def main():
parser = argparse.ArgumentParser(fromfile_prefix_chars='@')
parser.add_argument('extract',
help='Extracted tsv file of bdb-extract process')
parser.add_argument('--outpath',
default=None,
help='Output file containing frequencies')
parser.add_argument('--logdir',
default='.',
help='Directory to place log files.')
args = parser.parse_args()
initialize_logging(logdir=args.logdir)
regexify_keywords_to_file(**vars(args))
def main():
import argparse
parser = argparse.ArgumentParser(fromfile_prefix_chars='@!')
parser.add_argument('anndir',
help='Path to directory containing brat annotation files')
parser.add_argument('txtdir', default=None,
help='Path to directory containing brat annotation files')
parser.add_argument('outdir', default='bratdb',
help='Path to output directory where brat data will be stored.')
parser.add_argument('--logdir', default='.',
help='Directory to place log files.')
args = parser.parse_args()
initialize_logging(logdir=args.logdir)
build_brat_dump(args.anndir, args.txtdir, args.outdir)
def main():
parser = argparse.ArgumentParser(fromfile_prefix_chars='@')
parser.add_argument('regex',
help='Regex tsv file of bdb-extract-regex process;'
' concept {tab} term {tab} regex')
parser.add_argument('--directory',
default=None,
help='Directory containing files to process')
parser.add_argument('--extension',
default='.txt',
help='Only process files with this extension')
parser.add_argument('--connection-string',
default=None,
dest='connection_string',
help='sqlalchemy-flavored connection string')
parser.add_argument('--outpath',
default=None,
help='Output directory to place result.')
parser.add_argument(
'--exclude-captured',
default=False,
action='store_true',
dest='exclude_captured',
help=
'Only retain metadata; Exclude captured text as this may contain PII')
parser.add_argument('--run-hours',
default=None,
type=int,
dest='run_hours',
help='End program after specified hours of running.')
parser.add_argument(
'--logdir',
default=None,
help=
'Directory to place log files. If not specified, defaults to output directory.'
)
parser.add_argument(
'--query',
default=None,
nargs='+',
help='query to retrieve name, document_text pairs from database table;'
' additional items can be included, but text must be last')
args = parser.parse_args()
initialize_logging(logdir=args.logdir or args.outpath)
apply_regex_to_corpus(**vars(args))
def main():
import argparse
parser = argparse.ArgumentParser(fromfile_prefix_chars='@')
parser.add_argument('bratdb',
help='Path to brat data dump (result of build script)')
parser.add_argument('--outpath', default=None,
help='Output file containing frequencies')
parser.add_argument('--ignore-tags', dest='ignore_tags', default=None, nargs='+',
help='Ignore specified tags/labels;'
' ignored if `keep-tags` is specified')
parser.add_argument('--keep-tags', dest='keep_tags', default=None, nargs='+',
help='Keep only tags listed here; overrides `ignore-tags`')
parser.add_argument('--ignore-stopwords', dest='ignore_stopwords', default=False, action='store_true',
help='Ignore stopwords')
parser.add_argument('--allow-multiple-labels-per-term', dest='one_label_per_term',
default=True, action='store_false',
help='Allow all terms to be associated with more than one label/concept/term.')
parser.add_argument('--logdir', default='.',
help='Directory to place log files.')
args = parser.parse_args()
initialize_logging(logdir=args.logdir)
extract_keywords_to_file(**vars(args))