Al
|
40d18aa7f6
|
[polygons/osm] Switching back to buffer(0). Still destroys many polygons, may need to look into another solution
|
2015-11-25 17:10:50 -05:00 |
|
Al
|
a50c971732
|
[polygons/osm] Ommitting last node in every way of a connected component since that node is equal to the start node of its neighbor
|
2015-11-25 17:09:19 -05:00 |
|
Al
|
d6d5eab989
|
[geonames] Adding ability to lookup GeoNames alternate names (may obtain IDs from Quattroshapes). Not great for local-language primary names (OSM remains the best) but decent for extracting foreign toponyms
|
2015-11-25 17:07:14 -05:00 |
|
Al
|
3217fa39cd
|
[fix] add country randomly in the formatted language training data in cases where country is not present
|
2015-11-25 14:54:41 -05:00 |
|
Al
|
1a6618957b
|
[fix] Python float precision doesn't appear to be the problem
|
2015-11-25 11:29:08 -05:00 |
|
Al
|
5781813cbd
|
[fix] For countries like Denmark, removing country with a smaller probability
|
2015-11-25 00:39:52 -05:00 |
|
Al
|
e4b8349d98
|
[fix] sparsity of country tags should be enough for language address training data
|
2015-11-25 00:32:01 -05:00 |
|
Al
|
824c779107
|
[fix] Cutting down training repeatedly on country names
|
2015-11-24 23:22:57 -05:00 |
|
Al
|
88529d28e2
|
[fix] country formatting in language address training data
|
2015-11-24 23:20:31 -05:00 |
|
Al
|
cd74fcda3c
|
[fix] not requiring minimal keys in format language data
|
2015-11-24 23:13:28 -05:00 |
|
Al
|
e560e53308
|
[fix] formatter
|
2015-11-24 22:27:57 -05:00 |
|
Al
|
8c422a6e61
|
[osm] Adding new localized country names in anguage training data for formatted addresses
|
2015-11-24 21:49:10 -05:00 |
|
Al
|
e40ca0bb89
|
[fix] Removing house numbers from formatted address language training data, using a simple whitespace splitter
|
2015-11-24 21:15:22 -05:00 |
|
Al
|
a92cbb8003
|
[osm] Trying fixed-point precision in converting OSM coordinates to avoid issues with polygon self-intersection when the lines are very close together (e.g. parts of Berlin, UK country polygon)
|
2015-11-24 15:13:16 -05:00 |
|
Al
|
ef9c5c2ca1
|
[fix] args
|
2015-11-24 11:02:35 -05:00 |
|
Al
|
e75c1ce860
|
[fix] limited addresses
|
2015-11-24 11:01:22 -05:00 |
|
Al
|
94039f98ad
|
[fix] argument validation in OSM training data script
|
2015-11-24 10:59:16 -05:00 |
|
Al
|
de9f3120c8
|
[polygons] Trying a slightly higher value for buffer() as suggested by this issue https://github.com/Toblerity/Shapely/issues/277
|
2015-11-23 15:43:23 -05:00 |
|
Al
|
6d20d7348f
|
[osm] Using OSM namespaced tags from polygons in the case of non-local languages
|
2015-11-23 14:42:30 -05:00 |
|
Al
|
e46e1a93a0
|
[fix] ISO code and simple/international name checks should be on the polygons
|
2015-11-23 14:30:38 -05:00 |
|
Al
|
eb7488ab55
|
[fix] Making country replacement probability independent of the probability used for local vs non-local languages
|
2015-11-23 13:46:14 -05:00 |
|
Al
|
f4f7cceba2
|
