def test_runner_multiprocessing_convergence():
N, D = 4, 5
defn = model_definition(N, [bb] * D)
prng = rng()
Y, posterior = data_with_posterior(defn, r=prng)
view = numpy_dataview(Y)
latents = [model.initialize(defn, view, prng)
for _ in xrange(mp.cpu_count())]
runners = [runner.runner(defn, view, latent, ['assign'])
for latent in latents]
r = parallel.runner(runners)
r.run(r=prng, niters=1000) # burnin
idmap = {C: i for i, C in enumerate(permutation_iter(N))}
def sample_iter():
r.run(r=prng, niters=10)
for latent in r.get_latents():
yield idmap[tuple(permutation_canonical(latent.assignments()))]
ref = [None]
def sample_fn():
if ref[0] is None:
ref[0] = sample_iter()
try:
return next(ref[0])
except StopIteration:
ref[0] = None
return sample_fn()
assert_discrete_dist_approx(sample_fn, posterior, ntries=100, kl_places=2)
def test_runner_multyvac():
defn = model_definition(10, [bb, nich, niw(3)])
Y = toy_dataset(defn)
view = numpy_dataview(Y)
kc = runner.default_kernel_config(defn)
prng = rng()
latents = [model.initialize(defn, view, prng)
for _ in xrange(2)]
runners = [runner.runner(defn, view, latent, kc) for latent in latents]
r = parallel.runner(runners, backend='multyvac', layer='perf', core='f2')
r.run(r=prng, niters=1000)
r.run(r=prng, niters=1000)
def test_runner_multiprocessing():
defn = model_definition(10, [bb, nich, niw(3)])
Y = toy_dataset(defn)
view = numpy_dataview(Y)
kc = runner.default_kernel_config(defn)
prng = rng()
latents = [model.initialize(defn, view, prng)
for _ in xrange(mp.cpu_count())]
runners = [runner.runner(defn, view, latent, kc) for latent in latents]
r = parallel.runner(runners)
# check it is restartable
r.run(r=prng, niters=10)
r.run(r=prng, niters=10)
def run_dpgmm(niter=1000, datadir="../../", nfeatures=13):
ranking = [10, 6, 7, 26, 5, 8, 4, 19, 12, 23, 24, 33, 28, 25,
14, 3, 0, 1, 21, 30, 11, 31, 13, 9, 22, 2, 27, 29,
32, 17, 18, 20, 16, 15]
features, labels, lc, hr, tstart, \
features_lb, labels_lb, lc_lb, hr_lb, \
fscaled, fscaled_lb, fscaled_full, labels_all = \
load_data(datadir, tseg=1024.0, log_features=None,
ranking=ranking)
labels_phys = feature_engineering.convert_labels_to_physical(labels)
labels_phys_lb = feature_engineering.convert_labels_to_physical(labels_lb)
labels_all_phys = np.hstack([labels_phys["train"], labels_phys["val"],
labels_phys["test"]])
fscaled_small = fscaled_full[:, :13]
nchains = 8
# The random state object
prng = rng()
# Define a DP-GMM where the Gaussian is 2D
defn = model_definition(fscaled_small.shape[0],
[normal_inverse_wishart(fscaled_small.shape[1])])
fscaled_rec = np.array([(list(f),) for f in fscaled_small],
dtype=[('', np.float32, fscaled_small.shape[1])])
# Create a wrapper around the numpy recarray which
# data-microscopes understands
view = numpy_dataview(fscaled_rec)
# Initialize nchains start points randomly in the state space
latents = [model.initialize(defn, view, prng) for _ in xrange(nchains)]
# Create a runner for each chain
runners = [runner.runner(defn, view, latent,
kernel_config=['assign']) for latent in latents]
r = parallel.runner(runners)
r.run(r=prng, niters=niter)
with open(datadir+"grs1915_dpgmm.pkl", "w") as f:
pickle.dump(r, f)
return
def test_runner_convergence():
N, D = 4, 5
defn = model_definition(N, [bb] * D)
prng = rng()
Y, posterior = data_with_posterior(defn, r=prng)
view = numpy_dataview(Y)
latent = model.initialize(defn, view, prng)
r = runner.runner(defn, view, latent, ['assign'])
r.run(r=prng, niters=1000) # burnin
idmap = {C: i for i, C in enumerate(permutation_iter(N))}
def sample_fn():
r.run(r=prng, niters=10)
new_latent = r.get_latent()
return idmap[tuple(permutation_canonical(new_latent.assignments()))]
assert_discrete_dist_approx(sample_fn, posterior, ntries=100)
def _test_runner_kernel_config(kc_fn, models):
defn = model_definition(10, models)
Y = toy_dataset(defn)
view = numpy_dataview(Y)
kc = kc_fn(defn)
prng = rng()
ntries = 5
while ntries:
latent = model.initialize(defn, view, prng)
assignments = latent.assignments()
r = runner.runner(defn, view, latent, kc)
r.run(r=prng, niters=10)
assignments1 = r.get_latent().assignments()
# XXX: it should be very unlikely the assignments are all equal
if assignments == assignments1:
ntries -= 1
else:
return # success
assert_true(False) # exceeded ntries
