model2.bpt.display(criterion_ids=cids)
model2.cv.display(criterion_ids=cids)
print("lambda: %.7s" % model.lbda)
model2.vpt.display(criterion_ids=cids)
model2.veto_weights.display(criterion_ids=cids)
print("veto lambda: %.7s" % model.veto_lbda)
aa2 = model2.get_assignments(pt)
if aa2 != meta.aa:
print('Error in classification accuracy computation!')
total = len(a)
nok = 0
anok = []
for alt in a:
if aa(alt.id) != aa2(alt.id):
anok.append(alt.id)
nok += 1
print("Good assignments: %3g %%" % (float(total - nok) / total * 100))
print("Bad assignments : %3g %%" % (float(nok) / total * 100))
if len(anok) > 0:
print("Alternatives wrongly assigned:")
print_pt_and_assignments(anok, model.criteria.keys(), [aa, aa2], pt)
aps = [pt["%s" % aid] for aid in anok]
display_electre_tri_models(
[model, model2], [worst, worst], [best, best],
[[ap for ap in model.vpt], [ap for ap in model2.vpt]])
print model2.veto_weights
# Display learned model parameters
print('Learned model')
print('=============')
model2.bpt.display(criterion_ids=cids)
model2.cv.display(criterion_ids=cids)
print("lambda: %.7s" % model2.lbda)
# Compute assignment with the learned model
aa2 = model2.pessimist(pt)
# Compute CA
total = len(a)
nok = 0
anok = []
for alt in a:
if aa(alt.id) != aa2(alt.id):
anok.append(alt)
nok += 1
print("Good assignments: %3g %%" % (float(total - nok) / total * 100))
print("Bad assignments : %3g %%" % (float(nok) / total * 100))
if len(anok) > 0:
print("Alternatives wrongly assigned:")
print_pt_and_assignments(anok.keys(), model.criteria.keys(), [aa, aa2],
pt)
# Display models
display_electre_tri_models([model, model2], [worst, worst], [best, best])
anok = []
for alt in a:
if aa(alt.id) <> aa_learned(alt.id):
anok.append(alt)
nok += 1
print("Good assignments: %g %%" % (float(total-nok)/total*100))
print("Bad assignments : %g %%" % (float(nok)/total*100))
win1, loose1 = compute_winning_and_loosing_coalitions(model.cv,
model.lbda)
win2, loose2 = compute_winning_and_loosing_coalitions(model2.cv,
model2.lbda)
coali = list(set(win1) & set(win2))
coal1e = list(set(win1) ^ set(coali))
coal2e = list(set(win2) ^ set(coali))
print("Number of coalitions original: %d"
% len(win1))
print("Number of coalitions learned: %d"
% len(win2))
print("Number of common coalitions: %d"
% len(coali))
print("Coallitions in original and not in learned: %s"
% '; '.join(map(str, coal1e)))
print("Coallitions in learned and not in original: %s"
% '; '.join(map(str, coal2e)))
display_electre_tri_models([model, model2],
[worst, worst], [best, best])
coal2_ni = list((set(winning) ^ set(win2)) & set(winning))
coal2_add = list((set(winning) ^ set(win2)) & set(win2))
print("Classification accuracy with random profiles: %g" % ca2)
print("Coalitions: total: %d, common: %d, added: %d" % \
(len(win2), (len(winning) - len(coal2_ni)), len(coal2_add)))
# Learn the weights with profiles generated by the heuristic
model3 = model.copy()
heur = HeurMRSortInitProfiles(model3, sorted_pt, aa)
heur.solve()
lp_weights = LpMRSortWeights(model3, pt, aa)
lp_weights.solve()
aa3 = model3.pessimist(pt)
ca3 = compute_ca(aa, aa3)
win3, loose3 = compute_winning_and_loosing_coalitions(
model3.cv, model3.lbda)
coal3_ni = list((set(winning) ^ set(win3)) & set(winning))
coal3_add = list((set(winning) ^ set(win3)) & set(win3))
print("Classification accuracy with heuristic: %g" % ca3)
print("Coalitions: total: %d, common: %d, added: %d" % \
(len(win3), (len(winning) - len(coal3_ni)), len(coal3_add)))
display_electre_tri_models([model], [pt.get_worst(model.criteria)],
[pt.get_best(model.criteria)],
[[ap for ap in model3.bpt]])
print("lambda: %.7s" % model.lbda)
model2.vpt.display(criterion_ids = cids)
model2.veto_weights.display(criterion_ids = cids)
print("veto lambda: %.7s" % model.veto_lbda)
aa2 = model2.get_assignments(pt)
if aa2 != meta.aa:
print('Error in classification accuracy computation!')
