This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.
Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Cmd+Shift+Enter.
# install.packages('tm')
# install.packages('RColorBrewer')
# install.packages('wordcloud')
library('tm')
## Loading required package: NLP
library('RColorBrewer')
library('wordcloud')
## [1] "Using direct authentication"
# Import data from a csv file to data frame
liuBK <- read.csv("liuBKData.csv", comment.char="#")
LIUTweets <- subset(liuBK)
# Save and read data to/from a R data object
saveRDS(LIUTweets, "LIUTweets.RDS")
LIUTweets <- readRDS("LIUTweets.RDS")
MLIUTweets <- LIUTweets$text
# Function to clean tweets
clean.text = function(x)
{
# tolower
x = tolower(x)
# remove rt
x = gsub("rt", "", x)
# remove at
x = gsub("@\\w+", "", x)
# remove punctuation
x = gsub("[[:punct:]]", "", x)
# remove numbers
x = gsub("[[:digit:]]", "", x)
# remove links http
x = gsub("http\\w+", "", x)
# remove tabs
x = gsub("[ |\t]{2,}", "", x)
# remove blank spaces at the beginning
x = gsub("^ ", "", x)
# remove blank spaces at the end
x = gsub(" $", "", x)
return(x)
}
# clean tweets
MLIUTweets = clean.text(MLIUTweets)
corpus = Corpus(VectorSource(MLIUTweets))
# corpus = Corpus(VectorSource(cmail))
# create term-document matrix
tdm = TermDocumentMatrix(
corpus,
control = list(
wordLengths=c(3,20),
removePunctuation = TRUE,
stopwords = c("the", "a", stopwords("english")),
removeNumbers = TRUE,
tolower = TRUE) )
# convert as matrix
tdm = as.matrix(tdm)
# get word counts in decreasing order
word_freqs = sort(rowSums(tdm), decreasing=TRUE)
#remove the top words which donât generate insights such as "the", "a", "and", etc.
#Here â1â is 1st word in the list we want to remove
word_freqs = word_freqs[-(1:9)]
# create a data frame with words and their frequencies
dm = data.frame(word=names(word_freqs), freq=word_freqs)
#Plot corpus in a clored graph; need RColorBrewer package
wordcloud(head(dm$word, 50), head(dm$freq, 50), random.order=FALSE, colors=brewer.pal(8, "Dark2"))
#check top 50 most mentioned words
head(word_freqs, 20)
## students eduaubdedububa eduaubdedubu glbs
## 9 8 8 7
## ubliubrooklynu ufufefpm gameday ufpm
## 7 7 6 6
## francis advocacyday albany standupstudentaid
## 6 5 5 5
## weareliubrooklyn big onepack saint
## 5 5 5 5
## wrac blackbirdnation spotlight blackbirds
## 5 5 4 4