install.packages('tm')
library(tm)

#load text mining library
library(topicmodels)
setwd("D:\\Implementations\\Experiments\\JabRef2.6\\Source\\")
inputFile <- "D:\\Implementations\\Experiments\\JabRef2.6\\Source\\SourceAndQueriesNonP.txt"
con  <- file(inputFile, open = "r")

files <- list()

while (length(oneLine <- readLines(con, n = 1, warn = FALSE)) > 0) {
    files <- c(files,oneLine)
  } 

close(con)
docs <- Corpus(VectorSource(files))
 
#inspect a particular document in corpus
writeLines(as.character(docs[[3]]))

toSpace <- content_transformer(function(x, pattern) { return (gsub(pattern," \\1", x))})
docs <- tm_map(docs, toSpace, "([A-Z]{1,1})")

#start preprocessing
#remove potentially problematic symbols
toSpace <- content_transformer(function(x, pattern) { return (gsub(pattern,' ' , x))})
#docs <- tm_map(docs, toSpace, "[^[:alnum:] ]")
docs <- tm_map(docs, toSpace, "'")
docs <- tm_map(docs, toSpace, ",")
docs <- tm_map(docs, toSpace, "\.")
docs <- tm_map(docs, toSpace, "\"")
docs <- tm_map(docs, toSpace, "_")
docs <- tm_map(docs, toSpace, "@")
docs <- tm_map(docs, toSpace, "-")
writeLines(as.character(docs[[3]]))



#Transform to lower case
docs <-tm_map(docs,content_transformer(tolower))
writeLines(as.character(docs[[3]]))

#remove punctuation
docs <- tm_map(docs, removePunctuation)
#Strip digits
#docs <- tm_map(docs, removeNumbers)
#remove stopwords
docs <- tm_map(docs, removeWords, stopwords("english"))
#remove whitespace
docs <- tm_map(docs, stripWhitespace)
#Good practice to check every now and then
writeLines(as.character(docs[[3]]))


#define and eliminate all custom stopwords
myStopwords <- c("a", "about", "above", "across", "after", "afterwards", "again", "against", "all", "almost", "alone", "along", "already", "also", "although", "always", "am", "among", "amongst", "amoungst", "amount", "an", "and", "another", "any", "anyhow", "anyone", "anything", "anyway", "anywhere", "are", "around", "as", "at", "back", "be", "became", "because", "become", "becomes", "becoming", "been", "before", "beforehand", "behind", "being", "below", "beside", "besides", "between", "beyond", "bill", "both", "bottom", "but", "by", "call", "can", "cannot", "cant", "co", "computer", "con", "could", "couldnt", "cry", "de", "describe", "detail", "do", "done", "down", "due", "during", "each", "eg", "eight", "either", "eleven", "else", "elsewhere", "empty", "enough", "etc", "even", "ever", "every", "everyone", "everything", "everywhere", "except", "few", "fifteen", "fify", "fill", "find", "fire", "first", "five", "for", "former", "formerly", "forty", "found", "four", "from", "front", "full", "further", "get", "give", "go", "had", "has", "hasnt", "have", "he", "hence", "her", "here", "hereafter", "hereby", "herein", "hereupon", "hers", "herself", "him", "himself", "his", "how", "however", "hundred", "i", "ie", "if", "in", "inc", "indeed", "interest", "into", "is", "it", "its", "itself", "keep", "last", "latter", "latterly", "least", "less", "ltd", "made", "many", "may", "me", "meanwhile", "might", "mill", "mine", "more", "moreover", "most", "mostly", "move", "much", "must", "my", "myself", "name", "namely", "neither", "never", "nevertheless", "next", "nine", "no", "nobody", "none", "noone", "nor", "not", "nothing", "now", "nowhere", "of", "off", "often", "on", "once", "one", "only", "onto", "or", "other", "others", "otherwise", "our", "ours", "ourselves", "out", "over", "own", "part", "per", "perhaps", "please", "put", "rather", "re", "same", "see", "seem", "seemed", "seeming", "seems", "serious", "several", "shall", "she", "should", "show", "side", "since", "sincere", "six", "sixty", "so", "some", "somehow", "someone", "something", "sometime", "sometimes", "somewhere", "still", "such", "take", "ten", "than", "that", "the", "their", "them", "themselves", "then", "thence", "there", "thereafter", "thereby", "therefore", "therein", "thereupon", "these", "they", "thick", "thin", "third", "this", "those", "though", "three", "through", "throughout", "thru", "thus", "to", "together", "too", "top", "toward", "towards", "twelve", "twenty", "two", "un", "under", "until", "up", "upon", "us", "very", "via", "was", "we", "well", "were", "what", "whatever", "when", "whence", "whenever", "where", "whereafter", "whereas", "whereby", "wherein", "whereupon", "wherever", "whether", "which", "while", "whither", "who", "whoever", "whole", "whom", "whose", "why", "will", "with", "within", "without", "would", "yet", "you", "your", "yours", "yourself", "yourselves")
docs <- tm_map(docs, removeWords, myStopwords)

