使用lsa
包和该包的手册
# create some files
library('lsa')
td = tempfile()
dir.create(td)
write( c("HDa","2Pb","2","BxU","BuQ","Bve"), file=paste(td, "D1", sep="/"))
write( c("HCK","2Pb","2","09","F","G"), file=paste(td, "D2", sep="/"))
# read files into a document-term matrix
myMatrix = textmatrix(td, minWordLength=1)
编辑:显示如何mymatrix
object
myMatrix
#myMatrix
# docs
# terms D1 D2
# 2 1 1
# 2pb 1 1
# buq 1 0
# bve 1 0
# bxu 1 0
# hda 1 0
# 09 0 1
# f 0 1
# g 0 1
# hck 0 1
# Calculate cosine similarity
res <- lsa::cosine(myMatrix[,1], myMatrix[,2])
res
#0.3333