def test_neg_metagraph_split_and_merge():
"""
Test that the negative metagraph tracks the number of negative edges
between PCCs through label-changing split and merge operations
"""
# Create a graph with 4 CCs, with 3-pos-redun, and no negative edges
infr = demo.demodata_infr(num_pccs=4, pcc_size=5, pos_redun=3,
ignore_pair=True, infer=True)
cc_a, cc_b, cc_c, cc_d = infr.positive_components()
a1, a2, a3, a4, a5 = cc_a
b1, b2, b3, b4, b5 = cc_b
c1, c2, c3, c4, c5 = cc_c
d1, d2, d3, d4, d5 = cc_d
nmg = infr.neg_metagraph
# Add three negative edges between a and b
# one between (a, c), (b, d), (a, d), and (c, d)
A, B, C, D = infr.node_labels(a1, b1, c1, d1)
infr.add_feedback((a1, b1), NEGTV)
infr.add_feedback((a2, b2), NEGTV)
infr.add_feedback((a3, b3), NEGTV)
infr.add_feedback((a4, c4), NEGTV)
infr.add_feedback((b4, d4), NEGTV)
infr.add_feedback((c1, d1), NEGTV)
infr.add_feedback((a4, d4), NEGTV)
assert nmg.edges[(A, B)]['weight'] == 3
assert nmg.edges[(A, C)]['weight'] == 1
assert (B, C) not in nmg.edges
assert nmg.edges[(A, D)]['weight'] == 1
assert nmg.edges[(B, D)]['weight'] == 1
assert nmg.number_of_edges() == 5
assert nmg.number_of_nodes() == 4
# merge A and B
infr.add_feedback((a1, b1), POSTV)
assert nmg.number_of_edges() == 4
assert nmg.number_of_nodes() == 3
AB = infr.node_label(a1)
assert nmg.edges[(AB, AB)]['weight'] == 2
# split A and B
# the number of nodes should increase, but the edges should stay the
# same because we added an incmp edge
infr.add_feedback((a1, b1), INCMP)
assert nmg.number_of_edges() == 5
assert nmg.number_of_nodes() == 4
assert nmg.edges[(A, B)]['weight'] == 2
infr.assert_neg_metagraph()
# remove all positive edges
for edge in list(infr.pos_graph.edges()):
infr.add_feedback(edge, INCMP)
# metagraph should not be isomorphic to infr.neg_graph
assert nmg.number_of_nodes() == infr.neg_graph.number_of_nodes()
assert nmg.number_of_edges() == infr.neg_graph.number_of_edges()
infr.assert_neg_metagraph()
def test_neg_metagraph_simple_add_remove():
"""
Test that the negative metagraph tracks the number of negative edges
between PCCs through non-label-changing operations
"""
# Create a graph with 5-sized CCs, with 3-pos-redun, and no negative edges
infr = demo.demodata_infr(num_pccs=4, pcc_size=5, pos_redun=3,
ignore_pair=True, infer=True)
cc_a, cc_b, cc_c, cc_d = infr.positive_components()
a1, a2, a3, a4, a5 = cc_a
b1, b2, b3, b4, b5 = cc_b
nmg = infr.neg_metagraph
# Check there are 4 meta-nodes and no edges
assert nmg.number_of_edges() == 0
assert nmg.number_of_nodes() == 4
# Should add 1 edge to the negative metagraph
u, v = a1, b1
infr.add_feedback((u, v), NEGTV)
nid1, nid2 = infr.node_labels(u, v)
assert nmg.edges[nid1, nid2]['weight'] == 1
assert nmg.number_of_edges() == 1
assert nmg.number_of_nodes() == 4
# Adding a second time should do nothing
edge = a1, b1
infr.add_feedback(edge, NEGTV)
name_edge = infr.node_labels(*edge)
assert nmg.edges[name_edge]['weight'] == 1
assert nmg.number_of_edges() == 1
assert nmg.number_of_nodes() == 4
# But adding a second between different nodes will increase the weight
edge = a1, b2
infr.add_feedback(edge, NEGTV)