#Stem document
docs <- tm_map(docs,stemDocument)
writeLines(as.character(docs[[3]]))
dtm <- DocumentTermMatrix(docs)
#convert rownames to filenames
rownames(dtm) <-  c(1:length(docs))


#Core LDA
#Set parameters for Gibbs sampling
burnin <- 4000
iter <- 1000
thin <- 500
nstart <- 5
best <- FALSE
 seed<-NULL

#Number of topics
k <- 200

#Run LDA using Gibbs sampling
#ldaOut <-LDA(dtm,k, method="Gibbs", control=list(nstart=nstart, seed = seed, best=best, burnin = burnin, iter = iter, thin=thin))
ldaOut <-LDA(dtm,k, method="Gibbs", control=list( alpha=1, best=TRUE, iter=1000))
#ldaOut <-lda.collapsed.gibbs.sampler(dtm,k, K=10,vocab=corpusLDA$vocab,burnin=9999,num.iterations=1000,alpha=1,eta=0.1)
phi <- posterior(ldaOut)$terms
theta <- posterior(ldaOut)$topics 
CP<-theta%*%phi
#Res<-as.matrix(topics(CP))
rownames(CP)<-rownames(posterior(ldaOut)$topics)
colnames(CP)<-colnames(posterior(ldaOut)$terms)
CP=CP+1
SFiles=4607
QFiles=39
	index<-rownames(posterior(ldaOut)$topics)
		from <- 1
		to <- SFiles
		from1 <- SFiles+1
		to1 <- length(index) 
		scores<- c()
		documents <- matrix(SFiles,QFiles)
		for (j in from1:to1) {
				for (i in from:to) {	
				score<-prod(CP[index[i],Filter(function(x) nchar(x) > 2, unlist(strsplit((docs[j])$content, " ")))])
				scores<-c(scores, score)
				}
		}
		
documents <- matrix(unlist(scores), ncol = SFiles, byrow = TRUE)
colnames(documents)<-rownames(posterior(ldaOut)$topics)[1:SFiles]
rownames(documents)<-rownames(posterior(ldaOut)$topics)[(SFiles+1):(SFiles+QFiles)]
write.csv(documents,file=paste("LDA_R",k,"JabRef2.6.csv"))		


library(tm)
install.packages('topicmodels')
#load text mining library
library(topicmodels)
setwd("D:\\Implementations\\Experiments\\jEdit4.3\\Source\\")
inputFile <- "D:\\Implementations\\Experiments\\jEdit4.3\\Source\\SourceAndQueriesNonP.txt"
con  <- file(inputFile, open = "r")

files <- list()

while (length(oneLine <- readLines(con, n = 1, warn = FALSE)) > 0) {
    files <- c(files,oneLine)
  } 

close(con)
docs <- Corpus(VectorSource(files))
 
#inspect a particular document in corpus
writeLines(as.character(docs[[3]]))

toSpace <- content_transformer(function(x, pattern) { return (gsub(pattern," \\1", x))})
docs <- tm_map(docs, toSpace, "([A-Z]{1,1})")

#start preprocessing
#remove potentially problematic symbols
toSpace <- content_transformer(function(x, pattern) { return (gsub(pattern,' ' , x))})
#docs <- tm_map(docs, toSpace, "[^[:alnum:] ]")
docs <- tm_map(docs, toSpace, "'")
docs <- tm_map(docs, toSpace, ",")
docs <- tm_map(docs, toSpace, "\.")
docs <- tm_map(docs, toSpace, "\"")
docs <- tm_map(docs, toSpace, "_")
docs <- tm_map(docs, toSpace, "@")
docs <- tm_map(docs, toSpace, "-")
writeLines(as.character(docs[[3]]))



#Transform to lower case
docs <-tm_map(docs,content_transformer(tolower))
writeLines(as.character(docs[[3]]))

#remove punctuation
docs <- tm_map(docs, removePunctuation)
#Strip digits
#docs <- tm_map(docs, removeNumbers)
#remove stopwords
docs <- tm_map(docs, removeWords, stopwords("english"))
#remove whitespace
docs <- tm_map(docs, stripWhitespace)
#Good practice to check every now and then
writeLines(as.character(docs[[3]]))


