def save_hyp_graph(self,
filename,
word_idict_trg,
detailed=True,
highlight_best=True):
"""
Writes this translation's search graph to disk.
"""
if self.hyp_graph:
renderer = HypGraphRenderer(self.hyp_graph)
renderer.wordify(word_idict_trg)
renderer.save_png(filename, detailed, highlight_best)
else:
pass #TODO: Warning if no search graph has been constructed during decoding?
def _parallelized_main(fs_init, fs_next, c, bpe, tokenizer, detokenizer):
source_file_t = sent_tokenize(c.recv(4096).decode('utf-8'))
#print(source_file_t[i])
while source_file_t[0] != "EOT":
for i in range(len(source_file_t)):
# print source_file_t[i].decode('utf-8')
#pipe = subprocess.Popen("echo " + source_file_t[i] + "| perl truecase.perl --model en-truecase.mdl", shell=True)
#pipe = subprocess.Popen(["echo", '"' + source_file_t[i] + '"', "|", "perl", "truecase.perl", "--model",
# "en-truecase.mdl"], stdout=subprocess.PIPE)
#result = pipe.stdout.read()
#print pipe.communicate()
#print pipe
#print pipe.stdout
#print pipe.stdout.read()
#print pipe.
#print "Here"
#print result
#source_file_t[i] = subprocess.check_output()
source_file_t[i] = bpe.segment(
tokenizer.tokenize(source_file_t[i],
return_str=True)).strip()
#print "Passed"
print source_file_t
detokenized = ''
queue = Queue()
rqueue = Queue()
processes = [None] * n_process
for midx in xrange(n_process):
processes[midx] = Process(
target=translate_model,
args=(queue, rqueue, midx, models, options, k, normalize,
verbose, nbest, save_alignment is not None,
suppress_unk, return_hyp_graph, fs_init, fs_next))
processes[midx].start()
n_samples, source_sentences = _send_jobs(source_file_t, processes,
queue)
_finish_processes(queue)
#### The model loading takes place in the head of for loop, prolly in _retrieve_jobs
for i, trans in enumerate(
_retrieve_jobs(n_samples, processes, queue, rqueue)):
print "NEXT SENTENCE:"
if nbest:
samples, scores, word_probs, alignment, hyp_graph = trans
if return_hyp_graph:
renderer = HypGraphRenderer(hyp_graph)
renderer.wordify(word_idict_trg)
renderer.save_png(return_hyp_graph,
detailed=True,
highlight_best=True)
order = numpy.argsort(scores)
for j in order:
if print_word_probabilities:
probs = " ||| " + " ".join(
"{0}".format(prob) for prob in word_probs[j])
else:
probs = ""
saveto.write('{0} ||| {1} ||| {2}{3}\n'.format(
i, _seqs2words(samples[j]), scores[j], probs))
# print alignment matrix for each hypothesis
# header: sentence id ||| translation ||| score ||| source ||| source_token_count+eos
# translation_token_count+eos
if save_alignment is not None:
if a_json:
print_matrix_json(
alignment[j], source_sentences[i],
_seqs2words(samples[j]).split(), i, i + j,
save_alignment)
else:
save_alignment.write(
'{0} ||| {1} ||| {2} ||| {3} ||| {4} {5}\n'
.format(i, _seqs2words(samples[j]),
scores[j],
' '.join(source_sentences[i]),
len(source_sentences[i]) + 1,
len(samples[j])))
print_matrix(alignment[j], save_alignment)
else:
samples, scores, word_probs, alignment, hyp_graph = trans
if return_hyp_graph:
renderer = HypGraphRenderer(hyp_graph)
renderer.wordify(word_idict_trg)
renderer.save_png(return_hyp_graph,
detailed=True,
highlight_best=True)
## TODO: Handle the output here
#print((_seqs2words(samples) + "\n").encode('utf-8'))
#text.append(_seqs2words(samples) + "\n")
x = _seqs2words(samples)
#print x[0].upper() + x[1:]
detokenized += detokenizer.detokenize(
(x.decode('utf-8') + " ").split(), return_str=True)
detokenized = detokenized[0].upper() + detokenized[1:]
#print "ref this"
#print detokenized
#detokenized[0] = detokenized[0].upper()
#c.send(detokenized.replace('@@ ', '').encode('utf-8').strip())
## TODO: End of output handling
if print_word_probabilities:
for prob in word_probs:
saveto.write("{} ".format(prob))
saveto.write('\n')
if save_alignment is not None:
if a_json:
print_matrix_json(alignment, source_sentences[i],
_seqs2words(trans[0]).split(), i,
i, save_alignment)
else:
save_alignment.write(
'{0} ||| {1} ||| {2} ||| {3} ||| {4} {5}\n'.
format(i, _seqs2words(trans[0]), 0,
' '.join(source_sentences[i]),
len(source_sentences[i]) + 1,
len(trans[0])))
print_matrix(alignment, save_alignment)
c.send(detokenized.replace('@@ ', '').encode('utf-8').strip())
source_file_t = sent_tokenize(c.recv(4096).decode('utf-8'))
c.close()
sys.stderr.write('Done\n')
def main(models, source_file, saveto, save_alignment=None, k=5,
normalization_alpha=0.0, n_process=5, chr_level=False, verbose=False, nbest=False, suppress_unk=False, a_json=False, print_word_probabilities=False, return_hyp_graph=False, device_list=[]):
# load model model_options
options = []
for model in models:
options.append(load_config(model))
fill_options(options[-1])
dictionaries = options[0]['dictionaries']
dictionaries_source = dictionaries[:-1]
dictionary_target = dictionaries[-1]
# load source dictionary and invert
word_dicts = []
word_idicts = []
for dictionary in dictionaries_source:
word_dict = load_dict(dictionary)
if options[0]['n_words_src']:
for key, idx in word_dict.items():
if idx >= options[0]['n_words_src']:
del word_dict[key]
word_idict = dict()
for kk, vv in word_dict.iteritems():
word_idict[vv] = kk
word_idict[0] = '<eos>'
word_idict[1] = 'UNK'
word_dicts.append(word_dict)
word_idicts.append(word_idict)
# load target dictionary and invert
word_dict_trg = load_dict(dictionary_target)
word_idict_trg = dict()
for kk, vv in word_dict_trg.iteritems():
word_idict_trg[vv] = kk
word_idict_trg[0] = '<eos>'
word_idict_trg[1] = 'UNK'
print 'input dict - 100 most common'
for i in xrange(100):
print i, " ", word_idict[i]
print 'output dict - 100 most common'
for i in xrange(100):
print i, " ", word_idict_trg[i]
# create input and output queues for processes
queue = Queue()
rqueue = Queue()
processes = [None] * n_process
for midx in xrange(n_process):
deviceid = ''
if device_list is not None and len(device_list) != 0:
deviceid = device_list[midx % len(device_list)].strip()
processes[midx] = Process(
target=translate_model,
args=(queue, rqueue, midx, models, options, k, normalization_alpha, verbose, nbest, save_alignment is not None, suppress_unk, return_hyp_graph, deviceid))
processes[midx].start()
# utility function
def _seqs2words(cc):
ww = []
for w in cc:
if w == 0:
break
ww.append(word_idict_trg[w])
return ' '.join(ww)
def _send_jobs(f):
source_sentences = []
for idx, line in enumerate(f):
if chr_level:
words = list(line.decode('utf-8').strip())
else:
words = line.strip().split()
x = []
for w in words:
w = [word_dicts[i][f] if f in word_dicts[i] else 1 for (i,f) in enumerate(w.split('|'))]
if len(w) != options[0]['factors']:
sys.stderr.write('Error: expected {0} factors, but input word has {1}\n'.format(options[0]['factors'], len(w)))
for midx in xrange(n_process):
processes[midx].terminate()
sys.exit(1)
x.append(w)
x += [[0]*options[0]['factors']]
queue.put((idx, x))
source_sentences.append(words)
return idx+1, source_sentences
def _finish_processes():
for midx in xrange(n_process):
queue.put(None)
def _retrieve_jobs(n_samples):
trans = [None] * n_samples
out_idx = 0
for idx in xrange(n_samples):
resp = None
while resp is None:
try:
resp = rqueue.get(True, 5)
# if queue is empty after 5s, check if processes are still alive
except Empty:
for midx in xrange(n_process):
if not processes[midx].is_alive() and processes[midx].exitcode != 0:
# kill all other processes and raise exception if one dies
queue.cancel_join_thread()
rqueue.cancel_join_thread()
for idx in xrange(n_process):
processes[idx].terminate()
sys.stderr.write("Error: translate worker process {0} crashed with exitcode {1}".format(processes[midx].pid, processes[midx].exitcode))
sys.exit(1)
trans[resp[0]] = resp[1]
if verbose and numpy.mod(idx, 10) == 0:
sys.stderr.write('Sample {0} / {1} Done\n'.format((idx+1), n_samples))
while out_idx < n_samples and trans[out_idx] != None:
yield trans[out_idx]
out_idx += 1
sys.stderr.write('Translating {0} ...\n'.format(source_file.name))
n_samples, source_sentences = _send_jobs(source_file)
_finish_processes()
for i, trans in enumerate(_retrieve_jobs(n_samples)):
if nbest:
samples, scores, word_probs, alignment, hyp_graph = trans
if return_hyp_graph:
renderer = HypGraphRenderer(hyp_graph)
renderer.wordify(word_idict_trg)
renderer.save_png(return_hyp_graph, detailed=True, highlight_best=True)
order = numpy.argsort(scores)
for j in order:
if print_word_probabilities:
probs = " ||| " + " ".join("{0}".format(prob) for prob in word_probs[j])
else:
probs = ""
saveto.write('{0} ||| {1} ||| {2}{3}\n'.format(i, _seqs2words(samples[j]), scores[j], probs))
# print alignment matrix for each hypothesis
# header: sentence id ||| translation ||| score ||| source ||| source_token_count+eos translation_token_count+eos
if save_alignment is not None:
if a_json:
print_matrix_json(alignment[j], source_sentences[i], _seqs2words(samples[j]).split(), i, i+j,save_alignment)
else:
save_alignment.write('{0} ||| {1} ||| {2} ||| {3} ||| {4} {5}\n'.format(
i, _seqs2words(samples[j]), scores[j], ' '.join(source_sentences[i]) , len(source_sentences[i])+1, len(samples[j])))
print_matrix(alignment[j], save_alignment)
else:
samples, scores, word_probs, alignment, hyp_graph = trans
if return_hyp_graph:
renderer = HypGraphRenderer(hyp_graph)
renderer.wordify(word_idict_trg)
renderer.save_png(return_hyp_graph, detailed=True, highlight_best=True)
saveto.write(_seqs2words(samples) + "\n")
if i%1==0:
print 'input:'
print ' '.join(source_sentences[i])
print 'output:'
print _seqs2words(samples) + "\n"
if print_word_probabilities:
for prob in word_probs:
saveto.write("{} ".format(prob))
saveto.write('\n')
if save_alignment is not None:
if a_json:
print_matrix_json(alignment, source_sentences[i], _seqs2words(trans[0]).split(), i, i,save_alignment)
else:
save_alignment.write('{0} ||| {1} ||| {2} ||| {3} ||| {4} {5}\n'.format(
i, _seqs2words(trans[0]), 0, ' '.join(source_sentences[i]) , len(source_sentences[i])+1, len(trans[0])))
print_matrix(alignment, save_alignment)
sys.stderr.write('Done\n')
def main(models, source_file, saveto, save_alignment=None, k=5,
normalize=False, n_process=5, chr_level=False, verbose=False, nbest=False, suppress_unk=False, a_json=False, print_word_probabilities=False, return_hyp_graph=False):
# load model model_options
options = []
for model in models:
options.append(load_config(model))
fill_options(options[-1])
dictionaries = options[0]['dictionaries']
dictionaries_source = dictionaries[:-1]
dictionary_target = dictionaries[-1]
# load source dictionary and invert
word_dicts = []
word_idicts = []
for dictionary in dictionaries_source:
word_dict = load_dict(dictionary)
if options[0]['n_words_src']:
for key, idx in word_dict.items():
if idx >= options[0]['n_words_src']:
del word_dict[key]
word_idict = dict()
for kk, vv in word_dict.iteritems():
word_idict[vv] = kk
word_idict[0] = '<eos>'
word_idict[1] = 'UNK'
word_dicts.append(word_dict)
word_idicts.append(word_idict)
# load target dictionary and invert
word_dict_trg = load_dict(dictionary_target)
word_idict_trg = dict()
for kk, vv in word_dict_trg.iteritems():
word_idict_trg[vv] = kk
word_idict_trg[0] = '<eos>'
