Kaggle项目实战

# 比赛链接：https://www.kaggle.com/competitions/house-prices-advanced-regression-techniques

import hashlib
import os
import tarfile
import zipfile
import requests
import pandas as pd
import torch
from torch import nn
from torch.utils import data

DATA_HUB = dict()
DATA_URL = 'http://d2l-data.s3-accelerate.amazonaws.com/'

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

def download_extract(name, folder=None):
    """下载并解压zip/tar文件"""
    fname = download(name)
    base_dir = os.path.dirname(fname)
    data_dir, ext = os.path.splitext(fname)
    if ext == '.zip':
        fp = zipfile.ZipFile(fname, 'r')
    elif ext in ('.tar', '.gz'):
        fp = tarfile.open(fname, 'r')
    else:
        assert False, '只有zip/tar文件可以被解压缩'
    fp.extractall(base_dir)
    return os.path.join(base_dir, folder) if folder else data_dir

def download_all():
    """下载DATA_HUB中的所有文件"""
    for name in DATA_HUB:
        download(name)

# 下载并缓存Kaggle房屋数据集
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')

# 使用pandas分别加载包含训练数据和测试数据的两个CSV文件
train_data = pd.read_csv(download('kaggle_house_train'))
test_data = pd.read_csv(download('kaggle_house_test'))

# 训练数据集包括1460个样本，每个样本80个特征和1个标签，而测试数据集包含1459个样本，每个样本80个特征
print(train_data.shape)
print(test_data.shape)

# 看看前四个和最后两个特征，以及相应标签（房价）
print(train_data.iloc[0:4, [0, 1, 2, 3, -3, -2, -1]])

# 在每个样本中，第一个特征是ID，这有助于模型识别每个训练样本。虽然这很方便，但它不携带任何用于预测的信息。因此，在将数据提供给模型之前，我们将其从数据集中删除
all_features = pd.concat((train_data.iloc[:, 1:-1], test_data.iloc[:, 1:]))  # train数据的最后一列为label

# 在开始建模之前，我们需要对数据进行预处理。首先，我们将所有缺失的值替换为相应特征的平均值
# 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 = all_features.dtypes[all_features.dtypes != 'object'].index  # 数值类型特征的下标
all_features[numeric_features] = all_features[numeric_features].apply(lambda x: (x - x.mean()) / (x.std()))  # 将所有数值特征的均值变成0，方差变成1
# 在标准化数据之后，所有均值消失，因此我们可以将缺失值设置为0
all_features[numeric_features] = all_features[numeric_features].fillna(0)

# 接下来，我们处理离散值。这包括诸如“MSZoning”之类的特征。我们用独热编码替换它们，pandas软件包会自动为我们实现这一点
# dummy_na=True将'na'（缺失值）视为有效的特征值，并为其创建指示符特征
all_features = pd.get_dummies(all_features, dummy_na=True)
print(all_features.shape)  # (2919, 331)

# 通过values属性，我们可以从pandas格式中提取NumPy格式，并将其转换为张量表示用于训练
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)

# 训练
loss_function = nn.MSELoss()
in_features = train_features.shape[1]

net = nn.Sequential(nn.Linear(in_features, 128),
                    nn.ReLU(),
                    nn.Dropout(0.1),
                    nn.Linear(128, 1))

# 房价就像股票价格一样，我们关心的是相对数量，而不是绝对数量，我们更关心相对误差，即：(真实值-预测值)/真实值，解决这个问题的一种方法是用价格预测的对数来衡量差异
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'))  # 将inf变成1
    rmse = torch.sqrt(loss_function(torch.log(clipped_preds), torch.log(labels)))
    return rmse.item()

def load_array(data_arrays, batch_size, is_train=True):
    dataset = data.TensorDataset(*data_arrays)
    return data.DataLoader(dataset, batch_size, shuffle=is_train)

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 = load_array((train_features, train_labels), batch_size)

    optimizer = torch.optim.Adam(net.parameters(), lr=learning_rate, weight_decay=weight_decay)  # 这里使用的是Adam优化算法

    for epoch in range(num_epochs):
        for X, y in train_iter:
            optimizer.zero_grad()
            loss = loss_function(net(X), y)
            loss.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，有助于模型选择和超参数调整，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
def get_k_fold_data(k, i, X, y):
    assert k > 1
    fold_size = X.shape[0] // k  # 每一折的大小
    X_train, y_train = None, None
    for j in range(k):  # 分成k份
        idx = slice(j * fold_size, (j + 1) * fold_size)
        X_part, y_part = X[idx, :], y[idx]
        if j == i:  # 将第i折的数据作为验证数据
            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

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)
        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]
        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

k, num_epochs, lr, weight_decay, batch_size = 5, 250, 0.5, 1e-3, 32

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}')

# 使用所有数据对其进行训练
def train_and_pred(train_features, test_features, train_labels, test_data, num_epochs, lr, weight_decay, batch_size):
    train_ls, _ = train(net, train_features, train_labels, None, None, num_epochs, lr, weight_decay, batch_size)
    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，将预测保存在CSV文件中可以简化将结果上传到Kaggle的过程
    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/submission.csv', index=False)

train_and_pred(train_features, test_features, train_labels, test_data, num_epochs, lr, weight_decay, batch_size)