def discrepancy_seeds(goods, bads, all_locs):
"""Find regions with concentration of good points compared with bad
ones."""
import spatial_scan as sps
size = 50
support = 8
sps.GRID_SIZE = size
sps.TOP_K = 500
xedges, yedges = [
np.linspace(low, high, size + 1)
for low, high in zip(np.min(all_locs, 0), np.max(all_locs, 0))
]
bins = (xedges, yedges)
good_ids, good_loc = goods
bad_ids, bad_loc = bads
count, _, _ = np.histogram2d(good_loc[:, 0], good_loc[:, 1], bins=bins)
measured = count.T.ravel()
count, _, _ = np.histogram2d(bad_loc[:, 0], bad_loc[:, 1], bins=bins)
background = count.T.ravel()
total_b = np.sum(background)
total_m = np.sum(measured)
discrepancy = sps.get_discrepancy_function(total_m, total_b, support)
def euc_index_to_rect(idx):
"""Return the bounding box of a grid's cell defined by its
`idx`"""
i = idx % size
j = idx / size
return [xedges[i], yedges[j], xedges[i + 1], yedges[j + 1]]
sps.index_to_rect = euc_index_to_rect
top_loc = sps.exact_grid(np.reshape(measured, (size, size)),
np.reshape(background, (size, size)), discrepancy,
sps.TOP_K, sps.GRID_SIZE / 8)
merged = sps.merge_regions(top_loc)
gcluster = []
bcluster = []
hulls = []
for region in merged:
gcluster.append([
id_ for id_, loc in zip(good_ids, good_loc)
if region[1].contains(sgeo.Point(loc))
])
bcluster.append([
id_ for id_, loc in zip(bad_ids, bad_loc)
if region[1].contains(sgeo.Point(loc))
])
hulls.append(region[1].convex_hull)
return hulls, gcluster, bcluster
def discrepancy_seeds(goods, bads, all_locs):
"""Find regions with concentration of good points compared with bad
ones."""
import spatial_scan as sps
size = 50
support = 8
sps.GRID_SIZE = size
sps.TOP_K = 500
xedges, yedges = [np.linspace(low, high, size+1)
for low, high in zip(np.min(all_locs, 0),
np.max(all_locs, 0))]
bins = (xedges, yedges)
good_ids, good_loc = goods
bad_ids, bad_loc = bads
count, _, _ = np.histogram2d(good_loc[:, 0], good_loc[:, 1], bins=bins)
measured = count.T.ravel()
count, _, _ = np.histogram2d(bad_loc[:, 0], bad_loc[:, 1], bins=bins)
background = count.T.ravel()
total_b = np.sum(background)
total_m = np.sum(measured)
discrepancy = sps.get_discrepancy_function(total_m, total_b, support)
def euc_index_to_rect(idx):
"""Return the bounding box of a grid's cell defined by its
`idx`"""
i = idx % size
j = idx / size
return [xedges[i], yedges[j], xedges[i+1], yedges[j+1]]
sps.index_to_rect = euc_index_to_rect
top_loc = sps.exact_grid(np.reshape(measured, (size, size)),
np.reshape(background, (size, size)),
discrepancy, sps.TOP_K,
sps.GRID_SIZE/8)
merged = sps.merge_regions(top_loc)
gcluster = []
bcluster = []
hulls = []
for region in merged:
gcluster.append([id_ for id_, loc in zip(good_ids, good_loc)
if region[1].contains(sgeo.Point(loc))])
bcluster.append([id_ for id_, loc in zip(bad_ids, bad_loc)
if region[1].contains(sgeo.Point(loc))])
hulls.append(region[1].convex_hull)
return hulls, gcluster, bcluster
def do_scan(client, city, k, photos_as_background=True):
"""Perform discrepancy scan on `city` with grid_size."""
background, measured = load_frequency(client, city, k,
photos_as_background)
total_b = np.sum(background)
total_m = np.sum(measured)
if not total_m > 0:
return
if 0 < total_m <= 500:
support = 20
if 500 < total_m <= 2000:
support = 40
if 2000 < total_m:
support = sps.MAX_SUPPORT
discrepancy = sps.get_discrepancy_function(total_m, total_b, support)
grid_dim = (k, k)
info = u'g={}, s={}, k={}, w={}, h={}, max={}'
print(info.format(k, support, sps.TOP_K, sps.MIN_WIDTH, sps.MIN_HEIGHT,
sps.MAX_SIZE))
top_loc = sps.exact_grid(np.reshape(measured, grid_dim),
np.reshape(background, grid_dim),
discrepancy, sps.TOP_K, k/sps.MAX_SIZE)
return top_loc, compute_ratio(background, measured)
def do_scan(client, city, k, photos_as_background=True):
"""Perform discrepancy scan on `city` with grid_size."""
background, measured = load_frequency(client, city, k,
photos_as_background)
total_b = np.sum(background)
total_m = np.sum(measured)
if not total_m > 0:
return
if 0 < total_m <= 500:
support = 20
if 500 < total_m <= 2000:
support = 40
if 2000 < total_m:
support = sps.MAX_SUPPORT
discrepancy = sps.get_discrepancy_function(total_m, total_b, support)
grid_dim = (k, k)
info = u'g={}, s={}, k={}, w={}, h={}, max={}'
print(
info.format(k, support, sps.TOP_K, sps.MIN_WIDTH, sps.MIN_HEIGHT,
sps.MAX_SIZE))
top_loc = sps.exact_grid(np.reshape(measured, grid_dim),
np.reshape(background, grid_dim), discrepancy,
sps.TOP_K, k / sps.MAX_SIZE)
return top_loc, compute_ratio(background, measured)
