[R]R语言创建 TF-IDF矩阵_r tf-idf-优快云博客

用处：Textming ，构建VSM

第一种方法：

# environment 
library(tm)
library(proxy)
library(dplyr)

doc <- c( "The sky is blue.", "The sun is bright today.",
          "The sun in the sky is bright.", "We can see the shining sun, the bright sun." )


# create term frequency matrix using functions from tm library
doc_corpus <- Corpus( VectorSource(doc) )
control_list <- list(removePunctuation = TRUE, stopwords = TRUE, tolower = TRUE)
tdm <- TermDocumentMatrix(doc_corpus, control = control_list)

# print
( tf <- as.matrix(tdm) )

# idf
( idf <- log( ncol(tf) / ( 1 + rowSums(tf != 0) ) ) )

# diagonal matrix
( idf <- diag(idf) )

# tf-idf matrix
tf_idf <- crossprod(tf, idf)
colnames(tf_idf) <- rownames(tf)
tf_idf
# Note that normalization is computed "row-wise"
tf_idf / sqrt( rowSums( tf_idf^2 ) )

第二种方法：

tfidf=function(mat){
  tf <- mat
  id=function(col){sum(!col==0)}
  idf <- log(nrow(mat)/apply(mat, 2, id))
  tfidf <- mat
  for(word in names(idf)){tfidf[,word] <- tf[,word] * idf[word]}
  return(tfidf)
  }

第三种方法：

#creating term matrix with TF-IDF weighting
terms <-DocumentTermMatrix(corpus,control = list(weighting = function(x) weightTfIdf(x, normalize = FALSE)))

第4种方法：

library(textir)

data(we8there)
## 20 high-variance tf-idf terms
colnames(we8thereCounts)[
	order(-sdev(tfidf(we8thereCounts)))[1:20]]

参考：

https://stats.stackexchange.com/questions/78321/term-frequency-inverse-document-frequency-tf-idf-weighting

http://ethen8181.github.io/machine-learning/clustering_old/tf_idf/tf_idf.html