def data_with_posterior(defn,
cluster_hp=None,
feature_hps=None,
preprocess_data_fn=None,
r=None):
# XXX(stephentu): should only accept conjugate models
if r is None:
r = rng()
Y_clusters, _ = sample(defn, cluster_hp, feature_hps, r)
Y = np.hstack(Y_clusters)
if preprocess_data_fn:
Y = preprocess_data_fn(Y)
data = numpy_dataview(Y)
def score_fn(assignment):
s = initialize(defn,
data,
r,
cluster_hp=cluster_hp,
feature_hps=feature_hps,
assignment=assignment)
return s.score_joint(r)
posterior = dist_on_all_clusterings(score_fn, defn.n())
return Y, posterior
def test_sample_sanity():
# just a sanity check
defn = model_definition(10, [bb, bnb, gp, nich, dd(5), niw(4)])
clusters, samplers = sample(defn)
assert_equals(len(clusters), len(samplers))
for cluster in clusters:
assert_true(len(cluster) > 0)
for v in cluster:
assert_equals(len(v), len(defn.models()))
def _test_nonconj_inference(initialize_fn,
dataview,
bind,
assign_nonconj_fn,
slice_theta_fn,
R,
ntries,
nsamples,
tol):
N, D = 1000, 5
defn = model_definition(N, [bbnc] * D)
cluster_hp = {'alpha': 0.2}
feature_hps = [{'alpha': 1.0, 'beta': 1.0}] * D
while True:
Y_clustered, cluster_samplers = sample(
defn, cluster_hp, feature_hps, R)
if len(Y_clustered) == 2:
break
dominant = np.argmax(map(len, Y_clustered))
truth = np.array([s.p for s in cluster_samplers[dominant]])
print 'truth:', truth
# see if we can learn the p-values for each of the two clusters. we proceed
# by running gibbs_assign_nonconj, followed by slice sampling on the
# posterior p(\theta | Y). we'll "cheat" a little by bootstrapping the
# DP with the correct assignment (but not with the correct p-values)
Y, assignment = data_with_assignment(Y_clustered)
view = dataview(Y)
s = initialize_fn(
defn, view, cluster_hp=cluster_hp,
feature_hps=feature_hps, assignment=assignment, r=R)
bs = bind(s, view)
def mkparam():
return {'p': 0.1}
thetaparams = {fi: mkparam() for fi in xrange(D)}
def kernel():
assign_nonconj_fn(bs, 10, R)
slice_theta_fn(bs, R, tparams=thetaparams)
def inference(niters):
for _ in xrange(niters):
kernel()
groups = s.groups()
inferred_dominant = groups[
np.argmax([s.groupsize(gid) for gid in groups])]
inferred = [s.get_suffstats(inferred_dominant, d)['p']
for d in xrange(D)]
inferred = np.array(inferred)
yield inferred
posterior = []
while ntries:
samples = list(inference(nsamples))
posterior.extend(samples)
inferred = sum(posterior) / len(posterior)
diff = np.linalg.norm(truth - inferred)
print 'inferred:', inferred
print 'diff:', diff
if diff <= tol:
return
ntries -= 1
print 'tries left:', ntries
assert False, 'did not converge'
def _test_nonconj_inference(initialize_fn, dataview, bind, assign_nonconj_fn,
slice_theta_fn, R, ntries, nsamples, tol):
N, D = 1000, 5
defn = model_definition(N, [bbnc] * D)
cluster_hp = {'alpha': 0.2}
feature_hps = [{'alpha': 1.0, 'beta': 1.0}] * D
while True:
Y_clustered, cluster_samplers = sample(defn, cluster_hp, feature_hps,
R)
if len(Y_clustered) == 2:
break
dominant = np.argmax(map(len, Y_clustered))
truth = np.array([s.p for s in cluster_samplers[dominant]])
print 'truth:', truth
# see if we can learn the p-values for each of the two clusters. we proceed
# by running gibbs_assign_nonconj, followed by slice sampling on the
# posterior p(\theta | Y). we'll "cheat" a little by bootstrapping the
# DP with the correct assignment (but not with the correct p-values)
Y, assignment = data_with_assignment(Y_clustered)
view = dataview(Y)
s = initialize_fn(defn,
view,
cluster_hp=cluster_hp,
feature_hps=feature_hps,
assignment=assignment,
r=R)
bs = bind(s, view)
def mkparam():
return {'p': 0.1}
thetaparams = {fi: mkparam() for fi in xrange(D)}
def kernel():
assign_nonconj_fn(bs, 10, R)
slice_theta_fn(bs, R, tparams=thetaparams)
def inference(niters):
for _ in xrange(niters):
kernel()
groups = s.groups()
inferred_dominant = groups[np.argmax(
[s.groupsize(gid) for gid in groups])]
inferred = [
s.get_suffstats(inferred_dominant, d)['p'] for d in xrange(D)
]
inferred = np.array(inferred)
yield inferred
posterior = []
while ntries:
samples = list(inference(nsamples))
posterior.extend(samples)
inferred = sum(posterior) / len(posterior)
diff = np.linalg.norm(truth - inferred)
print 'inferred:', inferred
print 'diff:', diff
if diff <= tol:
return
ntries -= 1
print 'tries left:', ntries
assert False, 'did not converge'
def toy_dataset(defn):
samples, _ = sample(defn)
return np.hstack(samples)