来探索该列表：
更新：颜色相同（基于关系矩阵的特征向量），并且没有自学习标签
您可以进一步清理该图（例如，删除与统计概念无关的标签，例如软件标签，在上图中，这已经针对“ r”标签完成了），并改善了视觉效果，但我想上面的图像已经显示了一个不错的起点。
R代码：
#the sql-script saved like an sql file
network <- read.csv("~/../Desktop/network.csv", stringsAsFactors = 0)
#it looks like this:
> network[1][1:5,]
[1] "<r><biostatistics><bioinformatics>"
[2] "<hypothesis-testing><nonlinear-regression><regression-coefficients>"
[3] "<aic>"
[4] "<regression><nonparametric><kernel-smoothing>"
[5] "<r><regression><experiment-design><simulation><random-generation>"
l <- length(network[,1])
nk <- 1
keywords <- c("<r>")
M <- matrix(0,1)
for (j in 1:l) { # loop all lines in the text file
s <- stringr::str_match_all(network[j,],"<.*?>") # extract keywords
m <- c(0)
for (is in s[[1]]) {
if (sum(keywords == is) == 0) { # check if there is a new keyword
keywords <- c(keywords,is) # add to the keywords table
nk<-nk+1
M <- cbind(M,rep(0,nk-1)) # expand the relation matrix with zero's
M <- rbind(M,rep(0,nk))
}
m <- c(m, which(keywords == is))
lm <- length(m)
if (lm>2) { # for keywords >2 add +1 to the relations
for (mi in m[-c(1,lm)]) {
M[mi,m[lm]] <- M[mi,m[lm]]+1
M[m[lm],mi] <- M[m[lm],mi]+1
}
}
}
}
#getting rid of < >
skeywords <- sub(c("<"),"",keywords)
skeywords <- sub(c(">"),"",skeywords)
# plotting connections
library(igraph)
library("visNetwork")
# reduces nodes and edges
Ms<-M[-1,-1] # -1,-1 elliminates the 'r' tag which offsets the graph
Ms[which(Ms<50)] <- 0
ww <- colSums(Ms)
el <- which(ww==0)
# convert to data object for VisNetwork function
g <- graph.adjacency(Ms[-el,-el], weighted=TRUE, mode = "undirected")
data <- toVisNetworkData(g)
# adjust some plotting parameters some
data$nodes['label'] <- skeywords[-1][-el]
data$nodes['title'] <- skeywords[-1][-el]
data$nodes['value'] <- colSums(Ms)[-el]
data$edges['width'] <- sqrt(data$edges['weight'])*1
data$nodes['font.size'] <- 20+log(ww[-el])*6
data$edges['color'] <- "#eeeeff"
#plot
visNetwork(nodes = data$nodes, edges = data$edges) %>%
visPhysics(solver = "forceAtlas2Based", stabilization = TRUE,
forceAtlas2Based = list(nodeDistance=70, springConstant = 0.04,
springLength = 50,
avoidOverlap =1)
)
层次分支
我认为，上述类型的网络图与对纯分支层次结构的一些批评有关。如果您愿意，我想您可以执行分层群集以将其强制为分层结构。
以下是这种分层模型的示例。仍然需要为各个集群找到合适的组名（但是，我认为这种分层集群并不是一个好的方向，因此我将其保留为开放状态）。
通过反复试验发现了聚类的距离度量（进行调整，直到聚类看起来不错为止。
#####
##### cluster
library(cluster)
Ms<-M[-1,-1]
Ms[which(Ms<50)] <- 0
ww <- colSums(Ms)
el <- which(ww==0)
Ms<-M[-1,-1]
R <- (keycount[-1]^-1) %*% t(keycount[-1]^-1)
Ms <- log(Ms*R+0.00000001)
Mc <- Ms[-el,-el]
colnames(Mc) <- skeywords[-1][-el]
cmod <- agnes(-Mc, diss = TRUE)
plot(as.hclust(cmod), cex = 0.65, hang=-1, xlab = "", ylab ="")
由StackExchangeStrike撰写
