def _compute_unique_state_ids(self):
import vtool as vt
# data_ids = vt.compute_ndarray_unique_rowids_unsafe(self.state_idxs)
data_ids = np.array(
vt.compute_unique_data_ids_(list(map(tuple, self.state_idxs))))
return data_ids
def collapse_labels(model, evidence, reduced_variables, reduced_row_idxs,
reduced_values):
import vtool as vt
#assert np.all(reduced_joint.values.ravel() == reduced_joint.values.flatten())
reduced_ttypes = [model.var2_cpd[var].ttype for var in reduced_variables]
evidence_vars = list(evidence.keys())
evidence_state_idxs = ut.dict_take(evidence, evidence_vars)
evidence_ttypes = [model.var2_cpd[var].ttype for var in evidence_vars]
ttype2_ev_indices = dict(zip(*ut.group_indices(evidence_ttypes)))
ttype2_re_indices = dict(zip(*ut.group_indices(reduced_ttypes)))
# ttype2_ev_indices = ut.group_items(range(len(evidence_vars)), evidence_ttypes)
# ttype2_re_indices = ut.group_items(range(len(reduced_variables)), reduced_ttypes)
# Allow specific types of labels to change
# everything is the same, only the names have changed.
# TODO: allow for multiple different label_ttypes
# for label_ttype in label_ttypes
if 'name' not in model.ttype2_template:
return reduced_row_idxs, reduced_values
label_ttypes = ['name']
for label_ttype in label_ttypes:
ev_colxs = ttype2_ev_indices[label_ttype]
re_colxs = ttype2_re_indices[label_ttype]
ev_state_idxs = ut.take(evidence_state_idxs, ev_colxs)
ev_state_idxs_tile = np.tile(ev_state_idxs, (len(reduced_values), 1)).astype(np.int)
num_ev_ = len(ev_colxs)
aug_colxs = list(range(num_ev_)) + (np.array(re_colxs) + num_ev_).tolist()
aug_state_idxs = np.hstack([ev_state_idxs_tile, reduced_row_idxs])
# Relabel rows based on the knowledge that
# everything is the same, only the names have changed.
num_cols = len(aug_state_idxs.T)
mask = vt.index_to_boolmask(aug_colxs, num_cols)
other_colxs, = np.where(~mask)
relbl_states = aug_state_idxs.compress(mask, axis=1)
other_states = aug_state_idxs.compress(~mask, axis=1)
tmp_relbl_states = np.array(list(map(make_temp_state, relbl_states)))
max_tmp_state = -1
min_tmp_state = tmp_relbl_states.min()
# rebuild original state structure with temp state idxs
tmp_state_cols = [None] * num_cols
for count, colx in enumerate(aug_colxs):
tmp_state_cols[colx] = tmp_relbl_states[:, count:count + 1]
for count, colx in enumerate(other_colxs):
tmp_state_cols[colx] = other_states[:, count:count + 1]
tmp_state_idxs = np.hstack(tmp_state_cols)
data_ids = np.array(
vt.compute_unique_data_ids_(list(map(tuple, tmp_state_idxs))))
unique_ids, groupxs = vt.group_indices(data_ids)
print('Collapsed %r states into %r states' % (
len(data_ids), len(unique_ids),))
# Sum the values in the cpd to marginalize the duplicate probs
new_values = np.array([
g.sum() for g in vt.apply_grouping(reduced_values, groupxs)
])
# Take only the unique rows under this induced labeling
unique_tmp_groupxs = np.array(ut.get_list_column(groupxs, 0))
new_aug_state_idxs = tmp_state_idxs.take(unique_tmp_groupxs, axis=0)
tmp_idx_set = set((-np.arange(-max_tmp_state,
(-min_tmp_state) + 1)).tolist())
true_idx_set = set(range(len(model.ttype2_template[label_ttype].basis)))
# Relabel the rows one more time to agree with initial constraints
for colx, true_idx in enumerate(ev_state_idxs):
tmp_idx = np.unique(new_aug_state_idxs.T[colx])
assert len(tmp_idx) == 1
tmp_idx_set -= {tmp_idx[0]}
true_idx_set -= {true_idx}
new_aug_state_idxs[new_aug_state_idxs == tmp_idx] = true_idx
# Relabel the remaining idxs
remain_tmp_idxs = sorted(list(tmp_idx_set))[::-1]
remain_true_idxs = sorted(list(true_idx_set))
for tmp_idx, true_idx in zip(remain_tmp_idxs, remain_true_idxs):
new_aug_state_idxs[new_aug_state_idxs == tmp_idx] = true_idx
# Remove evidence based augmented labels
new_state_idxs = new_aug_state_idxs.T[num_ev_:].T
return new_state_idxs, new_values
def collapse_labels(model, evidence, reduced_variables, reduced_row_idxs,
reduced_values):
import vtool as vt
# assert np.all(reduced_joint.values.ravel() == reduced_joint.values.flatten())
reduced_ttypes = [model.var2_cpd[var].ttype for var in reduced_variables]
evidence_vars = list(evidence.keys())
evidence_state_idxs = ut.dict_take(evidence, evidence_vars)
evidence_ttypes = [model.var2_cpd[var].ttype for var in evidence_vars]
ttype2_ev_indices = dict(zip(*ut.group_indices(evidence_ttypes)))
ttype2_re_indices = dict(zip(*ut.group_indices(reduced_ttypes)))
# ttype2_ev_indices = ut.group_items(range(len(evidence_vars)), evidence_ttypes)
# ttype2_re_indices = ut.group_items(range(len(reduced_variables)), reduced_ttypes)
# Allow specific types of labels to change
# everything is the same, only the names have changed.
# TODO: allow for multiple different label_ttypes
# for label_ttype in label_ttypes
if NAME_TTYPE not in model.ttype2_template:
return reduced_row_idxs, reduced_values
label_ttypes = [NAME_TTYPE]
for label_ttype in label_ttypes:
ev_colxs = ttype2_ev_indices[label_ttype]
re_colxs = ttype2_re_indices[label_ttype]
ev_state_idxs = ut.take(evidence_state_idxs, ev_colxs)
ev_state_idxs_tile = np.tile(ev_state_idxs,
(len(reduced_values), 1)).astype(np.int)
num_ev_ = len(ev_colxs)
aug_colxs = list(
range(num_ev_)) + (np.array(re_colxs) + num_ev_).tolist()
aug_state_idxs = np.hstack([ev_state_idxs_tile, reduced_row_idxs])
# Relabel rows based on the knowledge that
# everything is the same, only the names have changed.
num_cols = len(aug_state_idxs.T)
mask = vt.index_to_boolmask(aug_colxs, num_cols)
(other_colxs, ) = np.where(~mask)
relbl_states = aug_state_idxs.compress(mask, axis=1)
other_states = aug_state_idxs.compress(~mask, axis=1)
tmp_relbl_states = np.array(list(map(make_temp_state, relbl_states)))
max_tmp_state = -1
min_tmp_state = tmp_relbl_states.min()
# rebuild original state structure with temp state idxs
tmp_state_cols = [None] * num_cols
for count, colx in enumerate(aug_colxs):
tmp_state_cols[colx] = tmp_relbl_states[:, count:count + 1]
for count, colx in enumerate(other_colxs):
tmp_state_cols[colx] = other_states[:, count:count + 1]
tmp_state_idxs = np.hstack(tmp_state_cols)
data_ids = np.array(
vt.compute_unique_data_ids_(list(map(tuple, tmp_state_idxs))))
unique_ids, groupxs = vt.group_indices(data_ids)
logger.info('Collapsed %r states into %r states' % (
len(data_ids),
len(unique_ids),
))
# Sum the values in the cpd to marginalize the duplicate probs
new_values = np.array(
[g.sum() for g in vt.apply_grouping(reduced_values, groupxs)])
# Take only the unique rows under this induced labeling
unique_tmp_groupxs = np.array(ut.get_list_column(groupxs, 0))
new_aug_state_idxs = tmp_state_idxs.take(unique_tmp_groupxs, axis=0)
tmp_idx_set = set((-np.arange(-max_tmp_state,
(-min_tmp_state) + 1)).tolist())
true_idx_set = set(range(len(
model.ttype2_template[label_ttype].basis)))
# Relabel the rows one more time to agree with initial constraints
for colx, true_idx in enumerate(ev_state_idxs):
tmp_idx = np.unique(new_aug_state_idxs.T[colx])
assert len(tmp_idx) == 1
tmp_idx_set -= {tmp_idx[0]}
true_idx_set -= {true_idx}
new_aug_state_idxs[new_aug_state_idxs == tmp_idx] = true_idx
# Relabel the remaining idxs
remain_tmp_idxs = sorted(list(tmp_idx_set))[::-1]
remain_true_idxs = sorted(list(true_idx_set))
for tmp_idx, true_idx in zip(remain_tmp_idxs, remain_true_idxs):
new_aug_state_idxs[new_aug_state_idxs == tmp_idx] = true_idx
# Remove evidence based augmented labels
new_state_idxs = new_aug_state_idxs.T[num_ev_:].T
return new_state_idxs, new_values
def _compute_unique_state_ids(self):
import vtool as vt
#data_ids = vt.compute_ndarray_unique_rowids_unsafe(self.state_idxs)
data_ids = np.array(vt.compute_unique_data_ids_(list(map(tuple, self.state_idxs))))
return data_ids
def get_review_edges(cm_list, ibs=None, review_cfg={}):
r"""
Needs to be moved to a better file. Maybe something to do with
identification.
