def probability_list_to_vocabulary(target, source, env):
with meta_open(source[0].rstr()) as ifd:
probs = ProbabilityList(ifd)
with meta_open(target[0].rstr(), "w") as ofd:
vocab = Vocabulary.from_set(probs.get_words())
ofd.write(vocab.format())
return None
def top_words(target, source, env):
args = source[-1].read()
with meta_open(source[0].rstr()) as words_ifd, meta_open(source[1].rstr()) as pron_ifd:
top = ProbabilityList(words_ifd).get_top_n(args["COUNT"])
prons = Pronunciations(pron_ifd)
prons.filter_by(top)
with meta_open(target[0].rstr(), "w") as words_ofd, meta_open(target[1].rstr(), "w") as pron_ofd:
words_ofd.write(top.format())
pron_ofd.write(prons.format())
return None
def filter_babel_gum(target, source, env):
with meta_open(source[0].rstr()) as pron_ifd, meta_open(source[1].rstr()) as prob_ifd, meta_open(source[2].rstr()) as lim_ifd:
pron = Pronunciations(pron_ifd)
logging.info("Old pronunciations: %s", pron)
prob = ProbabilityList(prob_ifd)
logging.info("Old probabilities: %s", prob)
filt = Vocabulary(lim_ifd)
logging.info("Correct words: %s", filt)
pron.filter_by(filt)
logging.info("New pronunciations: %s", pron)
prob.filter_by(filt)
logging.info("New probabilities: %s", prob)
with meta_open(target[0].rstr(), "w") as pron_ofd, meta_open(target[1].rstr(), "w") as prob_ofd:
pron_ofd.write(pron.format())
prob_ofd.write(prob.format())
return None
def plot_probabilities(target, source, env):
p = ProbabilityList(meta_open(source[0].rstr()))
ps = sorted([x.prob() for x in p.values()])
pyplot.plot(ps)
pyplot.savefig(target[0].rstr())
return None