#define and eliminate all custom stopwords
myStopwords <- c("a", "about", "above", "across", "after", "afterwards", "again", "against", "all", "almost", "alone", "along", "already", "also", "although", "always", "am", "among", "amongst", "amoungst", "amount", "an", "and", "another", "any", "anyhow", "anyone", "anything", "anyway", "anywhere", "are", "around", "as", "at", "back", "be", "became", "because", "become", "becomes", "becoming", "been", "before", "beforehand", "behind", "being", "below", "beside", "besides", "between", "beyond", "bill", "both", "bottom", "but", "by", "call", "can", "cannot", "cant", "co", "computer", "con", "could", "couldnt", "cry", "de", "describe", "detail", "do", "done", "down", "due", "during", "each", "eg", "eight", "either", "eleven", "else", "elsewhere", "empty", "enough", "etc", "even", "ever", "every", "everyone", "everything", "everywhere", "except", "few", "fifteen", "fify", "fill", "find", "fire", "first", "five", "for", "former", "formerly", "forty", "found", "four", "from", "front", "full", "further", "get", "give", "go", "had", "has", "hasnt", "have", "he", "hence", "her", "here", "hereafter", "hereby", "herein", "hereupon", "hers", "herself", "him", "himself", "his", "how", "however", "hundred", "i", "ie", "if", "in", "inc", "indeed", "interest", "into", "is", "it", "its", "itself", "keep", "last", "latter", "latterly", "least", "less", "ltd", "made", "many", "may", "me", "meanwhile", "might", "mill", "mine", "more", "moreover", "most", "mostly", "move", "much", "must", "my", "myself", "name", "namely", "neither", "never", "nevertheless", "next", "nine", "no", "nobody", "none", "noone", "nor", "not", "nothing", "now", "nowhere", "of", "off", "often", "on", "once", "one", "only", "onto", "or", "other", "others", "otherwise", "our", "ours", "ourselves", "out", "over", "own", "part", "per", "perhaps", "please", "put", "rather", "re", "same", "see", "seem", "seemed", "seeming", "seems", "serious", "several", "shall", "she", "should", "show", "side", "since", "sincere", "six", "sixty", "so", "some", "somehow", "someone", "something", "sometime", "sometimes", "somewhere", "still", "such", "take", "ten", "than", "that", "the", "their", "them", "themselves", "then", "thence", "there", "thereafter", "thereby", "therefore", "therein", "thereupon", "these", "they", "thick", "thin", "third", "this", "those", "though", "three", "through", "throughout", "thru", "thus", "to", "together", "too", "top", "toward", "towards", "twelve", "twenty", "two", "un", "under", "until", "up", "upon", "us", "very", "via", "was", "we", "well", "were", "what", "whatever", "when", "whence", "whenever", "where", "whereafter", "whereas", "whereby", "wherein", "whereupon", "wherever", "whether", "which", "while", "whither", "who", "whoever", "whole", "whom", "whose", "why", "will", "with", "within", "without", "would", "yet", "you", "your", "yours", "yourself", "yourselves")
docs <- tm_map(docs, removeWords, myStopwords)

#Stem document
docs <- tm_map(docs,stemDocument)
writeLines(as.character(docs[[3]]))
dtm <- DocumentTermMatrix(docs)
#convert rownames to filenames
rownames(dtm) <-  c(1:length(docs))


#Core LDA
#Set parameters for Gibbs sampling
burnin <- 4000
iter <- 1000
thin <- 500
nstart <- 5
best <- FALSE
 seed<-NULL

#Number of topics
k <- 200

#Run LDA using Gibbs sampling
#ldaOut <-LDA(dtm,k, method="Gibbs", control=list(nstart=nstart, seed = seed, best=best, burnin = burnin, iter = iter, thin=thin))
ldaOut <-LDA(dtm,k, method="Gibbs", control=list( alpha=1, best=TRUE, iter=1000))
#ldaOut <-lda.collapsed.gibbs.sampler(dtm,k, K=10,vocab=corpusLDA$vocab,burnin=9999,num.iterations=1000,alpha=1,eta=0.1)
phi <- posterior(ldaOut)$terms
theta <- posterior(ldaOut)$topics 
CP<-theta%*%phi
#Res<-as.matrix(topics(CP))
rownames(CP)<-rownames(posterior(ldaOut)$topics)
colnames(CP)<-colnames(posterior(ldaOut)$terms)
CP=CP+1
SFiles=6413
QFiles=150
	index<-rownames(posterior(ldaOut)$topics)
		from <- 1
		to <- SFiles
		from1 <- SFiles+1
		to1 <- length(index) 
		scores<- c()
		documents <- matrix(SFiles,QFiles)
		for (j in from1:to1) {
				for (i in from:to) {	
				score<-prod(CP[index[i],Filter(function(x) nchar(x) > 2, unlist(strsplit((docs[j])$content, " ")))])
				scores<-c(scores, score)
				}
		}
		
