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

[fix] Making sure rare components are dropped first, adding state and country back in

Browse Source
This commit is contained in:
Al
2016-01-22 04:17:19 -05:00
parent adc3a00264
commit cd1db7b288
1 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
scripts/geodata/osm/osm_address_training_data.py
View File

@@ -529,6 +529,8 @@ class OSMAddressFormatter(object):
AddressFormatter.SUBURB, AddressFormatter.SUBURB,
AddressFormatter.CITY_DISTRICT, AddressFormatter.CITY_DISTRICT,
AddressFormatter.STATE_DISTRICT, AddressFormatter.STATE_DISTRICT,
AddressFormatter.STATE,
AddressFormatter.COUNTRY,
} }
def __init__(self, admin_rtree, language_rtree, neighborhoods_rtree, quattroshapes_rtree, geonames, splitter=None): def __init__(self, admin_rtree, language_rtree, neighborhoods_rtree, quattroshapes_rtree, geonames, splitter=None):
@@ -1178,9 +1180,12 @@ class OSMAddressFormatter(object):
if not address_components: if not address_components:
return [] return []
current_components = address_components.keys() current_components = [k for k in address_components.keys() if k not in self.rare_components]
current_components_rare = [k for k in address_components.keys() if k in self.rare_components]
random.shuffle(current_components) random.shuffle(current_components)
random.shuffle(current_components_rare)
current_components = current_components_rare + current_components
component_set = component_bitset(address_components.keys()) component_set = component_bitset(address_components.keys())
for component in current_components: for component in current_components: