动手学PyTorch（李沐）9 ---- 房价预测

数据下载和前期准备

import hashlib
import os
import tarfile
import zipfile
import requests
DATA_HUB = dict()
DATA_URL = 'http://d2l-data.s3-accelerate.amazonaws.com/'

```python
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)

%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'] = ( 
  DATA_URL + 'kaggle_house_pred_train.csv',
  '585e9cc93e70b39160e7921475f9bcd7d31219ce')
DATA_HUB['kaggle_house_test'] = ( 
  DATA_URL + 'kaggle_house_pred_test.csv',
  'fa19780a7b011d9b009e8bff8e99922a8ee2eb90')

数据获取

# 获取数据
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)

查看数据 前四条的前四列和后三列

print(train_data.iloc[0:4,[0,1,2,3,-3,-2,-1]])

删除数据ID并拼接test和train的共有特征

all_features = pd.concat((train_data.iloc[:, 1:-1], test_data.iloc[:, 1:]))

数据预处理

将所有的缺失值替换为相应特征的平均值，通过将特征重新缩放到均值为零和方差为1来标准化数据。

# 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

# all_features的data type如果不是object，那么就是数值特征，numeric_features就是找到数值特征
numeric_features = all_features.dtypes[all_features.dtypes != 'object'].index

# 将数值列的每一个元素减去均值除以方差（这里是训练集和测试集放一起计算），此操作后，均值变为0
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)

# “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
# 处理离散值，用one_hot编码替换他们
all_features = pd.get_dummies(all_features, dummy_na=True)
all_features.shape

从pandas格式中提取numpy格式，并将其转换为张量表示

整理数据集

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 = nn.MSELoss()
in_features = train_features.shape[1]
def get_net():
  net = nn.Sequential(nn.Linear(in_features,1))
  return net

对于房价而言，更关心相对误差：

$$\frac{y-\hat{y}}{y}$$

解决办事是用价格预测是对数来衡量误差

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'))
  # 这里是把正常值和预测值都log了
  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，Adam对学习率没那么敏感，但没sgd上线高
  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

# 交叉验证数据整理
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

返回训练和验证误差的均值

# 交叉验证
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

# 要做的就是调整参数
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}')

测试

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()
  # print(preds)
  # 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)