def finalize_splits(nz, n_splits, splitted, Dts, Trace, nh, ns, kernel):
new_nz = nz + n_splits
if kernel.get_priors().shape[0] > 0:
new_P = [row for row in kernel.get_state()]
for _ in xrange(n_splits):
new_P.append(kernel.get_priors())
else:
new_P = kernel.get_state()
Trace[:, -1] = splitted
#Populate new counts
Count_zh_new = np.zeros(shape=(new_nz, nh), dtype='i4')
Count_sz_new = np.zeros(shape=(ns, new_nz), dtype='i4')
count_z_new = np.zeros(new_nz, dtype='i4')
count_h_new = np.zeros(nh, dtype='i4')
_learn.fast_populate(Trace, Count_zh_new, Count_sz_new, \
count_h_new, count_z_new)
new_stamps = StampLists(new_nz)
for z in xrange(new_nz):
idx = Trace[:, -1] == z
topic_stamps = Dts[idx]
new_stamps._extend(z, topic_stamps[:, -1])
return Trace, Count_zh_new, Count_sz_new, \
count_z_new, new_stamps, np.array(new_P)
def test_all():
slists = StampLists(4)
E = []
for i in xrange(4):
E.append([])
for _ in xrange(200):
e = np.random.rand()
slists._append(i, e)
E[i].append(e)
kern = ECCDFKernel(True)
kern.build(800, 4, np.array([1.0, 3.0]))
kern._mstep(slists)
for i in xrange(4):
assert_array_equal(sorted(E[i]), slists._get_all(i))
for i in xrange(4):
for _ in xrange(200):
p = kern._pdf(i, np.random.rand(), slists)
assert p <= 1
assert p >= 0
def test_pdf():
for mu in [0, 1, 10]:
for v in [1, 10]:
for std in [1, 10]:
priors = np.array([mu, v, std], dtype='d')
kernel = TStudentKernel()
kernel.build(999, 1, priors) #99... is just the max freed
truth = t(v, loc=mu, scale=std)
for x in np.linspace(-100, 100, 200):
print(mu, v, std, x, truth.pdf(x),
kernel._pdf(x, 0, StampLists(1)))
assert_almost_equal(truth.pdf(x), \
kernel._pdf(x, 0, StampLists(1)))
def main(model, out_fpath_rrs, out_fpath_pred):
store = pd.HDFStore(model)
trace_fpath = store['trace_fpath'][0][0]
tsFile = open(
'/home/zahran/Desktop/tribeFlow/zahranData/lastfm-dataset-1K/PARSED_74123_B10_zahran_sampledData',
'r')
sequenceLength = 10
from_ = store['from_'][0][0]
to = store['to'][0][0]
assert from_ == 0
kernel_class = store['kernel_class'][0][0]
kernel_class = eval(kernel_class)
Theta_zh = store['Theta_zh'].values
Psi_sz = store['Psi_sz'].values
count_z = store['count_z'].values[:, 0]
P = store['P'].values
residency_priors = store['residency_priors'].values[:, 0]
previous_stamps = StampLists(
count_z.shape[0]) #previous_stamps has a length = nz
true_mem_size = store['Dts'].values.shape[1]
tstamps = store[
'Dts'].values[:,
0] #tstamps (#trainingLines,) contains the t(xi)-t(xi-1)
assign = store[
'assign'].values[:,
0] # assign (#trainingLines,) each dim has the env id used in that training instance
for z in xrange(count_z.shape[0]):
idx = assign == z
previous_stamps._extend(
z, tstamps[idx]
) #tstamps[idx]: is the tstamps whose corresponding index in idx is True
hyper2id = dict(store['hyper2id'].values)
obj2id = dict(store['source2id'].values)
trace_size = sum(count_z) #sum of the number of appearances of all envs
kernel = kernel_class()
kernel.build(trace_size, count_z.shape[0], residency_priors)
kernel.update_state(P)
with open(trace_fpath) as traceFile:
predictObject(store, sequenceLength, tsFile, traceFile, true_mem_size,
hyper2id, obj2id, previous_stamps, Theta_zh, Psi_sz,
count_z, kernel)
tsFile.close()
traceFile.close()
def finalize_merge(nz, to_merge, Dts, Trace, nh, ns, kernel):
for z1, z2 in to_merge:
idx = Trace[:, -1] == z2
Trace[:, -1][idx] = z1
if to_merge and kernel.get_priors().shape[0] > 0:
