因为需要使用Kaggle的房屋价格数据集，所以先写一个download函数将数据集下载到本地：
import hashlib import os import tarfile import zipfile import requests DATA_HUB = dict() #用于存放数据集名称映射到(数据集url,sha-1密钥) DATA_URL = 'http://d2l-data.s3-accelerate.amazonaws.com/' def download(name, cache_dir=os.path.join('..', 'data')):# @save 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 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同时实现解压缩tar/zip文件代码
def download_extract(name, folder=None): #@save 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', '.gz', 'tgz'): 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(): #@save for name in DATA_HUB: download(name)利用pandas的read_csv函数读取下载到的数据集，并查看数据集
import numpy as np import pandas as pd import torch from torch import nn 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') train_data = pd.read_csv(download('kaggle_house_train')) test_data = pd.read_csv(download('kaggle_house_test')) print(train_data.shape) print(test_data.shape)训练集总共有1460个样本，80个特征和1个标签，测试集右1459个样本，80个特征。
查看训练集样本的前四个和后两个特征以及标签，有：
print(train_data.iloc[0:4, [0,1,2,3,-3,-2,-1]])由于数据的第一列是ID，ID数据能够帮助模型判断是哪个训练样本，但是对于拟合数据毫无帮助，因此我们去掉该数据。
all_features = pd.concat((train_data.iloc[:, 1:-1], test_data.iloc[:, 1:]))接下来进行数据预处理，由于原始数据中包含大量空数据na、文字数据，因此我们将原始数据中的空数据替换为相应特征的均值，并将所有特征重新缩放到零均值和单位方差：
numeric_features = all_features.select_dtypes(include=[np.number]).columns all_features[numeric_features] = all_features[numeric_features].apply(lambda x:(x - x.mean())/x.std()) all_features[numeric_features] = all_features[numeric_features].fillna(0) #因为标准化后均值为0,因此将空缺值修改为0接下来处理离散值，对于离散值，我们可以使用独热编码
all_features = pd.get_dummies(all_features, dummy_na=True, dtype=float) print(all_features.shape)在数据预处理后，数据变为330个特征，将pandas数据转换为torch数据，准备开始训练：
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.iloc[:, -1].values, dtype=torch.float32) print(train_features.shape, train_labels.shape, test_features.shape)对于房价这类目标值范围很大的回归任务中，计算对数均方误差。
loss = nn.MSELoss() in_features = train_features.shape[1] def get_net(): net = nn.Sequential(nn.Linear(in_features, 1)) return net 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() 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 = 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接下来实现K折交叉验证
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 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: 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 / k进行训练并进行模型选择
k, num_epochs, learning_rate, weight_decay, batch_size = 5, 100, 5, 0, 64 train_l, valid_l = k_fold(k, train_features, train_labels, num_epochs, learning_rate, 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}") plt.show()训练并将结果保存，提交Kaggle
def train_and_pred(train_features,test_features, train_labels, test_data,num_epochs, lr, weigh_decay, batch_size): net = get_net() train_ls, _ = train(net, train_features, train_labels, None, None, num_epochs, lr, weight_decay, batch_size) 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) train_and_pred(train_features, test_features, train_labels, test_data,num_epochs, learning_rate, weight_decay, batch_size) plt.show()查看submission.csv
将结果提交到Kaggle
