kidwellj/eco-emails
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Create newsletter-parse.R

Browse source
This commit is contained in:
Jeremy Kidwell 2019-02-20 19:45:35 +00:00 committed by GitHub
parent c2a8d4387c
commit 0d39e4d19a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 39 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

39
newsletter-parse.R Normal file
View file

@ -0,0 +1,39 @@
# Script to parse email newsletters from environmental groups
# Note: There doesn't seem to be a good package for ingesting email mbox files in R,
# so I have already processed an exported mbox file using python (https://github.com/jarrodparkes/mbox-to-csv)
# PRELIMINARIES, load libraries and data
require(tm)
require(wordcloud)
require(stringr)
# Start by generating wordcloud from CCF applications stored in CSV
# Clean data set
newsletters <- Corpus (DirSource("CCF/"))
ccf <- tm_map(ccf, stripWhitespace)
ccf <- tm_map(ccf, tolower)
ccf <- tm_map(ccf, removeNumbers)
ccf <- tm_map(ccf, removePunctuation)
# tweak by adding extra stopwords, "will"
myStopwords <- c(stopwords('english'), "will", "project")
# tweak by removing extra stopwords, in this example "r"
# idx <- which(myStopwords == "r")
# myStopwords <- myStopwords[-idx]
ccf <- tm_map(ccf, removeWords, myStopwords)
# ccf <- tm_map(ccf, stemDocument)
ccf <- tm_map(ccf, PlainTextDocument)
# Create word cloud
# wordcloud(ccf, scale=c(5,0.5), max.words=100, random.order=FALSE, rot.per=0.35, use.r.layout=FALSE, colors=brewer.pal(8, "Dark2"))
# wordcloud(ccf, scale=c(8,.2), min.freq=2, max.words=Inf, random.order=FALSE, rot.per=.15, colors=brewer.pal(8, "Dark2"))
wordcloud(ccf, scale=c(5,.3), max.words=250, random.order=FALSE, rot.per=0.35, use.r.layout=FALSE, colors=brewer.pal(8, "Dark3"))