name_edge = infr.node_labels(*edge)
assert nmg.edges[name_edge]['weight'] == 2
assert nmg.number_of_edges() == 1
assert nmg.number_of_nodes() == 4
infr.add_feedback((u, v), NEGTV)
assert nmg.edges[name_edge]['weight'] == 2
# Removing or relabeling the edge will decrease the weight
infr.add_feedback((a1, b2), INCMP)
assert nmg.edges[name_edge]['weight'] == 1
# And removing all will remove the negative edge
infr.add_feedback((a1, b1), INCMP)
assert not nmg.has_edge(*name_edge)
infr.assert_neg_metagraph()
def test_neg_metagraph_split_incomp():
infr = demo.demodata_infr(num_pccs=4, pcc_size=5, pos_redun=3,
ignore_pair=True, infer=True)
nmg = infr.neg_metagraph
assert nmg.number_of_nodes() < infr.neg_graph.number_of_nodes()
assert nmg.number_of_edges() == 0
# remove all positive edges
for edge in list(infr.pos_graph.edges()):
infr.add_feedback(edge, INCMP)
# metagraph should not be isomorphic to infr.neg_graph
assert nmg.number_of_nodes() == infr.neg_graph.number_of_nodes()
assert nmg.number_of_edges() == 0
infr.assert_neg_metagraph()
def test_pos_neg():
"""
python ~/code/graphid/tests/test_graph_iden.py test_pos_neg
"""
infr = demo.demodata_infr(num_pccs=0)
# Make 3 inconsistent CCs
infr.add_feedback((1, 2), POSTV)
infr.add_feedback((2, 3), POSTV)
infr.add_feedback((3, 4), POSTV)
infr.add_feedback((4, 1), POSTV)
infr.add_feedback((1, 3), NEGTV)
# -----
infr.add_feedback((11, 12), POSTV)
infr.add_feedback((12, 13), POSTV)
infr.add_feedback((13, 11), NEGTV)
# -----
infr.add_feedback((21, 22), POSTV)
infr.add_feedback((22, 23), POSTV)
infr.add_feedback((23, 21), NEGTV)
# -----
# Fix inconsistency
infr.add_feedback((23, 21), POSTV)
# Merge inconsistent CCS
infr.add_feedback((1, 11), POSTV)
# Negative edge within an inconsistent CC
infr.add_feedback((2, 13), NEGTV)
# Negative edge external to an inconsistent CC
infr.add_feedback((12, 21), NEGTV)
# -----
# Make inconsistency from positive
infr.add_feedback((31, 32), POSTV)
infr.add_feedback((33, 34), POSTV)
infr.add_feedback((31, 33), NEGTV)
infr.add_feedback((32, 34), NEGTV)
infr.add_feedback((31, 34), POSTV)
# Fix everything
infr.add_feedback((1, 3), POSTV)
infr.add_feedback((2, 4), POSTV)
infr.add_feedback((32, 34), POSTV)
infr.add_feedback((31, 33), POSTV)
infr.add_feedback((13, 11), POSTV)
infr.add_feedback((23, 21), POSTV)
infr.add_feedback((1, 11), NEGTV)
print('Final state:')
print(ub.repr2(sorted(infr.gen_edge_attrs('decision'))))
def test_neg_metagraph_split_neg():
"""
Test that the negative metagraph tracks the number of negative edges
between PCCs through label-changing split operations
"""
# Create a graph with 4 CCs, with 3-pos-redun, and no negative edges
infr = demo.demodata_infr(num_pccs=4, pcc_size=5, pos_redun=3,
ignore_pair=True, infer=True)
nmg = infr.neg_metagraph
assert nmg.number_of_nodes() != infr.neg_graph.number_of_nodes()
assert nmg.number_of_edges() == 0
# remove all positive edges
for edge in list(infr.pos_graph.edges()):
infr.add_feedback(edge, NEGTV)
# metagraph should not be isomorphic to infr.neg_graph
assert nmg.number_of_nodes() == infr.neg_graph.number_of_nodes()
assert nmg.number_of_edges() > 0
assert nmg.number_of_edges() == infr.neg_graph.number_of_edges()
