def create_wfsa(options):
# open output file or write to stdout
output = open(options.output, "w") if options.output else sys.stdout
# read initial transitions if given
it = options.initial_transitions
initial_transitions = Automaton.read_transitions(it) if it else {}
# create uniform automaton with given number of states per letter
# and the possibility of predefine some transitions
if options.emitfile:
numbers_per_letters = read_dict(open(options.emitfile))
automaton = Automaton.create_uniform_automaton(numbers_per_letters, initial_transitions=initial_transitions)
automaton.dump(output)
if not options.smooth:
automaton.smooth()
return
if options.numstate:
input_ = sys.stdin
corpus = read_corpus(input_, options.separator)
alphabet = get_alphabet(corpus)
numbers_per_letters = dict([(letter, options.numstate) for letter in alphabet])
if options.num_epsilons:
numbers_per_letters["EPSILON"] = options.num_epsilons
automaton = Automaton.create_uniform_automaton(numbers_per_letters, initial_transitions)
if options.smooth:
automaton.smooth()
automaton.dump(output)
return
if options.init_from_corpus:
if len(initial_transitions) > 0:
raise Exception(
"Using initial transitions (-I option) when " + "creating automaton from corpus is not implemented"
)
input_ = open(options.init_from_corpus)
corpus = read_corpus(input_, options.separator)
corpus = normalize_corpus(corpus)
automaton = Automaton.create_from_corpus(corpus)
if options.smooth:
automaton.smooth()
automaton.dump(output)
return
# fallback
logging.error("Options are not complete, something is missing to create " + "an Automaton")
sys.exit(-1)
def run_uniform_exp(self, quantizer, distance, emissions, state_bits, entropy):
exp_name = "{0}-{1}-{2}-{3}-{4}".format(
quantizer.levels,
abs(quantizer.neg_cutoff),
'm',
emissions,
distance[0])
logging.info("Running {0}".format(exp_name))
learnt_wfsa_filename = "{0}/{1}".format(self.workdir,
"learnt_{0}.wfsa".format(exp_name))
corpus = (self.morpheme_corpus if emissions == "m" else
self.unigram_corpus)
# read Automaton or learn it and dump it finally
if os.path.exists(learnt_wfsa_filename):
# read already learnt automaton
learnt_wfsa = Automaton.create_from_dump(open(learnt_wfsa_filename))
learnt_wfsa.quantizer = quantizer
learnt_wfsa.round_and_normalize()
else:
# create and learn new automaton
alphabet = get_alphabet(corpus)
numbers_per_letters = dict([(letter, 1)
for letter in alphabet])
#print numbers_per_letters
wfsa = Automaton.create_uniform_automaton(numbers_per_letters)
wfsa.finalize()
wfsa.quantizer = quantizer
wfsa.round_and_normalize()
cp = lambda *x: checkpoint_dump(wfsa,
"{0}/cp_{1}".format(self.workdir, exp_name), *x)
logging.info('learning starts here')
learnt_wfsa = learn_wfsa(wfsa, corpus, distance, cp)
# dump
with open(learnt_wfsa_filename, "w") as of:
learnt_wfsa.dump(of)
# encode automaton
encoder = Encoder(entropy)
bits_a, bits_e, bits_t, err, hq, tc = encode_wfsa(
learnt_wfsa, corpus, encoder)
return [exp_name, bits_a, bits_e, bits_t, err, hq, tc]