documents <- matrix(unlist(scores), ncol = SFiles, byrow = TRUE)
colnames(documents)<-rownames(posterior(ldaOut)$topics)[1:SFiles]
rownames(documents)<-rownames(posterior(ldaOut)$topics)[(SFiles+1):(SFiles+QFiles)]
write.csv(documents,file=paste("LDA_R",k,"jEdit4.3.csv"))		





install.packages('topicmodels')
library(tm)

#load text mining library
library(topicmodels)
setwd("D:\\Implementations\\Experiments\\Mylyn\\Source\\")
inputFile <- "D:\\Implementations\\Experiments\\Mylyn\\Source\\SourceAndQueriesNonP.txt"
con  <- file(inputFile, open = "r")

files <- list()

while (length(oneLine <- readLines(con, n = 1, warn = FALSE)) > 0) {
    files <- c(files,oneLine)
  } 

close(con)
docs <- Corpus(VectorSource(files))
 
#inspect a particular document in corpus
writeLines(as.character(docs[[3]]))

toSpace <- content_transformer(function(x, pattern) { return (gsub(pattern," \\1", x))})
docs <- tm_map(docs, toSpace, "([A-Z]{1,1})")

#start preprocessing
#remove potentially problematic symbols
toSpace <- content_transformer(function(x, pattern) { return (gsub(pattern,' ' , x))})
#docs <- tm_map(docs, toSpace, "[^[:alnum:] ]")
docs <- tm_map(docs, toSpace, "'")
docs <- tm_map(docs, toSpace, ",")
docs <- tm_map(docs, toSpace, "\.")
docs <- tm_map(docs, toSpace, "\"")
docs <- tm_map(docs, toSpace, "_")
docs <- tm_map(docs, toSpace, "@")
docs <- tm_map(docs, toSpace, "-")
writeLines(as.character(docs[[3]]))



#Transform to lower case
docs <-tm_map(docs,content_transformer(tolower))
writeLines(as.character(docs[[3]]))

#remove punctuation
docs <- tm_map(docs, removePunctuation)
#Strip digits
#docs <- tm_map(docs, removeNumbers)
#remove stopwords
docs <- tm_map(docs, removeWords, stopwords("english"))
#remove whitespace
docs <- tm_map(docs, stripWhitespace)
#Good practice to check every now and then
writeLines(as.character(docs[[3]]))


#define and eliminate all custom stopwords
myStopwords <- c("a", "about", "above", "across", "after", "afterwards", "again", "against", "all", "almost", "alone", "along", "already", "also", "although", "always", "am", "among", "amongst", "amoungst", "amount", "an", "and", "another", "any", "anyhow", "anyone", "anything", "anyway", "anywhere", "are", "around", "as", "at", "back", "be", "became", "because", "become", "becomes", "becoming", "been", "before", "beforehand", "behind", "being", "below", "beside", "besides", "between", "beyond", "bill", "both", "bottom", "but", "by", "call", "can", "cannot", "cant", "co", "computer", "con", "could", "couldnt", "cry", "de", "describe", "detail", "do", "done", "down", "due", "during", "each", "eg", "eight", "either", "eleven", "else", "elsewhere", "empty", "enough", "etc", "even", "ever", "every", "everyone", "everything", "everywhere", "except", "few", "fifteen", "fify", "fill", "find", "fire", "first", "five", "for", "former", "formerly", "forty", "found", "four", "from", "front", "full", "further", "get", "give", "go", "had", "has", "hasnt", "have", "he", "hence", "her", "here", "hereafter", "hereby", "herein", "hereupon", "hers", "herself", "him", "himself", "his", "how", "however", "hundred", "i", "ie", "if", "in", "inc", "indeed", "interest", "into", "is", "it", "its", "itself", "keep", "last", "latter", "latterly", "least", "less", "ltd", "made", "many", "may", "me", "meanwhile", "might", "mill", "mine", "more", "moreover", "most", "mostly", "move", "much", "must", "my", "myself", "name", "namely", "neither", "never", "nevertheless", "next", "nine", "no", "nobody", "none", "noone", "nor", "not", "nothing", "now", "nowhere", "of", "off", "often", "on", "once", "one", "only", "onto", "or", "other", "others", "otherwise", "our", "ours", "ourselves", "out", "over", "own", "part", "per", "perhaps", "please", "put", "rather", "re", "same", "see", "seem", "seemed", "seeming", "seems", "serious", "several", "shall", "she", "should", "show", "side", "since", "sincere", "six", "sixty", "so", "some", "somehow", "someone", "something", "sometime", "sometimes", "somewhere", "still", "such", "take", "ten", "than", "that", "the", "their", "them", "themselves", "then", "thence", "there", "thereafter", "thereby", "therefore", "therein", "thereupon", "these", "they", "thick", "thin", "third", "this", "those", "though", "three", "through", "throughout", "thru", "thus", "to", "together", "too", "top", "toward", "towards", "twelve", "twenty", "two", "un", "under", "until", "up", "upon", "us", "very", "via", "was", "we", "well", "were", "what", "whatever", "when", "whence", "whenever", "where", "whereafter", "whereas", "whereby", "wherein", "whereupon", "wherever", "whether", "which", "while", "whither", "who", "whoever", "whole", "whom", "whose", "why", "will", "with", "within", "without", "would", "yet", "you", "your", "yours", "yourself", "yourselves")
docs <- tm_map(docs, removeWords, myStopwords)

