Last active
November 15, 2016 17:47
-
-
Save martinctc/08d77f39d4b116c6e2e7fe1a7c52b050 to your computer and use it in GitHub Desktop.
Basic Text Analytics for NPS Open-Ended Responses
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library("tm") | |
library("wordcloud") | |
library("SnowballC") | |
library("RColorBrewer") | |
library("tcltk2") | |
tk_choose.dir(getwd(),"Choose a suitable folder") | |
db = file.choose() | |
data <-read.csv(db,stringsAsFactors = FALSE) | |
#Create text corpuses for Promoters and Detractors | |
PromoCorp <- Corpus(VectorSource(data$Promoters)) | |
DetraCorp <- Corpus(VectorSource(data$Detractors)) | |
set.seed(169) | |
#Create word cloud for Promoters | |
PromoCorp<- tm_map(PromoCorp, removePunctuation) | |
PromoCorp<- tm_map(PromoCorp, removeWords,c(stopwords('english'))) | |
#PromoCorp <- tm_map(PromoCorp, stemDocument) | |
png("wordcloud_promoter.png", width=1000,height=1000) | |
wordcloud(PromoCorp, max.words=300, random.order=FALSE, colors=brewer.pal(8,"Dark2"), rot.per=0) | |
dev.off() | |
#Create word cloud for Detractors | |
DetraCorp<- tm_map(DetraCorp, removePunctuation) | |
DetraCorp<- tm_map(DetraCorp, removeWords,c(stopwords('english'),'dont')) | |
#DetraCorp <- tm_map(DetraCorp, stemDocument) | |
png("wordcloud_detractor.png", width=1000,height=1000) | |
wordcloud(DetraCorp, max.words=300, random.order=FALSE, colors=brewer.pal(8,"Dark2"), rot.per=0) | |
dev.off() | |
#Create word frequency table for Promoters | |
tdmpro = TermDocumentMatrix(PromoCorp) | |
# tdmpro <- removeSparseTerms(tdmpro,0.1) | |
mpro = as.matrix(tdmpro) | |
word_freqsp = sort(rowSums(mpro),decreasing = TRUE) | |
dmpro = data.frame(word=names(word_freqsp),freqp=word_freqsp) | |
write.csv(file="dmpro.csv",x=dmpro) | |
#Create word frequency table for Detractors | |
tdmdet = TermDocumentMatrix(DetraCorp) | |
# tdmdet <- removeSparseTerms(tdmdet,0.1) | |
mdet = as.matrix(tdmdet) | |
word_freqsd = sort(rowSums(mdet),decreasing = TRUE) | |
dmdet = data.frame(word=names(word_freqsd),freqd=word_freqsd) | |
write.csv(file="dmdet.csv",x=dmdet) | |
#Hierarchical clustering for Promoters | |
dtmpro <- DocumentTermMatrix(PromoCorp) | |
dtmpro <- removeSparseTerms(dtmpro,0.96) | |
dtmpro <- as.matrix(dtmpro) | |
d <- dist(t(dtmpro),method="euclidean") | |
fitp <- hclust(d=d, method="ward.D") | |
png("hcluster_promoter.png") | |
plot(fitp,hang=-1) | |
groups <- cutree (fitp, k=5) | |
rect.hclust(fitp,k=5, border="blue") | |
dev.off() | |
#Hierarchical clustering for Detractors | |
dtmdet <- DocumentTermMatrix(DetraCorp) | |
dtmdet <- removeSparseTerms(dtmdet,0.995) | |
dtmdet <- as.matrix(dtmdet) | |
d <- dist(t(dtmdet),method="euclidean") | |
fitd <- hclust(d=d, method="ward.D") | |
png("hcluster_detractor.png") | |
plot(fitd,hang=-1) | |
groups <- cutree (fitd, k=5) | |
rect.hclust(fitd,k=5, border="blue") | |
dev.off() | |
#Tokens Big-grams Function for Phrase Frequency | |
BigramTokenizer <- | |
function(x) | |
unlist(lapply(ngrams(words(x), 2), paste, collapse = " "), use.names = FALSE) | |
#Create special TDMs for Promoters and Detractors | |
tdmb_pro <- TermDocumentMatrix(PromoCorp,control=list(tokenize=BigramTokenizer)) | |
tdmb_det <- TermDocumentMatrix(DetraCorp,control=list(tokenize=BigramTokenizer)) | |
#Create CSV files for Promoters and Detractors Phrase Frequency Tables | |
bigram_pro = as.matrix(tdmb_pro) | |
word_freqbp = sort(rowSums(bigram_pro),decreasing = TRUE) | |
bigram_pro = data.frame(word=names(word_freqbp),freqp=word_freqbp) | |
write.csv(file="bigram_pro.csv",x=bigram_pro) | |
bigram_det = as.matrix(tdmb_det) | |
word_freqbd = sort(rowSums(bigram_det),decreasing = TRUE) | |
bigram_det = data.frame(word=names(word_freqbd),freqp=word_freqbd) | |
write.csv(file="bigram_det.csv",x=bigram_det) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment