def add_variants(vids_to_add, variants, mutrel_posterior, mutrel_evidence,
logprior, pbar, parallel):
for vid in vids_to_add:
assert vid in variants
new_vids = mutrel_posterior.vids + vids_to_add
# M: number of variants we have now
# A: number of variants we added
M = len(new_vids)
A = len(vids_to_add)
assert len(mutrel_posterior.vids) == len(mutrel_evidence.vids) == M - A
variants = [
common.convert_variant_dict_to_tuple(variants[V]) for V in new_vids
]
new_posterior = mutrel.init_mutrel(new_vids)
new_evidence = mutrel.init_mutrel(new_vids)
new_posterior.rels[:-A, :-A] = mutrel_posterior.rels
new_evidence.rels[:-A, :-A] = mutrel_evidence.rels
pairs = [(I, J) for I in range(M) for J in range(M - A, M)]
return _compute_pairs(
pairs,
variants,
logprior,
new_posterior,
new_evidence,
pbar,
parallel,
)
def calc_posterior(variants, logprior, rel_type, parallel=1):
M = len(variants)
# Allow Numba use by converting to namedtuple.
vids = common.extract_vids(variants)
variants = [
common.convert_variant_dict_to_tuple(variants[V]) for V in vids
]
posterior = mutrel.init_mutrel(vids)
evidence = mutrel.init_mutrel(vids)
pairs = list(itertools.combinations(range(M), 2)) + [(V, V)
for V in range(M)]
_compute = lambda pbar: _compute_pairs(
pairs,
variants,
logprior,
posterior,
evidence,
pbar,
parallel,
)
if parallel > 0:
with tqdm.tqdm(total=len(pairs),
desc='Computing %s relations' % rel_type,
unit='pair',
dynamic_ncols=True) as pbar:
posterior, evidence = _compute(pbar)
else:
posterior, evidence = _compute(None)
return (posterior, evidence)
def merge_variants(to_merge, evidence, logprior):
assert np.all(
np.array([V for group in to_merge
for V in group]) < len(evidence.vids))
already_merged = set()
for vidxs in to_merge:
vidxs = set(vidxs)
assert len(vidxs & already_merged) == 0
M_old = len(evidence.vids)
merged_vid = ','.join([evidence.vids[V] for V in vidxs])
new_vids = evidence.vids + [merged_vid]
new_evidence = mutrel.init_mutrel(new_vids)
new_evidence.rels[:-1, :-1] = evidence.rels
merged_row = np.sum(np.array([evidence.rels[V] for V in vidxs]),
axis=0)
assert merged_row.shape == (M_old, NUM_MODELS)
merged_col = np.copy(merged_row)
merged_col[:, Models.A_B] = merged_row[:, Models.B_A]
merged_col[:, Models.B_A] = merged_row[:, Models.A_B]
new_evidence.rels[-1, :-1] = merged_row
new_evidence.rels[:-1, -1] = merged_col
new_evidence.rels[-1, -1, :] = -np.inf
new_evidence.rels[-1, -1, Models.cocluster] = 0
already_merged |= vidxs
evidence = new_evidence
evidence = mutrel.remove_variants_by_vidx(evidence, already_merged)
posterior = make_full_posterior(evidence, logprior)
return (posterior, evidence)
def add_garbage(posterior, garb_svids):
if len(garb_svids) == 0:
return posterior
assert len(set(posterior.vids) & set(garb_svids)) == 0
new_vids = posterior.vids + garb_svids
new_posterior = mutrel.init_mutrel(new_vids)
G = len(garb_svids)
M = len(new_posterior.vids)
# Rather than carefully slicing and dicing the array to set it, just use a
# series of carefully ordered overwrite operations to put it in the correct
# state.
new_posterior.rels[:] = 0
new_posterior.rels[:, :, Models.garbage] = 1
diag = range(M)
new_posterior.rels[diag, diag, :] = 0
new_posterior.rels[diag, diag, Models.cocluster] = 1
new_posterior.rels[:-G, :-G, :] = posterior.rels
mutrel.check_posterior_sanity(new_posterior.rels)
return new_posterior