#Stem document
docs <- tm_map(docs,stemDocument)
writeLines(as.character(docs[[3]]))
dtm <- DocumentTermMatrix(docs)
#convert rownames to filenames
rownames(dtm) <-  c(1:length(docs))


#Core LDA
#Set parameters for Gibbs sampling
burnin <- 4000
iter <- 1000
thin <- 500
nstart <- 5
best <- FALSE
 seed<-NULL

#Number of topics
k <- 200

#Run LDA using Gibbs sampling
#ldaOut <-LDA(dtm,k, method="Gibbs", control=list(nstart=nstart, seed = seed, best=best, burnin = burnin, iter = iter, thin=thin))
ldaOut <-LDA(dtm,k, method="Gibbs", control=list( alpha=1, best=TRUE, iter=1000))
#ldaOut <-lda.collapsed.gibbs.sampler(dtm,k, K=10,vocab=corpusLDA$vocab,burnin=9999,num.iterations=1000,alpha=1,eta=0.1)
phi <- posterior(ldaOut)$terms
theta <- posterior(ldaOut)$topics 
CP<-theta%*%phi
#Res<-as.matrix(topics(CP))
rownames(CP)<-rownames(posterior(ldaOut)$topics)
colnames(CP)<-colnames(posterior(ldaOut)$terms)
CP=CP+1
SFiles=482
QFiles=25
	index<-rownames(posterior(ldaOut)$topics)
		from <- 1
		to <- SFiles
		from1 <- SFiles+1
		to1 <- length(index) 
		scores<- c()
		documents <- matrix(SFiles,QFiles)
		for (j in from1:to1) {
				for (i in from:to) {	
				score<-prod(CP[index[i],Filter(function(x) nchar(x) > 2, unlist(strsplit((docs[j])$content, " ")))])
				scores<-c(scores, score)
				}
		}
		
documents <- matrix(unlist(scores), ncol = SFiles, byrow = TRUE)
colnames(documents)<-rownames(posterior(ldaOut)$topics)[1:SFiles]
rownames(documents)<-rownames(posterior(ldaOut)$topics)[(SFiles+1):(SFiles+QFiles)]
write.csv(documents,file=paste("LDA_R",k,"Mylyn.csv"))		




install.packages('topicmodels')
library(tm)

#load text mining library
library(topicmodels)
setwd("D:\\Implementations\\Experiments\\Rhino\\Source\\")
inputFile <- "D:\\Implementations\\Experiments\\Rhino\\Source\\SourceAndQueriesNonP.txt"
con  <- file(inputFile, open = "r")

files <- list()

while (length(oneLine <- readLines(con, n = 1, warn = FALSE)) > 0) {
    files <- c(files,oneLine)
  } 

close(con)
docs <- Corpus(VectorSource(files))
 
#inspect a particular document in corpus
writeLines(as.character(docs[[3]]))

toSpace <- content_transformer(function(x, pattern) { return (gsub(pattern," \\1", x))})
docs <- tm_map(docs, toSpace, "([A-Z]{1,1})")