total = len(a)
nok = 0
anok = []
for alt in a:
if aa(alt.id) != aa2(alt.id):
anok.append(alt.id)
nok += 1
print("Good assignments: %3g %%" % (float(total-nok)/total*100))
print("Bad assignments : %3g %%" % (float(nok)/total*100))
if len(anok) > 0:
print("Alternatives wrongly assigned:")
print_pt_and_assignments(anok, model.criteria.keys(),
[aa, aa2], pt)
aps = [ pt["%s" % aid] for aid in anok ]
display_electre_tri_models([model, model2],
[worst, worst], [best, best],
[[ap for ap in model.vpt],
[ap for ap in model2.vpt]])
# Display learned model parameters
print('Learned model')
print('=============')
model.bpt.display()
model.cv.display()
print("lambda: %.7s" % model.lbda)
# Compute assignment with the learned model
aa2 = model.pessimist(pt)
# Compute CA
total = len(aa)
nok = 0
anok = []
for alt in aa:
if aa(alt.id) != aa2(alt.id):
anok.append(alt)
nok += 1
print("Good assignments: %3g %%" % (float(total - nok) / total * 100))
print("Bad assignments : %3g %%" % (float(nok) / total * 100))
if len(anok) > 0:
print("Alternatives wrongly assigned:")
print_pt_and_assignments(anok.keys(), model.criteria.keys(), [aa, aa2],
pt)
# Display models
display_electre_tri_models([model], [worst], [best])
# Display learned model parameters
print('Learned model')
print('=============')
model.bpt.display()
model.cv.display()
print("lambda: %.7s" % model.lbda)
# Compute assignment with the learned model
aa2 = model.pessimist(pt)
# Compute CA
total = len(aa)
nok = 0
anok = []
for alt in aa:
if aa(alt.id) != aa2(alt.id):
anok.append(alt)
nok += 1
print("Good assignments: %3g %%" % (float(total-nok)/total*100))
print("Bad assignments : %3g %%" % (float(nok)/total*100))
if len(anok) > 0:
print("Alternatives wrongly assigned:")
print_pt_and_assignments(anok.keys(), model.criteria.keys(),
[aa, aa2], pt)
# Display models
display_electre_tri_models([model], [worst], [best])
pt_learning_too_high = []
for a in a_learning:
i1 = categories.index(aa_learning_m1[a].category_id)
i2 = categories.index(aa_learning_m2[a].category_id)
if i1 == i2:
pt_learning_ok.append(pt_learning[a])
elif i1 < i2:
pt_learning_too_high.append(pt_learning[a])
elif i1 > i2:
pt_learning_too_low.append(pt_learning[a])
a_test = aa_test_m1.keys()
pt_test_ok = []
pt_test_too_low = []
pt_test_too_high = []
for a in a_test:
i1 = categories.index(aa_test_m1[a].category_id)
i2 = categories.index(aa_test_m2[a].category_id)
if i1 == i2:
pt_test_ok.append(pt_test[a])
elif i1 < i2:
pt_test_too_high.append(pt_test[a])
elif i1 > i2:
pt_test_too_low.append(pt_test[a])
display_electre_tri_models([m2, m2], [worst, worst], [best, best],
[m2.vpt, m2.vpt],
[pt_learning_too_low, pt_test_too_low],
None,
[pt_learning_too_high, pt_test_too_high])
if __name__ == "__main__":
m = generate_random_mrsort_model(5, 2, 123)
winning, loosing = compute_winning_and_loosing_coalitions(m.cv, m.lbda)
print("Number of winning coalitions: %d" % len(winning))
print("List of coalitions:")
display_coalitions(winning)
a = generate_alternatives(1000)
pt = generate_random_performance_table(a, m.criteria)
aa = m.pessimist(pt)
heur = HeurMRSortCoalitions(m.criteria, m.categories, pt, aa)
aids = [aid[0] for aid in heur.sorted_extrem ]
display_electre_tri_models([m], [pt.get_worst(m.criteria)],
[pt.get_best(m.criteria)],
[[pt[aid] for aid in aids[:100]]])
coal2 = heur.find_coalitions(100)
print("List of coalitions found:")
display_coalitions(coal2)
coal_ni = list((set(winning) ^ set(coal2)) & set(winning))
print("List of coalitions not identified (%d):" % len(coal_ni))
display_coalitions(coal_ni)
coal_add = list((set(winning) ^ set(coal2)) & set(coal2))
print("List of coalitions added (%s):" % len(coal_add))
display_coalitions(coal_add)
#!/usr/bin/python
import sys
sys.path.append("..")
from pymcda.electre_tri import ElectreTri
from pymcda.ui.graphic import display_electre_tri_models
from datasets import ticino
from datasets import loulouka
if __name__ == "__main__":
etri = ElectreTri(ticino.c, ticino.cv, ticino.ptb, ticino.lbda, ticino.cps)
etri2 = ElectreTri(loulouka.c, loulouka.cv, loulouka.ptb, loulouka.lbda,
loulouka.cps)
worst_ticino = ticino.pt.get_worst(ticino.c)
worst_loulouka = loulouka.pt.get_worst(loulouka.c)
best_ticino = ticino.pt.get_best(ticino.c)
best_loulouka = loulouka.pt.get_best(loulouka.c)
display_electre_tri_models([etri, etri2], [worst_ticino, worst_loulouka],
[best_ticino, best_loulouka])
coal2_ni = list((set(winning) ^ set(win2)) & set(winning))
coal2_add = list((set(winning) ^ set(win2)) & set(win2))
print("Classification accuracy with random profiles: %g" % ca2)
print("Coalitions: total: %d, common: %d, added: %d" % \
(len(win2), (len(winning) - len(coal2_ni)), len(coal2_add)))
# Learn the weights with profiles generated by the heuristic
model3 = model.copy()
heur = HeurMRSortInitProfiles(model3, sorted_pt, aa)
heur.solve()
lp_weights = LpMRSortWeights(model3, pt, aa)
lp_weights.solve()
aa3 = model3.pessimist(pt)
ca3 = compute_ca(aa, aa3)
win3, loose3 = compute_winning_and_loosing_coalitions(model3.cv,
model3.lbda)
coal3_ni = list((set(winning) ^ set(win3)) & set(winning))
coal3_add = list((set(winning) ^ set(win3)) & set(win3))
print("Classification accuracy with heuristic: %g" % ca3)
print("Coalitions: total: %d, common: %d, added: %d" % \
(len(win3), (len(winning) - len(coal3_ni)), len(coal3_add)))
display_electre_tri_models([model], [pt.get_worst(model.criteria)],
[pt.get_best(model.criteria)],
[[ap for ap in model3.bpt]])
