def test_em_gmm_heterosc(verbose=0):
# testing the model in very ellipsoidal data: compute the big values
# for several values of k and check that the macimal is 1 or 2
# generate some data
dim = 2
x = nr.randn(100, dim)
x[:50, :] += 3
# x[:,0]*=10
# estimate different GMMs of that data
maxiter = 100
delta = 1.0e-4
bic = np.zeros(5)
for k in range(1, 6):
lgmm = GMM(k, dim)
lgmm.initialize(x)
bic[k - 1] = lgmm.estimate(x, maxiter, delta, 0)
if verbose:
print "bic of the %d-classes model" % k, bic
if verbose:
# plot the result
z = lgmm.map_label(x)
from test_bgmm import plot2D
plot2D(x, lgmm, z, show=1, verbose=0)
assert bic[4] < bic[1]
def test_em_gmm_multi(verbose=0):
# Playing with various initilizations on the same data
# generate some data
dim = 2
x = np.concatenate((nr.randn(1000, dim), 3 + 2 * nr.randn(100, dim)))
# estimate different GMMs of that data
maxiter = 100
delta = 1.0e-4
ninit = 5
k = 2
lgmm = GMM(k, dim)
bgmm = lgmm.initialize_and_estimate(x, maxiter, delta, ninit, verbose)
bic = bgmm.evidence(x)
if verbose:
print "bic of the best model", bic
if verbose:
# plot the result
from test_bgmm import plot2D
z = lgmm.map_label(x)
plot2D(x, lgmm, z, show=1, verbose=0)
assert_true(np.isfinite(bic))