-
Notifications
You must be signed in to change notification settings - Fork 5
/
bench_ball_tree.py
212 lines (172 loc) · 6.56 KB
/
bench_ball_tree.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
from time import time
import numpy as np
from scipy.spatial.distance import cdist
import ball_tree
from ball_tree import DTYPE, ITYPE, BallTree
from sklearn.neighbors import BallTree as skBallTree
def simul_sort_numpy(dist, ind):
i = np.argsort(dist, axis=1)
row_ind = np.arange(dist.shape[0])[:, None]
return dist[row_ind, i], ind[row_ind, i]
def bench_simultaneous_sort(n_rows=2000, n_pts=21):
print("Simultaneous sort")
dist1 = np.random.random((n_rows, n_pts)).astype(DTYPE)
ind1 = (np.arange(n_pts) + np.zeros((n_rows, 1))).astype(ITYPE)
dist2 = dist1.copy()
ind2 = ind1.copy()
t0 = time()
dist1, ind1 = simul_sort_numpy(dist1, ind1) # note: not an in-place sort
t1 = time()
ball_tree.simultaneous_sort(dist2, ind2)
t2 = time()
print(" numpy: %.2g sec" % (t1 - t0))
print(" new: %.2g sec" % (t2 - t1))
print(" results match: (%s, %s)\n" % (np.allclose(dist1, dist2),
np.allclose(ind1, ind2)))
def bench_neighbors_heap(n_rows=1000, n_pts=200, n_nbrs=21):
print("Heap push + extracting data")
X = np.random.random((n_rows, n_pts)).astype(DTYPE)
t0 = time()
I0 = np.argsort(X, 1)[:, :n_nbrs]
D0 = X[np.arange(X.shape[0])[:, None], I0]
t1 = time()
D1, I1 = ball_tree.load_heap(X, n_nbrs)
t2 = time()
print(" memviews: %.2g sec" % (t2 - t1))
print(" results match: (%s, %s)\n" % (np.allclose(D1, D0),
np.allclose(I1, I0)))
def bench_euclidean_dist(n1=1000, n2=1100, d=3):
print("Euclidean distances")
X = np.random.random((n1, d)).astype(DTYPE)
Y = np.random.random((n2, d)).astype(DTYPE)
eucl = ball_tree.EuclideanDistance()
funcs = [cdist,
ball_tree.euclidean_pairwise_inline,
ball_tree.euclidean_pairwise_class,
ball_tree.euclidean_pairwise_polymorphic,
eucl.pairwise]
labels = ["scipy/cdist",
"inline",
"class/direct",
"class/polymorphic",
"class/member func"]
D = []
for func, label in zip(funcs, labels):
t0 = time()
Di = func(X, Y)
t1 = time()
D.append(Di)
print(" %s: %.2g sec" % (label, t1 - t0))
print(" results match: (%s)\n"
% ', '.join(['%s' % np.allclose(D[i - 1], D[i])
for i in range(len(D))]))
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))
if __name__ == '__main__':
bench_simultaneous_sort()
bench_neighbors_heap()
bench_euclidean_dist()
bench_ball_tree()
bench_KDE()