deepnet.R

library(tm)
library(Matrix)

setwd('/Users/thiagomarzagao/Dropbox/dataScience/UnB-CIC/aulaText/')
comprasnet <- read.table('subset.csv', 
                         stringsAsFactors = FALSE, 
                         sep = ',',
                         nrows = 1000)
corpus <- Corpus(VectorSource(comprasnet$V2))
corpus <- tm_map(corpus, PlainTextDocument)
tfidf <- DocumentTermMatrix(corpus, control = list(weighting = weightTfIdf))
tfidf <- as.matrix(as.data.frame(inspect(tfidf)))
labels <- as.factor(comprasnet$V1)

library(caret)

fitControl <- trainControl(method = 'repeatedcv',
                           number = 10)
trainedModel <- train(x = Matrix(tfidf, sparse = TRUE), 
                      y = labels, 
                      method = 'dnn',
                      trControl = fitControl)