def perform_search(from_city, to_city, region, metric):
start = clock()
for res, _, progress in nb.best_match(from_city, to_city, region, 900,
progressive=True,
metric=metric):
# print(progress)
try:
distance, r_vids, center, radius = res
except (ValueError, TypeError):
import json
desc = {"type": "Feature", "properties":
{"nb_venues": len(res),
"venues": res,
"origin": from_city},
"geometry": region}
with open('scratch.json', 'a') as out:
out.write(json.dumps(desc, sort_keys=True, indent=2,
separators=(',', ': '))+'\n')
return
if len(center) == 2:
center = c.euclidean_to_geo(to_city, center)
relevant = {'dst': distance, 'radius': radius, 'center': center,
'nb_venues': len(r_vids)}
SEARCH_STATUS.update(dict(seen=False, progress=progress, res=relevant))
print("done search in {:.3f}".format(clock() - start))
SEARCH_STATUS.update(dict(seen=False, progress=1.0, done=True,
res=relevant))
def batch_matching(query_city='paris'):
"""Match preselected regions of `query_city` into the other target
cities"""
import ujson
global QUERY_NAME
global OTMPDIR
with open('static/ground_truth.json') as gt:
regions = ujson.load(gt)
districts = sorted(regions.keys())
cities = sorted(regions.values()[0]['gold'].keys())
assert query_city in cities
cities.remove(query_city)
OTMPDIR = os.path.join(OTMPDIR, 'www_comparaison_'+query_city)
try:
os.mkdir(OTMPDIR)
except OSError:
pass
# cities = ['berlin']
# districts = ['montmartre', 'triangle']
for city in cities:
print(city)
for neighborhood in districts:
# for _ in [1]:
# for city, neighborhood in [('washington', 'marais'), ('washington', 'montmartre')]:
print(neighborhood)
possible_regions = regions[neighborhood]['gold'].get(query_city)
rgeo = choose_query_region(possible_regions)
if not rgeo:
continue
for metric in ['emd-itml', 'emd-tsne']:
# for metric in ['jsd', 'emd', 'cluster', 'emd-lmnn', 'leftover']:
print(metric)
for radius in np.linspace(200, 500, 5):
print(radius)
QUERY_NAME = '{}_{}_{}_{}.my'.format(city, neighborhood,
int(radius),
metric)
logging.info('will write: '+str(os.path.join(OTMPDIR, QUERY_NAME)))
if os.path.isfile(os.path.join(OTMPDIR, QUERY_NAME)):
continue
res, values, _ = best_match(query_city, city, rgeo, radius,
metric=metric).next()
continue
distance, r_vids, center, radius = res
print(distance)
if center is None:
result = {'dst': distance, 'metric': metric,
'nb_venues': 0}
else:
center = cities.euclidean_to_geo(city, center)
result = {'geo': {'type': 'circle',
'center': center, 'radius': radius},
'dst': distance, 'metric': metric,
'nb_venues': len(r_vids)}
regions[neighborhood][city].append(result)
# outname = '{}_{}_{}_{}.png'.format(city, neighborhood,
# int(radius), metric)
# interpolate_distances(values, outname)
with open('static/cpresets.js', 'w') as out:
out.write('var PRESETS =' + ujson.dumps(regions) + ';')
def venues_to_geojson(vids, city):
"""Convert a list of venues id into a GeoJSON polygon"""
mask = itemgetter(*vids)(cities_index[city])
locs = cities_venues[city][mask, :]
hull = locs[ConvexHull(locs).vertices, :]
geohull = c.euclidean_to_geo(city, hull)
return sgeo.mapping(sgeo.Polygon(np.fliplr(geohull)))
def venues_to_geojson(vids, city):
"""Convert a list of venues id into a GeoJSON polygon"""
mask = itemgetter(*vids)(cities_index[city])
locs = cities_venues[city][mask, :]
hull = locs[ConvexHull(locs).vertices, :]
geohull = c.euclidean_to_geo(city, hull)
return sgeo.mapping(sgeo.Polygon(np.fliplr(geohull)))
def circle_to_poly(city, geo, resolution=4):
"""Discretize a circle (LngLat) to a Shapely polygon (LatLng)"""
center, radius = geo['center'], geo['radius']
local_center = c.GEO_TO_2D[city](list(reversed(center)))
approx = sgeo.Point(*local_center).buffer(radius, resolution)
local_exterior = c.euclidean_to_geo(city, np.array(approx.exterior.coords))
return sgeo.Polygon(np.fliplr(local_exterior).tolist())
def circle_to_poly(city, geo, resolution=4):
"""Discretize a circle (LngLat) to a Shapely polygon (LatLng)"""
center, radius = geo['center'], geo['radius']
local_center = c.GEO_TO_2D[city](list(reversed(center)))
approx = sgeo.Point(*local_center).buffer(radius, resolution)
local_exterior = c.euclidean_to_geo(city, np.array(approx.exterior.coords))
return sgeo.Polygon(np.fliplr(local_exterior).tolist())
def to_json(city, cell, pos, alt=False):
"""Convert a `cell` ranked `pos` in `city` to a GeoJSONish dict"""
distance, venues, center, radius, metric = cell
suffix = '_alt' if alt else ''
center = cities.euclidean_to_geo(city, center)
return {'geo': {'type': 'circle', 'center': center, 'radius': radius},
'dst': distance, 'metric': metric+suffix, 'venues': venues,
'pos': pos}
def to_json(city, cell, pos, alt=False):
"""Convert a `cell` ranked `pos` in `city` to a GeoJSONish dict"""
