def main(fname, N, n, params):
"""Run GMM EM on the data in @fname"""
gmm = GaussianMixtureModel.from_file(fname)
k, d, M, S, w = gmm.k, gmm.d, gmm.means, gmm.sigmas, gmm.weights
X = gmm.sample(N, n)
# Set seed for the algorithm
sc.random.seed(int(params.seed))
algo = GaussianMixtureEM(k, d)
O = M, S, w
def report(i, O_, lhood):
M_, _, _ = O_
lhood, Z, O_ = algo.run(X, None, report)
M_, S_, w_ = O_
M_ = closest_permuted_matrix(M.T, M_.T).T
# Table
print column_aerr(M, M_), column_rerr(M, M_)
def test_gaussian_em():
"""Test the Gaussian EM on a small generated dataset"""
fname = "gmm-3-10-0.7.npz"
gmm = GaussianMixtureModel.generate(fname, 3, 3)
k, d, M, S, w = gmm.k, gmm.d, gmm.means, gmm.sigmas, gmm.weights
N, n = 1e6, 1e5
X = gmm.sample(N, n)
algo = GaussianMixtureEM(k, d)
def report(i, O_, lhood):
M_, _, _ = O_
lhood, Z, O_ = algo.run(X, None, report)
M_, S_, w_ = O_
M_ = closest_permuted_matrix(M, M_)
w_ = closest_permuted_vector(w, w_)
print w, w_
print norm(M - M_) / norm(M)
print abs(S - S_).max()
print norm(w - w_)
assert (norm(M - M_) / norm(M) < 1e-1)
assert (abs(S - S_) < 1).all()
assert (norm(w - w_) < 1e-2)
def test_gaussian_em():
"""Test the Gaussian EM on a small generated dataset"""
fname = "gmm-3-10-0.7.npz"
gmm = GaussianMixtureModel.generate( fname, 3, 3 )
k, d, M, S, w = gmm.k, gmm.d, gmm.means, gmm.sigmas, gmm.weights
N, n = 1e6, 1e5
X = gmm.sample( N, n )
algo = GaussianMixtureEM(k, d)
def report( i, O_, lhood ):
M_, _, _ = O_
lhood, Z, O_ = algo.run( X, None, report )
M_, S_, w_ = O_
M_ = closest_permuted_matrix( M, M_ )
w_ = closest_permuted_vector( w, w_ )
print w, w_
print norm( M - M_ )/norm(M)
print abs(S - S_).max()
print norm( w - w_ )
assert( norm( M - M_ )/norm(M) < 1e-1 )
assert (abs(S - S_) < 1 ).all()
assert( norm( w - w_ ) < 1e-2 )
def test_gaussian_mom():
"""Test the Gaussian EM on a small generated dataset"""
fname = "gmm-3-10-0.7.npz"
gmm = GaussianMixtureModel.generate( fname, 2, 3 )
k, d, M, S, w = gmm.k, gmm.d, gmm.means, gmm.sigmas, gmm.weights
N, n = 1e6, 1e6
X = gmm.sample( N, n )
M_ = find_means(X, k)
print "M_", M_
M_ = closest_permuted_matrix( M, M_ )
print M, M_
print norm( M - M_ )/norm(M)
assert( norm( M - M_ )/norm(M) < 1e-1 )
def test_gaussian_mom():
"""Test the Gaussian EM on a small generated dataset"""
fname = "gmm-3-10-0.7.npz"
gmm = GaussianMixtureModel.generate(fname, 2, 3)
k, d, M, S, w = gmm.k, gmm.d, gmm.means, gmm.sigmas, gmm.weights
N, n = 1e6, 1e6
X = gmm.sample(N, n)
M_ = find_means(X, k)
print "M_", M_
M_ = closest_permuted_matrix(M, M_)
print M, M_
print norm(M - M_) / norm(M)
assert (norm(M - M_) / norm(M) < 1e-1)
def test_mom():
"""Test the whether spectral can recover from simple mixture of 3 identical"""
model = MixtureModel.generate(2, 2, dirichlet_scale = 0.9)
k, d, M, w = model["k"], model["d"], model["M"], model["w"]
N = 1e5
print "M", M
xs = model.sample(N)
print model.exact_moments(model.observed_monomials(3))
print model.empirical_moments(xs, model.observed_monomials(3))
M_ = find_means(xs, k)
print "M_", M_
M_ = closest_permuted_matrix( M.T, M_.T ).T
print "M", M
print "M_", M_
print norm( M - M_ )/norm(M)
assert( norm( M - M_ )/norm(M) < 1e-1 )
def main(fname, N, n, params):
"""Run GMM EM on the data in @fname"""
gmm = GaussianMixtureModel.from_file( fname )
k, d, M, S, w = gmm.k, gmm.d, gmm.means, gmm.sigmas, gmm.weights
X = gmm.sample( N, n )
# Set seed for the algorithm
sc.random.seed( int( params.seed ) )
algo = GaussianMixtureEM( k, d )
O = M, S, w
def report( i, O_, lhood ):
M_, _, _ = O_
lhood, Z, O_ = algo.run( X, None, report )
M_, S_, w_ = O_
M_ = closest_permuted_matrix( M.T, M_.T ).T
# Table
print column_aerr( M, M_ ), column_rerr( M, M_ )
