def main(self):
user_ratings_train = self.load_data(self.train_data_path)
self.load_test_data(self.test_data_path)
for u in range(self.user_count):
for item in range(self.item_count):
if int(self.test_data[u][item]) == 1:
self.test[u * self.item_count + item] = 1
else:
self.test[u * self.item_count + item] = 0
for i in range(self.user_count * self.item_count):
self.test[i] = int(self.test[i])
# training
for i in range(self.train_count):
if random.randint(1, i + 2) > i:
self.set_up()
self.train(user_ratings_train)
predict_matrix = self.predict(self.U, self.V)
# prediction
self.predict_ = predict_matrix.getA().reshape(-1)
self.predict_ = pre_handel(user_ratings_train, self.predict_,
self.item_count)
auc_score = roc_auc_score(self.test, self.predict_)
print('AUC:', auc_score)
# Top-K evaluation
str(
scores.topK_scores(self.test, self.predict_, 20, self.user_count,
self.item_count))
def main(self):
user_ratings_train = self.load_data(
self.train_data_path
) #将训练集变为{u1:{i_1,i_3,...},u2:{i_2,i_6,...},...}的形式
self.load_test_data(self.test_data_path) #将测试集数据以二维矩阵的形式存在test_data中
for u in range(self.user_count):
for item in range(self.item_count):
if int(self.test_data[u][item]) == 1: #对于存在于测试集的物品在一维test中标记为1
self.test[u * self.item_count + item] = 1
else: #不存在标记为0
self.test[u * self.item_count + item] = 0
# training
for i in range(self.train_count): #迭代次数
self.train(user_ratings_train)
predict_matrix = self.predict(self.U, self.V)
# prediction 模型评价
self.predict_ = predict_matrix.getA().reshape(-1)
self.predict_ = pre_handel(user_ratings_train, self.predict_,
self.item_count)
auc_score = roc_auc_score(self.test, self.predict_)
print('AUC:', auc_score)
# Top-K evaluation 自定义模型评价
str(
scores.topK_scores(self.test, self.predict_, 5, self.user_count,
self.item_count))
def main(self):
user_ratings_train = self.load_data(self.train_data_path)
self.load_test_data(self.test_data_path)
tbar_1 = tqdm(total=self.user_count * self.item_count)
for u in range(self.user_count):
for item in range(self.item_count):
tbar_1.update(1)
if int(self.test_data[u][item]) == 1:
self.test[u * self.item_count + item] = 1
else:
self.test[u * self.item_count + item] = 0
tbar_1.close()
# training
max_re_count = 30
tbar_2 = tqdm(total=self.train_count * max_re_count)
wb = Workbook()
sheet = wb.active
sheet.title = "New Shit"
re_count = 3
for t in range(max_re_count):
for i in range(self.train_count):
if random.randint(1, i + 2) > i:
self.set_up()
tbar_2.update(1)
self.train(user_ratings_train)
predict_matrix = self.predict(self.U, self.V)
# prediction
self.predict_ = predict_matrix.getA().reshape(-1)
self.predict_ = pre_handel(user_ratings_train, self.predict_,
self.item_count)
auc_score = roc_auc_score(self.test, self.predict_)
print('AUC:', auc_score)
# Top-K evaluation
# str(scores.topK_scores(self.test, self.predict_, 5, self.user_count, self.item_count))
MAP, MRR, Prec, Rec, F1, NDCG, l_call = scores.topK_scores(
self.test, self.predict_, re_count, self.user_count,
self.item_count)
sheet["A%d" % (t + 1)].value = re_count
sheet["B%d" % (t + 1)].value = auc_score
sheet["C%d" % (t + 1)].value = MAP
sheet["D%d" % (t + 1)].value = MRR
sheet["E%d" % (t + 1)].value = Prec
sheet["F%d" % (t + 1)].value = Rec
sheet["G%d" % (t + 1)].value = F1
sheet["H%d" % (t + 1)].value = NDCG
sheet["I%d" % (t + 1)].value = l_call
if re_count > 30:
break
re_count += 1
# self.U = np.random.rand(self.user_count, self.latent_factors) * 0.01
self.U = np.loadtxt("U.txt")
# self.V = np.random.rand(self.item_count, self.latent_factors) * 0.01
self.V = np.loadtxt("V.txt")
# self.biasV = np.random.rand(self.item_count) * 0.01
self.biasV = np.loadtxt("biasV.txt")
wb.save("MPR各评价标准.xlsx")
wb.close()
tbar_2.close()
def main(self):
user_ratings_train = self.load_data(self.train_data_path)
self.load_test_data(self.test_data_path)
tbar_1 = tqdm(total=self.user_count * self.item_count)
for u in range(self.user_count):
for item in range(self.item_count):
tbar_1.update(1)
if int(self.test_data[u][item]) == 1:
self.test[u * self.item_count + item] = 1
else:
self.test[u * self.item_count + item] = 0
tbar_1.close()
# training
tbar_2 = tqdm(total=self.train_count)
re_count = 5
for i in range(self.train_count):
if random.randint(1, i + 2) > i:
self.set_up()
tbar_2.update(1)
self.train(user_ratings_train)
predict_matrix = self.predict(self.U, self.V)
# prediction
self.predict_ = predict_matrix.getA().reshape(-1)
self.predict_ = pre_handel(user_ratings_train, self.predict_,
self.item_count)
auc_score = roc_auc_score(self.test, self.predict_)
print('AUC:', auc_score)
# Top-K evaluation
# str(scores.topK_scores(self.test, self.predict_, 5, self.user_count, self.item_count))
MAP, MRR, Prec, Rec, F1, NDCG, l_call = scores.topK_scores(
self.test, self.predict_, re_count, self.user_count,
self.item_count)
tbar_2.close()
def main(self):
user_ratings_train = self.load_data(self.train_data_path)
self.load_test_data(self.test_data_path)
tbar_1 = tqdm(total=self.user_count * self.item_count)
for u in range(self.user_count):
for item in range(self.item_count):
tbar_1.update(1)
if int(self.test_data[u][item]) == 1:
self.test[u * self.item_count + item] = 1
else:
self.test[u * self.item_count + item] = 0
re_count = 30
# BPR加噪音
# self.U = np.loadtxt("self.U.txt")
# self.V = np.loadtxt("self.V.txt")
# MBPR加噪音
self.U = np.loadtxt("self.U_MBPR.txt")
self.V = np.loadtxt("self.V_MBPR.txt")
# 此处可加噪音
noise_U = np.random.rand(self.U.shape[0], self.U.shape[1]) * 1.0
noise_V = np.random.rand(self.V.shape[0], self.V.shape[1]) * 1.0
self.U = self.U + noise_U
self.V = self.V + noise_V
predict_matrix = self.predict(self.U, self.V)
# prediction
self.predict_ = predict_matrix.getA().reshape(-1)
self.predict_ = pre_handel(user_ratings_train, self.predict_,
self.item_count)
auc_score = roc_auc_score(self.test, self.predict_)
print('AUC:', auc_score)
# Top-K evaluation
MAP, MRR, Prec, Rec, F1, NDCG, l_call = scores.topK_scores(
self.test, self.predict_, re_count, self.user_count,
self.item_count)
