def test_1D_ks_2samp(self):
# Compare with scipy.stats.ks_2samp
x = np.random.randn(50) + 1
y = np.random.randn(50)
s, p = stats.ks_2samp(x, y)
dm = dd.kolmogorov_smirnov(x, y)
aaeq(dm, s, 3)
def test_1D_ks_2samp(self):
# Compare with scipy.stats.ks_2samp
x = np.random.randn(50) + 1
y = np.random.randn(50)
s, p = stats.ks_2samp(x, y)
dm = dd.kolmogorov_smirnov(x, y)
aaeq(dm, s, 3)
def test_mvnormal(self):
"""Compare the results to the figure 2 in the paper."""
from numpy.random import normal, multivariate_normal
N = 30000
p = normal(0, 1, size=(N, 2))
np.random.seed(1)
q = multivariate_normal([.5, -.5], [[.5, .1], [.1, .3]], size=N)
aaeq(dd.kldiv(p, q), 1.39, 1)
aaeq(dd.kldiv(q, p), 0.62, 1)
def test_mvnormal(self):
"""Compare the results to the figure 2 in the paper."""
from numpy.random import normal, multivariate_normal
n = 30000
p = normal(0, 1, size=(n, 2))
np.random.seed(1)
q = multivariate_normal([.5, -.5], [[.5, .1], [.1, .3]], size=n)
aaeq(dd.kldiv(p, q), 1.39, 1)
aaeq(dd.kldiv(q, p), 0.62, 1)
def test_simple(self):
# Over these 7 points, there are 2 with edges within the same sample.
# [1,2]-[2,2] & [3,2]-[4,2]
# |
# | x
# | o o x x
# | x o
# |_ _ _ _ _ _ _
x = np.array([[1, 2], [2, 2], [3, 1]])
y = np.array([[1, 1], [2, 4], [3, 2], [4, 2]])
dm = dd.friedman_rafsky(x, y)
aaeq(dm, 2. / 7, 3)
def test_simple(self):
# Over these 7 points, there are 2 with edges within the same sample.
# [1,2]-[2,2] & [3,2]-[4,2]
# |
# | x
# | o o x x
# | x o
# |_ _ _ _ _ _ _
x = np.array([[1, 2], [2, 2], [3, 1]])
y = np.array([[1, 1], [2, 4], [3, 2], [4, 2]])
dm = dd.friedman_rafsky(x, y)
aaeq(dm, 2. / 7, 3)
def test_against_analytic(self):
p = stats.norm(2, 1)
q = stats.norm(2.6, 1.4)
ra = analytical_KLDiv(p, q)
N = 10000
np.random.seed(2)
# x, y = p.rvs(N), q.rvs(N)
re = dd.kldiv(p.rvs(N), q.rvs(N))
aaeq(re, ra, 1)
def test_against_analytic(self):
p = stats.norm(2, 1)
q = stats.norm(2.6, 1.4)
ra = analytical_KLDiv(p, q)
N = 10000
np.random.seed(2)
x, y = p.rvs(N), q.rvs(N)
re = dd.kldiv(p.rvs(N), q.rvs(N))
aaeq(re, ra, 1)
def test_simple(self):
d = 2
n, m = 25, 30
x = randn(0, 1, (n, d))
y = randn([1, 2], 1, (m, d))
dm = dd.seuclidean(x, y)
aaeq(dm, np.hypot(1, 2), 2)
# Variance of the candidate sample does not affect answer.
x = randn(0, 1, (n, d))
y = randn([1, 2], 2, (m, d))
dm = dd.seuclidean(x, y)
aaeq(dm, np.hypot(1, 2), 2)
def test_simple(self):
d = 2
n, m = 25, 30
x = randn(0, 1, (n, d))
y = randn([1, 2], 1, (m, d))
dm = dd.seuclidean(x, y)
aaeq(dm, np.hypot(1, 2), 2)
