def testSeed(self):
P = RDSE_Parameters()
P.size = 1000
P.sparsity = .08
P.radius = 12
P.seed = 98
R = RDSE(P)
A = R.encode(987654)
P.seed = 99
R = RDSE(P)
B = R.encode(987654)
assert (A != B)
def testAverageOverlap(self):
""" Verify that nearby values have the correct amount of semantic
similarity. Also measure sparsity & activation frequency. """
P = RDSE_Parameters()
P.size = 2000
P.sparsity = .08
P.radius = 12
P.seed = 42
R = RDSE(P)
A = SDR(R.parameters.size)
num_samples = 10000
M = Metrics(A, num_samples + 1)
for i in range(num_samples):
R.encode(i, A)
print(M)
assert (M.overlap.min() > (1 - 1. / R.parameters.radius) - .04)
assert (M.overlap.max() < (1 - 1. / R.parameters.radius) + .04)
assert (M.overlap.mean() > (1 - 1. / R.parameters.radius) - .001)
assert (M.overlap.mean() < (1 - 1. / R.parameters.radius) + .001)
assert (M.sparsity.min() > R.parameters.sparsity - .01)
assert (M.sparsity.max() < R.parameters.sparsity + .01)
assert (M.sparsity.mean() > R.parameters.sparsity - .005)
assert (M.sparsity.mean() < R.parameters.sparsity + .005)
assert (M.activationFrequency.min() > R.parameters.sparsity - .05)
assert (M.activationFrequency.max() < R.parameters.sparsity + .05)
assert (M.activationFrequency.mean() > R.parameters.sparsity - .005)
assert (M.activationFrequency.mean() < R.parameters.sparsity + .005)
assert (M.activationFrequency.entropy() > .99)
def testRandomOverlap(self):
""" Verify that distant values have little to no semantic similarity.
Also measure sparsity & activation frequency. """
P = RDSE_Parameters()
P.size = 2000
P.sparsity = .08
P.radius = 12
P.seed = 42
R = RDSE(P)
num_samples = 1000
A = SDR(R.parameters.size)
M = Metrics(A, num_samples + 1)
for i in range(num_samples):
X = i * R.parameters.radius
R.encode(X, A)
print(M)
assert (M.overlap.max() < .15)
assert (M.overlap.mean() < .10)
assert (M.sparsity.min() > R.parameters.sparsity - .01)
assert (M.sparsity.max() < R.parameters.sparsity + .01)
assert (M.sparsity.mean() > R.parameters.sparsity - .005)
assert (M.sparsity.mean() < R.parameters.sparsity + .005)
assert (M.activationFrequency.min() > R.parameters.sparsity - .05)
assert (M.activationFrequency.max() < R.parameters.sparsity + .05)
assert (M.activationFrequency.mean() > R.parameters.sparsity - .005)
assert (M.activationFrequency.mean() < R.parameters.sparsity + .005)
assert (M.activationFrequency.entropy() > .99)
def testDeterminism(self):
""" Verify that the same seed always gets the same results. """
GOLD = SDR(1000)
GOLD.sparse = [
28, 47, 63, 93, 123, 124, 129, 131, 136, 140, 196, 205, 213, 239,
258, 275, 276, 286, 305, 339, 345, 350, 372, 394, 395, 443, 449,
462, 468, 471, 484, 514, 525, 557, 565, 570, 576, 585, 600, 609,
631, 632, 635, 642, 651, 683, 693, 694, 696, 699, 721, 734, 772,
790, 792, 795, 805, 806, 833, 836, 842, 846, 892, 896, 911, 914,
927, 936, 947, 953, 955, 962, 965, 989, 990, 996
]
P = RDSE_Parameters()
P.size = GOLD.size
P.sparsity = .08
P.radius = 12
P.seed = 42
R = RDSE(P)
A = R.encode(987654)
print(A)
assert (A == GOLD)
def testRadiusResolution(self):
""" Check that these arguments are equivalent. """
# radius -> resolution
P = RDSE_Parameters()
P.size = 2000
P.activeBits = 100
P.radius = 12
R = RDSE(P)
self.assertAlmostEqual(R.parameters.resolution, 12. / 100, places=5)
# resolution -> radius
P = RDSE_Parameters()
P.size = 2000
P.activeBits = 100
P.resolution = 12
R = RDSE(P)
self.assertAlmostEqual(R.parameters.radius, 12 * 100, places=5)
# Moving 1 resolution moves 1 bit (usually)
P = RDSE_Parameters()
P.size = 2000
P.activeBits = 100
P.resolution = 3.33
P.seed = 42
R = RDSE(P)
sdrs = []
for i in range(100):
X = i * (R.parameters.resolution)
sdrs.append(R.encode(X))
print("X", X, sdrs[-1])
moved_one = 0
moved_one_samples = 0
for A, B in zip(sdrs, sdrs[1:]):
delta = A.getSum() - A.getOverlap(B)
if A.getSum() == B.getSum():
assert (delta < 2)
moved_one += delta
moved_one_samples += 1
assert (moved_one >= .9 * moved_one_samples)