diff --git a/scripts/geodata/osm/osm_address_training_data.py b/scripts/geodata/osm/osm_address_training_data.py index bee89c27..68138070 100644 --- a/scripts/geodata/osm/osm_address_training_data.py +++ b/scripts/geodata/osm/osm_address_training_data.py @@ -707,6 +707,9 @@ def build_address_format_training_data_limited(language_rtree, infile, out_dir): have_country = True _ = value.pop(k, None) + if have_country and random.random() < 0.8: + have_country = False + if not value: continue