def main(args=None):
usage = "%prog dataset [CoreNLP_dir]"
parser = OptionParser(usage=usage)
parser.add_option('-s', dest='skip_corenlp', action="store_true", default=False,
help='Skip processing by CoreNLP and just parse the xml output; default=%default')
parser.add_option('-x', dest='extension', default='.xml',
help='Extension for CoreNLP files; default=%default')
parser.add_option('-o', dest='overwrite', action="store_true", default=False,
help='Redo parsing for all files; default=%default')
parser.add_option('-n', dest='nice', action="store_true", default=False,
help='Call CoreNLP with "nice"; default=%default')
(options, args) = parser.parse_args()
skip_corenlp = options.skip_corenlp
overwrite = options.overwrite
extension = options.extension
nice = options.nice
print skip_corenlp
project_name = args[0]
if not skip_corenlp:
corenlp_dir = args[1]
else:
corenlp_dir = ''
global verbosity
dirs.make_base_dir(project_name)
run_pipeline(skip_corenlp, corenlp_dir, overwrite, extension, nice)
def main():
usage = "%prog dataset"
parser = OptionParser(usage=usage)
parser.add_option('-n', dest='n_files', default=None,
help='Only process the first n files: default=%default')
parser.add_option('--lemmas', action="store_false", dest="use_lemmas", default=True,
help='If false, use word instead of lemmas: default=%default')
#parser.add_option('--word2vec', dest='word2vec', default=None,
# help='word2vec.bin file: default=%default')
parser.add_option('--min_wf', dest='min_wf', default=4,
help='Exclude target words that occur less than this many times: default=%default')
parser.add_option('--min_tuples', dest='min_tuples', default=3,
help='Exclude entities with less than this many tuples: default=%default')
(options, args) = parser.parse_args()
use_lemmas = options.use_lemmas
n_files = options.n_files
word2vec_file = None
min_wf = int(options.min_wf)
min_tuples = int(options.min_tuples)
if len(args) < 1:
#sys.exit("Please specify a project / dataset")
project = 'mfc_v3'
else:
project = args[0]
dirs.make_base_dir(project)
trees, clustered_indices = find_entities(n_files, use_lemmas)
filtered_indices, bamman_entities = get_bamman_entities(trees, clustered_indices, word2vec_file=word2vec_file, min_role_vocab=min_wf, min_tuples=min_tuples)
def main():
# Handle input options and arguments
usage = "%prog project"
parser = OptionParser(usage=usage)
(options, args) = parser.parse_args()
project = args[0]
dirs.make_base_dir(project)
preprocess_for_easysrl()
def main():
# Handle input options and arguments
usage = "%prog project semafor_dir"
parser = OptionParser(usage=usage)
(options, args) = parser.parse_args()
project = args[0]
semafor_dir = args[1]
dirs.make_base_dir(project)
sentences = parse_tokens(os.path.join(semafor_dir, 'tokenized'))
parse_semafor_output(os.path.join(semafor_dir, 'fes'), sentences)
def main():
# Handle input options and arguments
usage = "%prog project"
parser = OptionParser(usage=usage)
(options, args) = parser.parse_args()
project = args[0]
dirs.make_base_dir(project)
input_filename = dirs.data_raw_text_file
write_sentences(input_filename)
def main():
usage = "%prog dataset"
parser = OptionParser(usage=usage)
#parser.add_option('--keyword', dest='key', default=None,
# help='Keyword argument: default=%default')
#parser.add_option('--boolarg', action="store_true", dest="boolarg", default=False,
# help='Keyword argument: default=%default')
(options, args) = parser.parse_args()
if len(args) < 1:
sys.exit("Please specify a project / dataset")
project = args[0]
dirs.make_base_dir(project)
extract_story_elements()
def main():
usage = "%prog dataset output_filename"
parser = OptionParser(usage=usage)
#parser.add_option('--keyword', dest='key', default=None,
# help='Keyword argument: default=%default')
#parser.add_option('--boolarg', action="store_true", dest="boolarg", default=False,
# help='Keyword argument: default=%default')
(options, args) = parser.parse_args()
if len(args) < 2:
sys.exit("Please specify a project / dataset and output filename")
project = args[0]
output_filename = args[1]
dirs.make_base_dir(project)
identify_rnn_targets(output_filename)
def main():
usage = "%prog project"
parser = OptionParser(usage=usage)
#parser.add_option('--keyword', dest='key', default=None,
# help='Keyword argument: default=%default')
#parser.add_option('--boolarg', action="store_true", dest="boolarg", default=False,
# help='Keyword argument: default=%default')
(options, args) = parser.parse_args()
if len(args) < 1:
sys.exit("Please specify a project name")
project_name = args[0]
dirs.make_base_dir(project_name)
entities_file = os.path.join(dirs.data_stanford_dir, 'all_groups.json')
cluster_entities(entities_file)