Returns a list of matches that should be inspected
This function is more lightweight than orgres or allres.
Used in id_review_api and interact_qres2
Args:
cm_list (list): list of chip match objects
ranks_top (int): put all ranks less than this number into the graph
directed (bool):
Returns:
tuple: review_edges = (qaid_arr, daid_arr, score_arr, rank_arr)
CommandLine:
python -m ibeis.gui.id_review_api get_review_edges:0
Example0:
>>> # ENABLE_DOCTEST
>>> from ibeis.gui.id_review_api import * # NOQA
>>> import ibeis
>>> ibs = ibeis.opendb('PZ_MTEST')
>>> qreq_ = ibeis.main_helpers.testdata_qreq_()
>>> cm_list = qreq_.execute()
>>> review_cfg = dict(ranks_top=5, directed=True, name_scoring=False,
>>> filter_true_matches=True)
>>> review_edges = get_review_edges(cm_list, ibs=ibs, review_cfg=review_cfg)
>>> print(review_edges)
Example1:
>>> # UNSTABLE_DOCTEST
>>> from ibeis.gui.id_review_api import * # NOQA
>>> import ibeis
>>> cm_list, qreq_ = ibeis.testdata_cmlist('PZ_MTEST', a='default:qsize=5,dsize=20')
>>> review_cfg = dict(ranks_top=5, directed=True, name_scoring=False,
>>> filter_reviewed=False, filter_true_matches=True)
>>> review_edges = get_review_edges(cm_list, review_cfg=review_cfg, ibs=ibs)
>>> print(review_edges)
Example3:
>>> # UNSTABLE_DOCTEST
>>> from ibeis.gui.id_review_api import * # NOQA
>>> import ibeis
>>> cm_list, qreq_ = ibeis.testdata_cmlist('PZ_MTEST', a='default:qsize=1,dsize=100')
>>> review_cfg = dict(ranks_top=1, directed=False, name_scoring=False,
>>> filter_reviewed=False, filter_true_matches=True)
>>> review_edges = get_review_edges(cm_list, review_cfg=review_cfg, ibs=ibs)
>>> print(review_edges)
Example4:
>>> # UNSTABLE_DOCTEST
>>> from ibeis.gui.id_review_api import * # NOQA
>>> import ibeis
>>> cm_list, qreq_ = ibeis.testdata_cmlist('PZ_MTEST', a='default:qsize=10,dsize=10')
>>> ranks_top = 3
>>> review_cfg = dict(ranks_top=3, directed=False, name_scoring=False,
>>> filter_reviewed=False, filter_true_matches=True)
>>> review_edges = get_review_edges(cm_list, review_cfg=review_cfg, ibs=ibs)
>>> print(review_edges)
"""
import vtool as vt
from ibeis.algo.hots import chip_match
automatch_kw = REVIEW_CFG_DEFAULTS.copy()
automatch_kw = ut.update_existing(automatch_kw, review_cfg)
print('[resorg] get_review_edges(%s)' % (ut.repr2(automatch_kw)))
print('[resorg] len(cm_list) = %d' % (len(cm_list)))
qaids_stack = []
daids_stack = []
ranks_stack = []
scores_stack = []
# For each QueryResult, Extract inspectable candidate matches
if isinstance(cm_list, dict):
cm_list = list(cm_list.values())
if len(cm_list) == 0:
return ([], [], [], [])
for cm in cm_list:
if isinstance(cm, chip_match.ChipMatch):
daids = cm.get_top_aids(ntop=automatch_kw['ranks_top'])
scores = cm.get_top_scores(ntop=automatch_kw['ranks_top'])
ranks = np.arange(len(daids))
qaids = np.full(daids.shape, cm.qaid, dtype=daids.dtype)
else:
(qaids, daids, scores, ranks) = cm.get_match_tbldata(
ranks_top=automatch_kw['ranks_top'],
name_scoring=automatch_kw['name_scoring'],
ibs=ibs)
qaids_stack.append(qaids)
daids_stack.append(daids)
scores_stack.append(scores)
ranks_stack.append(ranks)
# Stack them into a giant array
qaid_arr = np.hstack(qaids_stack)
daid_arr = np.hstack(daids_stack)
score_arr = np.hstack(scores_stack)
rank_arr = np.hstack(ranks_stack)
# Sort by scores
sortx = score_arr.argsort()[::-1]
qaid_arr = qaid_arr[sortx]
daid_arr = daid_arr[sortx]
