def all_gold_dst():
"""Compute the distance between all gold regions and the query ones for
all metrics."""
assert GROUND_TRUTH, 'load GROUND_TRUTH before calling'
districts = GROUND_TRUTH.keys()
cities = GROUND_TRUTH.items()[0][1]['gold'].keys()
cities.remove('paris')
metrics = ['cluster', 'emd', 'emd-lmnn', 'jsd']
results = {}
for city, district in i.product(cities, districts):
geo = GROUND_TRUTH[district]['gold']['paris'][0]['geometry']
for metric in metrics:
name = '_'.join([city, district, metric])
info = interpret_query('paris', city, geo, metric)
_, target_city, target_desc, regions_distance, _, threshold = info
support = target_desc[1]
candidates = get_gold_desc(target_city, district)
if not candidates:
print(name + ' is empty')
continue
current_dsts = []
for region in candidates:
features, _, weights, _ = region
if metric == 'cluster' and weights.size < 3:
print("{}: can't make three clusters".format(name))
continue
dst = generic_distance(metric, regions_distance, features,
weights, support)
if metric == 'leftover':
dst = emd_leftover.collect_matlab_output(1)
clean_tmp_mats()
current_dsts.append(dst)
results[name] = current_dsts
return results
def all_gold_dst():
"""Compute the distance between all gold regions and the query ones for
all metrics."""
assert GROUND_TRUTH, 'load GROUND_TRUTH before calling'
districts = GROUND_TRUTH.keys()
cities = GROUND_TRUTH.items()[0][1]['gold'].keys()
cities.remove('paris')
metrics = ['cluster', 'emd', 'emd-lmnn', 'jsd']
results = {}
for city, district in i.product(cities, districts):
geo = GROUND_TRUTH[district]['gold']['paris'][0]['geometry']
for metric in metrics:
name = '_'.join([city, district, metric])
info = interpret_query('paris', city, geo, metric)
_, target_city, target_desc, regions_distance, _, threshold = info
support = target_desc[1]
candidates = get_gold_desc(target_city, district)
if not candidates:
print(name + ' is empty')
continue
current_dsts = []
for region in candidates:
features, _, weights, _ = region
if metric == 'cluster' and weights.size < 3:
print("{}: can't make three clusters".format(name))
continue
dst = generic_distance(metric, regions_distance, features,
weights, support)
if metric == 'leftover':
dst = emd_leftover.collect_matlab_output(1)
clean_tmp_mats()
current_dsts.append(dst)
results[name] = current_dsts
return results
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 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) + ';')