infr.assert_neg_metagraph()
def test_incomp_inference():
infr = demo.demodata_infr(num_pccs=0)
# Make 2 consistent and 2 inconsistent CCs
infr.add_feedback((1, 2), POSTV)
infr.add_feedback((2, 3), POSTV)
infr.add_feedback((3, 4), POSTV)
infr.add_feedback((4, 1), POSTV)
# -----
infr.add_feedback((11, 12), POSTV)
infr.add_feedback((12, 13), POSTV)
infr.add_feedback((13, 14), POSTV)
infr.add_feedback((14, 11), POSTV)
infr.add_feedback((12, 14), NEGTV)
# -----
infr.add_feedback((21, 22), POSTV)
infr.add_feedback((22, 23), POSTV)
infr.add_feedback((23, 21), NEGTV)
# -----
infr.add_feedback((31, 32), POSTV)
infr.add_feedback((32, 33), POSTV)
infr.add_feedback((33, 31), POSTV)
infr.add_feedback((2, 32), NEGTV)
infr.add_feedback((3, 33), NEGTV)
infr.add_feedback((12, 21), NEGTV)
# -----
# Incomparable within CCs
print('==========================')
infr.add_feedback((1, 3), INCMP)
infr.add_feedback((1, 4), INCMP)
infr.add_feedback((1, 2), INCMP)
infr.add_feedback((11, 13), INCMP)
infr.add_feedback((11, 14), INCMP)
infr.add_feedback((11, 12), INCMP)
infr.add_feedback((1, 31), INCMP)
infr.add_feedback((2, 32), INCMP)
infr.add_feedback((12, 21), INCMP)
infr.add_feedback((23, 21), INCMP)
infr.add_feedback((12, 14), INCMP)
print('Final state:')
print(ub.repr2(sorted(infr.gen_edge_attrs('decision'))))
def run_demo():
"""
CommandLine:
python -m graphid.demo.demo_script run_demo --viz
python -m graphid.demo.demo_script run_demo
Example:
>>> run_demo()
"""
from graphid import demo
import matplotlib as mpl
TMP_RC = {
'axes.titlesize': 12,
'axes.labelsize': int(ub.argval('--labelsize', default=8)),
'font.family': 'sans-serif',
'font.serif': 'CMU Serif',
'font.sans-serif': 'CMU Sans Serif',
'font.monospace': 'CMU Typewriter Text',
'xtick.labelsize': 12,
'ytick.labelsize': 12,
# 'legend.alpha': .8,
'legend.fontsize': 12,
'legend.facecolor': 'w',
}
mpl.rcParams.update(TMP_RC)
# ---- Synthetic data params
params = {
'redun.pos': 2,
'redun.neg': 2,
}
# oracle_accuracy = .98
# oracle_accuracy = .90
# oracle_accuracy = (.8, 1.0)
oracle_accuracy = (.85, 1.0)
# oracle_accuracy = 1.0
# --- draw params
VISUALIZE = ub.argflag('--viz')
# QUIT_OR_EMEBED = 'embed'
QUIT_OR_EMEBED = 'quit'
def asint(p):
return p if p is None else int(p)
TARGET_REVIEW = asint(ub.argval('--target', default=None))
START = asint(ub.argval('--start', default=None))
END = asint(ub.argval('--end', default=None))
# ------------------
# rng = np.random.RandomState(42)
# infr = demo.demodata_infr(num_pccs=4, size=3, size_std=1, p_incon=0)
# infr = demo.demodata_infr(num_pccs=6, size=7, size_std=1, p_incon=0)
# infr = demo.demodata_infr(num_pccs=3, size=5, size_std=.2, p_incon=0)
infr = demo.demodata_infr(pcc_sizes=[5, 2, 4])
infr.verbose = 100
infr.ensure_cliques()
infr.ensure_full()
# Dummy scoring
infr.init_simulation(oracle_accuracy=oracle_accuracy, name='run_demo')
# infr_gt = infr.copy()
dpath = ub.ensuredir(ub.truepath('~/Desktop/demo'))
if 0:
ub.delete(dpath)
ub.ensuredir(dpath)
fig_counter = it.count(0)
def show_graph(infr, title, final=False, selected_edges=None):
from matplotlib import pyplot as plt
if not VISUALIZE:
