h2o.R

library(tm)

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

library(h2o)

h2o.init(ip = 'localhost', 
         port = 54321, 
         nthreads = -1, 
         max_mem_size = '14G')
trainedModel <- h2o.deeplearning(x = xnames, 
                                 y = 'labels', 
                                 training_frame = as.h2o(tfidf), 
                                 nfolds = 10,
                                 sparse = TRUE)