def pre_training_without_SMOTE(self, pre_training_ratio):
clf = ElasticNet(max_iter=10000)
# self.smote_for_positive()
positive_index = np.where(self.labels == 1)
self.labels = [0 if label == -1 else label for label in self.labels]
# verify the count of labeling negative
label_negative_count = int(pre_training_ratio *
np.bincount(self.labels)[0])
# fit pre-training model
clf.fit(self.samples, self.labels)
# get and sort distances
distances = clf._decision_function(self.samples)
distances_copy = distances.copy()
distances_copy.sort()
# get threshold
negative_threshold = distances_copy[label_negative_count]
self.labels = np.array(
[-1 if label == 0 else label for label in self.labels])
label_negative_count_cur = 0
for i in range(self.length):
if label_negative_count_cur >= label_negative_count:
break
if distances[i] <= negative_threshold and i not in positive_index[
0]:
self.labels[i] = 0
label_negative_count_cur += 1
print Counter(self.labels)
return self.labels[:self.length]
def pre_training(self, pre_training_ratio):
# clf = SVC(kernel='linear', probability=True, class_weight='balanced')
# clf = SGDClassifier(loss='log', max_iter=10000)
# clf = LogisticRegression(max_iter=10000)
clf = ElasticNet(max_iter=10000)
# clf = RandomForestClassifier()
self.smote_for_positive()
positive_index = np.where(self.labels == 1)
self.labels = [0 if label == -1 else label for label in self.labels]
# verify the count of labeling negative
label_negative_count = int(pre_training_ratio *
np.bincount(self.labels)[0])
# fit pre-training model
clf.fit(self.samples, self.labels)
# get and sort distances
distances = clf._decision_function(self.samples)
# proba = clf.predict_proba(self.samples)
# print [distances[index] for index in positive_index]
distances_copy = distances.copy()
distances_copy.sort()
# get threshold
negative_threshold = distances_copy[label_negative_count]
self.labels = np.array([
0 if distance < negative_threshold else -1
for distance in distances
])
self.labels[positive_index] = 1
return self.labels[:self.length]
def add_reliable_samples(self,
class_prior,
speed,
add_ratio,
real_label,
model=RandomForestClassifier(n_estimators=100)):
max_label_count = int(add_ratio * self.length)
label_count = 0
positive_label_count = 0
positive_count_each_round = int(speed * class_prior)
negative_count_each_round = int(speed * (1 - class_prior))
while label_count < max_label_count:
self.smote_for_positive()
labeled_index = np.where(self.labels != -1)[0]
unlabeled_index = np.where(self.labels == -1)[0]
labeled_set = self.samples[labeled_index]
unlabeled_set = self.samples[unlabeled_index]
if len(unlabeled_set) == 0:
break
'''
random forest
'''
clf = model
clf.fit(labeled_set, self.labels[np.where(self.labels != -1)])
prob_list = clf.predict_proba(unlabeled_set)
prob_list = np.array([prob[1] for prob in prob_list])
'''
linear model
'''
clf_2 = ElasticNet(max_iter=10000)
clf_2.fit(labeled_set, self.labels[np.where(self.labels != -1)])
dis_list = clf_2._decision_function(unlabeled_set)
distance_list = prob_list.tolist()
distance_list.sort()
'''get the index of positive and negative index in unlabeled samples'''
negative_threshold = distance_list[negative_count_each_round - 1]
positive_threshold = distance_list[-positive_count_each_round]
'''use linear model select samples'''
select_dis_list = dis_list[np.where(
prob_list <= negative_threshold)].tolist()
select_dis_list.sort()
negative_dis_threshold = select_dis_list[negative_count_each_round
- 1]
select_dis_list = dis_list[np.where(
prob_list >= positive_threshold)].tolist()
select_dis_list.sort()
positive_dis_threshold = select_dis_list[
-positive_count_each_round]
positive_count_cur = 0
negative_count_cur = 0
for i in range(len(prob_list)):
if prob_list[i] <= negative_threshold and dis_list[
i] <= negative_dis_threshold and negative_count_cur < negative_count_each_round:
label_count += 1
negative_count_cur += 1
self.labels[unlabeled_index[i]] = 0
elif prob_list[i] >= positive_threshold and dis_list[
i] >= positive_dis_threshold and positive_count_cur < positive_count_each_round:
label_count += 1
positive_label_count += 1
positive_count_cur += 1
self.labels[unlabeled_index[i]] = real_label[
unlabeled_index[i]]
print real_label[unlabeled_index[i]]
if label_count > max_label_count:
break
print max(distance_list), min(distance_list)
print label_count, positive_label_count
print 'finish add reliable samples'
return self.labels[:self.length], positive_label_count