new_P_dict = dict((i, row) for i, row in enumerate(kernel.get_state()))
for z1, z2 in to_merge:
del new_P_dict[z2]
new_P = []
for i in sorted(new_P_dict):
new_P.append(new_P_dict[i])
else:
new_P = kernel.get_state()
#Make sure new trace has contiguous ids
new_assign = Trace[:, -1].copy()
old_assign = Trace[:, -1].copy()
if to_merge:
new_nz = len(set(new_assign))
for i, z in enumerate(set(new_assign)):
idx = old_assign == z
new_assign[idx] = i
else:
new_nz = nz
Trace[:, -1] = new_assign
#Populate new counts
Count_zh_new = np.zeros(shape=(new_nz, nh), dtype='i4')
Count_sz_new = np.zeros(shape=(ns, new_nz), dtype='i4')
count_z_new = np.zeros(new_nz, dtype='i4')
count_h_new = np.zeros(nh, dtype='i4')
_learn.fast_populate(Trace, Count_zh_new, Count_sz_new, \
count_h_new, count_z_new)
new_stamps = StampLists(new_nz)
for z in xrange(new_nz):
idx = Trace[:, -1] == z
topic_stamps = Dts[idx]
new_stamps._extend(z, topic_stamps[:, -1])
return Trace, Count_zh_new, Count_sz_new, \
count_z_new, new_stamps, np.array(new_P)
def sample(Dts, Trace, Count_zh, Count_sz_local, \
count_h, count_z, alpha_zh, beta_zs, kernel, num_iter, comm):
previous_encounters_s = {}
for other_processor in xrange(1, comm.size):
previous_encounters_s[other_processor] = np.zeros_like(Count_sz_local)
stamps = StampLists(Count_zh.shape[0])
for z in xrange(Count_zh.shape[0]):
idx = Trace[:, -1] == z
#dts_assigned = Dts[idx:, 0].ravel().copy()
#np.sort(dts_assigned)
stamps._extend(z, Dts[idx][:, -1])
aux = np.zeros(Count_zh.shape[0], dtype='f8')
Count_sz_pair = np.zeros_like(Count_sz_local)
Count_sz_others = np.zeros_like(Count_sz_local)
Count_sz_sum = np.zeros_like(Count_sz_local)
Theta_zh = np.zeros_like(Count_zh, dtype='f8')
Psi_sz = np.zeros_like(Count_sz_local, dtype='f8')
can_pair = True
for i in xrange(num_iter // CACHE_SIZE):
#Sample from the local counts and encountered counts
Count_sz_sum[:] = Count_sz_local + Count_sz_others
count_z[:] = Count_sz_sum.sum(axis=0)
em(Dts, Trace, stamps, Count_zh, Count_sz_sum, \
count_h, count_z, alpha_zh, beta_zs, aux, Theta_zh, \
Psi_sz, CACHE_SIZE, CACHE_SIZE * 2, kernel, False)
#Update local counts
Count_sz_local[:] = Count_sz_sum - Count_sz_others
count_z[:] = Count_sz_local.sum(axis=0)
#Update expected belief of other processors
if can_pair:
P_local = kernel.get_state()
can_pair = paired_update(comm, previous_encounters_s, \
Count_sz_local, Count_sz_pair, Count_sz_others, \
P_local, np.zeros_like(P_local))
kernel.update_state(P_local)
def sample(Dts, Trace, Count_zh, Count_sz_local, \
count_h, count_z, alpha_zh, beta_zs, kernel, num_iter, comm):
previous_encounters_s = {}
for other_processor in xrange(1, comm.size):
previous_encounters_s[other_processor] = np.zeros_like(Count_sz_local)
stamps = StampLists(Count_zh.shape[0])
for z in xrange(Count_zh.shape[0]):
idx = Trace[:, -1] == z
#dts_assigned = Dts[idx:, 0].ravel().copy()
#np.sort(dts_assigned)
stamps._extend(z, Dts[idx][:, -1])
aux = np.zeros(Count_zh.shape[0], dtype='f8')
Count_sz_pair = np.zeros_like(Count_sz_local)
Count_sz_others = np.zeros_like(Count_sz_local)
Count_sz_sum = np.zeros_like(Count_sz_local)
Theta_zh = np.zeros_like(Count_zh, dtype='f8')
Psi_sz = np.zeros_like(Count_sz_local, dtype='f8')
can_pair = True
for i in xrange(num_iter // CACHE_SIZE):
#Sample from the local counts and encountered counts
Count_sz_sum[:] = Count_sz_local + Count_sz_others