word_idict_trg[1] = 'UNK'
# create input and output queues for processes
queue = Queue()
rqueue = Queue()
processes = [None] * n_process
for midx in xrange(n_process):
processes[midx] = Process(
target=translate_model,
args=(queue, rqueue, midx, models, options, k, normalize, verbose, nbest, save_alignment is not None, suppress_unk, return_hyp_graph))
processes[midx].start()
# utility function
def _seqs2words(cc):
ww = []
for w in cc:
if w == 0:
break
ww.append(word_idict_trg[w])
return ' '.join(ww)
def _send_jobs(f):
source_sentences = []
for idx, line in enumerate(f):
if chr_level:
words = list(line.decode('utf-8').strip())
else:
words = line.strip().split()
x = []
for w in words:
w = [word_dicts[i][f] if f in word_dicts[i] else 1 for (i,f) in enumerate(w.split('|'))]
if len(w) != options[0]['factors']:
sys.stderr.write('Error: expected {0} factors, but input word has {1}\n'.format(options[0]['factors'], len(w)))
for midx in xrange(n_process):
processes[midx].terminate()
sys.exit(1)
x.append(w)
x += [[0]*options[0]['factors']]
queue.put((idx, x))
source_sentences.append(words)
return idx+1, source_sentences
def _finish_processes():
for midx in xrange(n_process):
queue.put(None)
def _retrieve_jobs(n_samples):
trans = [None] * n_samples
out_idx = 0
for idx in xrange(n_samples):
resp = rqueue.get()
trans[resp[0]] = resp[1]
if verbose and numpy.mod(idx, 10) == 0:
sys.stderr.write('Sample {0} / {1} Done\n'.format((idx+1), n_samples))
while out_idx < n_samples and trans[out_idx] != None:
yield trans[out_idx]
out_idx += 1
sys.stderr.write('Translating {0} ...\n'.format(source_file.name))
n_samples, source_sentences = _send_jobs(source_file)
_finish_processes()
for i, trans in enumerate(_retrieve_jobs(n_samples)):
if nbest:
samples, scores, word_probs, alignment, hyp_graph = trans
if return_hyp_graph:
renderer = HypGraphRenderer(hyp_graph)
renderer.wordify(word_idict_trg)
renderer.save_png(return_hyp_graph, detailed=True, highlight_best=True)
order = numpy.argsort(scores)
for j in order:
if print_word_probabilities:
probs = " ||| " + " ".join("{0}".format(prob) for prob in word_probs[j])
else:
probs = ""
saveto.write('{0} ||| {1} ||| {2}{3}\n'.format(i, _seqs2words(samples[j]), scores[j], probs))
# print alignment matrix for each hypothesis
# header: sentence id ||| translation ||| score ||| source ||| source_token_count+eos translation_token_count+eos
if save_alignment is not None:
if a_json:
print_matrix_json(alignment[j], source_sentences[i], _seqs2words(samples[j]).split(), i, i+j,save_alignment)
else:
save_alignment.write('{0} ||| {1} ||| {2} ||| {3} ||| {4} {5}\n'.format(
i, _seqs2words(samples[j]), scores[j], ' '.join(source_sentences[i]) , len(source_sentences[i])+1, len(samples[j])))
print_matrix(alignment[j], save_alignment)
else:
samples, scores, word_probs, alignment, hyp_graph = trans
if return_hyp_graph:
renderer = HypGraphRenderer(hyp_graph)
renderer.wordify(word_idict_trg)
renderer.save_png(return_hyp_graph, detailed=True, highlight_best=True)
saveto.write(_seqs2words(samples) + "\n")
if print_word_probabilities:
for prob in word_probs:
saveto.write("{} ".format(prob))
saveto.write('\n')
if save_alignment is not None:
if a_json:
print_matrix_json(alignment, source_sentences[i], _seqs2words(trans[0]).split(), i, i,save_alignment)
else:
save_alignment.write('{0} ||| {1} ||| {2} ||| {3} ||| {4} {5}\n'.format(
i, _seqs2words(trans[0]), 0, ' '.join(source_sentences[i]) , len(source_sentences[i])+1, len(trans[0])))
print_matrix(alignment, save_alignment)
sys.stderr.write('Done\n')