Machine Learning avec Scikit-Learn

46

Chapitre 2. Un projet de Machine Learning de bout en bout

Voici la fonction qui récupère les données

28

:

import os

import tarfile

import urllib

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"

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)

housing_tgz = tarfile.open(tgz_path)

housing_tgz.extractall(path=housing_path) ...