def train(epochs=20, batchSize=1024, lr=0.01, lamda=0.1, factors_dim=64):
'''
:param epochs: 迭代次数
:param batchSize: 一批次的数量
:param lr: 学习率
:param lamda: 正则系数
:param factors_dim: 隐因子数量
:return:
'''
user_set, item_set, train_set, test_set = dataloader.readRecData(
fp.Ml_100K.RATING5, test_ratio=0.1)
#初始化ALS模型
als = ALS(len(user_set), len(item_set), factors_dim)
#初始化批量提出数据的迭代器
dataIter = DataIter(train_set)
for e in range(epochs):
for batch in tqdm(dataIter.iter(batchSize)):
#将用户id,物品id,评分从三元组中拆出
u = batch[:, 0]
i = batch[:, 1]
r = batch[:, 2].reshape(-1, 1) #形状变一变是为了方便等会广播计算
#得到预测评分
r_pred = als.forward(u, i)
#根据梯度下降迭代
als.backword(r, r_pred, u, i, lr, lamda)
print("TrainSet: Epoch {} | RMSE {:.4f} ".format(
e, evaluateRMSE(train_set, als)))
print("TestSet: Epoch {} | RMSE {:.4f} ".format(
e, evaluateRMSE(test_set, als)))
def train(epochs=10, batchSize=1024, lr=0.01, dim=256, eva_per_epochs=1):
'''
:param epochs: 迭代次数
:param batchSize: 一批次的数量
:param lr: 学习率
:param dim: 用户物品向量的维度
:param eva_per_epochs: 设定每几次进行一次验证
'''
#读取数据
user_set, item_set, train_set, test_set = \
dataloader.readRecData(fp.Ml_100K.RATING, test_ratio = 0.1)
#初始化DSSM模型
net = DSSM(len(user_set), len(item_set), dim)
#定义优化器
optimizer = torch.optim.AdamW(net.parameters(), lr=lr)
#定义损失函数
criterion = torch.nn.BCELoss()
#开始迭代
for e in range(epochs):
net.train()
all_lose = 0
#每一批次地读取数据
for u, i, r in DataLoader(train_set,
batch_size=batchSize,
shuffle=True):
optimizer.zero_grad()
r = torch.FloatTensor(r.detach().numpy())
result = net(u, i)
loss = criterion(result, r)
all_lose += loss
loss.backward()
optimizer.step()
print('epoch {}, avg_loss = {:.4f}'.format(
e, all_lose / (len(train_set) // batchSize)))
#评估模型
if e % eva_per_epochs == 0:
p, r, acc = doEva(net, train_set)
print('train: Precision {:.4f} | Recall {:.4f} | accuracy {:.4f}'.
format(p, r, acc))
p, r, acc = doEva(net, test_set)
print('test: Precision {:.4f} | Recall {:.4f} | accuracy {:.4f}'.
format(p, r, acc))
return net
def get_recomedations_by_itemCF(item_sims, user_o_set):
'''
:param item_sims: 物品的近邻集:{样本1:[近邻1,近邻2，近邻3]}
:param user_o_set: 用户的原本喜欢的物品集合:{用户1:{物品1,物品2，物品3}}
:return: 每个用户的推荐列表{用户1:[物品1，物品2，物品3]}
'''
recomedations = collections.defaultdict(set)
for u in user_o_set:
for item in user_o_set[u]:
# 将自己喜欢物品的近邻物品与自己观看过的视频去重后推荐给自己
if item in item_sims:
recomedations[u] |= set(item_sims[item]) - user_o_set[u]
return recomedations
#得到基于ItemCF的推荐列表
def trainItemCF(item_users, sim_method, user_items, k=5):
item_sims = userCF.knn4set(item_users, k, sim_method)
recomedations = get_recomedations_by_itemCF(item_sims, user_items)
return recomedations
if __name__ == '__main__':
_, _, train_set, test_set = dataloader.readRecData(fp.Ml_100K.RATING,
test_ratio=0.1)
item_users, user_items = getSet(train_set)
recomedations_by_itemCF = trainItemCF(item_users,
b_sim.cos4set,
user_items,
k=5)
print(recomedations_by_itemCF)