file,
generation=20,
scale=20,
conjunction=False,
maxsat_on=True,
tailor=False,
fitness_func='Pro')
param = m.pso()
phi = param[0]
theta = param[1]
psi = param[2]
k = param[3]
ex = Extractor(clf, phi, theta, psi)
ex.extract_forest_paths()
ex.rule_filter()
print('max_rule', ex.max_rule, 'max_node', ex.max_node)
print("original path number: ", ex.n_original_leaves_num)
print('original scale: ', ex.scale)
print("original path number after rule filter: ", len(ex._forest_values))
sat = Z3Process(ex, k)
sat.leaves_partition()
sat.maxsat()
sat.run_filter()
print("original path number after maxsat: ", sat.n_rules_after_max,
" after filter: ", sat.n_rules_after_filter, '\n')
print('classes:', clf.classes_)
f = FormulaeEstimator(sat, conjunction=True, classes=clf.classes_)
def explain(self, param, label='', auc_plot=False):
print('------------ Explanation -------------')
self._file.write('------------ Explanation -------------\n')
phi = param[0]
theta = param[1]
psi = param[2]
k = param[3]
start1 = time()
ex = Extractor(self._clf, phi, theta, psi)
ex.extract_forest_paths()
ex.rule_filter()
print('max_rule', ex.max_rule, 'max_node', ex.max_node)
print('min_rule', ex.min_rule, 'min_node', ex.min_node)
end1 = time()
print("EX Running time: %s seconds" % (end1 - start1))
print("original path number: ", ex.n_original_leaves_num)
print("original scale: ", ex.scale)
print("path number after rule filter: ", len(ex._forest_values))
self._file.write('original path number: {}\n'.format(
ex.n_original_leaves_num))
self._file.write('original scale: {}\n'.format(ex.scale))
self._file.write('path number after rule filter: {}\n'.format(
len(ex._forest_values)))
start2 = time()
sat = Z3Process(ex, k)
sat.leaves_partition()
if self._maxsat_on is True:
sat.maxsat()
print("path number after maxsat: ", sat.n_rules_after_max,
" after filter: ", sat.n_rules_after_filter, '\n')
self._file.write(
'path number after maxsat: {}\tafter filter: {}\n\nclasses:\t{}\n\n'
.format(sat.n_rules_after_max, sat.n_rules_after_filter,
self._clf.classes_))
else:
print('no maxsat')
self._file.write('/no MAX-SAT\n')
sat.run_filter()
end2 = time()
print("SAT Running time: %s seconds" % (end2 - start2))
print('classes:', self._clf.classes_)
start3 = time()
f = FormulaeEstimator(sat,
conjunction=self._conjunction,
classes=self._clf.classes_)
f.get_formulae_text(self._file)
print('\n------------ Performance -------------')
self._file.write('\n------------ Performance -------------\n')
c_ans = self._clf.predict(self._X_test)
ans = f.classify_samples(self._X_test)
end3 = time()
print("ET Running time: %s seconds" % (end3 - start3))
RF_accuracy = accuracy_score(self._y_test, c_ans)
EX_accuracy = accuracy_score(self._y_test, ans)
performance = accuracy_score(c_ans, ans)
no_ans = 0
overlap = 0
for each in f.sat_group:
if len(each) > 1:
overlap += 1
elif len(each) == 0:
no_ans += 1
if label == '': # 计算AUC
label = self._clf.classes_[0]
fpr, tpr, thresholds = roc_curve(self._y_test,
self._clf.predict_proba(
self._X_test)[:, 1],
pos_label=label)
ori_auc = auc(fpr, tpr)
ex_test = f.classify_samples_values(self._X_test)
efpr, etpr, ethresholds = roc_curve(self._y_test,
ex_test[:, 1],
pos_label=label)
ex_auc = auc(efpr, etpr)
print('sample size:\t', len(self._y_test))
self._file.write('sample size:\t{}\n'.format(len(self._y_test)))
print('RF accuracy:\t', RF_accuracy)
self._file.write('RF accuracy:\t{}\n'.format(RF_accuracy))
print('RF AUC:\t\t\t', ori_auc)
self._file.write('RF AUC:\t\t\t{:.2f}\n'.format(ori_auc))
# print('错误结果覆盖：', f_count)
print('EX accuracy:\t', EX_accuracy)
self._file.write('EX accuracy:\t{}\n'.format(EX_accuracy))
print('EX AUC:\t\t\t', ex_auc)
self._file.write('EX AUC:\t\t\t{:.2f}\n'.format(ex_auc))
print('Coverage:\t\t',
(len(self._y_test) - no_ans) / len(self._y_test))
self._file.write('Coverage:\t\t{}\n'.format(
(len(self._y_test) - no_ans) / len(self._y_test)))
print('Overlap:\t\t', overlap / len(self._y_test))
self._file.write('Overlap:\t\t{}\n'.format(overlap /
len(self._y_test)))
print('*Performance:\t', performance)
self._file.write('*Performance:\t{}\n'.format(performance))
if auc_plot is True:
plt.plot(fpr,
tpr,
linewidth=2,
label="RF ROC curve (area = {:.2f})".format(ori_auc))
plt.plot(efpr,
etpr,
linewidth=2,
label="Explain ROC curve (area = {:.2f})".format(ex_auc))
plt.xlabel("false positive rate")
plt.ylabel("true positive rate")
plt.ylim(0, 1.05)
plt.xlim(0, 1.05)
plt.legend(loc=4) # 图例的位置
plt.show()