return
# TODO: rich colored text?
latest = '\n'.join(infr.latest_logs())
showkw = dict(
# fontsize=infr.graph.graph['fontsize'],
# fontname=infr.graph.graph['fontname'],
show_unreviewed_edges=True,
show_inferred_same=False,
show_inferred_diff=False,
outof=(len(infr.aids)),
# show_inferred_same=True,
# show_inferred_diff=True,
selected_edges=selected_edges,
show_labels=True,
simple_labels=True,
# show_recent_review=not final,
show_recent_review=False,
# splines=infr.graph.graph['splines'],
reposition=False,
# with_colorbar=True
)
verbose = infr.verbose
infr.verbose = 0
infr_ = infr.copy()
infr_ = infr
infr_.verbose = verbose
infr_.show(pickable=True, verbose=0, **showkw)
infr.verbose = verbose
# print('status ' + ub.repr2(infr_.status()))
# infr.show(**showkw)
ax = plt.gca()
ax.set_title(title, fontsize=20)
fig = plt.gcf()
# fontsize = 22
fontsize = 12
if True:
# postprocess xlabel
lines = []
for line in latest.split('\n'):
if False and line.startswith('ORACLE ERROR'):
lines += ['ORACLE ERROR']
else:
lines += [line]
latest = '\n'.join(lines)
if len(lines) > 10:
fontsize = 16
if len(lines) > 12:
fontsize = 14
if len(lines) > 14:
fontsize = 12
if len(lines) > 18:
fontsize = 10
if len(lines) > 23:
fontsize = 8
if True:
util.mplutil.adjust_subplots(top=.95,
left=0,
right=1,
bottom=.45,
fig=fig)
ax.set_xlabel('\n' + latest)
xlabel = ax.get_xaxis().get_label()
xlabel.set_horizontalalignment('left')
# xlabel.set_x(.025)
# xlabel.set_x(-.6)
xlabel.set_x(-2.0)
# xlabel.set_fontname('CMU Typewriter Text')
xlabel.set_fontname('Inconsolata')
xlabel.set_fontsize(fontsize)
ax.set_aspect('equal')
# ax.xaxis.label.set_color('red')
fpath = join(dpath, 'demo_{:04d}.png'.format(next(fig_counter)))
fig.savefig(
fpath,
dpi=300,
# transparent=True,
edgecolor='none')
# pt.save_figure(dpath=dpath, dpi=300)
infr.latest_logs()
if VISUALIZE:
infr.update_visual_attrs(groupby='name_label')
infr.set_node_attrs('pin', 'true')
node_dict = infr.graph.nodes
print(ub.repr2(node_dict[1]))
if VISUALIZE:
infr.latest_logs()
# Pin Nodes into the target groundtruth position
show_graph(infr, 'target-gt')
print(ub.repr2(infr.status()))
infr.clear_feedback()
infr.clear_name_labels()
infr.clear_edges()
print(ub.repr2(infr.status()))
infr.latest_logs()
if VISUALIZE:
infr.update_visual_attrs()
infr.prioritize('prob_match')
if VISUALIZE or TARGET_REVIEW is None or TARGET_REVIEW == 0:
show_graph(infr, 'initial state')
def on_new_candidate_edges(infr, edges):
# hack updateing visual attrs as a callback
if VISUALIZE:
infr.update_visual_attrs()
infr.on_new_candidate_edges = on_new_candidate_edges
infr.params.update(**params)
infr.refresh_candidate_edges()
VIZ_ALL = (VISUALIZE and TARGET_REVIEW is None and START is None)
print('VIZ_ALL = %r' % (VIZ_ALL, ))
if VIZ_ALL or TARGET_REVIEW == 0:
show_graph(infr, 'find-candidates')
# _iter2 = enumerate(infr.generate_reviews(**params))
# _iter2 = list(_iter2)
# assert len(_iter2) > 0
# prog = ub.ProgIter(_iter2, label='run_demo', bs=False, adjust=False,
# enabled=False)
count = 1
first = 1
for edge, priority in infr._generate_reviews(data=True):
msg = 'review #%d, priority=%.3f' % (count, priority)
print('\n----------')
infr.print('pop edge {} with priority={:.3f}'.format(edge, priority))
# print('remaining_reviews = %r' % (infr.remaining_reviews()),)
# Make the next review
if START is not None:
