| Title: | Word Clouds |
|---|---|
| Description: | Functionality to create pretty word clouds, visualize differences and similarity between documents, and avoid over-plotting in scatter plots with text. |
| Authors: | Ian Fellows |
| Maintainer: | Ian Fellows <[email protected]> |
| License: | LGPL-2.1 |
| Version: | 2.6 |
| Built: | 2024-08-21 04:00:09 UTC |
| Source: | https://github.com/ifellows/wordcloud |
Plot a cloud of words shared across documents
commonality.cloud(term.matrix,comonality.measure=min,max.words=300,...)commonality.cloud(term.matrix,comonality.measure=min,max.words=300,...)
term.matrix |
A term frequency matrix whose rows represent words and whose columns represent documents. |
comonality.measure |
A function taking a vector of frequencies for a single term, and returning a common frequency |
max.words |
Maximum number of words to be plotted. least frequent terms dropped |
... |
Additional parameters to be passed to wordcloud. |
nothing
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) }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 cloud comparing the frequencies of words across documents.
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", ...)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", ...)
term.matrix |
A term frequency matrix whose rows represent words and whose columns represent documents. |
scale |
A vector of length 2 indicating the range of the size of the words. |
max.words |
Maximum number of words to be plotted. least frequent terms dropped |
random.order |
plot words in random order. If false, they will be plotted in decreasing frequency |
rot.per |
proportion words with 90 degree rotation |
colors |
Color words in the order of columns in |
use.r.layout |
if false, then c++ code is used for collision detection, otherwise R is used |
title.size |
Size of document titles |
title.colors |
Colors used for document titles. See details. |
match.colors |
Logical: should colors document titles colors match word colors? See details. |
title.bg.colors |
Colors used for the background of document titles. |
... |
Additional parameters to be passed to text (and strheight,strwidth). |
Let be the rate at which word i occurs in document j, and be the
average across documents(). The size of each word is mapped to its maximum deviation
( ), 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.
nothing
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) }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) }
Transcripts of the state of the union speeches. saved as a tm Corpus.
data(SOTU)data(SOTU)
Barack Obama
An x y plot of non-overlapping text
textplot(x, y, words, cex=1,new=TRUE, show.lines=TRUE, ...)textplot(x, y, words, cex=1,new=TRUE, show.lines=TRUE, ...)
x |
x coordinates |
y |
y coordinates |
words |
the text to plot |
cex |
font size |
new |
should a new plot be created |
show.lines |
if true, then lines are plotted between x,y and the word, for those words not covering their x,y coordinates |
... |
Additional parameters to be passed to wordlayout and text. |
nothing
#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))#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
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, ...)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, ...)
words |
the words |
freq |
their frequencies |
scale |
A vector of length 2 indicating the range of the size of the words. |
min.freq |
words with frequency below min.freq will not be plotted |
max.words |
Maximum number of words to be plotted. least frequent terms dropped |
random.order |
plot words in random order. If false, they will be plotted in decreasing frequency |
random.color |
choose colors randomly from the colors. If false, the color is chosen based on the frequency |
rot.per |
proportion words with 90 degree rotation |
colors |
color words from least to most frequent |
ordered.colors |
if true, then colors are assigned to words in order |
use.r.layout |
if false, then c++ code is used for collision detection, otherwise R is used |
fixed.asp |
if TRUE, the aspect ratio is fixed. Variable aspect ratio only supported if rot.per==0 |
... |
Additional parameters to be passed to text (and strheight,strwidth). |
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.
nothing
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) }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) }
finds text plot layout coordinates such that no text overlaps
wordlayout(x, y, words, cex=1, rotate90 = FALSE, xlim=c(-Inf,Inf), ylim=c(-Inf,Inf), tstep=.1, rstep=.1, ...)wordlayout(x, y, words, cex=1, rotate90 = FALSE, xlim=c(-Inf,Inf), ylim=c(-Inf,Inf), tstep=.1, rstep=.1, ...)
x |
x coordinates |
y |
y coordinates |
words |
the text to plot |
cex |
font size |
rotate90 |
a value or vector indicating whether words should be rotated 90 degrees |
xlim |
x axis bounds for text |
ylim |
y axis bounds for text |
tstep |
the angle (theta) step size as the algorithm spirals out |
rstep |
the radius step size (in standard deviations) as the algorithm spirals out |
... |
Additional parameters to be passed to strwidth and strheight. |
A matrix with columns representing x, y width and height.
#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)#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)