[fix] var, non-local languages
|
2015-11-23 12:51:26 -05:00 |
|
Al
|
6aa640b5f0
|
[fix] Moving is_in:country to lower priority
|
2015-11-23 12:36:05 -05:00 |
|
Al
|
2b1c346fde
|
[osm] Using name:simple and int_name to capture more variations for US addresses, adding ISO codes occationally instead of names
|
2015-11-23 12:35:44 -05:00 |
|
Al
|
f1b6620369
|
[osm/formatting] replacing keys with the highest priority so addr:* tags take precedence over is_in:* tags
|
2015-11-22 22:25:44 -05:00 |
|
Al
|
2695b5dd26
|
[osm] Shortening state names obtained from reverse geocoding for relevant countries
|
2015-11-22 22:09:31 -05:00 |
|
Al
|
8b035814c7
|
[osm] Change probabilities for country names
|
2015-11-22 18:52:17 -05:00 |
|
Al
|
04183c672e
|
[fix] non-integer admin levels
|
2015-11-22 18:33:27 -05:00 |
|
Al
|
7ee8045a0f
|
[fix] comparison
|
2015-11-22 18:27:05 -05:00 |
|
Al
|
efa0e38e45
|
[fix] another issue with tokenize API
|
2015-11-22 18:08:45 -05:00 |
|
Al
|
ce065bb9ec
|
[fix] using new pypostal tokenize API
|
2015-11-22 18:01:07 -05:00 |
|
Al
|
71afcafe11
|
[fix] key names
|
2015-11-22 17:46:56 -05:00 |
|
Al
|
f77ddc71e7
|
[fix] reverting to old Rtree index filename
|
2015-11-22 17:25:51 -05:00 |
|
Al
|
ee482e7a07
|
[fix] import
|
2015-11-22 16:04:50 -05:00 |
|
Al
|
ee75ffccd5
|
[fix] import
|
2015-11-22 15:51:13 -05:00 |
|
Al
|
c6f531ca95
|
[fix] arguments
|
2015-11-22 15:35:25 -05:00 |
|
Al
|
c851cf2547
|
[fix] OSM R-tree
|
2015-11-22 15:24:35 -05:00 |
|
Al
|
d3703ce6b4
|
[fix] var name
|
2015-11-22 14:27:25 -05:00 |
|
Al
|
5b6fbd66e0
|
[fix] arg
|
2015-11-22 14:24:05 -05:00 |
|
Al
|
422ea668d8
|
[fix] import
|
2015-11-22 14:23:09 -05:00 |
|
Al
|
4f0d6fbf79
|
[fix] default arg again
|
2015-11-22 14:22:09 -05:00 |
|
Al
|
4cc275e313
|
[fix] doc and default arg
|
2015-11-22 14:21:20 -05:00 |
|
Al
|
c8f47b38a2
|
[osm/formatting] Adding OSM polygon lookups and neighborhood polygon lookups to the training data in order to provide more variations for the model to work with
|
2015-11-21 17:05:35 -05:00 |
|
Al
|
9fc60600dd
|
[fix] OSM reverse geocoder polygon ordering
|
2015-11-20 14:49:37 -05:00 |
|
Al
|
130518fe58
|
[polygons] OSM reverse geocoder sort levels
|
2015-11-20 13:52:30 -05:00 |
|
Al
|
b948a8ebd8
|
[osm] Adding global keys which map to OSM address components
|
2015-11-20 12:48:54 -05:00 |
|
Al
|
85667997cd
|
[formatting] Adding city_district and state_district tags to address formatting templates where it makes sense. These will not be in all addresses, tags can be added and removed from the training data with certain probabilities
|
2015-11-20 12:24:51 -05:00 |
|
Al
|
946bce1cb9
|
[osm] Adding a few more boundary types to planet admin borders
|
2015-11-17 11:40:42 -05:00 |
|
Al
|
b3ef8ded12
|
[formatting] Adding OSM address components lookup by country
|
2015-11-17 11:39:39 -05:00 |
|
Al
|
0b74039a6a
|
[formatting] Adding city_district as a separate format tag
|
2015-11-17 11:38:38 -05:00 |
|