VIZ_ALL = count >= START
if END is not None and count >= END:
break
infr.print(msg)
if ub.allsame(infr.pos_graph.node_labels(*edge)) and first:
# Have oracle make a mistake early
feedback = infr.request_oracle_review(edge, accuracy=0)
first -= 1
else:
feedback = infr.request_oracle_review(edge)
AT_TARGET = TARGET_REVIEW is not None and count >= TARGET_REVIEW - 1
SHOW_CANDIATE_POP = True
if SHOW_CANDIATE_POP and (VIZ_ALL or AT_TARGET):
infr.print(
ub.repr2(infr.task_probs['match_state'][edge],
precision=4,
si=True))
infr.print('len(queue) = %r' % (len(infr.queue)))
# Show edge selection
infr.print('Oracle will predict: ' + feedback['evidence_decision'])
show_graph(infr, 'pre' + msg, selected_edges=[edge])
if count == TARGET_REVIEW:
infr.EMBEDME = QUIT_OR_EMEBED == 'embed'
infr.add_feedback(edge, **feedback)
infr.print('len(queue) = %r' % (len(infr.queue)))
# infr.apply_nondynamic_update()
# Show the result
if VIZ_ALL or AT_TARGET:
show_graph(infr, msg)
# import sys
# sys.exit(1)
if count == TARGET_REVIEW:
break
count += 1
infr.print('status = ' + ub.repr2(infr.status(extended=False)))
show_graph(infr, 'post-review (#reviews={})'.format(count), final=True)
if VISUALIZE:
if not getattr(infr, 'EMBEDME', False):
# import plottool as pt
# util.mplutil.all_figures_tile()
util.mplutil.show_if_requested()
def test_neg_metagraph_merge():
"""
Test that the negative metagraph tracks the number of negative edges
between PCCs through label-changing merge operations
python ~/code/graphid/tests/test_neg_metagraph.py test_neg_metagraph_merge
"""
# Create a graph with 4 CCs, with 3-pos-redun, and no negative edges
infr = demo.demodata_infr(num_pccs=4, pcc_size=5, pos_redun=3,
ignore_pair=True, infer=True)
infr.verbose = 1000
cc_a, cc_b, cc_c, cc_d = infr.positive_components()
a1, a2, a3, a4, a5 = cc_a
b1, b2, b3, b4, b5 = cc_b
c1, c2, c3, c4, c5 = cc_c
d1, d2, d3, d4, d5 = cc_d
nmg = infr.neg_metagraph
# The initial negative metagraph has 4 nodes representing the PCCs
# and no edges becase we have not added any negative feedback
assert nmg.number_of_nodes() == 4
assert nmg.number_of_edges() == 0
# Remember the original PCC labels
# (pccs are the nodes in the negative metagraph)
A, B, C, D = infr.node_labels(a1, b1, c1, d1)
# Add three negative edges between a and b
# one between (a, c), (b, d), (a, d), and (c, d)
print('\nSetting up negative edges, before the merge test')
infr.add_feedback((a1, b1), NEGTV)
infr.add_feedback((a2, b2), NEGTV)
infr.add_feedback((a3, b3), NEGTV)
infr.add_feedback((a4, c4), NEGTV)
infr.add_feedback((b4, d4), NEGTV)
infr.add_feedback((c1, d1), NEGTV)
infr.add_feedback((a4, d4), NEGTV)
assert nmg.edges[(A, B)]['weight'] == 3
assert nmg.edges[(A, C)]['weight'] == 1
assert (B, C) not in nmg.edges
assert nmg.edges[(A, D)]['weight'] == 1
assert nmg.edges[(B, D)]['weight'] == 1
assert nmg.number_of_edges() == 5
assert nmg.number_of_nodes() == 4
# Now merge A and B into a single PCC
print('\nMerging A and B into a single PCC: AB')
infr.add_feedback((a1, b1), POSTV)
AB = infr.node_label(a1)
# The original meta-nodes A and B should not be combined into AB
assert infr.node_label(b1) == AB
assert A != B
assert A == AB or A not in nmg.nodes
assert B == AB or B not in nmg.nodes
