def binary_keyword(text_tag_recommend_model):
# pop
all_mashup_num = len(
text_tag_recommend_model.pd.get_mashup_api_index2name('mashup'))
all_api_num = len(
text_tag_recommend_model.pd.get_mashup_api_index2name('api'))
api_co_vecs, api2pop = text_tag_recommend_model.pd.get_api_co_vecs()
gd = gensim_data(*text_tag_recommend_model.get_instances(
[i for i in range(all_mashup_num)], [i for i in range(all_api_num)],
False))
mashup_binary_matrix, api_binary_matrix, mashup_words_list, api_words_list = gd.get_binary_v(
all_mashup_num, all_api_num)
# 测试WVSM(Weighted Vector Space Model)
candidate_ids_list = []
all_predict_results = []
for i in range(len(Para.test_mashup_id_list)):
test_mashup_id = Para.test_mashup_id_list[i][0] # 每个mashup id
candidate_ids = Para.test_api_id_list[i]
candidate_ids_list.append(candidate_ids)
predict_results = []
for api_id in candidate_ids: # id
sim_score = cos_sim(mashup_binary_matrix[test_mashup_id],
api_binary_matrix[api_id]) * api2pop[api_id]
predict_results.append(sim_score)
all_predict_results.append(predict_results)
print('WVSM test,done!')
evaluate_result = evalute(candidate_ids_list, all_predict_results,
Para.grounds, Para.topKs) # 评价
csv_table_name = Para.data_name + 'WVSM' + "\n" # model.name
summary(Para.evaluate_path, csv_table_name, evaluate_result,
Para.topKs) # 记录
# 测试WJaccard(Weighted Jaccard)
candidate_ids_list = []
all_predict_results = []
for i in range(len(Para.test_mashup_id_list)):
test_mashup_id = Para.test_mashup_id_list[i][0] # 每个mashup id
candidate_ids = Para.test_api_id_list[i]
candidate_ids_list.append(candidate_ids)
predict_results = []
for api_id in candidate_ids: # id
mashup_set = set(mashup_words_list[test_mashup_id])
api_set = set(api_words_list[api_id])
sim_score = 1.0 * len(mashup_set.intersection(api_set)) / len(
mashup_set.union(api_set)) * api2pop[api_id]
predict_results.append(sim_score)
all_predict_results.append(predict_results)
print('WJaccard test,done!')
evaluate_result = evalute(candidate_ids_list, all_predict_results,
Para.grounds, Para.topKs) # 评价
csv_table_name = Para.data_name + 'WJaccard' + "\n" # model.name
summary(Para.evaluate_path, csv_table_name, evaluate_result,
Para.topKs) # 记录
def binary_keyword(if_pop = False):
# pop
api_co_vecs, api2pop = meta_data.pd.get_api_co_vecs ()
gd = get_default_gd()
mashup_binary_matrix, api_binary_matrix, mashup_words_list, api_words_list = gd.get_binary_v ()
# 测试WVSM(Weighted Vector Space Model)
candidate_ids_list = []
all_predict_results=[]
for i in range(len(dataset.crt_ds.test_mashup_id_list)):
test_mashup_id=dataset.crt_ds.test_mashup_id_list[i][0] # 每个mashup id
candidate_ids = dataset.crt_ds.test_api_id_list[i]
candidate_ids_list.append(candidate_ids)
predict_results = []
for api_id in candidate_ids: # id
if if_pop:
sim_score = cos_sim(mashup_binary_matrix[test_mashup_id], api_binary_matrix[api_id]) * api2pop[api_id]
else:
sim_score = cos_sim(mashup_binary_matrix[test_mashup_id], api_binary_matrix[api_id]) # 测试只使用特征向量的效果
predict_results.append(sim_score)
all_predict_results.append(predict_results)
print('WVSM test,done!')
evaluate_result = evalute(candidate_ids_list, all_predict_results, dataset.crt_ds.grounds, new_Para.param.topKs) # 评价
name = 'WVSM_pop' if if_pop else 'WVSM'
csv_table_name = dataset.crt_ds.data_name + name + "\n" # model.name
summary(new_Para.param.evaluate_path, csv_table_name, evaluate_result, new_Para.param.topKs) # 记录
"""
def TF_IDF(if_pop):
"""
可以跟写到Samanta的类中，但太混乱，没必要
:return:
"""
gd = get_default_gd()
api_co_vecs, api2pop = meta_data.pd.get_api_co_vecs()
_mashup_IFIDF_features, _api_IFIDF_features = gd.model_pcs ('TF_IDF')
candidate_ids_list = []
all_predict_results=[]
for i in range(len(dataset.crt_ds.test_mashup_id_list)):
test_mashup_id=dataset.crt_ds.test_mashup_id_list[i][0] # 每个mashup id
candidate_ids = dataset.crt_ds.test_api_id_list[i]
candidate_ids_list.append(candidate_ids)
predict_results = []
for api_id in candidate_ids: # id
sim_score=cos_sim(_mashup_IFIDF_features[test_mashup_id],_api_IFIDF_features[api_id])
if if_pop:
predict_results.append(sim_score*api2pop[api_id])
else:
predict_results.append(sim_score )
predict_results.append(sim_score)
all_predict_results.append(predict_results)
print('TF_IDF test,done!')
name = 'TFIDF_pop' if if_pop else 'TFIDF'
evaluate_result = evalute(candidate_ids_list, all_predict_results, dataset.crt_ds.grounds, new_Para.param.topKs) # 评价
csv_table_name = dataset.crt_ds.data_name + name + "\n" # model.name
summary(new_Para.param.evaluate_path, csv_table_name, evaluate_result, new_Para.param.topKs) # 记录
def hdp_pop(if_pop = True):
# pop
root = os.path.join(dataset.crt_ds.root_path,'baselines')
if not os.path.exists(root):
os.makedirs(root)
mashup_hdp_path=os.path.join(root, 'mashup_HDP.txt') # ...
api_hdp_path = os.path.join(root, 'api_HDP.txt')
_mashup_hdp_features = np.loadtxt (mashup_hdp_path)
_api_hdp_features = np.loadtxt (api_hdp_path)
if if_pop:
api_co_vecs, api2pop = meta_data.pd.get_api_co_vecs ()
# 测试
candidate_ids_list = []
all_predict_results=[]
for i in range(len(dataset.crt_ds.test_mashup_id_list)):
test_mashup_id=dataset.crt_ds.test_mashup_id_list[i][0] # 每个mashup id
candidate_ids = dataset.crt_ds.test_api_id_list[i]
candidate_ids_list.append(candidate_ids)
predict_results = []
for api_id in candidate_ids: # id
sim_score=cos_sim(_mashup_hdp_features[test_mashup_id],_api_hdp_features[api_id])
if if_pop:
sim_score *= api2pop[api_id]
predict_results.append(sim_score)
all_predict_results.append(predict_results)
print('hdp_pop test,done!')
evaluate_result = evalute(candidate_ids_list, all_predict_results, dataset.crt_ds.grounds, new_Para.param.topKs) # 评价
name = 'hdp_pop' if if_pop else 'hdp'
csv_table_name = dataset.crt_ds.data_name + name + "\n" # model.name
summary(new_Para.param.evaluate_path, csv_table_name, evaluate_result, new_Para.param.topKs) # 记录
def pop():
"""
:return:
"""
api_co_vecs, api2pop = meta_data.pd.get_api_co_vecs ()
candidate_ids_list = []
all_predict_results=[]
for i in range(len(dataset.crt_ds.test_mashup_id_list)):
test_mashup_id=dataset.crt_ds.test_mashup_id_list[i][0] # 每个mashup id
candidate_ids = dataset.crt_ds.test_api_id_list[i]
candidate_ids_list.append(candidate_ids)
predict_results = []
for api_id in candidate_ids: # id
predict_results.append(api2pop[api_id])
all_predict_results.append(predict_results)
print('pop test,done!')
