def main():
viterbi_parser = pcfg_chartparser("wsjp.cfg")
sents = cfg_parse.read_sentences("sentences.txt")
# print ("sentence\ttime elapsed (us)")
for sent in sents:
print (sent)
for tree in viterbi_parser.parse(sent):
print (tree)
def main():
viterbi_parser = pcfg_chartparser("wsjp.cfg")
sents = cfg_parse.read_sentences("sentences.txt")
# print ("sentence\ttime elapsed (us)")
for sent in sents:
print(sent)
for tree in viterbi_parser.parse(sent):
print(tree)
def main():
grammarp = pcfg_chartparser("wsjp.cfg")
sents = cfg_parse.read_sentences("sentences.txt")
print "sentence\ttime elapsed (us)"
for sent in sents:
start = datetime.now()
tree = grammarp.parse(sent)
end = datetime.now()
elapsed = end - start
microseconds = elapsed.microseconds + 1000000 * elapsed.seconds
print "%s\t%d" % (sent, microseconds)
print tree
def main():
grammarp = pcfg_chartparser("wsjp.cfg")
sents = cfg_parse.read_sentences("sentences.txt")
print "sentence\ttime elapsed (us)"
for sent in sents:
start = datetime.now()
tree = grammarp.parse(sent)
end = datetime.now()
elapsed = end - start
microseconds = elapsed.microseconds + 1000000*elapsed.seconds
print "%s\t%d" %(sent, microseconds)
print tree
tokens = line.split()
total += len(tokens)
fd.close()
return total
if __name__ == "__main__":
if len(sys.argv) >= 4:
root = sys.argv[1]
sentence_file = sys.argv[2]
sent_num = int(sys.argv[3])
else:
print "usage %s <grammar directory> <sentence file> <sentence number>" %(sys.argv[0])
exit(1)
dirs = os.listdir(root)
sentences = cfg_parse.read_sentences(sentence_file)
if sent_num < 0 or sent_num >= len(sentences):
print "error: sentence %d not in %s" %(sent_num, sentence_file)
exit(1)
sys.stdout.write("filename\tgrammar_size\tnum_branches\tnum_parses\ttime_taken\n");
dirs.sort()
for filename in dirs:
if re.match(".*\.cfg$", filename):
grammar_file = "%s/%s" %(root, filename)
grammar_size = num_symbols(grammar_file)
sent, num_parses, time_taken, trees = \
cfg_parse.parse(sentences[sent_num], grammar_file)
nbranches = num_branches(grammar_file)