def get_AL_predict(test_feature, choose_feature, unlabel_feature, test_query, choose_query, choose_answer, unlabel_query, unlabel_answer, rec_api_test, rec_api_choose, rec_api_unlabel, w2v, idf):
unlabel_feedback_info = feedback.get_feedback_inf(unlabel_query, choose_query, choose_answer, rec_api_unlabel, w2v, idf)
label_feedback_info = feedback.get_feedback_inf(choose_query, choose_query, choose_answer, rec_api_choose, w2v, idf)
X_train, y_train = braid_AL.get_active_data(unlabel_feedback_info, unlabel_feature)
X_feedback, y_feedback = braid_AL.get_active_data(label_feedback_info, choose_feature)
# initializing the active learner
learner = ActiveLearner(
estimator=KNeighborsClassifier(n_neighbors=4),
# estimator=LogisticRegression(penalty='l1', solver='liblinear'),
X_training=X_feedback, y_training=y_feedback
)
length = len(rec_api_test)
predict, sel_query, add_unlabel_feature = [], [], []
if len(unlabel_query) > 0:
# pool-based sampling
n_queries = 40
for idx in range(n_queries):
query_idx, query_instance = uncertainty_sampling(classifier=learner, X=X_train)
idx = int(query_idx/10)
learner.teach(
X=X_train[query_idx].reshape(1, -1),
y=y_train[query_idx].reshape(1, )
)
# add queried instance into FR
choose_query.append(unlabel_query[idx])
choose_answer.append(unlabel_answer[idx])
rec_api_choose.extend(rec_api_unlabel[idx*10:idx*10+10])
choose_feature.extend(unlabel_feature[idx*10:idx*10+10])
# remove queried instance from pool
for i in range(10):
X_train = np.delete(X_train, idx*10, axis=0)
y_train = np.delete(y_train, idx*10)
del unlabel_query[idx]
del unlabel_answer[idx]
del rec_api_unlabel[idx*10:idx*10+10]
del unlabel_feature[idx*10:idx*10+10]
if len(X_train) == 0:
break
add_label_feedback_info = feedback.get_feedback_inf(choose_query, choose_query, choose_answer, rec_api_choose, w2v, idf)
new_X_feedback, new_y_feedback = braid_AL.get_active_data(add_label_feedback_info, choose_feature)
learner = ActiveLearner(
estimator=KNeighborsClassifier(n_neighbors=4),
# estimator=LogisticRegression(penalty='l1', solver='liblinear'),
X_training=new_X_feedback, y_training=new_y_feedback
)
feedback_info = feedback.get_feedback_inf(test_query, choose_query, choose_answer, rec_api_test, w2v, idf)
X = split_data.get_test_feature_matrix(feedback_info, test_feature)
X_test = np.array(X)
# 用反馈数据学习过后的模型来预测测试数据
for query_idx in range(length):
try:
y_pre = learner.predict_proba(X=X_test[query_idx].reshape(1, -1))
except ValueError:
predict = [0.0 for n in range(length)]
else:
predict.append(float(y_pre[0, 1]))
return predict, X, new_X_feedback, new_y_feedback
def get_AL_predict(test_feature, choose_feature, unlabel_feature, test_query, choose_query, choose_answer, unlabel_query, unlabel_answer, rec_api_test, rec_api_choose, rec_api_unlabel, w2v, idf):
unlabel_feedback_info = feedback.get_feedback_inf(unlabel_query, choose_query, choose_answer, rec_api_unlabel, w2v, idf)
label_feedback_info = feedback.get_feedback_inf(choose_query, choose_query, choose_answer, rec_api_choose, w2v, idf)
X_train, y_train = get_active_data(unlabel_feedback_info, unlabel_feature)
X_feedback, y_feedback = get_active_data(label_feedback_info, choose_feature)
# initializing the active learner
learner = ActiveLearner(
# estimator=KNeighborsClassifier(n_neighbors=4),
estimator=LogisticRegression(penalty='l1', solver='liblinear'),
X_training=X_feedback, y_training=y_feedback
)
predict, sel_query, add_unlabel_feature = [], [], []
if len(unlabel_query) > 0:
# pool-based sampling
n_queries = 100
sel_idx, sel_label = [], []
for idx in range(n_queries):
# query_idx, query_instance = learner.query(X=X_train)
query_idx, query_instance = uncertainty_sampling(classifier=learner, X=X_train)
idx = int(query_idx/10)
# print(idx, len(X_train))
# print('uncertain', query_idx, X_train[query_idx], y_train[query_idx])
learner.teach(
X=X_train[query_idx].reshape(1, -1),
y=y_train[query_idx].reshape(1, )
)
# add queried instance into FR
choose_query.append(unlabel_query[idx])
choose_answer.append(unlabel_answer[idx])
rec_api_choose.extend(rec_api_unlabel[idx*10:idx*10+10])
choose_feature.extend(unlabel_feature[idx*10:idx*10+10])
# learner.teach(
# X=new_X_train.reshape(1, -1),
# y=new_y_train.reshape(1, )
# )
# print(unlabel_query[idx], unlabel_query[idx], rec_api_unlabel[idx*10:idx*10+10], rec_api_unlabel[idx*10:idx*10+10])
# remove queried instance from pool
for i in range(10):
X_train = np.delete(X_train, idx*10, axis=0)
y_train = np.delete(y_train, idx*10)
del unlabel_query[idx]
del unlabel_answer[idx]
del rec_api_unlabel[idx*10:idx*10+10]
del unlabel_feature[idx*10:idx*10+10]
if len(X_train) == 0:
break
add_label_feedback_info = feedback.get_feedback_inf(choose_query, choose_query, choose_answer, rec_api_choose, w2v, idf)
new_X_feedback, new_y_feedback = get_active_data(add_label_feedback_info, choose_feature)
learner = ActiveLearner(
# estimator=KNeighborsClassifier(n_neighbors=4),
estimator=LogisticRegression(penalty='l1', solver='liblinear'),
X_training=new_X_feedback, y_training=new_y_feedback
)
feedback_info = feedback.get_feedback_inf(test_query, choose_query, choose_answer, rec_api_test, w2v, idf)
X = split_data.get_test_feature_matrix(feedback_info, test_feature)
X_test = np.array(X)
# 用反馈数据学习过后的模型来预测测试数据
for query_idx in range(400):
y_pre = learner.predict_proba(X=X_test[query_idx].reshape(1, -1))
predict.append(float(y_pre[0, 1]))
# predict.append(math.log(float(y_pre[0, 1])+1))
# predict.extend(y_pre.tolist())
x = X_test[query_idx].reshape(1, -1)
# print(predict)
# print('new_choose', len(choose_query), len(choose_answer))
# fw = open('../data/add_FR.csv', 'a+', newline='')
# writer = csv.writer(fw)
# for i, fr_q in enumerate(choose_query):
# writer.writerow((fr_q, choose_answer[i]))
# fw.close()
return predict, X, new_X_feedback, new_y_feedback #sorted(sel_query)