导入
文档-词项矩阵
了解文档-词项矩阵为何是自然语言处理中一种被广泛接受的数据结构。
library(tm, quietly = TRUE)
docDir <- DirSource(directory = "data", pattern = "mws_.+txt")
newCorpus <- Corpus(docDir)
DTmatrix <- DocumentTermMatrix(newCorpus) inspect(DTmatrix)
library(tm, quietly = TRUE)
docDir <- DirSource(directory = "data", pattern = "mws_.+txt")
newCorpus <- Corpus(docDir)
DTmatrix <- DocumentTermMatrix(newCorpus)
print("查找频繁项 -----------") findFreqTerms(DTmatrix, lowfreq = 400) print("查找最高频项 --------") findMostFreqTerms(DTmatrix)