（pytorch-深度学习系列）简单实现kaggle房价预测-学习笔记

实现kaggle房价预测

导入所需模块：

%matplotlib inline
import torch
import torch.nn as nn
import numpy as np
import pandas as pd

print(torch.__version__)
torch.set_default_tensor_type(torch.FloatTensor)

读取数据集：
（具体以自己存放的数据集的位置为准）

train_data = pd.read_csv('./data/train.csv')
test_data = pd.read_csv('./data/test.csv')

数据集的基本情况：

train_data.shape # 输出 (1460, 81)，训练数据集包括1460个样本、80个特征和1个标签。
test_data.shape # 输出 (1459, 80)，测试数据集包括1459个样本、80个特征

#查看前5个样本的前4个特征、后2个特征和标签（SalePrice）：
train_data.iloc[0:5, [0, 1, 2, 3, -3, -2, -1]]

第一个特征是Id，对于机器学习来说，id不能带来有效的特征信息，所以我们不使用这个属性作为特征。

# 将所有的训练数据和测试数据的79个特征按样本连结
all_features = pd.concat((train_data.iloc[:, 1:-1], test_data.iloc[:, 1:]))

对数据进行预处理：

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())) #标准化处理，对所有的特征减去均值，再除以标准差
# 标准化后，每个数值特征的均值变为0，所以可以直接用0来替换缺失值
all_features[numeric_features] = all_features[numeric_features].fillna(0)

# 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
这一步操作相当于进行one_hot编码
all_features = pd.get_dummies(all_features, dummy_na=True)
all_features.shape # (2919, 331)，这一步转换将特征数从79增加到了331

#将numpy数据转化为tensor，便于后面的训练
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)

标准化后，每个数值特征的均值变为0，所以可以直接用0来替换缺失值
使用one_hot编码将离散的特征分解成多个特征，分解之后的特征可以用0/1来表示，这样，这个转换将特征数从79增加到了331

定义模型所需的函数：

loss = torch.nn.MSELoss()

def get_net(feature_num):
    net = nn.Linear(feature_num, 1)
    for param in net.parameters():
        nn.init.normal_(param, mean=0, std=0.01)
    return net
    
#对数均方差损失的实现
def log_rmse(net, features, labels):
    with torch.no_grad():
        # 将小于1的值设成1，使得取对数时数值更稳定
        clipped_preds = torch.max(net(features), torch.tensor(1.0))
        rmse = torch.sqrt(loss(clipped_preds.log(), labels.log()))
    return rmse.item()

给定预测值${\hat{y}}_1,\dots ,{\hat{y}}_n$和对应的真实标签$y_1,\dots ,y_n$，对数均方根误差的定义为

$$\sqrt{\frac{1}{n}\sum _{i=1}^n{\left(\log (y_i)-\log ({\hat{y}}_i)\right)}^2}.$$

实现K折交叉验证：

def semilogy(x_vals, y_vals, x_label, y_label, x2_vals=None, y2_vals=None,
             legend=None, figsize=(3.5, 2.5)):
    set_figsize(figsize)
    plt.xlabel(x_label)
    plt.ylabel(y_label)
    plt.semilogy(x_vals, y_vals)
    if x2_vals and y2_vals:
        plt.semilogy(x2_vals, y2_vals, linestyle=':')
        plt.legend(legend)

def get_k_fold_data(k, i, X, y):
    # 返回第i折交叉验证时所需要的训练和验证数据
    assert k > 1
    fold_size = X.shape[0] // k
    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

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

。
。
训练模型：

def train(net, train_features, train_labels, test_features, test_labels,
          num_epochs, learning_rate, weight_decay, batch_size):
    train_ls, test_ls = [], []
    dataset = torch.utils.data.TensorDataset(train_features, train_labels)
    train_iter = torch.utils.data.DataLoader(dataset, batch_size, shuffle=True)
    # 这里使用了Adam优化算法
    optimizer = torch.optim.Adam(params=net.parameters(), lr=learning_rate, weight_decay=weight_decay) 
    net = net.float()
    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, 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('%d-fold validation: avg train rmse %f, avg valid rmse %f' % (k, train_l, valid_l))

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('./submission.csv', index=False)
    
train_and_pred(train_features, test_features, train_labels, test_data, num_epochs, lr, weight_decay, batch_size)

上述代码执行完之后会生成一个submission.csv文件，该文件符合kaggle的提交格式，可以直接将结果再kaggle比赛链接进行提交。