for index, token in enumerate(tokens):
resulting_chart[index, index] = token
for row in range(1, L):
for col in range(0, row):
resulting_chart[row][col] = ' '
for row in range(0, L):
for col in range(row+2, L+1):
if not resulting_chart[row, col]:
resulting_chart[row, col] = ' '
f.write(str(resulting_chart))
f.write('\n')
f.close()
return (chart, best_probability[0])
if __name__ == "__main__":
try:
os.remove('workfile.txt')
except OSError:
pass
sentences_to_parse = 10
pcfg = PCFG.load(PCFG_SOURCE)
with open(TOKEN_SOURCE, "r") as source:
for index, line in enumerate(source):
if index == sentences_to_parse:
break
tokens = line.split()
(_, best_probability) = CKY_chart(tokens, pcfg)
print("{:.4f}: {}".format(best_probability.bw, " ".join(tokens)))
class Timeout(object):
def __init__(self, seconds=1, error_message="Timeout"):
self.seconds = seconds
self.error_message = error_message
def handle_timeout(self, signum, frame):
raise TimeoutError(self.error_message)
def __enter__(self):
signal.signal(signal.SIGALRM, self.handle_timeout)
signal.alarm(self.seconds)
def __exit__(self, type, value, traceback):
signal.alarm(0)
if __name__ == "__main__":
pcfg = PCFG.load(PCFG_SOURCE)
print "PCFG loaded."
with open(TREE_SOURCE, "r") as source:
for tree in Tree.from_stream(source):
tokens = [leaf.decode("ASCII") for leaf in tree.leaves()]
try:
with Timeout(TIMEOUT):
(_, bw_prob) = CYK_chart(pcfg, tokens)
print bw_prob
except TimeoutError:
pass
