def bench_ball_tree(N=2000, D=3, k=15, leaf_size=30):
print("Ball Tree")
X = np.random.random((N, D)).astype(DTYPE)
t0 = time()
btskl = skBallTree(X, leaf_size=leaf_size)
t1 = time()
bt = BallTree(X, leaf_size=leaf_size)
t2 = time()
print("Build:")
print(" sklearn : %.2g sec" % (t1 - t0))
print(" new : %.2g sec" % (t2 - t1))
t0 = time()
Dskl, Iskl = btskl.query(X, k)
t1 = time()
dist = [Dskl]
ind = [Iskl]
times = [t1 - t0]
labels = ['sklearn']
counts = [-1]
for dualtree in (False, True):
for breadth_first in (False, True):
bt.reset_n_calls()
t0 = time()
D, I = bt.query(X,
k,
dualtree=dualtree,
breadth_first=breadth_first)
t1 = time()
dist.append(D)
ind.append(I)
times.append(t1 - t0)
counts.append(bt.get_n_calls())
if dualtree:
label = 'dual/'
else:
label = 'single/'
if breadth_first:
label += 'breadthfirst'
else:
label += 'depthfirst'
labels.append(label)
print("Query:")
for lab, t, c in zip(labels, times, counts):
print(" %s : %.2g sec (%i calls)" % (lab, t, c))
print
print(
" distances match: %s" % ', '.join([
'%s' % np.allclose(dist[i - 1], dist[i]) for i in range(len(dist))
]))
print(
" indices match: %s" % ', '.join(
['%s' % np.allclose(ind[i - 1], ind[i]) for i in range(len(ind))]))
def bench_ball_tree(N=2000, D=3, k=15, leaf_size=30):
print("Ball Tree")
X = np.random.random((N, D)).astype(DTYPE)
t0 = time()
btskl = skBallTree(X, leaf_size=leaf_size)
t1 = time()
bt = BallTree(X, leaf_size=leaf_size)
t2 = time()
print("Build:")
print(" sklearn : %.2g sec" % (t1 - t0))
print(" new : %.2g sec" % (t2 - t1))
t0 = time()
Dskl, Iskl = btskl.query(X, k)
t1 = time()
dist = [Dskl]
ind = [Iskl]
times = [t1 - t0]
labels = ['sklearn']
counts = [-1]
for dualtree in (False, True):
for breadth_first in (False, True):
bt.reset_n_calls()
t0 = time()
D, I = bt.query(X, k, dualtree=dualtree,
breadth_first=breadth_first)
t1 = time()
dist.append(D)
ind.append(I)
times.append(t1 - t0)
counts.append(bt.get_n_calls())
if dualtree:
label = 'dual/'
else:
label = 'single/'
if breadth_first:
label += 'breadthfirst'
else:
label += 'depthfirst'
labels.append(label)
print("Query:")
for lab, t, c in zip(labels, times, counts):
print(" %s : %.2g sec (%i calls)" % (lab, t, c))
print
print(" distances match: %s"
% ', '.join(['%s' % np.allclose(dist[i - 1], dist[i])
for i in range(len(dist))]))
print(" indices match: %s"
% ', '.join(['%s' % np.allclose(ind[i - 1], ind[i])
for i in range(len(ind))]))
def bench_KDE(N=1000, D=3, h=0.5, leaf_size=30):
X = np.random.random((N, D))
bt = BallTree(X, leaf_size=leaf_size)
kernel = 'gaussian'
print "Kernel Density:"
atol = 1E-5
rtol = 1E-5
for h in [0.001, 0.01, 0.1]:
t0 = time()
dens_true = np.exp(-0.5 * ((X[:, None, :]
- X) ** 2).sum(-1) / h ** 2).sum(-1)
dens_true /= h * np.sqrt(2 * np.pi)
t1 = time()
bt.reset_n_calls()
t2 = time()
