使用 PyTorch 和 Pandas 进行 Kaggle 房价预测

---

在本篇博文中，我们将探索如何使用 PyTorch 和 Pandas 库，构建一个用于 Kaggle 房价预测的模型。我们将详细讨论数据加载、预处理、模型构建、训练、验证及最终预测的全过程。

1、环境设置

我们首先需要导入所需的库，包括用于数据处理的 pandas 和 numpy，以及用于深度学习的 torch。

import hashlib
import os
import requests
import numpy as np
import pandas as pd
import torch
from torch import nn
from d2l import torch as d2l

2、数据下载

为了下载数据，我们需要定义一个下载函数，并在其中实现数据缓存机制以避免重复下载。

# 保存DATA_HUB字典以便下载数据
DATA_HUB = dict()
DATA_URL = 'http://d2l-data.s3-accelerate.amazonaws.com/'

# 保存下载函数
def download(name, cache_dir=os.path.join('..', 'data')):
    """下载一个DATA_HUB中的文件，返回本地文件名"""
    assert name in DATA_HUB, f"{name} 不存在于 {DATA_HUB}"
    url, sha1_hash = DATA_HUB[name]
    os.makedirs(cache_dir, exist_ok=True)
    fname = os.path.join(cache_dir, url.split('/')[-1])
    if os.path.exists(fname):
        sha1 = hashlib.sha1()
        with open(fname, 'rb') as f:
            while True:
                data = f.read(1048576)
                if not data:
                    break
                sha1.update(data)
        if sha1.hexdigest() == sha1_hash:
            return fname  # 命中缓存
    print(f'正在从{url}下载{fname}...')
    r = requests.get(url, stream=True, verify=True)
    with open(fname, 'wb') as f:
        f.write(r.content)
    return fname

接下来，我们在 DATA_HUB 中注册 Kaggle 房价预测的训练和测试数据集，并下载这些数据。

# 在DATA_HUB中注册Kaggle房价预测的训练和测试数据集
DATA_HUB['kaggle_house_train'] = (
    DATA_URL + 'kaggle_house_pred_train.csv',
    '585e9cc93e70b39160e7921475f9bcd7d31219ce')

DATA_HUB['kaggle_house_test'] = (
    DATA_URL + 'kaggle_house_pred_test.csv',
    'fa19780a7b011d9b009e8bff8e99922a8ee2eb90')

# 下载并加载数据
train_data = pd.read_csv(download('kaggle_house_train'))
test_data = pd.read_csv(download('kaggle_house_test'))

3、数据预处理

我们首先查看数据集的形状和部分内容。

# 查看数据集的形状和部分内容
print(train_data.shape)
print(test_data.shape)
print(train_data.iloc[0:4, [0, 1, 2, 3, -3, -2, -1]])

然后，我们合并所有特征以进行统一预处理，并标准化数值特征，填充缺失值为0，处理离散数值特征。

# 合并所有特征以进行预处理
all_features = pd.concat((train_data.iloc[:, 1:-1], test_data.iloc[:, 1:]))

# 标准化数值特征
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()))
# 填充缺失值为0
all_features[numeric_features] = all_features[numeric_features].fillna(0)

# 处理离散数值特征（dummy_na=True包括缺失值）
all_features = pd.get_dummies(all_features, dummy_na=True)

# 确保所有特征都是数值类型
all_features = all_features.astype(np.float32)

将数据转换为 tensor 格式，以便 PyTorch 使用。

# 将数据转换为tensor格式
n_train = train_data.shape[0]
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)

4、模型构建

我们定义一个简单的线性回归模型，并设置损失函数。

# 定义损失函数和获取网络结构
loss = nn.MSELoss()
in_features = train_features.shape[1]

def get_net():
    net = nn.Sequential(nn.Linear(in_features, 1))
    return net

5、训练和验证

为了更好地评估模型，我们定义了 K 折交叉验证和训练函数。

# 定义log_rmse函数
def log_rmse(net, features, labels):
    clipped_preds = torch.clamp(net(features), 1, float('inf'))
    rmse = torch.sqrt(loss(torch.log(clipped_preds), torch.log(labels)))
    return rmse.item()

# 定义训练函数
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)
    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

# 获取k折交叉验证的数据
def get_k_fold_data(k, i, X, y):
    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], 0)
            y_train = torch.cat([y_train, y_part], 0)
    return X_train, y_train, X_valid, y_valid

# 定义k折交叉验证函数
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}, 验证log rmse{float(valid_ls[-1]):f}')
    return train_l_sum / k, valid_l_sum / k

