将数据帧转换为r中的邻接/权重矩阵

这里有一个非常粗糙而且可能非常低效的解决方案 tidyverse 争论和 combinat 生成排列。

library(tidyverse)
library(combinat)

df <- data.frame(n = c(2, 3, 2, 2), 
                 x = c("a, b", "a, c, d", "c, d", "d, b"))

df %>% 
    ## Parse entries in x into distinct elements
    mutate(split = map(x, str_split, pattern = ', '), 
           flat = flatten(split)) %>% 
    ## Construct 2-element subsets of each set of elements
    mutate(combn = map(flat, combn, 2, simplify = FALSE)) %>% 
    unnest(combn) %>% 
    ## Construct permutations of the 2-element subsets
    mutate(perm = map(combn, permn)) %>% 
    unnest(perm) %>% 
    ## Parse the permutations into row and column indices
    mutate(row = map_chr(perm, 1), 
           col = map_chr(perm, 2)) %>% 
    count(row, col) %>% 
    ## Long to wide representation
    spread(key = col, value = nn, fill = 0) %>% 
    ## Coerce to matrix
    column_to_rownames(var = 'row') %>% 
    as.matrix()

使用R基,你可以做如下的事情

a = strsplit(as.character(df$x),', ')
b = unique(unlist(a))
d = unlist(sapply(a,combn,2,toString))
e = data.frame(table(factor(d,c(paste(b,b,sep=','),combn(b,2,toString)))))
f = read.table(text = do.call(paste,c(sep =',', e)),sep=',',strip.white = T)
g = xtabs(V3~V1+V2,f)
g[lower.tri(g)] = t(g)[lower.tri(g)]
g
   V2
V1  a b c d
  a 0 1 1 1
  b 1 0 0 0
  c 1 0 0 2
  d 1 0 2 0

下面是另一种可能的方法 data.table :

#generate the combis
combis <- df[, transpose(combn(sort(strsplit(x, ", ")[[1L]]), 2L, simplify=FALSE)), 
    by=1L:df[,.N]]

#create new rows for identical letters within a pair or any other missing combi
withDiag <- out[CJ(c(V1,V2), c(V1,V2), unique=TRUE), on=.(V1, V2)]

#duplicate the above for lower triangular part of the matrix
withLowerTri <- rbindlist(list(withDiag, withDiag[,.(df, V2, V1)]))

#pivot to get weights matrix
outDT <- dcast(withLowerTri, V1 ~ V2, function(x) sum(!is.na(x)), value.var="df")

outDT 输出:

   V1 a b c d
1:  a 0 1 1 1
2:  b 1 0 0 1
3:  c 1 0 0 2
4:  d 1 1 2 0

如果需要矩阵输出,则

mat <- as.matrix(outDT[, -1L])
rownames(mat) <- unlist(outDT[,1L])

输出:

  a b c d
a 0 1 1 1
b 1 0 0 1
c 1 0 0 2
d 1 1 2 0