count_z[:] = Count_sz_sum.sum(axis=0)
em(Dts, Trace, stamps, Count_zh, Count_sz_sum, \
count_h, count_z, alpha_zh, beta_zs, aux, Theta_zh, \
Psi_sz, CACHE_SIZE, CACHE_SIZE * 2, kernel, False)
#Update local counts
Count_sz_local[:] = Count_sz_sum - Count_sz_others
count_z[:] = Count_sz_local.sum(axis=0)
#Update expected belief of other processors
if can_pair:
P_local = kernel.get_state()
can_pair = paired_update(comm, previous_encounters_s, \
Count_sz_local, Count_sz_pair, Count_sz_others, \
P_local, np.zeros_like(P_local))
kernel.update_state(P_local)
def split(Dts, Trace, previous_stamps, Count_zh, Count_sz, \
count_h, count_z, alpha_zh, beta_zs, ll_per_z, kernel, \
perc=0.05, min_stamps=50):
nz = Count_zh.shape[0]
nh = Count_zh.shape[1]
ns = Count_sz.shape[0]
assert nz == ll_per_z.shape[0]
idx_int_all = np.arange(Trace.shape[0], dtype='i4')
#Initiate auxiliary matrices
Count_zh_spl = np.zeros(shape=(nz + 1, nh), dtype='i4')
Count_sz_spl = np.zeros(shape=(ns, nz + 1), dtype='i4')
count_z_spl = np.zeros(nz + 1, dtype='i4')
Count_zh_spl[:-1, :] = Count_zh
Count_sz_spl[:, :-1] = Count_sz
count_z_spl[:-1] = count_z
ll_per_z_new = np.zeros(nz + 1, dtype='f8')
ll_per_z_new[:-1] = ll_per_z
new_stamps = StampLists(nz + 1)
for z in xrange(nz):
new_stamps._extend(z, previous_stamps._get_all(z))
splitted = Trace[:, -1].copy()
shift = 0
#Do the splits per topic
for z in xrange(nz):
#Candidates for removal
topic_stamps = np.asanyarray(previous_stamps._get_all(z))
idx = Trace[:, -1] == z
assert topic_stamps.shape[0] == idx.sum()
argsrt = topic_stamps.argsort()
top = int(np.ceil(perc * topic_stamps.shape[0]))
#If not at least min stamps, exit, not enough for a CCDF estimation
if top < min_stamps:
continue
#Populate stamps
new_stamps._clear_one(z)
new_stamps._clear_one(nz)
new_stamps._extend(z, topic_stamps[:-top])
new_stamps._extend(nz, topic_stamps[-top:])
#Split topic on the Trace. The trace has to be sorted by timestamp!!
old_assign = Trace[:, -1][idx].copy()
new_assign = Trace[:, -1][idx].copy()
new_assign[-top:] = nz
Trace[:, -1][idx] = new_assign
#Update matrices. Can't really vectorize this :(
for line in Trace[idx][-top:]:
h = line[0]
Count_zh_spl[z, h] -= 1
for o in line[1:-1]:
Count_sz_spl[o, z] -= 1
count_z_spl[z] -= 1
Count_zh_spl[nz, h] += 1
for o in line[1:-1]:
Count_sz_spl[o, nz] += 1
count_z_spl[nz] += 1
#New LL
ll_per_z_new[z] = 0
ll_per_z_new[-1] = 0
idx_int = idx_int_all[idx]
_eval.quality_estimate(Dts, Trace, \
new_stamps, Count_zh_spl, Count_sz_spl, count_h, \
count_z_spl, alpha_zh, beta_zs, \
ll_per_z_new, idx_int, kernel)
if ll_per_z_new.sum() > ll_per_z.sum():
new_assign[-top:] = nz + shift
splitted[idx] = new_assign
shift += 1
#Revert trace
new_stamps._clear_one(z)
new_stamps._clear_one(nz)
new_stamps._extend(z, previous_stamps._get_all(z))
Count_zh_spl[:-1, :] = Count_zh
Count_sz_spl[:, :-1] = Count_sz
count_z_spl[:-1] = count_z
Count_zh_spl[-1, :] = 0
Count_sz_spl[:, -1] = 0
count_z_spl[-1] = 0
ll_per_z_new[z] = ll_per_z[z]
ll_per_z_new[-1] = 0
Trace[:, -1][idx] = old_assign
return finalize_splits(nz, shift, splitted, Dts, Trace, nh, ns, kernel)
def main(model, out_fpath_rrs, out_fpath_pred):
store = pd.HDFStore(model)
from_ = store['from_'][0][0]
to = store['to'][0][0]
assert from_ == 0
trace_fpath = store['trace_fpath'][0][0]
kernel_class = store['kernel_class'][0][0]
kernel_class = eval(kernel_class)
Theta_zh = store['Theta_zh'].values
