Data Science Day #12 - Text Processing in R

Today's post is basics on text processing using R. We look at removing stop words, numbers, punctuations, lower case conversion etc..

	#Assign vector list of messages
	data <- c("This AAAA is a CAPITAL is a tweet123455, . ,,,,,,","This 333 spam , ... prize","Congratz Prize Winner22222222222343434","^&^*&*&^*&^*&")
	#View few records
	head(data)
	#Library for data cleansing
	library(tm)
	#Convert to message corpus
	msg_corpus <- Corpus(VectorSource(data))
	inspect(msg_corpus[1:4])
	#Remove punctuation
	refine_corpus <- tm_map(msg_corpus, removePunctuation)
	#String whitespaces
	refine_corpus <- tm_map(refine_corpus, stripWhitespace)
	#Convert to lower case
	refine_corpus <- tm_map(refine_corpus, content_transformer(tolower))
	#Remove Numbers
	refine_corpus <- tm_map(refine_corpus, removeNumbers)
	#Remove Stop Words
	refine_corpus <- tm_map(refine_corpus, removeWords, stopwords())
	writeLines(as.character(msg_corpus[1]))
	writeLines(as.character(refine_corpus[1]))
	writeLines(as.character(msg_corpus[2]))
	writeLines(as.character(refine_corpus[2]))
	writeLines(as.character(msg_corpus[3]))
	writeLines(as.character(refine_corpus[3]))
	writeLines(as.character(msg_corpus[4]))
	writeLines(as.character(refine_corpus[4]))

view raw RTextProcess.R hosted with ❤ by GitHub

	#set the working directory
	setwd("E:/Data/")
	#Tip #1 - List and iterate all files in directory
	filenames <- list.files(pattern="*.csv")
	print(filenames)
	#Tip #2 - Loop through all files
	for(i in seq_along(filenames))
	{
	print(filenames[i])
	}
	#Tip #3 - Initialize Empty Vectors
	a <- vector(mode="numeric", length=0)
	b <- vector(mode="numeric", length=0)

view raw RFilebasics.R hosted with ❤ by GitHub

Happy Learning!!!