#start preprocessing
#remove potentially problematic symbols
toSpace <- content_transformer(function(x, pattern) { return (gsub(pattern,' ' , x))})
#docs <- tm_map(docs, toSpace, "[^[:alnum:] ]")
docs <- tm_map(docs, toSpace, "'")
docs <- tm_map(docs, toSpace, ",")
docs <- tm_map(docs, toSpace, "\.")
docs <- tm_map(docs, toSpace, "\"")
docs <- tm_map(docs, toSpace, "_")
docs <- tm_map(docs, toSpace, "@")
docs <- tm_map(docs, toSpace, "-")
writeLines(as.character(docs[[3]]))



#Transform to lower case
docs <-tm_map(docs,content_transformer(tolower))
writeLines(as.character(docs[[3]]))

#remove punctuation
docs <- tm_map(docs, removePunctuation)
#Strip digits
#docs <- tm_map(docs, removeNumbers)
#remove stopwords
docs <- tm_map(docs, removeWords, stopwords("english"))
#remove whitespace
docs <- tm_map(docs, stripWhitespace)
#Good practice to check every now and then
writeLines(as.character(docs[[3]]))


#define and eliminate all custom stopwords
myStopwords <- c("a", "about", "above", "across", "after", "afterwards", "again", "against", "all", "almost", "alone", "along", "already", "also", "although", "always", "am", "among", "amongst", "amoungst", "amount", "an", "and", "another", "any", "anyhow", "anyone", "anything", "anyway", "anywhere", "are", "around", "as", "at", "back", "be", "became", "because", "become", "becomes", "becoming", "been", "before", "beforehand", "behind", "being", "below", "beside", "besides", "between", "beyond", "bill", "both", "bottom", "but", "by", "call", "can", "cannot", "cant", "co", "computer", "con", "could", "couldnt", "cry", "de", "describe", "detail", "do", "done", "down", "due", "during", "each", "eg", "eight", "either", "eleven", "else", "elsewhere", "empty", "enough", "etc", "even", "ever", "every", "everyone", "everything", "everywhere", "except", "few", "fifteen", "fify", "fill", "find", "fire", "first", "five", "for", "former", "formerly", "forty", "found", "four", "from", "front", "full", "further", "get", "give", "go", "had", "has", "hasnt", "have", "he", "hence", "her", "here", "hereafter", "hereby", "herein", "hereupon", "hers", "herself", "him", "himself", "his", "how", "however", "hundred", "i", "ie", "if", "in", "inc", "indeed", "interest", "into", "is", "it", "its", "itself", "keep", "last", "latter", "latterly", "least", "less", "ltd", "made", "many", "may", "me", "meanwhile", "might", "mill", "mine", "more", "moreover", "most", "mostly", "move", "much", "must", "my", "myself", "name", "namely", "neither", "never", "nevertheless", "next", "nine", "no", "nobody", "none", "noone", "nor", "not", "nothing", "now", "nowhere", "of", "off", "often", "on", "once", "one", "only", "onto", "or", "other", "others", "otherwise", "our", "ours", "ourselves", "out", "over", "own", "part", "per", "perhaps", "please", "put", "rather", "re", "same", "see", "seem", "seemed", "seeming", "seems", "serious", "several", "shall", "she", "should", "show", "side", "since", "sincere", "six", "sixty", "so", "some", "somehow", "someone", "something", "sometime", "sometimes", "somewhere", "still", "such", "take", "ten", "than", "that", "the", "their", "them", "themselves", "then", "thence", "there", "thereafter", "thereby", "therefore", "therein", "thereupon", "these", "they", "thick", "thin", "third", "this", "those", "though", "three", "through", "throughout", "thru", "thus", "to", "together", "too", "top", "toward", "towards", "twelve", "twenty", "two", "un", "under", "until", "up", "upon", "us", "very", "via", "was", "we", "well", "were", "what", "whatever", "when", "whence", "whenever", "where", "whereafter", "whereas", "whereby", "wherein", "whereupon", "wherever", "whether", "which", "while", "whither", "who", "whoever", "whole", "whom", "whose", "why", "will", "with", "within", "without", "would", "yet", "you", "your", "yours", "yourself", "yourselves")
docs <- tm_map(docs, removeWords, myStopwords)

#Stem document
docs <- tm_map(docs,stemDocument)
writeLines(as.character(docs[[3]]))
dtm <- DocumentTermMatrix(docs)
#convert rownames to filenames
rownames(dtm) <-  c(1:length(docs))


#Core LDA
#Set parameters for Gibbs sampling
burnin <- 4000
iter <- 1000
thin <- 500
nstart <- 5
best <- FALSE
 seed<-NULL

