深度学习笔记11：实战 Kaggle房价预测

实战 Kaggle 比赛：预测房价

实现几个函数来方便下载数据

import hashlib
import os
import tarfile
import zipfile
import requests

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

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
    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

使用pandas读入并处理数据

%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',