evaluate_result = evalute(candidate_ids_list, all_predict_results, dataset.crt_ds.grounds, new_Para.param.topKs) # 评价
csv_table_name = dataset.crt_ds.data_name + 'pop' + "\n" # model.name
summary(new_Para.param.evaluate_path, csv_table_name, evaluate_result, new_Para.param.topKs) # 记录
def TF_IDF(text_tag_recommend_model):
"""
可以跟写到Samanta的类中，但太混乱，没必要
:return:
"""
all_mashup_num = len(
text_tag_recommend_model.pd.get_mashup_api_index2name('mashup'))
all_api_num = len(
text_tag_recommend_model.pd.get_mashup_api_index2name('api'))
gd = gensim_data(*text_tag_recommend_model.get_instances(
[i for i in range(all_mashup_num)], [i for i in range(all_api_num)],
False))
_mashup_IFIDF_features, _api_IFIDF_features = gd.model_pcs(
'TF_IDF', all_mashup_num, all_api_num)
candidate_ids_list = []
all_predict_results = []
for i in range(len(Para.test_mashup_id_list)):
test_mashup_id = Para.test_mashup_id_list[i][0] # 每个mashup id
candidate_ids = Para.test_api_id_list[i]
candidate_ids_list.append(candidate_ids)
predict_results = []
for api_id in candidate_ids: # id
sim_score = cos_sim(_mashup_IFIDF_features[test_mashup_id],
_api_IFIDF_features[api_id])
predict_results.append(sim_score)
all_predict_results.append(predict_results)
print('TF_IDF test,done!')
evaluate_result = evalute(candidate_ids_list, all_predict_results,
Para.grounds, Para.topKs) # 评价
csv_table_name = Para.data_name + 'TF_IDF' + "\n" # model.name
summary(Para.evaluate_path, csv_table_name, evaluate_result,
Para.topKs) # 记录
def MF(train_datas,test_datas,mode = ''):
all_predict_results=[] # 每个测试样例(多个api的)的评分
for slt_num in range(1,new_Para.param.slt_item_num+1): # 不同个数的训练测试集
test_mashup_id_list, test_api_id_list, grounds = test_datas[slt_num-1]
# 增加处理和读取MF结果的接口
UV_obj = get_UV(dataset.crt_ds.root_path, mode,train_datas[slt_num-1],slt_num)
m_id2index,a_id2index = UV_obj.m_id2index,UV_obj.a_id2index
for i in range(len(test_mashup_id_list)):
test_mashup_id=test_mashup_id_list[i][0] # 每个mashup id
predict_results = []
for test_api_id in test_api_id_list[i]: # id
if test_mashup_id not in m_id2index or test_api_id not in a_id2index:
dot = 0
else:
m_embedding = UV_obj.m_embeddings[m_id2index[test_mashup_id]]
a_embedding = UV_obj.a_embeddings[a_id2index[test_api_id]]
dot = np.dot(m_embedding,a_embedding)
predict_results.append(dot)
all_predict_results.append(predict_results)
print('{}_{} test,done!'.format(mode,slt_num))
evaluate_result = evalute(test_api_id_list, all_predict_results, dataset.crt_ds.grounds, new_Para.param.topKs) # 评价
csv_table_name = dataset.crt_ds.data_name + mode + str(slt_num)+ "\n" # model.name
summary(new_Para.param.evaluate_path, csv_table_name, evaluate_result, new_Para.param.topKs) # 记录
def run_new_deepFM(CI_feas,
NI_feas,
train_data,
test_data,
all_api_num,
epoch_num=10):
# config = tf.ConfigProto()
# config.gpu_options.allow_growth = True
# session = tf.Session(config=config)
# graph = tf.get_default_graph()
# set_session(session)
model = simple_DeepFM(CI_feature_num=4,
NI_feature_num=2,
CI_feature_dim=50,
NI_feature_dim=25,
final_feature_dim=32,
task='binary',
use_fm=True,
l2_reg_linear=0,
dnn_hidden_units=[])
model.compile(
"adam",
"binary_crossentropy",
metrics=['binary_crossentropy'],
)
print('bulid simple_DeepFM,done!')
