def main():
parser = argparse.ArgumentParser(description="Positive and Unlabeled Extractor 1.0")
parser.add_argument("--corpus_dir", type=str, help="Corpus root dir.")
parser.add_argument("--samples_name", type=str, help="The samples's name in corpus.")
parser.add_argument("--result_dir", type=str, help="Dir to save result.")
subparsers = parser.add_subparsers(dest="subcommand", title="subcommands", help="sub-command help")
# -------- import_samples --------
parser_import_samples = subparsers.add_parser("import_samples", help="import samples help")
parser_import_samples.add_argument("--xls_file", type=str, help="The Excel file name will be imported.")
parser_import_samples.set_defaults(func=cmd_import_samples)
# -------- rebuild --------
parser_rebuild = subparsers.add_parser("rebuild", help="rebuild help")
parser_rebuild.set_defaults(func=cmd_rebuild)
# -------- show --------
parser_show = subparsers.add_parser("show", help="show help")
parser_show.set_defaults(func=cmd_show)
# -------- query_sample --------
parser_query_sample = subparsers.add_parser("query_sample", help="query sample help")
parser_query_sample.add_argument("--sample_id", type=int, help="The sample id.")
parser_query_sample.set_defaults(func=cmd_query_sample)
# -------- test --------
parser_test = subparsers.add_parser("test", help="test help")
parser_test.set_defaults(func=cmd_test)
# -------- export_samples --------
parser_export_samples = subparsers.add_parser("export_samples", help="export samples help")
parser_export_samples.add_argument("--xls_file", type=str, help="The Excel file name will be imported.")
parser_export_samples.set_defaults(func=cmd_export_samples)
# -------- query_keywords --------
parser_query_keywords = subparsers.add_parser("query_keywords", help="query keywords help")
parser_query_keywords.set_defaults(func=cmd_query_keywords)
# -------- iem --------
parser_iem = subparsers.add_parser("iem", help="IEM help")
parser_iem.add_argument("--positive_name", type=str, help="The positive samples's name in corpus.")
parser_iem.add_argument("--unlabeled_name", type=str, help="The unlabeled samples's name in corpus.")
parser_iem.set_defaults(func=cmd_iem)
# -------- sem --------
parser_sem = subparsers.add_parser("sem", help="SEM help")
parser_sem.add_argument("--positive_name", type=str, help="The positive samples's name in corpus.")
parser_sem.add_argument("--unlabeled_name", type=str, help="The unlabeled samples's name in corpus.")
parser_sem.set_defaults(func=cmd_sem)
# -------- pulearning --------
parser_pulearning = subparsers.add_parser("pulearning", help="PULearning help")
parser_pulearning.add_argument("--positive_name", type=str, help="The positive samples's name in corpus.")
parser_pulearning.add_argument("--unlabeled_name", type=str, help="The unlabeled samples's name in corpus.")
parser_pulearning.set_defaults(func=cmd_pulearning)
args = parser.parse_args()
print args
aa = AppArgs(["/etc/diggerd/diggerrc", "~/.diggerrc", "./.diggerrc"])
update_args(aa, args)
aa.write_to_file("./.diggerrc")
args.func(aa)
def main_1():
s_time = datetime.utcnow()
aa = AppArgs()
aa.parse_from_file('/etc/diggerd/diggerrc')
aa.parse_from_file('~/.diggerrc')
aa.parse_from_file('./.diggerrc')
args = docopt(__doc__, version="Positive and Unlabeled Extractor 1.0")
#print args
corpus_dir = args['--corpus_dir']
result_dir = args['--result_dir']
#positive_name_list = args['--positive_name']
positive_name = args['--positive_name']
unlabeled_name = args['--unlabeled_name']
model_file = args['--model_file']
svm_file = args['--svm_file']
samples_name = args['--samples_name']
model_name = args['--model_name']
arg_sample_id = args['--sample_id']
if not arg_sample_id is None:
sample_id = int(arg_sample_id)
else:
sample_id = None
xls_file = args['--xls_file']
aa.parse_from_args(args)
corpus_dir = aa.corpus_dir
samples_name = aa.samples_name
aa.print_status()
if args['test']:
do_test(corpus_dir, positive_name, unlabeled_name, model_file, svm_file)
elif args['import_samples']:
do_import_samples(corpus_dir, samples_name, xls_file)
elif args['export_samples']:
do_export_samples(corpus_dir, samples_name, xls_file)
elif args['export_urls']:
do_export_urls(corpus_dir, samples_name, xls_file)
elif args['rebuild']:
do_rebuild(corpus_dir, samples_name)
elif args['rebuild_categories']:
do_rebuild_categories(corpus_dir, samples_name)
elif args['query_sample']:
if not samples_name is None:
do_query_sample(corpus_dir, samples_name, sample_id)
else:
do_query_sample_by_pu(corpus_dir, positive_name_list, unlabeled_name, sample_id)
elif args['query_categories']:
do_query_categories(corpus_dir, samples_name, xls_file)
elif args['query_keywords']:
do_query_keywords(corpus_dir, samples_name, result_dir)
elif args['refresh']:
do_refresh(corpus_dir, samples_name)
elif args['show']:
do_show(corpus_dir, samples_name)
elif args['purge']:
do_purge(corpus_dir, samples_name)
elif args['sne']:
do_sne(corpus_dir, samples_name, result_dir)
elif args['train']:
do_train(corpus_dir, samples_name, model_name, result_dir)
elif args['predict']:
do_predict(corpus_dir, samples_name, model_name, result_dir)
elif args['iem']:
do_iem(corpus_dir, positive_name, unlabeled_name, result_dir)
elif args['sem']:
do_sem(corpus_dir, positive_name, unlabeled_name, result_dir)
e_time = datetime.utcnow()
t_time = (e_time - s_time)
logging.info(Logger.info("Done.(%s)" % (str(t_time))))
