def text2feat(api, api_descriptions, w2v, idf, query_matrix, query_idf_vector):
api_matrix, api_idf_vector = feedback.load_matrix(api, w2v, idf)
api_descriptions_matrix, api_descriptions_idf_vector = feedback.load_matrix(
api_descriptions, w2v, idf)
# 获取api及doc信息并计算其相似度，相关问题在推荐中已经获得
api_sim = similarity.sim_doc_pair(query_matrix, api_matrix,
query_idf_vector, api_idf_vector)
if api_descriptions == 'null':
api_desc_sim = 0
else:
api_desc_sim = similarity.sim_doc_pair(query_matrix,
api_descriptions_matrix,
query_idf_vector,
api_descriptions_idf_vector)
# 将获得信息按api为一列放入sum_inf中
sum_inf = list()
sum_inf.append(api_sim)
sum_inf.append(api_desc_sim)
# 将所有特征封装成字典并返回，这样得到特征之后能直接输出topn的相关特征
api_inf = dict()
api_desc_inf = dict()
api_inf[api] = api_sim
api_desc_inf[api_descriptions] = api_desc_sim
return sum_inf, api_inf, api_desc_inf
def process_input(msg='how to convert int to string?'):
global rerank
global responseToClient
global g_query_str
global feedback_inf
global api_feature
global sort
query = msg
query_matrix, query_idf_vector = feedback.load_matrix(query, w2v, idf)
top_questions = recommendation.get_topk_questions(query, query_matrix, query_idf_vector, questions, 50, parent)
recommended_api = recommendation.recommend_api(query_matrix, query_idf_vector, top_questions, questions, javadoc,javadoc_dict_methods,-1)
# recommended_api = recommendation.recommend_api_class(query_matrix, query_idf_vector, top_questions, questions, javadoc,javadoc_dict_classes,-1)
# combine api_relevant feature with FF
pos = -1
rec_api = []
api_dict_desc = {}
x, api_feature, responseToClient = [], [], []
for i,api in enumerate(recommended_api):
# print('Rank',i+1,':',api)
rec_api.append(api)
# recommendation.summarize_api_method(api,top_questions,questions,javadoc,javadoc_dict_methods)
api_descriptions, questions_titles = recommendation.summarize_api_method(api, top_questions, questions, javadoc,
javadoc_dict_methods)
api_dict_desc[api] = api_descriptions
sum_inf, api_inf, api_desc_inf = text2feat(api, api_descriptions, w2v, idf, query_matrix, query_idf_vector)
api_feature.append(sum_inf)
# print(api_feature)
if i == 9:
break
# print('##################')
start1 = time.time()
# feedback info of user query from SO
fr = open('../data/feedback_all.csv', 'r')
reader = csv.reader(fr)
so_query, so_answer = [], []
for row in reader:
so_query.append(row[0])
so_answer.append(row[1:])
# feedback info of user query from FR
fr = open('../data/feedback_rec.csv', 'r')
reader = csv.reader(fr)
choose_query, choose_answer = [], []
for row in reader:
choose_query.append(row[0])
choose_answer.append(row[1:])
feedback_inf = feedback.get_feedback_inf(query, choose_query, choose_answer, rec_api, w2v, idf)
# FV = RF+FF
for i in range(len(api_feature)):
sum = api_feature[i]
sum.extend(feedback_inf[i])
x.append(sum)
# feature info of FR
fr = open('../data/feedback_feature_rec.csv', 'r')
reader = csv.reader(fr)
y_feature, x_feautre, api_relevant_feature, rec_api_choose = [], [], [], []
for row in reader:
# y_feature.append(row[0])
x_feautre.append(row[:-1])
api_relevant_feature.append(row[1:3])
rec_api_choose.append(row[-1])
#feature info of SO
fr = open('../data/get_feature_method.csv', 'r')
reader = csv.reader(fr)
unlabel_feature, rec_api_unlabel = [], []
for row in reader:
# y_feature.append(row[0])
unlabel_feature.append(row[:-1])
rec_api_unlabel.append(row[-1])
# AL_choose_feature, AL_unlabel_feature = split_data.get_choose(AL_train_feature, choose)
pred2, add_x_FR, add_x_FV, add_y_FV = get_AL_predict(x, x_feautre, unlabel_feature, query, choose_query, choose_answer, so_query, so_answer, rec_api, rec_api_choose, rec_api_unlabel, w2v, idf)
pred1 = braid_LTR.get_LTR_predict(add_x_FR, add_x_FV, add_y_FV)
rem = -10
rec, rec_LTR, rec_AL = [], [], []
sort, sort_LTR, sort_AL = [], [], []
pred = []
sum_pred1, sum_pred2 = 0, 0
for i in range(len(api_feature)):
sum_pred1 += pred1[i]+5
sum_pred2 += pred2[i]
al_idx = []
rerank_al = sorted(pred2, reverse=True)
for i in range(len(api_feature)):
temp = rerank_al.index(pred2[i])+1
while temp in al_idx:
temp += 1
al_idx.append(temp)
m = 0.6
for num in range(len(api_feature)):
sum = (pred1[num]+5)/len(api_feature) + m*pred2[num]/al_idx[num]
pred.append(sum)
for i in range(len(api_feature)):
sort.append(pred.index(max(pred)) + 1)
sort_LTR.append(pred1.index(max(pred1)) + 1)
sort_AL.append(pred2.index(max(pred2)) + 1)
rec.append(max(pred))
rec_LTR.append(max(pred1))
rec_AL.append(max(pred2))
pred[pred.index(max(pred))] = rem
pred1[pred1.index(max(pred1))] = rem
pred2[pred2.index(max(pred2))] = rem
# 将api重新排序，输出相关结果
for i in sort:
api_mod = rec_api[i-1]
print(sort.index(i) + 1, api_mod)
api_obj = {'id':sort.index(i) + 1, 'api':api_mod, 'desc':api_dict_desc[api_mod] }
rerank.append(api_mod)
responseToClient.append(api_obj)
print(type(rerank))
print(json.dumps(rerank))
print(rerank)
print(responseToClient)
return responseToClient
except ValueError:
predict = [0.0 for n in range(length)]
# print('Input the error query')
else:
predict.append(float(y_pre[0, 1]))
return predict, X, new_X_feedback, new_y_feedback
while True:
print('Please input your query:')
query = input()
# query = 'how to convert int to string?'
if not query:
continue
query_matrix, query_idf_vector = feedback.load_matrix(query, w2v, idf)
top_questions = recommendation.get_topk_questions(query, query_matrix,
query_idf_vector,
questions, 50, parent)
recommended_api = recommendation.recommend_api(query_matrix,
query_idf_vector,
top_questions, questions,
javadoc,
javadoc_dict_methods, -1)
# recommended_api = recommendation.recommend_api_class(query_matrix, query_idf_vector, top_questions, questions, javadoc,javadoc_dict_classes,-1)
# combine api_relevant feature with FF
pos = -1
rec_api = []
api_dict_desc = {}