batch_size = 32
len_train = len(train_data[0])
mashup_texts_features, mashup_tag_features, api_texts_features, api_tag_features = CI_feas
mashup_NI_features, api_NI_features = NI_feas
features = [
mashup_texts_features, mashup_tag_features, api_texts_features,
api_tag_features, mashup_NI_features, api_NI_features
]
train_generator = data_generator(train_data,
*features,
bs=batch_size,
all_api_num=all_api_num,
mode="train")
print('genarate train_generator ,done!')
# 每训练一次就测试一次
num_test_instances = getNum_testData(test_data)
for i in range(epoch_num):
history = model.fit_generator(train_generator,
steps_per_epoch=len_train // batch_size,
epochs=1,
verbose=2)
test_generator = data_generator(test_data,
*features,
bs=batch_size,
all_api_num=all_api_num,
mode="test")
print('genarate test_generator,done!')
predictions = model.predict_generator(
test_generator, steps=num_test_instances // batch_size + 1)[:, 1]
print(predictions.shape)
reshaped_predictions = []
# 评价
test_api_id_list, grounds = test_data[1], test_data[-1]
index = 0
for test_api_ids in test_api_id_list:
size = len(test_api_ids) # 当前mashup下的候选api的数目
reshaped_predictions.append(
predictions[index:index +
size]) # min(index + size,len(predictions))
index += size
print(index)
evaluate_result = evalute(test_api_id_list, reshaped_predictions,
grounds, new_Para.param.topKs) # 评价
summary(new_Para.param.evaluate_path, 'deepFM_epoch_{}'.format(i),
evaluate_result, new_Para.param.topKs) #
def Samanta(text_tag_recommend_model, topK, if_pop=False):
"""
:param Para:
:param text_tag_recommend_model: 基于该model的基本数据
:param topK:
:return:
"""
api2pop = None
if if_pop:
api_co_vecs, api2pop = text_tag_recommend_model.pd.get_api_co_vecs()
test_mashup_num = len(Para.test_mashup_id_list)
all_mashup_num = len(
text_tag_recommend_model.pd.get_mashup_api_index2name('mashup'))
all_api_num = len(
text_tag_recommend_model.pd.get_mashup_api_index2name('api'))
mashup_hdp_path = os.path.join(Para.data_dir, 'mashup_hdp.txt')
api_hdp_path = os.path.join(Para.data_dir, 'api_hdp.txt')
# 获取mashup_hdp_features,api_hdp_features
if not os.path.exists(api_hdp_path):
# text,tag在encoding之后的向量，array形式
gd = gensim_data(*text_tag_recommend_model.get_instances(
[i for i in range(all_mashup_num)],
[i for i in range(all_api_num)], False))
_mashup_hdp_features, _api_hdp_features = gd.model_pcs(
'HDP', all_mashup_num, all_api_num)
np.savetxt(mashup_hdp_path, _mashup_hdp_features)
np.savetxt(api_hdp_path, _api_hdp_features)
else:
_mashup_hdp_features = np.loadtxt(mashup_hdp_path)
_api_hdp_features = np.loadtxt(api_hdp_path)