#Number of topics
k <- 200

#Run LDA using Gibbs sampling
#ldaOut <-LDA(dtm,k, method="Gibbs", control=list(nstart=nstart, seed = seed, best=best, burnin = burnin, iter = iter, thin=thin))
ldaOut <-LDA(dtm,k, method="Gibbs", control=list( alpha=1, best=TRUE, iter=1000))
#ldaOut <-lda.collapsed.gibbs.sampler(dtm,k, K=10,vocab=corpusLDA$vocab,burnin=9999,num.iterations=1000,alpha=1,eta=0.1)
phi <- posterior(ldaOut)$terms
theta <- posterior(ldaOut)$topics 
CP<-theta%*%phi
#Res<-as.matrix(topics(CP))
rownames(CP)<-rownames(posterior(ldaOut)$topics)
colnames(CP)<-colnames(posterior(ldaOut)$terms)
CP=CP+1
SFiles=2801
QFiles=328
	index<-rownames(posterior(ldaOut)$topics)
		from <- 1
		to <- SFiles
		from1 <- SFiles+1
		to1 <- length(index) 
		scores<- c()
		documents <- matrix(SFiles,QFiles)
		for (j in from1:to1) {
				for (i in from:to) {	
				score<-prod(CP[index[i],Filter(function(x) nchar(x) > 2, unlist(strsplit((docs[j])$content, " ")))])
				scores<-c(scores, score)
				}
		}
		
documents <- matrix(unlist(scores), ncol = SFiles, byrow = TRUE)
colnames(documents)<-rownames(posterior(ldaOut)$topics)[1:SFiles]
rownames(documents)<-rownames(posterior(ldaOut)$topics)[(SFiles+1):(SFiles+QFiles)]
write.csv(documents,file=paste("LDA_R",k,"Rhino.csv"))		





library(tm)

#load text mining library
library(topicmodels)
setwd("D:\\Implementations\\Experiments\\iBatis\\Source\\")
inputFile <- "D:\\Implementations\\Experiments\\iBatis\\Source\\SourceAndQueriesNonP.txt"
con  <- file(inputFile, open = "r")

files <- list()

while (length(oneLine <- readLines(con, n = 1, warn = FALSE)) > 0) {
    files <- c(files,oneLine)
  } 

close(con)
docs <- Corpus(VectorSource(files))
 
#inspect a particular document in corpus
writeLines(as.character(docs[[3]]))

toSpace <- content_transformer(function(x, pattern) { return (gsub(pattern," \\1", x))})
docs <- tm_map(docs, toSpace, "([A-Z]{1,1})")

#start preprocessing
#remove potentially problematic symbols
toSpace <- content_transformer(function(x, pattern) { return (gsub(pattern,' ' , x))})
#docs <- tm_map(docs, toSpace, "[^[:alnum:] ]")
docs <- tm_map(docs, toSpace, "'")
docs <- tm_map(docs, toSpace, ",")
docs <- tm_map(docs, toSpace, "\.")
docs <- tm_map(docs, toSpace, "\"")
docs <- tm_map(docs, toSpace, "_")
docs <- tm_map(docs, toSpace, "@")
docs <- tm_map(docs, toSpace, "-")
writeLines(as.character(docs[[3]]))



#Transform to lower case
docs <-tm_map(docs,content_transformer(tolower))
writeLines(as.character(docs[[3]]))

#remove punctuation
docs <- tm_map(docs, removePunctuation)
#Strip digits
#docs <- tm_map(docs, removeNumbers)
#remove stopwords
docs <- tm_map(docs, removeWords, stopwords("english"))
#remove whitespace
docs <- tm_map(docs, stripWhitespace)
#Good practice to check every now and then
writeLines(as.character(docs[[3]]))


