dplyr中类别之间的混淆

library(dplyr)

df2 <- df
df2 <- inner_join(df,df, by = "patient")
table(df2$condition.x,df2$condition.y)

    A B C D
  A 5 2 2 1
  B 2 5 3 2
  C 2 3 6 2
  D 1 2 2 4

下面是一个基本答案 outer

count_patient <- function(x, y) {
  length(intersect(df$patient[df$condition == x],
                   df$patient[df$condition == y])) 
}
vec <- sort(unique(df$condition))
res <- outer(vec, vec, Vectorize(count_patient))
dimnames(res) <- list(vec, vec)
res

#  A B C D
#A 5 2 2 1
#B 2 5 3 2
#C 2 3 6 2
#D 1 2 2 4