USpresident

In the project, we plot two wordclouds. The first plot shows the most freqent words before President McKinley (1901). The second plot shows the most frequent words after President Roosevelt (1905). For comparison, the former is black and the latter is colorful.

require(tm)

## Loading required package: tm
## Loading required package: NLP

require(jiebaR)

## Loading required package: jiebaR
## Loading required package: jiebaRD

require(wordcloud)

## Loading required package: wordcloud
## Loading required package: RColorBrewer

USpresidentNameList <- read.table("~/Desktop/hw4_4/usP/before1901.txt",header=FALSE,sep='\n')
USpresidentList <-list()
total = c()
for (president in USpresidentNameList$V1){
    year <- substr(president,1,4)
    USpresidentList <- c(USpresidentList,year)
    fileName <- paste(c("usP",president),collapse='/')
    txt = scan(fileName, what = 'char')
    words_vector = worker() <= txt # word segmentation
    total <- append(total,words_vector)
}
t=table(total)
s=sort(t,decreasing=TRUE)
write.csv(s,'middle.csv')
oba <- read.csv('middle.csv')
words <- oba[,1]
word_freq <- oba[,2]
system("rm middle.csv")
wordcloud(words,word_freq,min.freq=30)

# Before 1901

USpresidentNameList <- read.table("~/Desktop/hw4_4/usP/after1905.txt",header=FALSE,sep='\n')
USpresidentList <-list()
total = c()
for (president in USpresidentNameList$V1){
    year <- substr(president,1,4)
    USpresidentList <- c(USpresidentList,year)
    fileName <- paste(c("usP",president),collapse='/')
    txt = scan(fileName, what = 'char')
    words_vector = worker() <= txt # word segmentation
    total <- append(total,words_vector)
}
t=table(total)
s=sort(t,decreasing=TRUE)
write.csv(s,'middle.csv')
oba <- read.csv('middle.csv')
words <- oba[,1]
word_freq <- oba[,2]
system("rm middle.csv")
pa12 <- brewer.pal(8,"Dark2")
wordcloud(words,word_freq,min.freq=30,colors=pa12)

# After 1905