distance, venues, center, radius, metric = cell
suffix = '_alt' if alt else ''
center = cities.euclidean_to_geo(city, center)
return {
'geo': {
'type': 'circle',
'center': center,
'radius': radius
},
'dst': distance,
'metric': metric + suffix,
'venues': venues,
'pos': pos
}
def perform_search(from_city, to_city, region, metric):
start = clock()
for res, _, progress in nb.best_match(from_city,
to_city,
region,
900,
progressive=True,
metric=metric):
# print(progress)
try:
distance, r_vids, center, radius = res
except (ValueError, TypeError):
import json
desc = {
"type": "Feature",
"properties": {
"nb_venues": len(res),
"venues": res,
"origin": from_city
},
"geometry": region
}
with open('scratch.json', 'a') as out:
out.write(
json.dumps(
desc, sort_keys=True, indent=2, separators=(',',
': ')) +
'\n')
return
if len(center) == 2:
center = c.euclidean_to_geo(to_city, center)
relevant = {
'dst': distance,
'radius': radius,
'center': center,
'nb_venues': len(r_vids)
}
SEARCH_STATUS.update(dict(seen=False, progress=progress, res=relevant))
print("done search in {:.3f}".format(clock() - start))
SEARCH_STATUS.update(
dict(seen=False, progress=1.0, done=True, res=relevant))
NTEST = 2000
city, districts = sys.argv[1], []
city_info = load_data(city)
gold_list = city_info[-1]
districts = sorted([nn for nn, gold in gold_list.iteritems()
if city in gold['gold']])
try:
os.mkdir('random')
except OSError:
pass
for district in districts:
savename = 'random/{}_{}.my'.format(city, district)
print(savename)
if os.path.isfile(savename):
continue
distrib, best_score, best_region = [], 0, None
for i in range(NTEST):
regions, score = mock_random_list(city, district, city_info)
if score > best_score:
best_score, best_region = score, regions
distrib.append(score)
p.save_var(savename, distrib)
outjson = [{
'pos': rank+1, 'metric': 'random', 'dst': -1, 'venues': r[1],
'geo': mapping(Polygon(np.fliplr(c.euclidean_to_geo(city, r[0]))))}
for rank, r in enumerate(best_region)]
filename = 'static/random_{}_{}.json'.format(city, district)
with open(filename, 'w') as f:
json.dump(outjson, f, sort_keys=True, indent=2,
separators=(',', ': '))
savename = 'random/{}_{}.my'.format(city, district)
print(savename)
if os.path.isfile(savename):
continue
distrib, best_score, best_region = [], 0, None
for i in range(NTEST):
regions, score = mock_random_list(city, district, city_info)
if score > best_score:
best_score, best_region = score, regions
distrib.append(score)
p.save_var(savename, distrib)
outjson = [{
'pos':
rank + 1,
'metric':
'random',
'dst':
-1,
'venues':
r[1],
'geo':
mapping(Polygon(np.fliplr(c.euclidean_to_geo(city, r[0]))))
} for rank, r in enumerate(best_region)]
filename = 'static/random_{}_{}.json'.format(city, district)
with open(filename, 'w') as f:
json.dump(outjson,
f,
sort_keys=True,
indent=2,
separators=(',', ': '))
def batch_matching(query_city='paris'):
"""Match preselected regions of `query_city` into the other target
cities"""
import ujson
global QUERY_NAME
global OTMPDIR
with open('static/ground_truth.json') as gt:
regions = ujson.load(gt)
districts = sorted(regions.keys())
cities = sorted(regions.values()[0]['gold'].keys())
assert query_city in cities
cities.remove(query_city)
OTMPDIR = os.path.join(OTMPDIR, 'www_comparaison_' + query_city)
try:
os.mkdir(OTMPDIR)
except OSError:
pass
# cities = ['berlin']
# districts = ['montmartre', 'triangle']
for city in cities:
print(city)
for neighborhood in districts:
# for _ in [1]:
# for city, neighborhood in [('washington', 'marais'), ('washington', 'montmartre')]:
print(neighborhood)
possible_regions = regions[neighborhood]['gold'].get(query_city)
rgeo = choose_query_region(possible_regions)
if not rgeo:
continue
for metric in ['emd-itml', 'emd-tsne']:
# for metric in ['jsd', 'emd', 'cluster', 'emd-lmnn', 'leftover']:
print(metric)
for radius in np.linspace(200, 500, 5):
print(radius)
QUERY_NAME = '{}_{}_{}_{}.my'.format(
city, neighborhood, int(radius), metric)
logging.info('will write: ' +
str(os.path.join(OTMPDIR, QUERY_NAME)))
if os.path.isfile(os.path.join(OTMPDIR, QUERY_NAME)):
continue
res, values, _ = best_match(query_city,
city,
rgeo,
radius,
metric=metric).next()
continue
distance, r_vids, center, radius = res
print(distance)
if center is None:
result = {
'dst': distance,
'metric': metric,
'nb_venues': 0
}
else:
center = cities.euclidean_to_geo(city, center)
result = {
'geo': {
'type': 'circle',
'center': center,
'radius': radius
},
'dst': distance,
'metric': metric,
'nb_venues': len(r_vids)
}
regions[neighborhood][city].append(result)
# outname = '{}_{}_{}_{}.png'.format(city, neighborhood,
# int(radius), metric)
# interpolate_distances(values, outname)
with open('static/cpresets.js', 'w') as out:
out.write('var PRESETS =' + ujson.dumps(regions) + ';')