Campania electorala 2016

corpus <- Corpus(DirSource("E:/Big Data/texte", encoding="windows-1250"),

readerControl=list(language="ro"))

corpusVars <- data.frame(var1=factor(rep("", length(corpus))),

row.names=names(corpus))

activeDataSet("corpusVars")

setCorpusVariables()

corpus <- splitTexts(corpus, 20)

meta(corpus, type="corpus", tag="split") <- TRUE

dtmCorpus <- corpus

dtmCorpus <- tm_map(dtmCorpus, content_transformer(tolower))

dtmCorpus <- tm_map(dtmCorpus, content_transformer(function(x)

gsub("(['’\n<U+202F><U+2009>]|[[:punct:]]|[[:space:]]|[[:cntrl:]])+", " ",

x)))

dtmCorpus <- tm_map(dtmCorpus, removeNumbers)

dtm <- DocumentTermMatrix(dtmCorpus, control=list(tolower=FALSE,

wordLengths=c(2, Inf)))

rm(dtmCorpus)

library(SnowballC)

dictionary <- data.frame(row.names=colnames(dtm),

"Occurrences"=col_sums(dtm), "Stemmed.Term"=wordStem(colnames(dtm), "ro"),

"Stopword"=ifelse(colnames(dtm) %in% stopwords("ro"), "Stopword", ""),

stringsAsFactors=FALSE)

dtm <- dtm[, !colnames(dtm) %in% stopwords("ro")]

dtm <- rollup(dtm, 2, dictionary[colnames(dtm), 2])

attr(dtm, "dictionary") <- dictionary

rm(dictionary)

meta(corpus, type="corpus", tag="language") <- attr(dtm, "language") <- "ro"

meta(corpus, type="corpus", tag="processing") <- attr(dtm, "processing") <-

c(lowercase=TRUE, punctuation=TRUE, digits=TRUE, stopwords=TRUE,

stemming=TRUE, customStemming=FALSE, twitter=FALSE, removeHashtags=NA,

removeNames=NA)

corpus

dtm

graphplot <-

function(x,

         terms = sample(Terms(x), 20),

         corThreshold = 0.7,

         weighted=TRUE,

   diag=FALSE,

         ...)

{

    if (system.file(package = "igraph") == "")

        stop("Plotting requires package 'igraph'.")

    m <- if (inherits(x, "TermDocumentMatrix")) t(x) else x

    m <- as.matrix(m[, terms])

    c <- cor(m)

    c[c < corThreshold] <- 0

    c[is.na(c)] <- 0

    diag(c) <- 0

 tmgraph <- graph.adjacency(c, mode=c("undirected"), weighted=TRUE, diag=FALSE,

        add.colnames=NULL, add.rownames=NA)

        plot(tmgraph)

   

    invisible(tmgraph)

}

library(igraph)

(freq.terms <- findFreqTerms(dtm, lowfreq = 20))

agraph <- graphplot(dtm,term = freq.terms,corThreshold = 0.2)

write.graph(agraph,"e:/agraphPoliticAdevarul.graphml", format=c("graphml"))