import os
import tarfile
import urllib
import pandas
import pandas as pd
import urllib.request
#fetch data
DOWNLOAD_ROOT = "https://raw.githubusercontent.com/ageron/handson-ml2/master/"
HOUSING_PATH = os.path.join("datasets","housing")
HOUSING_URL = DOWNLOAD_ROOT + "datasets/housing/housing.tgz"
#set function fetchdata
def fetch_housing_data(housing_url= HOUSING_URL,housing_path=HOUSING_PATH):
os.makedirs(housing_path,exist_ok=True)
tgz_path = os.path.join(housing_path,'housing.tgz')
urllib.request.urlretrieve(housing_url,tgz_path)
housing_tgz = tarfile.open(tgz_path)
housing_tgz.extractall(path=housing_path)
housing_tgz.close()
#return dataframe
def load_housing_data(housing_path = HOUSING_PATH):
csv_path = os.path.join(housing_path,"housing.csv")
return pd.read_csv(csv_path)
housing = load_housing_data()
housing_head = housing.head()