Psi_sz = store['Psi_sz'].values
count_z = store['count_z'].values[:, 0]
P = store['P'].values
residency_priors = store['residency_priors'].values[:, 0]
previous_stamps = StampLists(count_z.shape[0])
mem_size = store['Dts'].values.shape[1]
tstamps = store['Dts'].values[:, 0]
assign = store['assign'].values[:, 0]
for z in xrange(count_z.shape[0]):
idx = assign == z
previous_stamps._extend(z, tstamps[idx])
hyper2id = dict(store['hyper2id'].values)
obj2id = dict(store['source2id'].values)
HSDs = []
Dts = []
with open(trace_fpath) as trace_file:
for i, l in enumerate(trace_file):
if i < to:
continue
spl = l.strip().split('\t')
dts_line = [float(x) for x in spl[:mem_size]]
h = spl[mem_size]
d = spl[-1]
sources = spl[mem_size + 1:-1]
all_in = h in hyper2id and d in obj2id
for s in sources:
all_in = all_in and s in obj2id
if all_in:
trace_line = [hyper2id[h]] + [obj2id[s] for s in sources] + \
[obj2id[d]]
HSDs.append(trace_line)
Dts.append(dts_line)
trace_size = sum(count_z)
kernel = kernel_class()
kernel.build(trace_size, count_z.shape[0], residency_priors)
kernel.update_state(P)
num_queries = min(10000, len(HSDs))
queries = np.random.choice(len(HSDs), size=num_queries)
HSDs = np.array(HSDs, dtype='i4')[queries].copy()
Dts = np.array(Dts, dtype='d')[queries].copy()
rrs, preds = _eval.reciprocal_rank(Dts, \
HSDs, previous_stamps, Theta_zh, Psi_sz, count_z, kernel, True)
np.savetxt(out_fpath_rrs, rrs)
np.savetxt(out_fpath_pred, preds)
print((1.0 / rrs).mean(axis=0))
store.close()
def initialize_trace(trace_fpath, num_topics, num_iter, \
from_=0, to=np.inf, initial_assign=None):
'''
Given a trace (user trajectories) to learn from, this method will
initialize the necessary matrices and dicts to learn tribeflow.
Using from_, to_ the trace can be sliced. initial_assign is useful to
pickup learning from a previous model.
Parameters
----------
trace_fpath : string
The location of the trace
num_topics : int
The number of latent spaces
from_ : int
Where to begin reading the trace from. 0 is the first line.
to : int
We will stop reading the file here
initial_assign : array-like
Initial topic assignments.
Returns
-------
Count matrices and dicts used to learn tribeflow.
'''
count_zh_dict = defaultdict(int)
count_oz_dict = defaultdict(int)
count_z_dict = defaultdict(int)
count_h_dict = defaultdict(int)
hyper2id = OrderedDict()
obj2id = OrderedDict()
if initial_assign:
initial_assign = np.asarray(initial_assign, dtype='i')
assert initial_assign.min() >= 0
assert initial_assign.max() < num_topics
Dts = []
Trace = []
with open(trace_fpath, 'r') as trace_file:
for i, line in enumerate(trace_file):
if i < from_:
continue
if i >= to:
break
spl = line.strip().split('\t')
assert len(spl) >= 4
assert (len(spl) - 2) % 2 == 0
mem_size = (len(spl) - 2) // 2
line_dts = []
for j in xrange(mem_size):
line_dts.append(float(spl[j]))
Dts.append(line_dts)
hyper_str = spl[mem_size]
if hyper_str not in hyper2id:
hyper2id[hyper_str] = len(hyper2id)
if not initial_assign:
z = np.random.randint(num_topics)
else:
z = initial_assign[i]
h = hyper2id[hyper_str]
count_zh_dict[z, h] += 1
count_h_dict[h] += 1
line_int = [h]
for j in xrange(mem_size + 1, len(spl)):
obj_str = spl[j]
if obj_str not in obj2id:
obj2id[obj_str] = len(obj2id)
o = obj2id[obj_str]
line_int.append(o)
count_oz_dict[o, z] += 1
count_z_dict[z] += 1
line_int.append(z)
Trace.append(line_int)
#Sort by the last residency time.
