1. Kaggle房价竞赛¶

import hashlib
import os
import tarfile
import zipfile
import requests
import numpy as np
import pandas as pd
import torch
from torch import nn
from d2l import torch as d2l
%matplotlib inline

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

def download(name, cache_dir=os.path.join('.', '01_data/02_DataSet_Kaggle_House')):
    """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
    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_UHB中的所有文件"""
    for name in DATA_HUB:
        download(name)

DATA_HUB['kaggle_house_train'] = (DATA_URL + 'kaggle_house_pred_train.csv','585e9cc9370b9160e7921475fbcd7d31219ce')         
DATA_HUB['kaggle_house_test'] = (DATA_URL + 'kaggle_house_pred_test.csv', 'fal9780a7b011d9b009e8bff8e99922a8ee2eb90')     
train_data = pd.read_csv(download('kaggle_house_train'))
test_data = pd.read_csv(download('kaggle_house_test'))
print(train_data.shape) # 1460个样本，80个te特征，1个标号label
print(test_data.shape) # 测试样本没有标号label

print(train_data.iloc[0:4,[0,1,2,3,-3,-2,-1]]) # 前面四行的某些列特征

# 在每个样本中，第一个特征是ID，将其从数据集中删除  
all_features = pd.concat((train_data.iloc[:,1:-1],test_data.iloc[:,1:])) # 从第2列开始，第1列没有了 
print(all_features.iloc[0:4,[0,1,2,3,-3,-2,-1]])

# 将所有缺失的值替换成相应特征的平均值
# 通过将特征重新缩放到零均值和单位方差来标准化数据
print(all_features.dtypes) # 可以知道每一列分别为什么类型特征
numeric_features = all_features.dtypes[all_features.dtypes != 'object'].index  # 当值的类型不是object的话，就是一个数值
print(numeric_features)
all_features[numeric_features] = all_features[numeric_features].apply(
    lambda x: (x - x.mean()) / (x.std())) # 对数值数据变为总体为均值为0，方差为1的分布的数据        
all_features[numeric_features] = all_features[numeric_features].fillna(0)  # 将数值数据中not number的数据用0填充      

# 处理离散值。用一次独热编码替换它们
# 若一列里面有五个不同的值，则创建五个features，如果该列中为该feature则为1，不为该feature则为0
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
print(train_data.shape)
n_train = train_data.shape[0] # 样本个数
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_data的SalePrice列是label值
train_labels = torch.tensor(train_data.SalePrice.values.reshape(-1,1),
                            dtype=torch.float32)

# 训练
loss = nn.MSELoss()
print(train_features.shape[1]) # 所有特征个数
in_features = train_features.shape[1]
def get_net():
    net = nn.Sequential(nn.Linear(in_features,1)) # 单层线性回归
    return net

# 模型选择
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}')    

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'train 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.cvs',index = False)
    
train_and_pred(train_features, test_features, train_labels, test_data,
              num_epochs, lr, weight_decay, batch_size)