score_arr = score_arr[sortx]
rank_arr = rank_arr[sortx]
# IS_REVIEWED DOES NOT WORK
if automatch_kw['filter_reviewed']:
_is_reviewed = ibs.get_annot_pair_is_reviewed(qaid_arr.tolist(),
daid_arr.tolist())
is_unreviewed = ~np.array(_is_reviewed, dtype=np.bool)
qaid_arr = qaid_arr.compress(is_unreviewed)
daid_arr = daid_arr.compress(is_unreviewed)
score_arr = score_arr.compress(is_unreviewed)
rank_arr = rank_arr.compress(is_unreviewed)
# Remove directed edges
if not automatch_kw['directed']:
#nodes = np.unique(directed_edges.flatten())
directed_edges = np.vstack((qaid_arr, daid_arr)).T
#idx1, idx2 = vt.intersect2d_indices(directed_edges, directed_edges[:, ::-1])
unique_rowx = vt.find_best_undirected_edge_indexes(directed_edges,
score_arr)
qaid_arr = qaid_arr.take(unique_rowx)
daid_arr = daid_arr.take(unique_rowx)
score_arr = score_arr.take(unique_rowx)
rank_arr = rank_arr.take(unique_rowx)
# Filter Double Name Matches
if automatch_kw['filter_duplicate_true_matches']:
# filter_dup_namepairs
qnid_arr = ibs.get_annot_nids(qaid_arr)
dnid_arr = ibs.get_annot_nids(daid_arr)
if not automatch_kw['directed']:
directed_name_edges = np.vstack((qnid_arr, dnid_arr)).T
unique_rowx2 = vt.find_best_undirected_edge_indexes(
directed_name_edges, score_arr)
else:
namepair_id_list = np.array(vt.compute_unique_data_ids_(
list(zip(qnid_arr, dnid_arr))))
unique_namepair_ids, namepair_groupxs = vt.group_indices(namepair_id_list)
score_namepair_groups = vt.apply_grouping(score_arr, namepair_groupxs)
unique_rowx2 = np.array(sorted([
groupx[score_group.argmax()]
for groupx, score_group in zip(namepair_groupxs, score_namepair_groups)
]), dtype=np.int32)
qaid_arr = qaid_arr.take(unique_rowx2)
daid_arr = daid_arr.take(unique_rowx2)
score_arr = score_arr.take(unique_rowx2)
rank_arr = rank_arr.take(unique_rowx2)
# Filter all true matches
if automatch_kw['filter_true_matches']:
qnid_arr = ibs.get_annot_nids(qaid_arr)
dnid_arr = ibs.get_annot_nids(daid_arr)
valid_flags = qnid_arr != dnid_arr
qaid_arr = qaid_arr.compress(valid_flags)
daid_arr = daid_arr.compress(valid_flags)
score_arr = score_arr.compress(valid_flags)
rank_arr = rank_arr.compress(valid_flags)
if automatch_kw['filter_photobombs']:
unique_aids = ut.unique(ut.flatten([qaid_arr, daid_arr]))
#grouped_aids, unique_nids = ibs.group_annots_by_name(unique_aids)
invalid_nid_map = get_photobomber_map(ibs, qaid_arr)
nid2_aids = ut.group_items(unique_aids, ibs.get_annot_nids(unique_aids))
expanded_aid_map = ut.ddict(set)
for nid1, other_nids in invalid_nid_map.items():
for aid1 in nid2_aids[nid1]:
for nid2 in other_nids:
for aid2 in nid2_aids[nid2]:
expanded_aid_map[aid1].add(aid2)
expanded_aid_map[aid2].add(aid1)
valid_flags = [daid not in expanded_aid_map[qaid]
for qaid, daid in zip(qaid_arr, daid_arr)]
qaid_arr = qaid_arr.compress(valid_flags)
daid_arr = daid_arr.compress(valid_flags)
score_arr = score_arr.compress(valid_flags)
rank_arr = rank_arr.compress(valid_flags)
review_edges = (qaid_arr, daid_arr, score_arr, rank_arr)
return review_edges
def get_automatch_candidates(cm_list, ranks_lt=5, directed=True,
name_scoring=False, ibs=None, filter_reviewed=False,
filter_duplicate_namepair_matches=False):
"""
THIS IS PROBABLY ONE OF THE ONLY THINGS IN THIS FILE THAT SHOULD NOT BE
DEPRICATED
Returns a list of matches that should be inspected
This function is more lightweight than orgres or allres.
Used in inspect_gui and interact_qres2
Args:
qaid2_qres (dict): mapping from query annotaiton id to query result object
ranks_lt (int): put all ranks less than this number into the graph
directed (bool):
Returns:
tuple: candidate_matches = (qaid_arr, daid_arr, score_arr, rank_arr)
CommandLine:
python -m ibeis.expt.results_organizer --test-get_automatch_candidates:2
python -m ibeis.expt.results_organizer --test-get_automatch_candidates:0
Example0:
>>> # ENABLE_DOCTEST
>>> from ibeis.expt.results_organizer import * # NOQA
>>> import ibeis
>>> ibs = ibeis.opendb('PZ_MTEST')
>>> qreq_ = ibeis.main_helpers.testdata_qreq_()
>>> cm_list = ibs.query_chips(qreq_=qreq_, return_cm=True)
>>> ranks_lt = 5
>>> directed = True
>>> name_scoring = False
>>> candidate_matches = get_automatch_candidates(cm_list, ranks_lt, directed, ibs=ibs)
>>> print(candidate_matches)
Example1:
>>> # UNSTABLE_DOCTEST
>>> from ibeis.expt.results_organizer import * # NOQA
>>> import ibeis
>>> ibs = ibeis.opendb('PZ_MTEST')
>>> qaid_list = ibs.get_valid_aids()[0:5]
>>> daid_list = ibs.get_valid_aids()[0:20]
>>> cm_list = ibs.query_chips(qaid_list, daid_list, return_cm=True)
>>> ranks_lt = 5
>>> directed = False
>>> name_scoring = False
>>> filter_reviewed = False
>>> filter_duplicate_namepair_matches = True
>>> candidate_matches = get_automatch_candidates(
... cm_list, ranks_lt, directed, name_scoring=name_scoring,
... filter_reviewed=filter_reviewed,
... filter_duplicate_namepair_matches=filter_duplicate_namepair_matches,
... ibs=ibs)
>>> print(candidate_matches)
Example3:
>>> # UNSTABLE_DOCTEST
>>> from ibeis.expt.results_organizer import * # NOQA
>>> import ibeis
>>> ibs = ibeis.opendb('PZ_MTEST')
>>> qaid_list = ibs.get_valid_aids()[0:1]
>>> daid_list = ibs.get_valid_aids()[10:100]
>>> qaid2_cm = ibs.query_chips(qaid_list, daid_list, return_cm=True)
>>> ranks_lt = 1
>>> directed = False
>>> name_scoring = False
>>> filter_reviewed = False
>>> filter_duplicate_namepair_matches = True
>>> candidate_matches = get_automatch_candidates(
... cm_list, ranks_lt, directed, name_scoring=name_scoring,
... filter_reviewed=filter_reviewed,
... filter_duplicate_namepair_matches=filter_duplicate_namepair_matches,
... ibs=ibs)
>>> print(candidate_matches)
Example4:
>>> # UNSTABLE_DOCTEST
>>> from ibeis.expt.results_organizer import * # NOQA
>>> import ibeis
>>> ibs = ibeis.opendb('PZ_MTEST')
>>> qaid_list = ibs.get_valid_aids()[0:10]
>>> daid_list = ibs.get_valid_aids()[0:10]
>>> qres_list = ibs.query_chips(qaid_list, daid_list)
>>> ranks_lt = 3
>>> directed = False
>>> name_scoring = False
>>> filter_reviewed = False
>>> filter_duplicate_namepair_matches = True
>>> candidate_matches = get_automatch_candidates(
... qaid2_cm, ranks_lt, directed, name_scoring=name_scoring,
... filter_reviewed=filter_reviewed,
... filter_duplicate_namepair_matches=filter_duplicate_namepair_matches,
... ibs=ibs)
>>> print(candidate_matches)
"""
import vtool as vt
from ibeis.model.hots import chip_match
print(('[resorg] get_automatch_candidates('
'filter_reviewed={filter_reviewed},'
'filter_duplicate_namepair_matches={filter_duplicate_namepair_matches},'
'directed={directed},'
'ranks_lt={ranks_lt},'
).format(**locals()))
print('[resorg] len(cm_list) = %d' % (len(cm_list)))
qaids_stack = []
daids_stack = []
ranks_stack = []
scores_stack = []
# For each QueryResult, Extract inspectable candidate matches
if isinstance(cm_list, dict):
cm_list = list(cm_list.values())
for cm in cm_list:
if isinstance(cm, chip_match.ChipMatch2):
daids = cm.get_top_aids(ntop=ranks_lt)
scores = cm.get_top_scores(ntop=ranks_lt)
ranks = np.arange(len(daids))
qaids = np.full(daids.shape, cm.qaid, dtype=daids.dtype)
else:
(qaids, daids, scores, ranks) = cm.get_match_tbldata(
ranks_lt=ranks_lt, name_scoring=name_scoring, ibs=ibs)
qaids_stack.append(qaids)
daids_stack.append(daids)
scores_stack.append(scores)
ranks_stack.append(ranks)
# Stack them into a giant array
# utool.embed()
qaid_arr = np.hstack(qaids_stack)
daid_arr = np.hstack(daids_stack)
score_arr = np.hstack(scores_stack)
rank_arr = np.hstack(ranks_stack)
# Sort by scores
sortx = score_arr.argsort()[::-1]
qaid_arr = qaid_arr[sortx]
daid_arr = daid_arr[sortx]
score_arr = score_arr[sortx]
rank_arr = rank_arr[sortx]
if filter_reviewed:
_is_reviewed = ibs.get_annot_pair_is_reviewed(qaid_arr.tolist(), daid_arr.tolist())
is_unreviewed = ~np.array(_is_reviewed, dtype=np.bool)
qaid_arr = qaid_arr.compress(is_unreviewed)
daid_arr = daid_arr.compress(is_unreviewed)
score_arr = score_arr.compress(is_unreviewed)
rank_arr = rank_arr.compress(is_unreviewed)
# Remove directed edges
if not directed:
#nodes = np.unique(directed_edges.flatten())
directed_edges = np.vstack((qaid_arr, daid_arr)).T
#idx1, idx2 = vt.intersect2d_indices(directed_edges, directed_edges[:, ::-1])
unique_rowx = vt.find_best_undirected_edge_indexes(directed_edges, score_arr)
qaid_arr = qaid_arr.take(unique_rowx)
daid_arr = daid_arr.take(unique_rowx)
score_arr = score_arr.take(unique_rowx)
rank_arr = rank_arr.take(unique_rowx)
# Filter Double Name Matches
if filter_duplicate_namepair_matches:
qnid_arr = ibs.get_annot_nids(qaid_arr)
dnid_arr = ibs.get_annot_nids(daid_arr)
if not directed:
directed_name_edges = np.vstack((qnid_arr, dnid_arr)).T
unique_rowx2 = vt.find_best_undirected_edge_indexes(directed_name_edges, score_arr)
else:
namepair_id_list = np.array(vt.compute_unique_data_ids_(list(zip(qnid_arr, dnid_arr))))
unique_namepair_ids, namepair_groupxs = vt.group_indices(namepair_id_list)
score_namepair_groups = vt.apply_grouping(score_arr, namepair_groupxs)
unique_rowx2 = np.array(sorted([
groupx[score_group.argmax()]
for groupx, score_group in zip(namepair_groupxs, score_namepair_groups)
]), dtype=np.int32)
qaid_arr = qaid_arr.take(unique_rowx2)
daid_arr = daid_arr.take(unique_rowx2)
score_arr = score_arr.take(unique_rowx2)
rank_arr = rank_arr.take(unique_rowx2)
candidate_matches = (qaid_arr, daid_arr, score_arr, rank_arr)
return candidate_matches