def cluster():
sample_number, k, r = 2 ** 12, 2, 4
center = 100
data_2d = np.array([int(i) for i in normal(center, 50, sample_number)]).reshape((sample_number / 2, 2))
domain, desired_amount_of_points = (0, 100), 2000
approximation, failure, eps, delta, promise = 0.1, 0.1, 0.5, 2 ** -20, 100
return cl.find(data_2d, 2, domain, desired_amount_of_points, approximation, failure, eps, delta, promise, True)
def cluster():
sample_number, k, r = 2**12, 2, 4
center = 100
data_2d = np.array([int(i)
for i in normal(center, 50, sample_number)]).reshape(
(sample_number / 2, 2))
domain, desired_amount_of_points = (0, 100), 2000
approximation, failure, eps, delta, promise = 0.1, 0.1, 0.5, 2**-20, 100
return cl.find(data_2d, 2, domain, desired_amount_of_points, approximation,
failure, eps, delta, promise, True)
approximation, failure, eps, delta = 0.1, 0.1, 0.5, 2**-10
domain_end = max(abs(np.min(blob)), np.max(blob))
domain = (domain_end, 0.01)
desired_amount_of_points = 1000
failure_bound = bound(sample_number, dimension, eps, delta, approximation)
print "The probability of failure is somewhere between %s\n" % str(failure_bound)
radius, center = find_cluster(blob, desired_amount_of_points)
print "Test-radius: %d" % radius
for i in xrange(8):
middle_time = time.time()
try:
radius, center = cluster.find(blob, dimension, domain, desired_amount_of_points,
approximation, failure, eps, delta, shrink=False, use_histograms=False)
ball = [p for p in blob if euclidean(p, center) <= radius]
print "Good-radius: %d" % radius
# print "Good-center: %s" % str(center)
print "Desired number of points in resulting ball: %d" % desired_amount_of_points
print "Number of points in the resulting ball: %d" % len(ball)
except ValueError:
ball = []
print '_|_'
end_time = time.time()
print "Run-time: %.2f seconds\n" % (end_time - middle_time)
sample_number, dimension = 10000, 2
blobs = dss.make_blobs(sample_number, dimension, cluster_std=70)
blob = np.round(blobs[0], 2)
approximation, failure, eps, delta = 0.1, 0.1, 0.5, 2**-10
domain_end = max(abs(np.min(blob)), np.max(blob))
domain = (domain_end, 0.01)
desired_amount_of_points = 500
start_time = time.time()
radius, center = cluster.find(blob,
dimension,
domain,
desired_amount_of_points,
approximation,
failure,
eps,
delta,
use_histograms=True)
end_time = time.time()
ball = [p for p in blob if euclidean(p, center) <= radius]
# blob = [p for p in blob if tuple(p) not in map(tuple, ball)]
fig = plt.figure()
# ax = fig.add_subplot(111, projection='3d')
ax = fig.add_subplot(211, aspect='equal')
zipped_data = zip(*blob)
ax.scatter(*zipped_data, c='g')
zipped_ball = zip(*ball)
dimension, domain = 2, (domain_end, 0.1)
approximation, failure, eps, delta = 0.1, 0.1, 0.5, 2**-10
for c in clusters:
test_radius, test_center = find_cluster(np.round(c, 1), desired_amount_of_points)
print "Radius: %d" % test_radius
print "Center: %s" % str(test_center)
start_time = time.time()
test_radius, test_center = find_cluster(data, desired_amount_of_points)
print "Test-radius: %d" % test_radius
print "Test-center: %s" % str(test_center)
middle_time = time.time()
print "Run-time: %.2f seconds\n" % (middle_time - start_time)
radius, center = cluster.find(data, dimension, domain, desired_amount_of_points,
approximation, failure, eps, delta)
print "Good-radius: %d" % radius
print "Good-center: %s" % str(center)
end_time = time.time()
print "Run-time: %.2f seconds" % (end_time - middle_time)
fig = plt.figure()
ax = fig.add_subplot(111, aspect='equal')
ax.scatter(*zip(*data))
ax.annotate('center', xy=tuple(center), xytext=tuple(np.array(center)+100),
arrowprops=dict(facecolor='black', shrink=0.05),
)
phis = np.arange(0, 6.283, 0.01)
ax.plot(*circle(test_radius, phis, test_center), c='g', ls='-')
ax.plot(*circle(radius, phis, center), c='r', ls='-')