# Variance of the candidate sample does not affect answer.
x = randn(0, 1, (n, d))
y = randn([1, 2], 2, (m, d))
dm = dd.seuclidean(x, y)
aaeq(dm, np.hypot(1, 2), 2)
def check_different_sample_size(self):
p = stats.norm(2, 1)
q = stats.norm(2.6, 1.4)
ra = analytical_KLDiv(p, q)
n = 6000
# Same sample size for x and y
re = [dd.kldiv(p.rvs(n), q.rvs(n)) for i in range(30)]
aaeq(np.mean(re), ra, 2)
# Different sample sizes
re = [dd.kldiv(p.rvs(n * 2), q.rvs(n)) for i in range(30)]
aaeq(np.mean(re), ra, 2)
re = [dd.kldiv(p.rvs(n), q.rvs(n * 2)) for i in range(30)]
aaeq(np.mean(re), ra, 2)
def check_different_sample_size(self):
p = stats.norm(2, 1)
q = stats.norm(2.6, 1.4)
ra = analytical_KLDiv(p, q)
N = 6000
# Same sample size for x and y
re = [dd.kldiv(p.rvs(N), q.rvs(N)) for i in range(30)]
aaeq(np.mean(re), ra, 2)
# Different sample sizes
re = [dd.kldiv(p.rvs(N * 2), q.rvs(N)) for i in range(30)]
aaeq(np.mean(re), ra, 2)
re = [dd.kldiv(p.rvs(N), q.rvs(N * 2)) for i in range(30)]
aaeq(np.mean(re), ra, 2)
def test_simple(self):
d = 2
n, m = 200, 200
np.random.seed(1)
x = np.random.randn(n, d)
y = np.random.randn(m, d)
# Almost identical samples
dm = dd.nearest_neighbor(x + .001, x)
aaeq(dm, 0, 2)
# Same distribution but mixed
dm = dd.nearest_neighbor(x, y)
aaeq(dm, 0.5, 1)
# Two completely different distributions
dm = dd.nearest_neighbor(x + 10, y)
aaeq(dm, 1, 2)
def test_simple(self):
d = 2
n, m = 200, 200
np.random.seed(1)
x = np.random.randn(n, d)
y = np.random.randn(m, d)
# Almost identical samples
dm = dd.nearest_neighbor(x + .001, x)
aaeq(dm, 0, 2)
# Same distribution but mixed
dm = dd.nearest_neighbor(x, y)
aaeq(dm, 0.5, 1)
# Two completely different distributions
dm = dd.nearest_neighbor(x + 10, y)
aaeq(dm, 1, 2)
def test_compare_with_matlab(self):
x, y = matlab_sample()
dm = dd.seuclidean(x, y)
aaeq(dm, 2.8463, 4)
def test_compare_with_matlab(self):
x, y = matlab_sample()
dm = dd.friedman_rafsky(x, y)
aaeq(dm, 0.96667, 4)
def check_accuracy(self):
m, s = self.accuracy_vs_kth(N=500, trials=300)
aaeq(np.mean(m[0:2]), 0, 2)
def test_compare_with_matlab(self):
x, y = matlab_sample()
dm = dd.kolmogorov_smirnov(x, y)
aaeq(dm, 0.96667, 4)
def test_compare_with_matlab(self):
x, y = matlab_sample()
dm = dd.kolmogorov_smirnov(x, y)
aaeq(dm, 0.96667, 4)
def test_compare_with_matlab(self):
x, y = matlab_sample()
dm = dd.friedman_rafsky(x, y)
aaeq(dm, 0.96667, 4)
def check_accuracy(self):
m, _ = self.accuracy_vs_kth(n=500, trials=300)
aaeq(np.mean(m[0:2]), 0, 2)
def test_randn():
mu, std = [2, 3], [1, 2]
r = randn(mu, std, [10, 2])
aaeq(r.mean(0), mu)
aaeq(r.std(0, ddof=1), std)
def test_randn():
mu, std = [2, 3], [1, 2]
r = randn(mu, std, [10, 2])
aaeq(r.mean(0), mu)
aaeq(r.std(0, ddof=1), std)
def test_compare_with_matlab(self):
x, y = matlab_sample()
dm = dd.nearest_neighbor(x, y)
aaeq(dm, 1, 4)
def test_compare_with_matlab(self):
x, y = matlab_sample()
dm = dd.seuclidean(x, y)
aaeq(dm, 2.8463, 4)
def test_compare_with_matlab(self):
x, y = matlab_sample()
dm = dd.zech_aslan(x, y)
aaeq(dm, 0.77802, 4)
def test_compare_with_matlab(self):
x, y = matlab_sample()
dm = dd.nearest_neighbor(x, y)
aaeq(dm, 1, 4)
def test_compare_with_matlab(self):
x, y = matlab_sample()
dm = dd.zech_aslan(x, y)
aaeq(dm, 0.77802, 4)
