Pytorch【60天修炼计划】之第一阶段——入门：Kaggle实战-房价预测

谁借莪１个温暖的怀抱￠ 2023-06-08 06:18 6阅读 0赞

# Kaggle #

kaggle是一个著名的供机器学习爱好者交流的平台。网页为https://www.kaggle.com 。  
今天为入门阶段的最后一天，我们对kaggle中的房价预测进行实操练习。

# 项目结构图如下： #

按照之前转载知乎大佬的pytorch项目结构进行布置，最终结果如下：  
![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2thcnJ5X3p6ag_size_16_color_FFFFFF_t_70][]

# data / #

首先从kaggle中将数据集下载下来，即将train.csv和test.csv下载下来，并放到data/dataFile/下  
从数据集文件可以发现：  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2thcnJ5X3p6ag_size_16_color_FFFFFF_t_70 1]  
数据集包括每栋房子的特征，有连续值也有离散值，甚至还有缺失值na，所以我们需要将这些数据进行预处理。

因为csv并不能进行数据的操作，所以接下来我们进行数据集的读取：通过`pandas`读取csv文件。

import pandas as pd
    # 1460 × 81 其中最后一列为价格标签
    train_data = pd.read_csv('./data/dataFile/train.csv')
    # 1459 × 80
    test_data = pd.read_csv('./data/dataFile/test.csv')

读取完数据，我们需要进行数据的预处理。

*  将所有训练数据和测试和数据的特征**连接**`concat`起来。
 *  对连续数值的特征进行**标准化**
 *  标准化后用0代替缺失值na
 *  对离散数值的特征转成**指示特征**
 *  将数据转化为tensor类型

代码依次为：

# 将所有训练数据及测试数据的79个特征按照样本连接
     all_features = pd.concat((train_data.iloc[:, 1:-1], test_data.iloc[:, 1:]))
    
     # 对连续数值的特征做标准化
     numeric_features = all_features.dtypes[all_features.dtypes != 'object'].index
     all_features[numeric_features] = all_features[numeric_features].apply(lambda x: (x - x.mean()) / (x.std()))
     # 标准化后用0代替缺失值nan
     all_features = all_features.fillna(0)
    
     # 对离散数值转成指示特征
     # dummy_na = True将缺失值也当作合法的特征值并为其创建指示特征
     all_features = pd.get_dummies(all_features, dummy_na=True)
    
     # 再将数据转化为numpy格式的数据，并转为tensor
     n_train = train_data.shape[0]
     train_features = torch.tensor(all_features[:n_train].values, dtype=torch.float)
     test_features = torch.tensor(all_features[n_train:].values, dtype=torch.float)
     train_labels = torch.tensor(train_data.SalePrice.values,dtype=torch.float).view(-1, 1)

# model / #

模型就很简单了，一个Logistics回归就需要一个linear即可。  
代码如下：

class Linear(nn.Module):
        def __init__(self, feature_num):
            super(Linear, self).__init__()
            self.linear = nn.Linear(feature_num, 1)
    
        def forward(self, x):
            return self.linear(x)

# 训练模型 #

取出网络，并定义loss为平方损失函数

def get_net(feature_num):
        net = Linear(feature_num)
        return net
        
    loss = nn.MSELoss()

再定义比赛用评价模型的对数均方根误差。给定预测值  y 1 ^ , . . . , y n ^ \\hat\{y\_1\},...,\\hat\{y\_n\} y1^,...,yn^ 和对应的真实标签 y 1 , . . . , y n y\_1, ..., y\_n y1,...,yn ，它的定义为  
 1 n ∑ i = 1 n ( l o g ( y i ) − l o g ( y i ^ ) ) 2 \\sqrt\{\\frac\{1\}\{n\}\\sum\_\{i=1\}^n(log(y\_i) - log(\\hat\{y\_i\}))^2\} n1i=1∑n(log(yi)−log(yi^))2  
代码如下：