dens1 = bt.kernel_density(X, h, atol=atol, rtol=rtol, kernel=kernel,
dualtree=False, breadth_first=True)
t3 = time()
n1 = bt.get_n_calls()
bt.reset_n_calls()
t4 = time()
dens2 = bt.kernel_density(X, h, atol=atol, rtol=rtol, kernel=kernel,
dualtree=False, breadth_first=False)
t5 = time()
n2 = bt.get_n_calls()
bt.reset_n_calls()
t6 = time()
dens3 = bt.kernel_density(X, h, atol=atol, kernel=kernel,
dualtree=True, breadth_first=True)
t7 = time()
n3 = bt.get_n_calls()
bt.reset_n_calls()
t8 = time()
dens4 = bt.kernel_density(X, h, atol=atol, kernel=kernel,
dualtree=True, breadth_first=False)
t9 = time()
n4 = bt.get_n_calls()
print " h = %.3f" % h
print " brute force: %.2g sec (%i calls)" % (t1 - t0, N * N)
print(" single tree (depth first): %.2g sec (%i calls)"
% (t3 - t2, n1))
print(" single tree (breadth first): %.2g sec (%i calls)"
% (t5 - t4, n2))
print(" dual tree: (depth first) %.2g sec (%i calls)"
% (t7 - t6, n3))
print(" dual tree: (breadth first) %.2g sec (%i calls)"
% (t9 - t8, n4))
print " distances match:", (np.allclose(dens_true, dens1,
atol=atol, rtol=rtol),
np.allclose(dens_true, dens2,
atol=atol, rtol=rtol),
np.allclose(dens_true, dens3,
atol=atol),
np.allclose(dens_true, dens4,
atol=atol))
def bench_KDE(N=1000, D=3, h=0.5, leaf_size=30):
X = np.random.random((N, D))
bt = BallTree(X, leaf_size=leaf_size)
kernel = 'gaussian'
print "Kernel Density:"
atol = 1E-5
rtol = 1E-5
for h in [0.001, 0.01, 0.1]:
t0 = time()
dens_true = np.exp(-0.5 * ((X[:, None, :] - X)**2).sum(-1) /
h**2).sum(-1)
dens_true /= h * np.sqrt(2 * np.pi)
t1 = time()
bt.reset_n_calls()
t2 = time()
dens1 = bt.kernel_density(X,
h,
atol=atol,
rtol=rtol,
kernel=kernel,
dualtree=False,
breadth_first=True)
t3 = time()
n1 = bt.get_n_calls()
bt.reset_n_calls()
t4 = time()
dens2 = bt.kernel_density(X,
h,
atol=atol,
rtol=rtol,
kernel=kernel,
dualtree=False,
breadth_first=False)
t5 = time()
n2 = bt.get_n_calls()
bt.reset_n_calls()
t6 = time()
dens3 = bt.kernel_density(X,
h,
atol=atol,
kernel=kernel,
dualtree=True,
breadth_first=True)
t7 = time()
n3 = bt.get_n_calls()
bt.reset_n_calls()
t8 = time()
dens4 = bt.kernel_density(X,
h,
atol=atol,
kernel=kernel,
dualtree=True,
breadth_first=False)
t9 = time()
n4 = bt.get_n_calls()
print " h = %.3f" % h
print " brute force: %.2g sec (%i calls)" % (t1 - t0, N * N)
print(" single tree (depth first): %.2g sec (%i calls)" %
(t3 - t2, n1))
print(" single tree (breadth first): %.2g sec (%i calls)" %
(t5 - t4, n2))
print(" dual tree: (depth first) %.2g sec (%i calls)" %
(t7 - t6, n3))
print(" dual tree: (breadth first) %.2g sec (%i calls)" %
(t9 - t8, n4))
print " distances match:", (np.allclose(dens_true,
dens1,
atol=atol,
rtol=rtol),
np.allclose(dens_true,
dens2,
atol=atol,
rtol=rtol),
np.allclose(dens_true, dens3, atol=atol),
np.allclose(dens_true, dens4, atol=atol))
