动手学习深度学习——房价预测（详细注释）

李沐老师课程的房价预测

代码+详细注释
里面设计到的不懂的函数，可以查看这个博客

#数据预处理
#将所有缺失的值替换为相应特征的平均值。然后，为了将所有特征放在一个共同的尺度上， 我们通过将特征重新缩放到零均值和单位方差来标准化数据
# 若无法获得测试数据 则可根据训练数据计算均值和标准差
# numeric_features 是  all_features 的索引
numeric_features = all_features.dtypes[all_features.dtypes != 'object'].index
#标准化数据 将所有特征值减去平均值除以方差 将所有特征值标准化
#这样得到的数据是正态分布的 才能用均值填充
all_features[numeric_features] = all_features[numeric_features].apply(lambda x: (x - x.mean()) / (x.std()))

#标准化后 所有均值为o（因为数学期望E的分子为每个特征值减去均值的和，也等于所有特征值的和减去均值的和，就等于均值减去均值为0）
#均值为0，所以吧所有缺失值直接替换为0就可以啦
all_features[numeric_features] = all_features[numeric_features].fillna(0)

# 处理离散值，独热编码
# 例如，“MSZoning”包含值“RL”和“Rm”。 我们将创建两个新的指示器特征“MSZoning_RL”和“MSZoning_RM”，其值为0或1。 根据独热编码，如果“MSZoning”的原始值为“RL”， 则：“MSZoning_RL”为1，“MSZoning_RM”为0。
all_features = pd.get_dummies(all_features, dummy_na=True)
all_features.shape //(2919, 331)

n_train = train_data.shape[0]
#从pandas格式中提取Numpy格式，并将其转换为张量表示用于训练
train_features = torch.tensor(all_features[:n_train].values, dtype=torch.float32)
test_features = torch.tensor(all_features[n_train:].values, dtype=torch.float32)
train_labels = torch.tensor(
    train_data.SalePrice.values.reshape(-1, 1), dtype=torch.float32)

# 训练
# 使用一个带有损失的线性模型
loss = nn.MSELoss()
in_features = train_features.shape[1] #331

def get_net():
    net = nn.Sequential(nn.Linear(in_features, 1))
    return net
    
# 用价格预测的对数来衡量差异
# 预测价格的对数和真实标签价格取对数再求loss
# 求均方根误差
def log_rmse(net, features, labels):
    # 为了在取对数时进一步稳定该值，将小于1的值设置为1
    clipped_preds = torch.clamp(net(features), 1, float('inf'))
    rmse = torch.sqrt(loss(torch.log(clipped_preds),
                           torch.log(labels)))
    return rmse.item()

# 我们的训练函数将借助Adam优化器 
# Adam优化器的主要吸引力在于它对初始学习率不那么敏感
def train(net, train_features, train_labels, test_features, test_labels,
          num_epochs, learning_rate, weight_decay, batch_size):
    train_ls, test_ls = [], []
    train_iter = d2l.load_array((train_features, train_labels), batch_size)
    # 这里使用的是Adam优化算法
    optimizer = torch.optim.Adam(net.parameters(),
                                 lr = learning_rate,
                                 weight_decay = weight_decay)
    for epoch in range(num_epochs):
        for X, y in train_iter:
            optimizer.zero_grad()
            l = loss(net(X), y)
            l.backward()
            optimizer.step()
        train_ls.append(log_rmse(net, train_features, train_labels))
        if test_labels is not None:
            test_ls.append(log_rmse(net, test_features, test_labels))
    return train_ls, test_ls


## K折交叉验证
#我们首先需要定义一个函数，在K折交叉验证过程中返回第i折的数据。 具体地说，它选择第i个切片作为验证数据，其余部分作为训练数据.

# 步骤
# 1、首先，将全部样本划分成k个大小相等的样本子集；
# 2、依次遍历这k个子集，每次把当前子集作为验证集，其余所有样本作为训练集，进行模型的训练和评估；
# 3、最后把k次评估指标的平均值作为最终的评估指标。在实际实验中，k通常取10.

