United States State of the Union Addresses (2010 and 2011)

Description

Transcripts of the state of the union speeches. saved as a tm Corpus.

Usage

data(SOTU)

Author(s)

Barack Obama

Plot a commonality cloud

Description

Plot a cloud of words shared across documents

Usage

commonality.cloud(term.matrix,comonality.measure=min,max.words=300,...)

Arguments

Value

nothing

Examples

if(require(tm)){
	data(SOTU)
	corp <- SOTU
	corp <- tm_map(corp, removePunctuation)
	corp <- tm_map(corp, content_transformer(tolower))
	corp <- tm_map(corp, removeNumbers)
	corp <- tm_map(corp, function(x)removeWords(x,stopwords()))

	term.matrix <- TermDocumentMatrix(corp)
	term.matrix <- as.matrix(term.matrix)
	colnames(term.matrix) <- c("SOTU 2010","SOTU 2011")
	comparison.cloud(term.matrix,max.words=40,random.order=FALSE)
	commonality.cloud(term.matrix,max.words=40,random.order=FALSE)
}

Plot a comparison cloud

Description

Plot a cloud comparing the frequencies of words across documents.

Usage

comparison.cloud(term.matrix,scale=c(4,.5), max.words=300,
	random.order=FALSE, rot.per=.1,
	colors=brewer.pal(max(3,ncol(term.matrix)),"Dark2"),
	use.r.layout=FALSE, title.size=3,
	title.colors=NULL, match.colors=FALSE,
	title.bg.colors="grey90", ...)

Arguments

Details

Let p_{i,j} be the rate at which word i occurs in document j, and p_j be the average across documents(\sum_ip_{i,j}/ndocs). The size of each word is mapped to its maximum deviation ( max_i(p_{i,j}-p_j) ), and its angular position is determined by the document where that maximum occurs.

If title.colors is not NULL, it is used for document titles and match.colors is ignored.

Value

nothing

Examples

if(require(tm)){
	data(SOTU)
	corp <- SOTU
	corp <- tm_map(corp, removePunctuation)
	corp <- tm_map(corp, content_transformer(tolower))
	corp <- tm_map(corp, removeNumbers)
	corp <- tm_map(corp, function(x)removeWords(x,stopwords()))

	term.matrix <- TermDocumentMatrix(corp)
	term.matrix <- as.matrix(term.matrix)
	colnames(term.matrix) <- c("SOTU 2010","SOTU 2011")
	comparison.cloud(term.matrix,max.words=40,random.order=FALSE)
	comparison.cloud(term.matrix,max.words=40,random.order=FALSE,
		title.colors=c("red","blue"),title.bg.colors=c("grey40","grey70"))
	comparison.cloud(term.matrix,max.words=40,random.order=FALSE,
		match.colors=TRUE)

}

Text Plot

Description

An x y plot of non-overlapping text

Usage

textplot(x, y, words, cex=1,new=TRUE, show.lines=TRUE, ...)

Arguments

Value

nothing

Examples

#calculate standardized MDS coordinates
dat <- sweep(USArrests,2,colMeans(USArrests))
dat <- sweep(dat,2,sqrt(diag(var(dat))),"/")
loc <- cmdscale(dist(dat))

#plot with no overlap
textplot(loc[,1],loc[,2],rownames(loc))

#scale by urban population size
textplot(loc[,1],loc[,2],rownames(loc),cex=USArrests$UrbanPop/max(USArrests$UrbanPop))

#x limits sets x bounds of plot, and forces all words to be in bounds
textplot(loc[,1],loc[,2],rownames(loc),xlim=c(-3.5,3.5)) 

#compare to text (many states unreadable)
plot(loc[,1],loc[,2],type="n")
text(loc[,1],loc[,2],rownames(loc))

Plot a word cloud

Description

Plot a word cloud

Usage

wordcloud(words,freq,scale=c(4,.5),min.freq=3,max.words=Inf,
	random.order=TRUE, random.color=FALSE, rot.per=.1,
	colors="black",ordered.colors=FALSE,use.r.layout=FALSE,
	fixed.asp=TRUE, ...)

