tommy/libpostal
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[fix] simple whitespace field splits for the limited format training data (used for language classification)

Browse Source
This commit is contained in:
Al
2016-01-22 04:34:36 -05:00
parent cd1db7b288
commit f9f6558e06
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
scripts/geodata/osm/osm_address_training_data.py
View File

@@ -1647,7 +1647,7 @@ if __name__ == '__main__':
osm_formatter = OSMAddressFormatter(osm_rtree, language_rtree, neighborhoods_rtree, quattroshapes_rtree, geonames)
osm_formatter.build_training_data(args.address_file, args.out_dir, tag_components=not args.untagged)
if args.address_file and args.limited_addresses:
osm_formatter = OSMAddressFormatter(osm_rtree, language_rtree, neighborhoods_rtree, quattroshapes_rtree, geonames)
osm_formatter = OSMAddressFormatter(osm_rtree, language_rtree, neighborhoods_rtree, quattroshapes_rtree, geonames, splitter=u' ')
osm_formatter.build_limited_training_data(args.address_file, args.out_dir)
if args.venues_file:
build_venue_training_data(language_rtree, args.venues_file, args.out_dir)