---

分析於Acinetobater baumannii在Pubmed上的論文標題變化 :用以了解關於Ab菌的研究趨勢變化 =======================================================

匯入工具

library(RISmed)

## Warning: package 'RISmed' was built under R version 3.3.3

library("NLP")

## Warning: package 'NLP' was built under R version 3.3.3

library("tm")

## Warning: package 'tm' was built under R version 3.3.3

Sys.setenv(JAVA_HOME="C:\\Users\\jim87\\Documents\\R\\java")
library("rJava")

## Warning: package 'rJava' was built under R version 3.3.3

library("SnowballC")
library("slam")
library("Matrix")

## Warning: package 'Matrix' was built under R version 3.3.3

library("dplyr")

## Warning: package 'dplyr' was built under R version 3.3.3

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

以RISmed這個package從Pubmed上分別抓取2000~2017各年度的所有論文標題，並彙整到一個doc的資料夾中

匯入並轉換抓取到的資料

d.corpus <- Corpus(DirSource("doc"), list(language = NA))
d.corpus <- tm_map(d.corpus, removePunctuation)

TF-IDF演算法

control_list <- list(removePunctuation = TRUE, stopwords = TRUE, tolower = TRUE)
tdm <- TermDocumentMatrix(d.corpus,control = control_list)
tf <- apply(tdm, 2, sum) # term frequency
idf <- function(word_doc){ log2( (length(word_doc)+1) / nnzero(word_doc) ) }
idf <- apply(tdm, 1, idf)
options(scipen = 999)
doc.tfidf <- as.matrix(tdm)
for(i in 1:nrow(tdm)){
  for(j in 1:ncol(tdm)){
    doc.tfidf[i,j] <- (doc.tfidf[i,j] / tf[j]) * idf[i]
  }
}
colnames(doc.tfidf) <- c(2000:2017)
doc.tfidf = doc.tfidf*1000#TF-IDF太小，放大以方便計算
dataframe.tfidf = as.data.frame(doc.tfidf)