远程获取数据解压保存到指定目录 | urllib、tarfile、os
每次调用该函数,就会自动在工作区创建一个datasets/housing目录,然后下载tgz文件,并解压到该目录
import os
import tarfile
import urllib.request
DOWNLOAD_ROOT = "https://raw.githubusercontent.com/ageron/handson-ml2/master/"
HOUSING_PATH = os.path.join('datasets','housing') #地址拼接 part1/part2
HOUSING_URL = DOWNLOAD_ROOT+"datasets/housing/housing.tgz"
def fetch_housing_data(housing_url=HOUSING_URL,housing_path=HOUSING_PATH):
if not os.path.isdir(housing_path):
os.makedirs(housing_path)
tgz_path = os.path.join(housing_path,'housing.tgz')
urllib.request.urlretrieve(housing_url, tgz_path) # 从远程获取文件放入指定文件
housing_tgz = tarfile.open(tgz_path)
housing_tgz.extractall(path=housing_path) #解压文件到当前目录
housing_tgz.close()
快速了解数据类型的方法是绘制每个数值属性的直方图
housing.hist(bins=50,figsize=(20,15))
plt.show()