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

[fix] dictionary

Browse Source
This commit is contained in:
Al
2015-10-02 20:24:21 -04:00
parent 521f33d892
commit 49abb70b59
1 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
scripts/geodata/osm/osm_address_training_data.py
View File

@@ -492,14 +492,16 @@ def build_address_format_training_data(language_rtree, infile, out_dir, tag_comp
formatted_addresses = []
formatted_addresses.append(formatted_address)
address_components = {k: v for k, v in address_components.iteritems() if k in OSM_ADDRESS_COMPONENTS_VALID}
address_components = {k: v for k, v in address_components.iteritems() if k in OSM_ADDRESS_COMPONENT_VALUES}
if not address_components:
continue
current_components = component_bitset(address_components.keys())
for component in address_components.keys():
if current_components ^ OSM_ADDRESS_COMPONENTS_VALID[component] and random.random() >= 0.5:
if current_components ^ OSM_ADDRESS_COMPONENT_VALUES[component] and random.random() >= 0.5:
address_components.pop(component)
current_components ^= OSM_ADDRESS_COMPONENTS_VALID[component]
current_components ^= OSM_ADDRESS_COMPONENT_VALUES[component]
if not address_components:
break