codigo_R.txt

library(tm)
require(NLP)
require(openNLP)
library(shiny)
library(memoise)
library(qdap)

setDict("C:/Program Files (x86)/WordNet/2.1/dict")
Sys.setenv(WNHOME = "C:/Program Files (x86)/WordNet/2.1") 

inWordnet <- function(w, pos =  c("ADJECTIVE", "ADVERB", "NOUN", "VERB")) {
   for (x in pos) {
      filter <- getTermFilter("ExactMatchFilter", w, TRUE)
      terms <- getIndexTerms(x, 5, filter)
      if (!is.null(terms)) return(TRUE)
   }
   return(FALSE)
 }

if(initDict())

terms <- synonyms("realty", "NOUN")
terms_concepnet_one_gram <- c("property", "building", "ground", "realtor", "brownfield", "brownstone", "building", "grounds", "house", "modern","shelter", "construction", "plot", "land", "rental", "property", "residential", "safe", "house")
s<-Corpus(DirSource("D:/real_estate_50screen/"))
#match.string
phrase<-c("real estate")
word.freq <- apply_as_df(c, termco_d, match.string = phrase)
mcsv_w(word.freq, dir = NULL, open = F, sep = ", ", dataframes = NULL, pos = 1, envir = as.environment(pos))
removePuntuacoes <- function(x) gsub("[[:punct:]]","  ", x)
docs <- tm_map(c, content_transformer(removePuntuacoes))
alfa <- function(x) gsub("[^[:alnum:]]", "  ", x)
docs <- tm_map(docs, content_transformer(alfa))
docs <- tm_map(docs, tolower)
docs <- tm_map(docs, removeNumbers) 
docs <- tm_map(docs, stripWhitespace)
tdm<-TermDocumentMatrix(docs,control=list(wordLengths=c(3,Inf),weighting = weightTfIdf))
dtm<-DocumentTermMatrix(docs,control=list(wordLengths=c(3,Inf),weighting = weightTfIdf))
cor(as.matrix(dtm)[ , c("ground", "property")])