Arguments

Details

If freq is missing, then words can either be a character vector, or Corpus. If it is a vector and freq is missing, standard stop words will be removed prior to plotting.

Value

nothing

See Also

text

Examples

wordcloud(c(letters, LETTERS, 0:9), seq(1, 1000, len = 62))

if(require(tm)){

	##### 			from character 		#####
	wordcloud(
"Many years ago the great British explorer George Mallory, who 
was to die on Mount Everest, was asked why did he want to climb 
it. He said, \"Because it is there.\"

Well, space is there, and we're going to climb it, and the 
moon and the planets are there, and new hopes for knowledge 
and peace are there. And, therefore, as we set sail we ask 
God's blessing on the most hazardous and dangerous and greatest 
adventure on which man has ever embarked.",
	,random.order=FALSE)

## Not run: 
	data(crude)
	crude <- tm_map(crude, removePunctuation)
	crude <- tm_map(crude, function(x)removeWords(x,stopwords()))
	
	##### 			from corpus 		#####
	wordcloud(crude)
	
	
	##### 		from frequency counts 	#####
	tdm <- TermDocumentMatrix(crude)
	m <- as.matrix(tdm)
	v <- sort(rowSums(m),decreasing=TRUE)
	d <- data.frame(word = names(v),freq=v)
	
	wordcloud(d$word,d$freq)

	#A bigger cloud with a minimum frequency of 2
	wordcloud(d$word,d$freq,c(8,.3),2)

	#Now lets try it with frequent words plotted first
	wordcloud(d$word,d$freq,c(8,.5),2,,FALSE,.1)

	##### 			with colors 		#####
	if(require(RColorBrewer)){

		pal <- brewer.pal(9,"BuGn")
		pal <- pal[-(1:4)]
		wordcloud(d$word,d$freq,c(8,.3),2,,FALSE,,.15,pal)


		pal <- brewer.pal(6,"Dark2")
		pal <- pal[-(1)]
		wordcloud(d$word,d$freq,c(8,.3),2,,TRUE,,.15,pal)
		
		#random colors
		wordcloud(d$word,d$freq,c(8,.3),2,,TRUE,TRUE,.15,pal)
	}
	##### 			with font 			#####

	wordcloud(d$word,d$freq,c(8,.3),2,,TRUE,,.15,pal,
		vfont=c("gothic english","plain"))

	wordcloud(d$word,d$freq,c(8,.3),2,100,TRUE,,.15,pal,vfont=c("script","plain"))
	
	wordcloud(d$word,d$freq,c(8,.3),2,100,TRUE,,.15,pal,vfont=c("serif","plain"))

## End(Not run)
}

Word Layout

Description

finds text plot layout coordinates such that no text overlaps

Usage

wordlayout(x, y, words, cex=1, rotate90 = FALSE,
		xlim=c(-Inf,Inf), ylim=c(-Inf,Inf), tstep=.1, rstep=.1, ...)

Arguments

Value

A matrix with columns representing x, y width and height.

Examples

#calculate standardized MDS coordinates
dat <- sweep(USArrests,2,colMeans(USArrests))
dat <- sweep(dat,2,sqrt(diag(var(dat))),"/")
loc <- cmdscale(dist(dat))
x <- loc[,1]
y <- loc[,2]
w <- rownames(loc)

#plot with no overlap and all words visible
plot(x,y,type="n",xlim=c(-3,3),ylim=c(-3,2))
lay <- wordlayout(x,y,w,xlim=c(-3,3),ylim=c(-3,2))
text(lay[,1]+.5*lay[,3],lay[,2]+.5*lay[,4],w)

#notice north dakota is only partially visible
textplot(x,y,w)