From 2b0439c4be5ece5be53020bce6987d7d7e26355e Mon Sep 17 00:00:00 2001
From: toastedcornflakes <toastedcornflakes@gmail.com>
Date: Tue, 11 Oct 2016 23:03:05 +0200
Subject: [PATCH] Improve robustness of LFW dataset downloader (#6112)
---
sklearn/datasets/lfw.py | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/sklearn/datasets/lfw.py b/sklearn/datasets/lfw.py
index a8298cb52a..af6503f14d 100644
--- a/sklearn/datasets/lfw.py
+++ b/sklearn/datasets/lfw.py
@@ -23,7 +23,7 @@ detector from various online websites.
# Copyright (c) 2011 Olivier Grisel <olivier.grisel@ensta.org>
# License: BSD 3 clause
-from os import listdir, makedirs, remove
+from os import listdir, makedirs, remove, rename
from os.path import join, exists, isdir
from sklearn.utils import deprecated
@@ -98,9 +98,11 @@ def check_fetch_lfw(data_home=None, funneled=True, download_if_missing=True):
if not exists(archive_path):
if download_if_missing:
+ archive_path_temp = archive_path + ".tmp"
logger.warning("Downloading LFW data (~200MB): %s",
archive_url)
- urllib.urlretrieve(archive_url, archive_path)
+ urllib.urlretrieve(archive_url, archive_path_temp)
+ rename(archive_path_temp, archive_path)
else:
raise IOError("%s is missing" % target_filepath)
--
GitLab