def get_k_fold_data(k, i, X, y):
    assert k > 1
    fold_size = X.shape[0] // k #划分 用样本总数除以k 得到样本子集的大小
    X_train, y_train = None, None
    for j in range(k): #遍历k个子集
        idx = slice(j * fold_size, (j + 1) * fold_size) 
        X_part, y_part = X[idx, :], y[idx] #取第j个子集
        if j == i:
            X_valid, y_valid = X_part, y_part # 当前子集作为验证集
        elif X_train is None:
            X_train, y_train = X_part, y_part
        else:
            X_train = torch.cat([X_train, X_part], 0) # 剩余子集全部拼接到X_train作为训练集
            y_train = torch.cat([y_train, y_part], 0)
    return X_train, y_train, X_valid, y_valid

# 当我们在K折交叉验证中训练K次后，返回训练和验证误差的平均值
# 返回训练和验证误差的平均值
def k_fold(k, X_train, y_train, num_epochs, learning_rate, weight_decay,
           batch_size):
    train_l_sum, valid_l_sum = 0, 0
    for i in range(k):
        data = get_k_fold_data(k, i, X_train, y_train)
        net = get_net()
        train_ls, valid_ls = train(net, *data, num_epochs, learning_rate,
                                   weight_decay, batch_size)
        train_l_sum += train_ls[-1]
        valid_l_sum += valid_ls[-1]
        if i == 0:
            d2l.plot(list(range(1, num_epochs + 1)), [train_ls, valid_ls],
                     xlabel='epoch', ylabel='rmse', xlim=[1, num_epochs],
                     legend=['train', 'valid'], yscale='log')
        print(f'折{i + 1}，训练log rmse{float(train_ls[-1]):f}, '
              f'验证log rmse{float(valid_ls[-1]):f}')
    return train_l_sum / k, valid_l_sum / k

# 模型选择
k, num_epochs, lr, weight_decay, batch_size = 5, 100, 5, 0, 64
train_l, valid_l = k_fold(k, train_features, train_labels, num_epochs, lr,
                          weight_decay, batch_size)
print(f'{k}-折验证: 平均训练log rmse: {float(train_l):f}, '
      f'平均验证log rmse: {float(valid_l):f}')
      
# 输出：
# 折1，训练log rmse0.170648, 验证log rmse0.156788
# 折2，训练log rmse0.162362, 验证log rmse0.189082
# 折3，训练log rmse0.163824, 验证log rmse0.168649
# 折4，训练log rmse0.168383, 验证log rmse0.154595
# 折5，训练log rmse0.162834, 验证log rmse0.182902
# 5-折验证: 平均训练log rmse: 0.165610, 平均验证log rmse: 0.170403
# 


# 训练模型
def train_and_pred(train_features, test_features, train_labels, test_data,
                   num_epochs, lr, weight_decay, batch_size):
    net = get_net()
    train_ls, _ = train(net, train_features, train_labels, None, None,
                        num_epochs, lr, weight_decay, batch_size)
    d2l.plot(np.arange(1, num_epochs + 1), [train_ls], xlabel='epoch',
             ylabel='log rmse', xlim=[1, num_epochs], yscale='log')
    print(f'训练log rmse：{float(train_ls[-1]):f}')
    # 将网络应用于测试集。
    preds = net(test_features).detach().numpy()
    # 将其重新格式化以导出到Kaggle
    test_data['SalePrice'] = pd.Series(preds.reshape(1, -1)[0])
    submission = pd.concat([test_data['Id'], test_data['SalePrice']], axis=1)
    submission.to_csv('submission.csv', index=False)

train_and_pred(train_features, test_features, train_labels, test_data,
               num_epochs, lr, weight_decay, batch_size)
# 输出
# 训练log rmse：0.162592
#