4.10. 实战Kaggle比赛：预测房价
详细介绍数据预处理、模型设计和超参数选择。 通过亲身实践，你将获得一手经验，这些经验将有益数据科学家的职业成长。
import hashlibimport osimport tarfileimport zipfileimport requests#@saveDATA_HUB = dict()DATA_URL = 'http://d2l-data.s3-/'def download(name, cache_dir=os.path.join('..', 'data')): #@save"""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:breaksha1.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 fnamedef download_extract(name, folder=None): #@save"""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_dirdef download_all(): #@save"""下载DATA_HUB中的所有文件"""for name in DATA_HUB:download(name)# 如果你没有安装pandas，请取消下一行的注释# !pip install pandas# 如果你没有安装pandas，请取消下一行的注释# !pip install pandas# %matplotlib inlineimport numpy as npimport pandas as pdimport torchfrom torch import nnfrom d2l import torch as d2lDATA_HUB['kaggle_house_train'] = ( #@saveDATA_URL + 'kaggle_house_pred_train.csv','585e9cc93e70b39160e7921475f9bcd7d31219ce')DATA_HUB['kaggle_house_test'] = ( #@saveDATA_URL + 'kaggle_house_pred_test.csv','fa19780a7b011d9b009e8bff8e99922a8ee2eb90')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)# 让我们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]])# 我们可以看到，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:]))# 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#提取全是数字的特征名字numeric_features = all_features.dtypes[all_features.dtypes != 'object'].index#对数据做标准化处理,对应位置赋值all_features[numeric_features] = all_features[numeric_features].apply(lambda x: (x - x.mean()) / (x.std()))# 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0all_features[numeric_features] = all_features[numeric_features].fillna(0)# “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)all_features.shapen_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 = nn.MSELoss()in_features = train_features.shape[1]def get_net():net = nn.Sequential(nn.Linear(in_features,1))return netdef 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1clipped_preds = torch.clamp(net(features), 1, float('inf'))rmse = torch.sqrt(loss(torch.log(clipped_preds),torch.log(labels)))return rmse.item()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def get_k_fold_data(k, i, X, y):assert k > 1fold_size = X.shape[0] // kX_train, y_train = None, Nonefor 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_partelif X_train is None:X_train, y_train = X_part, y_partelse: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_validdef k_fold(k, X_train, y_train, num_epochs, learning_rate, weight_decay,batch_size):train_l_sum, valid_l_sum = 0, 0for 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 / kk, num_epochs, lr, weight_decay, batch_size = 5, 100, 5, 0, 64train_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}')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Kaggletest_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)
真实数据通常混合了不同的数据类型，需要进行预处理。
常用的预处理方法：将实值数据重新缩放为零均值和单位方法；用均值替换缺失值。
将类别特征转化为指标特征，可以使我们把这个特征当作一个独热向量来对待。
我们可以使用折交叉验证来选择模型并调整超参数。
对数对于相对误差很有用。