Dts = np.asarray(Dts)
argsort = Dts[:, -1].argsort()
assert Dts.shape[1] == mem_size
#Create contiguous arrays, not needed but adds a small speedup
Dts = np.asanyarray(Dts[argsort], order='C')
Trace = np.asarray(Trace)
Trace = np.asanyarray(Trace[argsort], dtype='i4', order='C')
nh = len(hyper2id)
no = len(obj2id)
nz = num_topics
previous_stamps = StampLists(num_topics)
for z in xrange(nz):
idx = Trace[:, -1] == z
topic_stamps = Dts[:, -1][idx]
previous_stamps._extend(z, topic_stamps)
Count_zh = np.zeros(shape=(nz, nh), dtype='i4')
Count_oz = np.zeros(shape=(no, nz), dtype='i4')
count_h = np.zeros(shape=(nh, ), dtype='i4')
count_z = np.zeros(shape=(nz, ), dtype='i4')
for z in xrange(Count_zh.shape[0]):
count_z[z] = count_z_dict[z]
for h in xrange(Count_zh.shape[1]):
count_h[h] = count_h_dict[h]
Count_zh[z, h] = count_zh_dict[z, h]
for o in xrange(Count_oz.shape[0]):
Count_oz[o, z] = count_oz_dict[o, z]
assert (Count_oz.sum(axis=0) == count_z).all()
prob_topics_aux = np.zeros(nz, dtype='f8')
Theta_zh = np.zeros(shape=(nz, nh), dtype='f8')
Psi_oz = np.zeros(shape=(no, nz), dtype='f8')
return Dts, Trace, previous_stamps, Count_zh, Count_oz, \
count_h, count_z, prob_topics_aux, Theta_zh, Psi_oz, \
hyper2id, obj2id
def main(model, out_fpath_rrs, out_fpath_pred):
store = pd.HDFStore(model)
from_ = store['from_'][0][0]
to = store['to'][0][0]
assert from_ == 0
trace_fpath = store['trace_fpath'][0][0]
kernel_class = store['kernel_class'][0][0]
kernel_class = eval(kernel_class)
Theta_zh = store['Theta_zh'].values
Psi_sz = store['Psi_sz'].values
count_z = store['count_z'].values[:, 0]
P = store['P'].values
residency_priors = store['residency_priors'].values[:, 0]
previous_stamps = StampLists(
count_z.shape[0]) #previous_stamps has a length = nz
#HERE
mem_size = store['Dts'].values.shape[1]
tstamps = store[
'Dts'].values[:,
0] #tstamps (#trainingLines,) contains the t(xi)-t(xi-1) (i.e. the col in the dts)
assign = store[
'assign'].values[:,
0] # assign (#trainingLines,) each dim has the env id used in that training instance
for z in xrange(count_z.shape[0]):
idx = assign == z
previous_stamps._extend(
z, tstamps[idx]
) #tstamps[idx]: is the tstamps whose corresponding index in idx is True
hyper2id = dict(store['hyper2id'].values)
obj2id = dict(store['source2id'].values)
HSDs = []
Dts = []
with open(trace_fpath) as trace_file:
for i, l in enumerate(trace_file):
if i < to:
continue #skipping the traininglines to reach to testSet
spl = l.strip().split('\t')
dts_line = [float(x) for x in spl[:mem_size]]
h = spl[mem_size]
d = spl[-1]
sources = spl[mem_size + 1:-1]
all_in = h in hyper2id and d in obj2id
for s in sources:
all_in = all_in and s in obj2id
if all_in:
trace_line = [hyper2id[h]] + [obj2id[s]
for s in sources] + [obj2id[d]]
HSDs.append(trace_line)
Dts.append(dts_line)
trace_size = sum(count_z) #sum of the number of appearances of all envs
kernel = kernel_class()
kernel.build(trace_size, count_z.shape[0], residency_priors)
kernel.update_state(P)
num_queries = min(10000, len(HSDs))
queries = np.random.choice(len(HSDs), size=num_queries)
HSDs = np.array(HSDs, dtype='i4')[queries].copy()
Dts = np.array(Dts, dtype='d')[queries].copy()
rrs, preds = _eval.reciprocal_rank(Dts, HSDs, previous_stamps, Theta_zh,
Psi_sz, count_z, kernel, True)
np.savetxt(out_fpath_rrs, rrs)
np.savetxt(out_fpath_pred, preds)
print(rrs.mean(axis=0))
store.close()
def initialize_trace(trace_fpath, num_topics, num_iter, \
from_=0, to=np.inf, initial_assign=None):
'''
Given a trace (user trajectories) to learn from, this method will
initialize the necessary matrices and dicts to learn tribeflow.