#define and eliminate all custom stopwords
myStopwords <- c("a", "about", "above", "across", "after", "afterwards", "again", "against", "all", "almost", "alone", "along", "already", "also", "although", "always", "am", "among", "amongst", "amoungst", "amount", "an", "and", "another", "any", "anyhow", "anyone", "anything", "anyway", "anywhere", "are", "around", "as", "at", "back", "be", "became", "because", "become", "becomes", "becoming", "been", "before", "beforehand", "behind", "being", "below", "beside", "besides", "between", "beyond", "bill", "both", "bottom", "but", "by", "call", "can", "cannot", "cant", "co", "computer", "con", "could", "couldnt", "cry", "de", "describe", "detail", "do", "done", "down", "due", "during", "each", "eg", "eight", "either", "eleven", "else", "elsewhere", "empty", "enough", "etc", "even", "ever", "every", "everyone", "everything", "everywhere", "except", "few", "fifteen", "fify", "fill", "find", "fire", "first", "five", "for", "former", "formerly", "forty", "found", "four", "from", "front", "full", "further", "get", "give", "go", "had", "has", "hasnt", "have", "he", "hence", "her", "here", "hereafter", "hereby", "herein", "hereupon", "hers", "herself", "him", "himself", "his", "how", "however", "hundred", "i", "ie", "if", "in", "inc", "indeed", "interest", "into", "is", "it", "its", "itself", "keep", "last", "latter", "latterly", "least", "less", "ltd", "made", "many", "may", "me", "meanwhile", "might", "mill", "mine", "more", "moreover", "most", "mostly", "move", "much", "must", "my", "myself", "name", "namely", "neither", "never", "nevertheless", "next", "nine", "no", "nobody", "none", "noone", "nor", "not", "nothing", "now", "nowhere", "of", "off", "often", "on", "once", "one", "only", "onto", "or", "other", "others", "otherwise", "our", "ours", "ourselves", "out", "over", "own", "part", "per", "perhaps", "please", "put", "rather", "re", "same", "see", "seem", "seemed", "seeming", "seems", "serious", "several", "shall", "she", "should", "show", "side", "since", "sincere", "six", "sixty", "so", "some", "somehow", "someone", "something", "sometime", "sometimes", "somewhere", "still", "such", "take", "ten", "than", "that", "the", "their", "them", "themselves", "then", "thence", "there", "thereafter", "thereby", "therefore", "therein", "thereupon", "these", "they", "thick", "thin", "third", "this", "those", "though", "three", "through", "throughout", "thru", "thus", "to", "together", "too", "top", "toward", "towards", "twelve", "twenty", "two", "un", "under", "until", "up", "upon", "us", "very", "via", "was", "we", "well", "were", "what", "whatever", "when", "whence", "whenever", "where", "whereafter", "whereas", "whereby", "wherein", "whereupon", "wherever", "whether", "which", "while", "whither", "who", "whoever", "whole", "whom", "whose", "why", "will", "with", "within", "without", "would", "yet", "you", "your", "yours", "yourself", "yourselves")
docs <- tm_map(docs, removeWords, myStopwords)

#Stem document
docs <- tm_map(docs,stemDocument)
writeLines(as.character(docs[[3]]))
dtm <- DocumentTermMatrix(docs)
#convert rownames to filenames
rownames(dtm) <-  c(1:length(docs))


#Core LDA
#Set parameters for Gibbs sampling
burnin <- 4000
iter <- 1000
thin <- 500
nstart <- 5
best <- FALSE
 seed<-NULL

#Number of topics
k <- 200

#Run LDA using Gibbs sampling
#ldaOut <-LDA(dtm,k, method="Gibbs", control=list(nstart=nstart, seed = seed, best=best, burnin = burnin, iter = iter, thin=thin))
ldaOut <-LDA(dtm,k, method="Gibbs", control=list( alpha=1, best=TRUE, iter=1000))
#ldaOut <-lda.collapsed.gibbs.sampler(dtm,k, K=10,vocab=corpusLDA$vocab,burnin=9999,num.iterations=1000,alpha=1,eta=0.1)
phi <- posterior(ldaOut)$terms
theta <- posterior(ldaOut)$topics 
CP<-theta%*%phi
#Res<-as.matrix(topics(CP))
rownames(CP)<-rownames(posterior(ldaOut)$topics)
colnames(CP)<-colnames(posterior(ldaOut)$terms)
CP=CP+1
SFiles=1869
QFiles=85
	index<-rownames(posterior(ldaOut)$topics)
		from <- 1
		to <- SFiles
		from1 <- SFiles+1
		to1 <- length(index) 
		scores<- c()
		documents <- matrix(SFiles,QFiles)
		for (j in from1:to1) {
				for (i in from:to) {	
				score<-prod(CP[index[i],Filter(function(x) nchar(x) > 2, unlist(strsplit((docs[j])$content, " ")))])
				scores<-c(scores, score)
				}
		}
		
documents <- matrix(unlist(scores), ncol = SFiles, byrow = TRUE)
colnames(documents)<-rownames(posterior(ldaOut)$topics)[1:SFiles]
rownames(documents)<-rownames(posterior(ldaOut)$topics)[(SFiles+1):(SFiles+QFiles)]
write.csv(documents,file=paste("LDA_R",k,"iBatis.csv"))		



