Creating wordcloud in R

# install.packages("tm")  # for text mining
# install.packages("wordcloud") # word-cloud generator 
# install.packages("RColorBrewer") # color palettes
# install.packages("wesanderson") # for Wes Anderson color palettes
# Load
library("tm")
# library("SnowballC")
library("wordcloud")
library("RColorBrewer")

setwd("~/Documents/playground")
text <-readLines("Sapiens.txt")
# Load the data as a corpus
docs <- Corpus(VectorSource(text))

toSpace <- content_transformer(function (x , pattern ) gsub(pattern, " ", x))
docs <- tm_map(docs, toSpace, "/")
docs <- tm_map(docs, toSpace, "@")
docs <- tm_map(docs, toSpace, "\\|")

# Convert the text to lower case
docs <- tm_map(docs, content_transformer(tolower))
# Remove numbers
docs <- tm_map(docs, removeNumbers)
# Remove english common stopwords
# Note that supported languages are danish, dutch, english, finnish, french, german, hungarian, italian, norwegian, portuguese, russian, spanish, and swedish. 
docs <- tm_map(docs, removeWords, stopwords("english"))
# Remove your own stop word
# specify your stopwords as a character vector
# cf. http://rstudio-pubs-static.s3.amazonaws.com/256588_57b585da6c054349825cba46685d8464.html#stop-words
# It's an iterative process to clean your corpus of text from stopwords.
all_stops <- c("can", "even", "one", "first", "will", "just", "yet",
              "two", "three", "also", "can", "may", "might", "another", "much", "many", "per",
              "now", "must", "next", "take", "may", "dont", "rather", "since", "ever", 
              "still", "humans", "made", "like", "almost", "however", "became", "without", 
              stopwords("en"))

# you can check the available 174 stopwords:
stopwords("en")
# and the newly created extended list:
all_stops
docs <- tm_map(docs, removeWords, all_stops) 
# Remove punctuations
# If your text is utf-8, you may want to use "ucp=TRUE" argument to get rid of some unwanted chars.
docs <- tm_map(docs, removePunctuation, ucp=TRUE)
# Eliminate extra white spaces
docs <- tm_map(docs, stripWhitespace)

dtm <- TermDocumentMatrix(docs)
m <- as.matrix(dtm)
v <- sort(rowSums(m),decreasing=TRUE)
d <- data.frame(word = names(v),freq=v)
head(d, 50)
# Pay attention to scale argument as well as min.freq.
set.seed(1234)
wordcloud(words = d$word, freq = d$freq, scale=c(1,.3), min.freq = 40,
          max.words=Inf, random.order=FALSE, rot.per=0.15, 
          colors=brewer.pal(8, "Dark2"))

library(wesanderson) #https://github.com/karthik/wesanderson
names(wes_palettes)
pal<-wes_palette("FantasticFox1")
pal

wordcloud(words = d$word, freq = d$freq, scale=c(1,.3), min.freq = 40,
          max.words=Inf, random.order=FALSE, rot.per=0.15, 
          colors=pal)

svg("sap_wc.svg")
wordcloud(words = d$word, freq = d$freq, scale=c(1,.3), min.freq = 40,
          max.words=Inf, random.order=FALSE, rot.per=0.15, 
          colors=pal)
dev.off()

png("sap_wc.png", width = 4, height = 4, units = 'in', res = 300)
wordcloud(words = d$word, freq = d$freq, scale=c(1,.3), min.freq = 40,
          max.words=Inf, random.order=FALSE, rot.per=0.15, 
          colors=pal)
dev.off()