Using from_, to_ the trace can be sliced. initial_assign is useful to
pickup learning from a previous model.
Parameters
----------
trace_fpath : string
The location of the trace
num_topics : int
The number of latent spaces
from_ : int
Where to begin reading the trace from. 0 is the first line.
to : int
We will stop reading the file here
initial_assign : array-like
Initial topic assignments.
Returns
-------
Count matrices and dicts used to learn tribeflow.
'''
count_zh_dict = defaultdict(int)
count_oz_dict = defaultdict(int)
count_z_dict = defaultdict(int)
count_h_dict = defaultdict(int)
hyper2id = OrderedDict()
obj2id = OrderedDict()
if initial_assign:
initial_assign = np.asarray(initial_assign, dtype='i')
assert initial_assign.min() >= 0
assert initial_assign.max() < num_topics
Dts = []
Trace = []
with open(trace_fpath, 'r') as trace_file:
for i, line in enumerate(trace_file):
if i < from_:
continue
if i >= to:
break
spl = line.strip().split('\t')
assert len(spl) >= 4
assert (len(spl) - 2) % 2 == 0
mem_size = (len(spl) - 2) // 2
line_dts = []
for j in xrange(mem_size):
line_dts.append(float(spl[j]))
Dts.append(line_dts)
hyper_str = spl[mem_size]
if hyper_str not in hyper2id:
hyper2id[hyper_str] = len(hyper2id)
if not initial_assign:
z = np.random.randint(num_topics)
else:
z = initial_assign[i]
h = hyper2id[hyper_str]
count_zh_dict[z, h] += 1
count_h_dict[h] += 1
line_int = [h]
for j in xrange(mem_size + 1, len(spl)):
obj_str = spl[j]
if obj_str not in obj2id:
obj2id[obj_str] = len(obj2id)
o = obj2id[obj_str]
line_int.append(o)
count_oz_dict[o, z] += 1
count_z_dict[z] += 1
line_int.append(z)
Trace.append(line_int)
#Sort by the last residency time.
Dts = np.asarray(Dts)
argsort = Dts[:, -1].argsort()
assert Dts.shape[1] == mem_size
#Create contiguous arrays, not needed but adds a small speedup
Dts = np.asanyarray(Dts[argsort], order='C')
Trace = np.asarray(Trace)
Trace = np.asanyarray(Trace[argsort], dtype='i4', order='C')
nh = len(hyper2id)
no = len(obj2id)
nz = num_topics
previous_stamps = StampLists(num_topics)
for z in xrange(nz):
idx = Trace[:, -1] == z
topic_stamps = Dts[:, -1][idx]
previous_stamps._extend(z, topic_stamps)
Count_zh = np.zeros(shape=(nz, nh), dtype='i4')
Count_oz = np.zeros(shape=(no, nz), dtype='i4')
count_h = np.zeros(shape=(nh,), dtype='i4')
count_z = np.zeros(shape=(nz,), dtype='i4')
for z in xrange(Count_zh.shape[0]):
count_z[z] = count_z_dict[z]
for h in xrange(Count_zh.shape[1]):
count_h[h] = count_h_dict[h]
Count_zh[z, h] = count_zh_dict[z, h]
for o in xrange(Count_oz.shape[0]):
Count_oz[o, z] = count_oz_dict[o, z]
assert (Count_oz.sum(axis=0) == count_z).all()
prob_topics_aux = np.zeros(nz, dtype='f8')
Theta_zh = np.zeros(shape=(nz, nh), dtype='f8')
Psi_oz = np.zeros(shape=(no, nz), dtype='f8')
return Dts, Trace, previous_stamps, Count_zh, Count_oz, \
count_h, count_z, prob_topics_aux, Theta_zh, Psi_oz, \
hyper2id, obj2id
