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 brute_search(city_desc, hsize, distance_function, threshold,
metric='jsd'):
"""Move a sliding circle over the whole city and keep track of the best
result."""
global SURROUNDINGS, CITY_FEATURES, THRESHOLD, RADIUS
global METRIC_NAME, CITY_SUPPORT, DISTANCE_FUNCTION
import multiprocessing
RADIUS = hsize
THRESHOLD = threshold
METRIC_NAME = metric
city_size, CITY_SUPPORT, CITY_FEATURES, city_infos = city_desc
SURROUNDINGS, bounds = city_infos
DISTANCE_FUNCTION = distance_function
minx, miny, maxx, maxy = bounds
nb_x_step = int(3*np.floor(city_size[0]) / hsize + 1)
nb_y_step = int(3*np.floor(city_size[1]) / hsize + 1)
best = [1e20, [], [], RADIUS]
res_map = []
pool = multiprocessing.Pool(4)
x_steps = np.linspace(minx+hsize, maxx-hsize, nb_x_step)
y_steps = np.linspace(miny+hsize, maxy-hsize, nb_y_step)
x_vals, y_vals = np.meshgrid(x_steps, y_steps)
to_cell_arg = lambda _: (float(_[1][0]), float(_[1][1]), _[0] % nb_x_step,
_[0]/nb_x_step, _[0])
cells = i.imap(to_cell_arg, enumerate(i.izip(np.nditer(x_vals),
np.nditer(y_vals))))
res = pool.map(one_cell, cells)
pool.close()
pool.join()
res_map = []
if metric == 'leftover':
dsts = emd_leftover.collect_matlab_output(len(res))
for cell, dst in i.izip(res, dsts):
if cell[0]:
cell[2] = dst
clean_tmp_mats()
for cell in res:
if cell[0] is None:
continue
res_map.append(cell[:3])
if cell[2] < best[0]:
best = [cell[2], cell[3], [cell[0], cell[1]], RADIUS]
if QUERY_NAME:
import persistent as p
logging.info('wrote: '+str(os.path.join(OTMPDIR, QUERY_NAME)))
p.save_var(os.path.join(OTMPDIR, QUERY_NAME),
[[cell[2], cell[3], [cell[0], cell[1]], RADIUS]
for cell in res if cell[0]])
yield best, res_map, 1.0
def brute_search(city_desc, hsize, distance_function, threshold, metric='jsd'):
"""Move a sliding circle over the whole city and keep track of the best
result."""
global SURROUNDINGS, CITY_FEATURES, THRESHOLD, RADIUS
global METRIC_NAME, CITY_SUPPORT, DISTANCE_FUNCTION
import multiprocessing
RADIUS = hsize
THRESHOLD = threshold
METRIC_NAME = metric
city_size, CITY_SUPPORT, CITY_FEATURES, city_infos = city_desc
SURROUNDINGS, bounds = city_infos
DISTANCE_FUNCTION = distance_function
minx, miny, maxx, maxy = bounds
nb_x_step = int(3 * np.floor(city_size[0]) / hsize + 1)
nb_y_step = int(3 * np.floor(city_size[1]) / hsize + 1)
best = [1e20, [], [], RADIUS]
res_map = []
pool = multiprocessing.Pool(4)
x_steps = np.linspace(minx + hsize, maxx - hsize, nb_x_step)
y_steps = np.linspace(miny + hsize, maxy - hsize, nb_y_step)
x_vals, y_vals = np.meshgrid(x_steps, y_steps)
to_cell_arg = lambda _: (float(_[1][0]), float(_[1][1]), _[0] % nb_x_step,
_[0] / nb_x_step, _[0])
cells = i.imap(to_cell_arg,
enumerate(i.izip(np.nditer(x_vals), np.nditer(y_vals))))
res = pool.map(one_cell, cells)
pool.close()
pool.join()
res_map = []
if metric == 'leftover':
dsts = emd_leftover.collect_matlab_output(len(res))
for cell, dst in i.izip(res, dsts):
if cell[0]:
cell[2] = dst
clean_tmp_mats()
for cell in res:
if cell[0] is None:
continue
res_map.append(cell[:3])
if cell[2] < best[0]:
best = [cell[2], cell[3], [cell[0], cell[1]], RADIUS]
if QUERY_NAME:
import persistent as p
logging.info('wrote: ' + str(os.path.join(OTMPDIR, QUERY_NAME)))
p.save_var(os.path.join(OTMPDIR, QUERY_NAME),
[[cell[2], cell[3], [cell[0], cell[1]], RADIUS]
for cell in res if cell[0]])
yield best, res_map, 1.0