# 求对数均方根误差
    def log_rmse(net, features, labels):
        with torch.no_grad():
            clipped_preds = torch.max(net(features), torch.tensor(1.0))
            rmse = torch.sqrt(2 * loss(clipped_preds.log(), labels.log()).mean())
        return rmse.item()

然后进行训练：

def train(net, train_features, train_labels, test_features, test_labels,
              num_epochs, learning_rate, weight_decay, batch_size):
        train_ls, test_ls = [], []
        # 将数据集特征和标签结合起来
        dataset = torch.utils.data.TensorDataset(train_features, train_labels)
        # 训练集迭代器
        train_iter = torch.utils.data.DataLoader(dataset, batch_size, shuffle = True)
        # 定义优化器Adam
        optimizer = torch.optim.Adam(params=net.parameters(), lr = learning_rate, weight_decay=weight_decay)
        net = net.float()
        # 进行迭代训练
        for epoch in range(num_epochs):
            for X, y in train_iter:
                l = loss(net(X.float()), y.float())
                optimizer.zero_grad()
                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 #

因为数据集只有训练集和测试集，那么为了得到验证集来选择模型并调节超参数。  
所以我们实现一个函数返回第  i i i 折交叉验证时所需要的训练和验证数据

# k折交叉验证，返回第i折交叉验证时所需要的训练和验证数据
    def get_k_fold_data(k, i, X, y):
        assert k > 1
        fold_size = X.shape[0] // k # 返回整数
        X_train, y_train = None, None
        for j in range(k):
            idx = slice(j * fold_size, (j + 1) * fold_size)
            X_part, y_part = X[idx, :], y[idx]
            if j == i:
                X_valid, y_valid = X_part, y_part
            elif X_train is None:
                X_train, y_train = X_part, y_part
            else:
                X_train = torch.cat((X_train, X_part), dim = 0)
                y_train = torch.cat((y_train, y_part), dim = 0)
        return X_train, y_train, X_valid, y_valid

在  K K K 折交叉验证中我们训练 次并返回训练和验证的平均误差。

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(X_train.shape[1])
            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:
                semilogy(range(1, num_epochs + 1), train_ls,'epochs', 'rmse',range(1, num_epochs + 1), valid_ls,['train', 'valid'])
            print('fold %d, train rmse %f, valid rmse %f' % (i, train_ls[-1], valid_ls[-1]))
        return train_l_sum / k, valid_l_sum / k

# 模型的选择。 #

我们使⽤⼀组未经调优的超参数并计算交叉验证误差。可以改动这些超参数来尽可能减⼩平均测试误  
差。

train_data, test_data, train_features, test_features ,train_lables= loadData()
    k, num_epochs, lr, weight_decay, batch_size = 5, 100, 5, 0, 64
    train_l, valid_l = k_fold(k, train_features, train_lables, num_epochs, lr, weight_decay, batch_size)
    print('%d-fold validation: avg train rmse %f, avg valid rmse %f' %(k, train_l, valid_l))

# 预测 #

def train_and_pred(train_features, test_features, train_labels, test_data,
                       num_epochs, lr, weight_decay, batch_size):
        net = get_net(train_features.shape[1])
        train_ls, _ = train(net, train_features, train_labels, None, None,
                            num_epochs, lr, weight_decay, batch_size)
        semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'rmse')
        print('train rmse %f' % train_ls[-1])
        preds = net(test_features).detach().numpy()
        test_data['SalePrice'] = pd.Series(preds.reshape(1, -1)[0])
        submission = pd.concat([test_data['Id'], test_data['SalePrice']], axis = 1)
        submission.to_csv('./data/dataFile/submission.csv', index = False)

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2thcnJ5X3p6ag_size_16_color_FFFFFF_t_70]: /images/20230531/1c44f93ed0334dc0aca0710e6fff2803.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2thcnJ5X3p6ag_size_16_color_FFFFFF_t_70 1]: /images/20230531/3aac2c917830464cb77c64e39b072556.png