# Should have combined weights from (A, D) and (B, D)
# And (A, C) should be brought over as-is
assert nmg.edges[(AB, D)]['weight'] == 2
assert nmg.edges[(AB, C)]['weight'] == 1
# should not have a self-loop weight weight 2
# (it decreased because we changed a previously neg edge to pos)
assert nmg.edges[(AB, AB)]['weight'] == 2
assert len(list(nx.selfloop_edges(nmg))) == 1
# nothing should change between C and D
assert nmg.edges[(C, D)]['weight'] == 1
# Should decrease number of nodes and edges
assert nmg.number_of_nodes() == 3
assert nmg.number_of_edges() == 4
infr.assert_neg_metagraph()
# Additional merge
print('\nMerging C and D into a single PCC: CD')
infr.add_feedback((c2, d2), POSTV)
CD = infr.node_label(c1)
infr.assert_neg_metagraph()
assert nmg.number_of_nodes() == 2
assert nmg.number_of_edges() == 3
assert nmg.edges[(CD, CD)]['weight'] == 1
assert nmg.edges[(AB, CD)]['weight'] == 3
assert nmg.edges[(AB, AB)]['weight'] == 2
# Yet another merge
print('\nMerging AB and CD into a single PCC: ABCD')
infr.add_feedback((a1, c1), POSTV)
ABCD = infr.node_label(c1)
assert nmg.number_of_nodes() == 1, 'should only be one PCC now'
assert nmg.number_of_edges() == 1
nmg.edges[(ABCD, ABCD)]['weight'] = 6
infr.assert_neg_metagraph()
def demo_refresh():
r"""
CommandLine:
python -m graphid.core.refresh demo_refresh \
--num_pccs=40 --size=2 --show
Example:
>>> # ENABLE_DOCTEST
>>> from graphid.core.refresh import * # NOQA
>>> demo_refresh()
>>> util.show_if_requested()
"""
from graphid import demo
# import utool as ut
# demokw = ut.argparse_dict({'num_pccs': 50, 'size': 4})
# refreshkw = ut.argparse_funckw(RefreshCriteria)
demokw = {'num_pccs': 50, 'size': 4}
refreshkw = dict(window=20, patience=72, thresh=.1,
method='binomial')
# make an inference object
infr = demo.demodata_infr(size_std=0, **demokw)
edges = list(infr.ranker.predict_candidate_edges(infr.aids, K=100))
scores = np.array(infr.verifier.predict_edges(edges))
sortx = scores.argsort()[::-1]
edges = list(ub.take(edges, sortx))
scores = scores[sortx]
ys = infr.match_state_df(edges)[POSTV].values
y_remainsum = ys[::-1].cumsum()[::-1]
# Do oracle reviews and wait to converge
refresh = RefreshCriteria(**refreshkw)
xdata = []
pprob_any = []
rfrac_any = []
for count, (edge, y) in enumerate(zip(edges, ys)):
refresh.add(y, user_id='user:oracle')
rfrac_any.append(y_remainsum[count] / y_remainsum[0])
pprob_any.append(refresh.prob_any_remain())
xdata.append(count + 1)
if refresh.check():
break
xdata = xdata
ydatas = ub.odict([
('Est. probability any remain', pprob_any),
('Fraction remaining', rfrac_any),
])
# xdoctest: +REQUIRES(--show)
from graphid import util
util.qtensure()
# from ibeis.scripts.thesis import TMP_RC
# import matplotlib as mpl
import matplotlib.pyplot as plt
# mpl.rcParams.update(TMP_RC)
util.multi_plot(
xdata, ydatas, xlabel='# manual reviews',
# rcParams=TMP_RC,
marker='',
ylim=(0, 1), use_legend=False,
)
demokw = ub.map_keys({'num_pccs': '#PCC', 'size': 'PCC size'},
demokw)
thresh = refreshkw.pop('thresh')
refreshkw['span'] = refreshkw.pop('window')
util.relative_text((.02, .58 + .0), ub.repr2(demokw, sep=' ', nl=0)[1:],
valign='bottom')
util.relative_text((.02, .68 + .0), ub.repr2(refreshkw, sep=' ', nl=0)[1:],
valign='bottom')
legend = plt.gca().legend()
legend.get_frame().set_alpha(1.0)
plt.plot([xdata[0], xdata[-1]], [thresh, thresh], 'g--', label='thresh')