我需要一个相关的更一般问题的答案。以下是我对 Ben Bolker 的解决方案的概括:
my.data <- read.table(text = '
my.string my.cov
1.2... 1
.21111 2
..2122 3
...211 2
112111 4
212222 1
', header = TRUE, stringsAsFactors = FALSE)
desired.result.2ch <- read.table(text = '
my.string my.cov n.11 n.12 n.21 n.22
1.2... 1 0 0 0 0
.21111 2 3 0 1 0
..2122 3 0 1 1 1
...211 2 1 0 1 0
112111 4 3 1 1 0
212222 1 0 1 1 3
', header = TRUE, stringsAsFactors = FALSE)
desired.result.3ch <- read.table(text = '
my.string my.cov n.111 n.112 n.121 n.122 n.222 n.221 n.212 n.211
1.2... 1 0 0 0 0 0 0 0 0
.21111 2 2 0 0 0 0 0 0 1
..2122 3 0 0 0 1 0 0 1 0
...211 2 0 0 0 0 0 0 0 1
112111 4 1 1 1 0 0 0 0 1
212222 1 0 0 0 1 2 0 1 0
', header = TRUE, stringsAsFactors = FALSE)
find_overlaps <- function(s, my.cov, p) {
gg <- gregexpr(paste0("(?=",p,")"),s,perl=TRUE)[[1]]
if (length(gg)==1 && gg==-1) 0 else length(gg)
}
p <- c('11', '12', '21', '22', '111', '112', '121', '122', '222', '221', '212', '211')
my.output <- matrix(0, ncol = (nrow(my.data)+1), nrow = length(p))
for(i in seq(1,length(p))) {
my.data$p <- p[i]
my.output[i,1] <- p[i]
my.output[i,(2:(nrow(my.data)+1))] <-apply(my.data, 1, function(x) find_overlaps(x[1], x[2], x[3]))
apply(my.data, 1, function(x) find_overlaps(x[1], x[2], x[3]))
}
my.output
desired.result.2ch
desired.result.3ch
pre.final.output <- matrix(t(my.output[,2:7]), ncol=length(p), nrow=nrow(my.data))
final.output <- data.frame(my.data[,1:2], t(apply(pre.final.output, 1, as.numeric)))
colnames(final.output) <- c(colnames(my.data[,1:2]), paste0('x', p))
final.output
# my.string my.cov x11 x12 x21 x22 x111 x112 x121 x122 x222 x221 x212 x211
#1 1.2... 1 0 0 0 0 0 0 0 0 0 0 0 0
#2 .21111 2 3 0 1 0 2 0 0 0 0 0 0 1
#3 ..2122 3 0 1 1 1 0 0 0 1 0 0 1 0
#4 ...211 2 1 0 1 0 0 0 0 0 0 0 0 1
#5 112111 4 3 1 1 0 1 1 1 0 0 0 0 1
#6 212222 1 0 1 1 3 0 0 0 1 2 0 1 0