def generate_dataset(d, k, mode, nframes):
"""Generate a dataset useful for EM anf GMM testing.
returns:
data : ndarray
data from the true model.
tgm : GM
the true model (randomly generated)
gm0 : GM
the initial model
gm : GM
the trained model
"""
# Generate a model
w, mu, va = GM.gen_param(d, k, mode, spread=2.0)
tgm = GM.fromvalues(w, mu, va)
# Generate data from the model
data = tgm.sample(nframes)
# Run EM on the model, by running the initialization separetely.
gmm = GMM(GM(d, k, mode), 'test')
gmm.init_random(data)
gm0 = copy.copy(gmm.gm)
gmm = GMM(copy.copy(gmm.gm), 'test')
em = EM()
em.train(data, gmm)
return data, tgm, gm0, gmm.gm
def cluster(data, k, mode='full'):
d = data.shape[1]
gm = GM(d, k, mode)
gmm = GMM(gm)
em = EM()
em.train(data, gmm, maxiter=20)
return gm
def cluster(data, k, mode='full'):
d = data.shape[1]
gm = GM(d, k, mode)
gmm = GMM(gm, 'random')
em = RegularizedEM(pcnt=pcnt, pval=pval)
em.train(data, gmm, maxiter=20)
return gm, gmm.bic(data)
def _create_model(self, d, k, mode, nframes, emiter):
#+++++++++++++++++++++++++++++++++++++++++++++++++
# Generate a model with k components, d dimensions
#+++++++++++++++++++++++++++++++++++++++++++++++++
w, mu, va = GM.gen_param(d, k, mode, spread=1.5)
gm = GM.fromvalues(w, mu, va)
# Sample nframes frames from the model
data = gm.sample(nframes)
#++++++++++++++++++++++++++++++++++++++++++
# Approximate the models with classical EM
#++++++++++++++++++++++++++++++++++++++++++
# Init the model
lgm = GM(d, k, mode)
gmm = GMM(lgm, 'kmean')
gmm.init(data, niter=KM_ITER)
self.gm0 = copy.copy(gmm.gm)
# The actual EM, with likelihood computation
for i in range(emiter):
g, tgd = gmm.compute_responsabilities(data)
gmm.update_em(data, g)
self.data = data
self.gm = lgm
def cluster(data, k):
d = data.shape[1]
gm = GM(d, k)
gmm = GMM(gm)
em = EM()
em.train(data, gmm, maxiter=20)
return gm, gmm.bic(data)
def _test(self, dataset, log):
dic = load_dataset(dataset)
gm = GM.fromvalues(dic['w0'], dic['mu0'], dic['va0'])
gmm = GMM(gm, 'test')
EM().train(dic['data'], gmm, log = log)
assert_array_almost_equal(gmm.gm.w, dic['w'], DEF_DEC)
assert_array_almost_equal(gmm.gm.mu, dic['mu'], DEF_DEC)
assert_array_almost_equal(gmm.gm.va, dic['va'], DEF_DEC)
def _create_model_and_run_em(self, d, k, mode, nframes):
#+++++++++++++++++++++++++++++++++++++++++++++++++
# Generate a model with k components, d dimensions
#+++++++++++++++++++++++++++++++++++++++++++++++++
w, mu, va = GM.gen_param(d, k, mode, spread = 1.5)
gm = GM.fromvalues(w, mu, va)
# Sample nframes frames from the model
data = gm.sample(nframes)
#++++++++++++++++++++++++++++++++++++++++++
# Approximate the models with classical EM
#++++++++++++++++++++++++++++++++++++++++++
# Init the model
lgm = GM(d, k, mode)
gmm = GMM(lgm, 'kmean')
em = EM()
lk = em.train(data, gmm)
def _test_common(self, d, k, mode):
dic = load_dataset('%s_%dd_%dk.mat' % (mode, d, k))
gm = GM.fromvalues(dic['w0'], dic['mu0'], dic['va0'])
gmm = GMM(gm, 'test')
a, na = gmm.compute_responsabilities(dic['data'])
la, nla = gmm.compute_log_responsabilities(dic['data'])
ta = N.log(a)
tna = N.log(na)
if not N.all(N.isfinite(ta)):
print "precision problem for %s, %dd, %dk, test need fixing" % (mode, d, k)
else:
assert_array_almost_equal(ta, la, DEF_DEC)
if not N.all(N.isfinite(tna)):
print "precision problem for %s, %dd, %dk, test need fixing" % (mode, d, k)
else:
assert_array_almost_equal(tna, nla, DEF_DEC)
k = 2 d = 2 mode = 'diag' nframes = 1e3 #+++++++++++++++++++++++++++++++++++++++++++ # Create an artificial GM model, samples it #+++++++++++++++++++++++++++++++++++++++++++ w, mu, va = GM.gen_param(d, k, mode, spread = 1.5) gm = GM.fromvalues(w, mu, va) # Sample nframes frames from the model data = gm.sample(nframes) #++++++++++++++++++++++++ # Learn the model with EM #++++++++++++++++++++++++ # Create a Model from a Gaussian mixture with kmean initialization lgm = GM(d, k, mode) gmm = GMM(lgm, 'kmean') # The actual EM, with likelihood computation. The threshold # is compared to the (linearly appromixated) derivative of the likelihood em = EM() like = em.train(data, gmm, maxiter = 30, thresh = 1e-8) # The computed parameters are in gmm.gm, which is the same than lgm # (remember, python does not copy most objects by default). You can for example # plot lgm against gm to compare