6、训练模型并生成预测结果

我们定义了最终的训练和预测函数，并训练模型生成预测结果。

# 定义超参数并进行k折交叉验证
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}, 平均验证log rmse: {float(valid_l):f}')

# 定义最终的训练和预测函数
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}')
    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)

# 训练模型并生成预测结果
train_and_pred(train_features, test_features, train_labels, test_data, num_epochs, lr, weight_decay, batch_size)

通过上述步骤，我们成功地使用 PyTorch 和 Pandas 实现了一个简单的线性回归模型，用于 Kaggle 房价预测任务。这篇博文涵盖了数据下载、预处理、模型构建、训练、验证及预测的全过程，为类似任务提供了一个完整的参考。

7、完整代码

import hashlib
import os
import tarfile
import zipfile
import requests
import numpy as np
import pandas as pd
import torch
from torch import nn
from d2l import torch as d2l

# 保存DATA_HUB字典以便下载数据
DATA_HUB = dict()
DATA_URL = 'http://d2l-data.s3-accelerate.amazonaws.com/'

# 保存下载函数
def download(name, cache_dir=os.path.join('..', 'data')):
    """下载一个DATA_HUB中的文件，返回本地文件名"""
    assert name in DATA_HUB, f"{name} 不存在于 {DATA_HUB}"
    url, sha1_hash = DATA_HUB[name]
    os.makedirs(cache_dir, exist_ok=True)
    fname = os.path.join(cache_dir, url.split('/')[-1])
    if os.path.exists(fname):
        sha1 = hashlib.sha1()
        with open(fname, 'rb') as f:
            while True:
                data = f.read(1048576)
                if not data:
                    break
                sha1.update(data)
        if sha1.hexdigest() == sha1_hash:
            return fname  # 命中缓存
    print(f'正在从{url}下载{fname}...')
    r = requests.get(url, stream=True, verify=True)
    with open(fname, 'wb') as f:
        f.write(r.content)
    return fname

# 在DATA_HUB中注册Kaggle房价预测的训练和测试数据集
DATA_HUB['kaggle_house_train'] = (
    DATA_URL + 'kaggle_house_pred_train.csv',
    '585e9cc93e70b39160e7921475f9bcd7d31219ce')

DATA_HUB['kaggle_house_test'] = (
    DATA_URL + 'kaggle_house_pred_test.csv',
    'fa19780a7b011d9b009e8bff8e99922a8ee2eb90')

# 下载并加载数据
train_data = pd.read_csv(download('kaggle_house_train'))
test_data = pd.read_csv(download('kaggle_house_test'))

# 查看数据集的形状和部分内容
print(train_data.shape)
print(test_data.shape)
print(train_data.iloc[0:4, [0, 1, 2, 3, -3, -2, -1]])

# 合并所有特征以进行预处理
all_features = pd.concat((train_data.iloc[:, 1:-1], test_data.iloc[:, 1:]))

# 标准化数值特征
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()))
# 填充缺失值为0
all_features[numeric_features] = all_features[numeric_features].fillna(0)

# 处理离散数值特征（dummy_na=True包括缺失值）
all_features = pd.get_dummies(all_features, dummy_na=True)

# 确保所有特征都是数值类型
all_features = all_features.astype(np.float32)

# 将数据转换为tensor格式
n_train = train_data.shape[0]
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)

# 定义损失函数和获取网络结构
loss = nn.MSELoss()
in_features = train_features.shape[1]

def get_net():
    net = nn.Sequential(nn.Linear(in_features, 1))
    return net

# 定义log_rmse函数
def log_rmse(net, features, labels):
    clipped_preds = torch.clamp(net(features), 1, float('inf'))
    rmse = torch.sqrt(loss(torch.log(clipped_preds), torch.log(labels)))
    return rmse.item()

# 定义训练函数
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)
    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

# 获取k折交叉验证的数据
def get_k_fold_data(k, i, X, y):
    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], 0)
            y_train = torch.cat([y_train, y_part], 0)
    return X_train, y_train, X_valid, y_valid

# 定义k折交叉验证函数
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}, 验证log rmse{float(valid_ls[-1]):f}')
    return train_l_sum / k, valid_l_sum / k

# 定义超参数并进行k折交叉验证
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}, 平均验证log rmse: {float(valid_l):f}')

# 定义最终的训练和预测函数
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}')
    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)

# 训练模型并生成预测结果
train_and_pred(train_features, test_features, train_labels, test_data, num_epochs, lr, weight_decay, batch_size)

提示：更多内容可以访问Clang’s Blog：https://www.clang.asia