r-pyglove.R

library(hadleyverse)
library(PythonInR)

# http://textminingonline.com/getting-started-with-word2vec-and-glove-in-python

# https://github.com/maciejkula/glove-python
# git clone https://github.com/maciejkula/glove-python.git
# $ sudo python setup.py develop
# $ sudo python setup.py install

# PythonInR::pyIsConnected()
# PythonInR::pyExit()
# PythonInR::pyConnect()

defPyConst <- function (
  param_list
) {
  sapply(
    X = seq(from = 1, to = length(param_list)),
    FUN = function (i) {
      cast_fun <- ifelse(test = is.integer(x = param_list[i][[1]]), yes = as.integer, no = as.numeric)
      PythonInR::pySet(
        key = stringr::str_to_lower(string = names(param_list[i])),
        value = cast_fun(param_list[i][[1]])
      )
    }
  )
}

callPyConst <- function (
  param_list_vec
){
  sapply(X = param_list_vec, FUN = defPyConst)
}


PythonInR::pyImport(import = c("Glove"), from = c("glove"))
PythonInR::pyImport(import = c("Corpus"), from = c("glove"))


SET_CORPUS <- list(
  FILE_NAME = "ptb.train.txt",
  CORPUS_PARAM = list(
    WINDOW_SIZE = 10L
  )
)

SET_GLOVE_PARAM <- list(
  MODEL = list(
    NO_COMPONENTS = 100L, LEARNING_RATE = 0.05
  ),
  TRAIN = list(
    EPOCHS = 30L, NO_THREADS = 1L
  )
)


callPyConst(
  param_list_vec = list(
    SET_CORPUS$CORPUS_PARAM, SET_GLOVE_PARAM$MODEL,  SET_GLOVE_PARAM$TRAIN
  )
)


sentences <- stringr::str_split(
  string = readr::read_lines(file = SET_CORPUS$FILE_NAME, n_max = -1),
  pattern = "[:space:]", n = Inf
)
PythonInR::pySet(key = "sentences", value = sentences)

create_corpus <- '
corpus = Corpus()
corpus.fit(corpus = sentences, window = window_size)
'
PythonInR::pyExec(code = create_corpus)

# PythonInR::pyPrint(objName = 'len(corpus.dictionary)')
# PythonInR::pyPrint(objName = 'corpus.dictionary')

train_glove <- '
glove_model = Glove(no_components = no_components, learning_rate = learning_rate)
glove_model.fit(matrix = corpus.matrix, epochs = epochs, no_threads = no_threads, verbose = False)
glove_model.add_dictionary(corpus.dictionary)
'
PythonInR::pyExec(code = train_glove)


word_vectors <- PythonInR::pyGet(key = 'glove_model.word_vectors')
words <- sort(x = PythonInR::pyGet(key = 'corpus.dictionary')) + 1
rownames(word_vectors) <- names(words)

word_similar <- do.call(what = "rbind", args = PythonInR::pyGet(key = 'glove_model.most_similar(word = "man", number = 10)'))