jiebaR - 中文分词

http://qinwenfeng.com/jiebaR/

library(jiebaR)

wkr = worker()

segment("今天天气好晴朗", wkr)

library(jiebaR) library(sqldf) TA = read.csv('R/table-A.csv', header = TRUE, sep = ",") txtdf = TA$BAK_TXT TA$BAK_TXT <- as.character(TA$BAK_TXT) wkr = worker() # vector words = c() for( txt in txtdf ){     # add new segment into words     words <- c(words, segment(txt, wkr) ) } #jieba functions freqrs <- freq(words) # sort and count rs <- table(words) # convert to data frame rsdf <- as.data.frame(rs) rsdf$words <- as.character(rsdf$words) lowChar <- grep("[a-z]", rsdf$words) upperChar <- grep("[A-Z]", rsdf$words) numbers <- grep("[0-9]", rsdf$words) # check encoding #Encoding( rsdf$words  ) rowNums <- c(lowChar, upperChar, numbers) # delete duplicate row numbers rowNums <- unique(rowNums) # selelct none char/number rows chrs <- rsdf[-rowNums,] # check the length of string #nchar(chrs$words) nwords <- dim(chrs)[1] nrow = dim(TA)[1] for( i in 1:nwords ){   word <- chrs$words[i]   wordCols <- character()   for( j in 1:nrow ){     flg <- grepl(word, TA$BAK_TXT[j])     if( flg == TRUE ){       wordCols <- c( wordCols, "Y" )     }else{       wordCols <- c( wordCols, "N" )     }   }   wordCols <- as.data.frame(wordCols)   names(wordCols) <- word   TA <- cbind(TA, wordCols) } write.csv(TA, file = "rs-words.csv")

https://www.r-bloggers.com/r-function-of-the-day-table/