candidate_ids_list = []
all_predict_results = []
for i in range(test_mashup_num):
test_mashup_id = Para.test_mashup_id_list[i][0] # 每个mashup id
candidate_ids = Para.test_api_id_list[i]
candidate_ids_list.append(candidate_ids)
id2sim = {}
for local_train_mashup_index in range(
len(Para.feature_train_mashup_ids)): # u_factors_matrix要用局部索引
id2sim[local_train_mashup_index] = cos_sim(
_mashup_hdp_features[test_mashup_id], _mashup_hdp_features[
Para.feature_train_mashup_ids[local_train_mashup_index]])
topK_indexes, topK_sims = zip(
*(sorted(id2sim.items(), key=lambda x: x[1], reverse=True)[:topK]))
topK_sims = np.array(topK_sims) / sum(topK_sims)
cf_feature = np.zeros((Para.num_feat))
for z in range(len(topK_indexes)):
cf_feature += topK_sims[z] * Para.u_factors_matrix[topK_indexes[z]]
predict_results = []
temp_predict_results = [] # 需要用pop进行重排序时的辅助
api_zeros = np.zeros((Para.num_feat))
for api_id in candidate_ids: # id
api_i_feature = Para.i_factors_matrix[
Para.i_id2index[api_id]] if api_id in Para.i_id2index.keys(
) else api_zeros # 可能存在测试集中的api不在train中出现过的场景
cf_score = np.sum(np.multiply(api_i_feature, cf_feature))
sim_score = cos_sim(_mashup_hdp_features[test_mashup_id],
_api_hdp_features[api_id])
if if_pop:
temp_predict_results.append((api_id, cf_score * sim_score))
else:
predict_results.append(cf_score * sim_score)
if if_pop:
max_k_pairs = heapq.nlargest(topK,
temp_predict_results,
key=lambda x: x[1]) # 根据score选取topK
max_k_candidates, _ = zip(*max_k_pairs)
max_k_candidates = set(max_k_candidates)
predict_results = [
api2pop[api_id] if api_id in max_k_candidates else -1
for api_id in candidate_ids
] # 重排序
all_predict_results.append(predict_results)
print('Samanta test,done!')
evaluate_result = evalute(candidate_ids_list, all_predict_results,
Para.grounds, Para.topKs) # 评价
_name = '_pop' if if_pop else ''
csv_table_name = Para.data_name + 'Samanta_model' + _name + "\n" # model.name
summary(Para.evaluate_path, csv_table_name, evaluate_result,
Para.topKs) # 记录
def Samanta(topK,if_pop=2,MF_mode='node2vec',pop_mode='',text_mode='HDP',LDA_topic_num=None):
"""
:param Para:
:param if_pop 如何使用pop 0 不使用；1，只做重排序；2总乘积做排序
:param topK: 使用KNN表示新query的mf特征
:param text_mode: 使用哪种特征提取方式 LDA HDP
:param pop_mode：pop值是否使用sigmoid规约到0-1区间
:param pop_mode：MF_mode 为了省事，直接用node2vec得了
:return:
"""
api2pop=None
if if_pop:
api_co_vecs, api2pop = meta_data.pd.get_api_co_vecs (pop_mode)
root = os.path.join(dataset.crt_ds.root_path,'baselines')
if not os.path.exists(root):
os.makedirs(root)
mashup_feature_path=os.path.join(root, 'mashup_{}.txt'.format(text_mode)) # ...
