def make_voter(estimators, y, voting='hard'):
estimators = list(estimators.items())
clf = VotingClassifier(estimators, voting)
clf.estimators_ = [estim for name, estim in estimators]
clf.le_ = LabelEncoder()
clf.le_.fit(y)
clf.classes_ = clf.le_.classes_
return clf
def _oos_eval(self, clfs, func, meta=False, *args, **kwargs):
# If we're in the meta case, just call this several times regularly
if meta:
oos = []
# Jackknife for proportionally fewer cases in meta eval
for _ in range(int(np.ceil(self.n_jack*self.n_oos))):
tmpclf, tmpoos = self._oos_eval(clfs, func, meta=False,
*args, **kwargs)
clf = tmpclf
oos += [tmpoos]
del tmpoos
return clf, oos
# Generate test / oos data
oos = {}
Xo, yo, grpo = self._prep_data(self.dat_t, self.tar_t, self.sam_t,
func, *args, **kwargs)
# Aggregate classifiers across folds and pre-load training
clf = VotingClassifier(voting='soft',
estimators=[(i, c) for i, c in enumerate(clfs)])
clf.estimators_ = clfs
clf.le_ = LabelEncoder().fit(yo)
clf.classes_ = clf.le_.classes_
# Evaluate voting classifier on test data
pred = clf.predict(Xo)
oos['true'] = yo
oos['pred'] = pred
oos['acc'] = accuracy_score(yo, pred)
oos['f1'] = f1_score(yo, pred)
# Compare to mean oos-performance of component classifiers
comp_preds = [c.predict(Xo) for c in clfs]
oos['comp_acc'] = np.mean([accuracy_score(yo, cp) for cp in comp_preds])
oos['comp_f1'] = np.mean([f1_score(yo, cp) for cp in comp_preds])
f1p, accp = self.performanceP(yo, oos['f1'], oos['acc'])
oos['p_f1'] = f1p
oos['p_acc'] = accp
# Print performance
if self.verbose:
print("Y: ", pred, "->", yo)
print("G: ", grpo)
print("Test Accuracy: {0} (p <= {1})".format(oos['acc'], accp))
print("Test F1: {0} (p<= {1})".format(oos['f1'], f1p))
return clf, oos
def train_ensemble_classifier(training_data, forest, dtree, adaboost,
extra_random, gnb, regression):
ensemble = VotingClassifier(estimators=[('rf', forest), ('dt', dtree),
('et', extra_random), ('gnb', gnb),
('lr', regression)],
voting='hard')
ensemble.classes_ = [0, 1]
scores = cross_val_score(ensemble,
training_data[:,
selected_features].astype('float'),
training_data[:, -1].astype('float'),
cv=5,
scoring='roc_auc')
print("Scores gotten using Ensemble classifier")
print(str(scores))
print(np.mean(scores))
return adaboost
