From 4f03711e6014b9d828db4dab605d6783642c7fcb Mon Sep 17 00:00:00 2001 From: Al Date: Sat, 23 Jan 2016 14:10:47 -0500 Subject: [PATCH] [osm] Adding abbreviated training examples to ways language training data --- scripts/geodata/osm/osm_address_training_data.py | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/scripts/geodata/osm/osm_address_training_data.py b/scripts/geodata/osm/osm_address_training_data.py index 9f151577..c6ff1d3a 100644 --- a/scripts/geodata/osm/osm_address_training_data.py +++ b/scripts/geodata/osm/osm_address_training_data.py @@ -496,9 +496,10 @@ def build_ways_training_data(language_rtree, infile, out_dir): if not name_language: continue - for k, v in name_language.iteritems(): - for s in v: - if k in languages: + for lang, val in name_language.iteritems(): + for s in val: + if lang in languages: + s = osm_abbreviate(street_types_gazetteer, s, lang) writer.writerow((k, country, tsv_string(s))) if i % 1000 == 0 and i > 0: print('did {} ways'.format(i)) @@ -1652,9 +1653,7 @@ if __name__ == '__main__': if args.borders_file: build_toponym_training_data(language_rtree, args.borders_file, args.out_dir) - if args.address_file and not args.format_only and not args.limited_addresses: - build_address_training_data(language_rtree, args.address_file, args.out_dir) - elif args.address_file: + if args.address_file: if osm_rtree is None: parser.error('--rtree-dir required for formatted addresses') elif neighborhoods_rtree is None: