def _print_previous_loop_statistics(infr, count):
# Print stats about what happend in the this loop
history = infr.metrics_list[-count:]
recover_blocks = ub.group_items([
(k, sum(1 for i in g))
for k, g in it.groupby(util.take_column(history, 'recovering'))
]).get(True, [])
infr.print(
('Recovery mode entered {} times, '
'made {} recovery decisions.').format(len(recover_blocks),
sum(recover_blocks)),
color='green')
testaction_hist = ub.dict_hist(util.take_column(
history, 'test_action'))
infr.print('Test Action Histogram: {}'.format(
ub.repr2(testaction_hist, si=True)),
color='yellow')
if infr.params['inference.enabled']:
action_hist = ub.dict_hist(
util.emap(frozenset, util.take_column(history, 'action')))
infr.print('Inference Action Histogram: {}'.format(
ub.repr2(action_hist, si=True)),
color='yellow')
infr.print('Decision Histogram: {}'.format(
ub.repr2(ub.dict_hist(util.take_column(history, 'pred_decision')),
si=True)),
color='yellow')
infr.print('User Histogram: {}'.format(
ub.repr2(ub.dict_hist(util.take_column(history, 'user_id')),
si=True)),
color='yellow')
def _make_lnbnn_scores(infr, edges):
edge_to_data = infr._get_cm_edge_data(edges)
edges = list(edge_to_data.keys())
edge_scores = list(util.take_column(edge_to_data.values(), 'score'))
edge_scores = util.replace_nones(edge_scores, np.nan)
edge_scores = np.array(edge_scores)
# take the inf-norm
normscores = edge_scores / util.safe_max(edge_scores, nans=False)
return normscores
def apply_match_scores(infr):
"""
Applies precomputed matching scores to edges that already exist in the
graph. Typically you should run infr.apply_match_edges() before running
this.
Example:
>>> # ENABLE_DOCTEST
>>> infr = testdata_infr('PZ_MTEST')
>>> infr.exec_matching()
>>> infr.apply_match_edges()
>>> infr.apply_match_scores()
>>> infr.get_edge_attrs('score')
"""
if infr.cm_list is None:
infr.print('apply_match_scores - no scores to apply!')
return
infr.print('apply_match_scores', 1)
edges = list(infr.graph.edges())
edge_to_data = infr._get_cm_edge_data(edges)
# Remove existing attrs
util.nx_delete_edge_attr(infr.graph, 'score')
util.nx_delete_edge_attr(infr.graph, 'rank')
util.nx_delete_edge_attr(infr.graph, 'normscore')
edges = list(edge_to_data.keys())
edge_scores = list(util.take_column(edge_to_data.values(), 'score'))
edge_scores = util.replace_nones(edge_scores, np.nan)
edge_scores = np.array(edge_scores)
edge_ranks = np.array(util.take_column(edge_to_data.values(), 'rank'))
# take the inf-norm
normscores = edge_scores / util.safe_max(edge_scores, nans=False)
# Add new attrs
infr.set_edge_attrs('score', ub.dzip(edges, edge_scores))
infr.set_edge_attrs('rank', ub.dzip(edges, edge_ranks))
# Hack away zero probabilites
# probs = np.vstack([p_nomatch, p_match, p_notcomp]).T + 1e-9
# probs = util.normalize(probs, axis=1, ord=1, out=probs)
# entropy = -(np.log2(probs) * probs).sum(axis=1)
infr.set_edge_attrs('normscore', dict(zip(edges, normscores)))
def _get_cm_agg_aid_ranking(infr, cc):
aid_to_cm = {cm.qaid: cm for cm in infr.cm_list}
all_scores = ub.ddict(list)
for qaid in cc:
cm = aid_to_cm[qaid]
# should we be doing nids?
for daid, score in zip(cm.get_top_aids(), cm.get_top_scores()):
all_scores[daid].append(score)
max_scores = sorted(
(max(scores), aid) for aid, scores in all_scores.items())[::-1]
ranked_aids = util.take_column(max_scores, 1)
return ranked_aids
def edge_attr_df(infr, key, edges=None, default=ub.NoParam):
""" constructs DataFrame using current predictions """
edge_states = infr.gen_edge_attrs(key, edges=edges, default=default)
edge_states = list(edge_states)
if isinstance(edges, pd.MultiIndex):
index = edges
else:
if edges is None:
edges_ = util.take_column(edge_states, 0)
else:
edges_ = list(map(tuple, util.aslist(edges)))
index = pd.MultiIndex.from_tuples(edges_, names=('aid1', 'aid2'))
records = util.itake_column(edge_states, 1)
edge_df = pd.Series.from_array(records)
edge_df.name = key
edge_df.index = index
return edge_df