Jun 4, 2016

Beginning R - A word cloud generated from American Express Cards home page




Code Used:

cards <- Corpus (DirSource("C:\\Users\\kavin_000\\Documents\\R_tmp"))
cards <- tm_map(cards, stripWhitespace)
cards <- tm_map(cards, toupper)
cards <- tm_map(cards, removeWords, stopwords("english"))
cards <- tm_map(cards, stemDocument)
cards <- tm_map(cards, PlainTextDocument)
cards <- tm_map(cards, removeWords, c("and", "the", "will"))
cards <- tm_map(cards, removeWords, "and")
wordcloud(cards, scale=c(5,0.5), min.freq=10, max.words=100, random.order=FALSE, rot.per=0.35, use.r.layout=FALSE, colors=brewer.pal(8, "Dark2"))

Errors faced:


ErrorFix
Error: inherits(doc, "TextDocument") is not TRUElords <- tm_map(lords, PlainTextDocument)
Error: could not find function "wordcloud"install.packages("wordcloud")
library("wordcloud")
Error in loadNamespace(name) : there is no package called ‘SnowballC’install.packages("SnowballC")
Error: could not find function "Corpus"library(tm)
Error: '\U' used without hex digits in character string starting ""C:\Ureplace all the \ with \\


What to do next?

- remove and, the, for, etc ...
- how to add them to stopwords

Reference:

https://georeferenced.wordpress.com/2013/01/15/rwordcloud/


No comments:

Post a Comment