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))
def test_em_gmm_largedim(verbose=0):
"""
testing the GMM model in larger dimensions
"""
# generate some data
dim = 10
x = nr.randn(100,dim)
x[:30,:] += 2
# estimate different GMMs of that data
maxiter = 100
delta = 1.e-4
for k in range(2,3):
lgmm = GMM(k,dim)
bgmm = lgmm.initialize_and_estimate(x, None, maxiter, delta, ninit=5)
z = bgmm.map_label(x)
# define the correct labelling
u = np.zeros(100)
u[:30]=1
#check the correlation between the true labelling
# and the computed one
eta = np.absolute(np.dot(z-z.mean(),u-u.mean())/(np.std(z)*np.std(u)*100))
assert (eta>0.3)