api_feature_path = os.path.join(root, 'api_{}.txt'.format(text_mode))
# 获取mashup_hdp_features,api_hdp_features
if not os.path.exists(api_feature_path):
gd=get_default_gd()
_mashup_features,_api_features=gd.model_pcs(text_mode,LDA_topic_num)
np.savetxt(mashup_feature_path,_mashup_features)
np.savetxt(api_feature_path, _api_features)
else:
_mashup_features=np.loadtxt(mashup_feature_path)
_api_features=np.loadtxt(api_feature_path)
# Para.set_MF_mode(MF_mode) # 设置latent factor
# new_Para.param.mf_mode = MF_mode # 修改参数对象，慎用
candidate_ids_list = []
all_predict_results=[]
test_mashup_num = len(dataset.crt_ds.test_mashup_id_list)
for i in range(test_mashup_num):
test_mashup_id=dataset.crt_ds.test_mashup_id_list[i][0] # 每个mashup id
candidate_ids = dataset.crt_ds.test_api_id_list[i]
candidate_ids_list.append(candidate_ids)
# 用近邻mashup的latent factor加权表示自己
localIndex2sim={}
for local_index,train_m_id in enumerate(dataset.UV_obj.m_ids): # u_factors_matrix要用局部索引
localIndex2sim[local_index]=cos_sim(_mashup_features[test_mashup_id],_mashup_features[train_m_id])
topK_indexes,topK_sims=zip(*(sorted(localIndex2sim.items(), key=lambda x: x[1], reverse=True)[:topK]))
topK_sims=np.array(topK_sims)/sum(topK_sims) # sim归一化
cf_feature=np.zeros((new_Para.param.num_feat,))
for z in range(len(topK_indexes)):
cf_feature+= topK_sims[z] * dataset.UV_obj.m_embeddings[topK_indexes[z]]
# 计算跟每个api的打分
predict_results = []
temp_predict_results=[] # 需要用pop进行重排序时的辅助
api_zeros=np.zeros((new_Para.param.num_feat))
for api_id in candidate_ids: # id
a_id2index = dataset.UV_obj.a_id2index
api_i_feature= dataset.UV_obj.a_embeddings[a_id2index[api_id]] if api_id in a_id2index.keys() else api_zeros # 可能存在测试集中的api不在train中出现过的场景
cf_score=np.sum(np.multiply(api_i_feature, cf_feature)) # mashup和api latent factor的内积
sim_score=cos_sim(_mashup_features[test_mashup_id],_api_features[api_id]) # 特征的余弦相似度
if if_pop==1:
temp_predict_results.append((api_id,cf_score*sim_score))
elif if_pop==0:
predict_results.append(cf_score*sim_score)
elif if_pop == 2:
predict_results.append (cf_score * sim_score*api2pop[api_id])
if if_pop==1:
max_k_pairs = heapq.nlargest (topK, temp_predict_results, key=lambda x: x[1]) # 首先利用乘积排一次序
max_k_candidates, _ = zip (*max_k_pairs)
max_k_candidates=set(max_k_candidates)
predict_results=[api2pop[api_id] if api_id in max_k_candidates else -1 for api_id in candidate_ids] # 重排序
all_predict_results.append(predict_results)
print('Samanta test,done!')
evaluate_result = evalute(candidate_ids_list, all_predict_results, dataset.crt_ds.grounds, new_Para.param.topKs) # 评价
_name='_pop_{}'.format(if_pop)
_name+= new_Para.param.mf_mode
csv_table_name = dataset.crt_ds.data_name + 'Samanta_model_{}'.format(topK)+_name + "\n" # model.name
summary(new_Para.param.evaluate_path, csv_table_name, evaluate_result, new_Para.param.topKs) # 记录
def divide(slt_apiNum):
test_api_id_list_, predictions_, grounds_ = [], [], []
for i in range(test_mashup_num):
if len(dataset.crt_ds.slt_api_ids_instances[i]) == slt_apiNum:
test_api_id_list_.append(candidate_ids_list[i])
predictions_.append(all_predict_results[i])
grounds_.append(dataset.crt_ds.grounds[i])
return test_api_id_list_, predictions_, grounds_
if new_Para.param.data_mode == 'newScene':
for slt_apiNum in range(3):
test_api_id_list_, predictions_, grounds_ = divide(slt_apiNum+1)
evaluate_result = evalute(test_api_id_list_, predictions_, grounds_, new_Para.param.topKs)
summary(new_Para.param.evaluate_path, str(slt_apiNum+1)+'_'+csv_table_name, evaluate_result, new_Para.param.topKs) #