这段代码展示了如何在Kaggle的房价预测竞赛中进行数据预处理，包括下载数据、合并特征、处理缺失值、标准化数值特征、one-hot编码非数值特征，并使用线性模型进行训练。还实现了K折交叉验证来评估模型性能。最后，训练模型并在测试集上进行预测，生成提交到Kaggle的CSV文件。
Kaggle竞赛：房价预测
下载和缓存数据集
import hashlib
import os
import tarfile
import zipfile
import requests
#@save
DATA_HUB = dict()
DATA_URL = 'http://d2l-data.s3-accelerate.amazonaws.com/'
我们建立字典
DATA_HUB， 它可以将数据集名称的字符串映射到数据集相关的二元组上， 这个二元组包含数据集的url和验证文件完整性的sha-1密钥。 所有类似的数据集都托管在地址为DATA_URL的站点上。
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:
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
download函数用来下载数据集， 将数据集缓存在本地目录（默认情况下为../data）中， 并返回下载文件的名称。 如果缓存目录中已经存在此数据集文件，并且其sha-1与存储在DATA_HUB中的相匹配， 我们将使用缓存的文件，以避免重复的下载。
def 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_dir
def download_all(): #@save
"""下载DATA_HUB中的所有文件"""
for name in DATA_HUB:
download(name)
download_extract一个将下载并解压缩一个zip或tar文件
download_all将本课程中使用的所有数据集从DATA_HUB下载到缓存目录中。
房价预测
读取数据集
%matplotlib inline
import numpy as np
import pandas as pd
import torch
from torch import nn
from d2l import torch as d2l
DATA_HUB['kaggle_house_train'] = ( #@save
DATA_URL + 'kaggle_house_pred_train.csv',
'585e9cc93e70b39160e7921475f9bcd7d31219ce')
DATA_HUB['kaggle_house_test'] = ( #@save
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'))
打印一下数据集
print(train_data.shape)
print(test_data.shape)
(1460, 81)
(1459, 80)
训练数据比测试数据多一维是因为有
标注
print(train_data.iloc[0:4, [0, 1, 2, 3, -3, -2, -1]])
Id MSSubClass MSZoning LotFrontage SaleType SaleCondition SalePrice
0 1 60 RL 65.0 WD Normal 208500
1 2 20 RL 80.0 WD Normal 181500
2 3 60 RL 68.0 WD Normal 223500
3 4 70 RL 60.0 WD Abnorml 140000
看看前四行的前四列和导数三列
all_features = pd.concat((train_data.iloc[:, 1:-1], test_data.iloc[:, 1:]))
训练数据和测试数据拼在一起，注意训练数据去掉了最后一列标注
数据预处理
# 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
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0
all_features[numeric_features] = all_features[numeric_features].fillna(0)
处理数字类型的特征：
进行归一化：均值为0，方差为1，空的地方填充“0”保持均值不变。
# “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)
处理非数字类型的特征：
使用one-hot编码，pandas提供了get_dummies，比如这一列有五个不同的值，就用一个五维向量来表示。
最后得到的特征格式
all_features.shape
(2919, 331)
特征总数从79变成了331
最后转换成张量格式
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)
训练
损失函数
loss = nn.MSELoss()
in_features = train_features.shape[1]
def get_net():
net = nn.Sequential(nn.Linear(in_features,1))
return net
我们训练一个带有损失平方的最简单的线性模型。
计算误差
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'))
rmse = torch.sqrt(loss(torch.log(clipped_preds),torch.log(labels)))
return rmse.item()
以前我们关心的都是绝对误差 ，但在房价预测上我们关心相对误差
clamp()把输入张量net(features)每个元素的范围限制到区间 [1, float(‘inf’)]，删掉负值，方便后面取对数。
训练
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
与前面的SGD不同，我们的训练函数将借助Adam优化器 （以后再讲）。 Adam优化器的好处在于它对初始学习率不那么敏感。
weight_decay权重衰减最后返回损失
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
fold_size = X.shape[0]把数据集分成k折，每一折的大小
j == i：第i折做验证集，其余做训练集拼接起来
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}, '
f'验证log rmse{float(valid_ls[-1]):f}')
return train_l_sum / k, valid_l_sum / k
*data是train_features, train_labels, test_features, test_labels
train_l_sum += train_ls[-1]
valid_l_sum += valid_ls[-1]求和
return train_l_sum / k, valid_l_sum / k最后再求平均
测试一下，调一调超参数
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}, '
f'平均验证log rmse: {float(valid_l):f}')
折1，训练log rmse0.170520, 验证log rmse0.156424
折2，训练log rmse0.162068, 验证log rmse0.188479
折3，训练log rmse0.164044, 验证log rmse0.168514
折4，训练log rmse0.167672, 验证log rmse0.154508
折5，训练log rmse0.163563, 验证log rmse0.183131
5-折验证: 平均训练log rmse: 0.165573, 平均验证log rmse: 0.170211
def train_and_pred(train_features, test_feature, 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Kaggle
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)
训练log rmse：0.162508
扫一扫
330
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
