Move datasets to project ageron/data to shrink this repo

This commit is contained in:
Aurélien Geron
2022-02-19 21:36:43 +13:00
parent 8745a9c2ac
commit c9b977309a
6 changed files with 27 additions and 31 deletions

View File

@@ -1635,8 +1635,8 @@
" filepath = titanic_path / filename\n",
" if filepath.is_file():\n",
" continue\n",
" root = \"https://raw.githubusercontent.com/ageron/handson-ml3/main/\"\n",
" url = root + \"/datasets/titanic/\" + filename\n",
" data_root = \"https://github.com/ageron/data/raw/main/\"\n",
" url = data_root + \"titanic/\" + filename\n",
" print(\"Downloading\", filename)\n",
" urllib.request.urlretrieve(url, filepath)\n",
" return [pd.read_csv(titanic_path / filename) for filename in filenames]"
@@ -2123,9 +2123,9 @@
"import tarfile\n",
"\n",
"def fetch_spam_data():\n",
" root = \"http://spamassassin.apache.org/old/publiccorpus/\"\n",
" ham_url = root + \"20030228_easy_ham.tar.bz2\"\n",
" spam_url = root + \"20030228_spam.tar.bz2\"\n",
" spam_root = \"http://spamassassin.apache.org/old/publiccorpus/\"\n",
" ham_url = spam_root + \"20030228_easy_ham.tar.bz2\"\n",
" spam_url = spam_root + \"20030228_spam.tar.bz2\"\n",
"\n",
" spam_path = Path() / \"datasets\" / \"spam\"\n",
" spam_path.mkdir(parents=True, exist_ok=True)\n",