From 5a3dc759e96dcadb50bfdcc96fd1e68e8b77abab Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Lo=C3=AFc=20Est=C3=A8ve?= Date: Thu, 6 Jul 2017 16:08:03 +0200 Subject: [PATCH] Add data_home parameter to fetch_kddcup99 --- doc/whats_new.rst | 3 +++ sklearn/datasets/kddcup99.py | 12 ++++++++++-- 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/doc/whats_new.rst b/doc/whats_new.rst index 73fa6dcee8b06..0203511348510 100644 --- a/doc/whats_new.rst +++ b/doc/whats_new.rst @@ -459,6 +459,9 @@ Bug fixes `, and `Joel Nothman`_. + - Add ``data_home`` parameter to + :func:`sklearn.datasets.fetch_kddcup99` by `Loic Esteve`_. + API changes summary ------------------- diff --git a/sklearn/datasets/kddcup99.py b/sklearn/datasets/kddcup99.py index 762ca58a63554..89c74238bc4f3 100644 --- a/sklearn/datasets/kddcup99.py +++ b/sklearn/datasets/kddcup99.py @@ -39,7 +39,8 @@ logger = logging.getLogger() -def fetch_kddcup99(subset=None, shuffle=False, random_state=None, +def fetch_kddcup99(subset=None, data_home=None, shuffle=False, + random_state=None, percent10=True, download_if_missing=True): """Load and return the kddcup 99 dataset (classification). @@ -124,6 +125,11 @@ def fetch_kddcup99(subset=None, shuffle=False, random_state=None, To return the corresponding classical subsets of kddcup 99. If None, return the entire kddcup 99 dataset. + data_home : string, optional + Specify another download and cache folder for the datasets. By default + all scikit-learn data is stored in '~/scikit_learn_data' subfolders. + .. versionadded:: 0.19 + random_state : int, RandomState instance or None, optional (default=None) Random state for shuffling the dataset. If int, random_state is the seed used by the random number generator; @@ -162,7 +168,9 @@ def fetch_kddcup99(subset=None, shuffle=False, random_state=None, and data mining, pages 320-324. ACM Press, 2000. """ - kddcup99 = _fetch_brute_kddcup99(shuffle=shuffle, percent10=percent10, + data_home = get_data_home(data_home=data_home) + kddcup99 = _fetch_brute_kddcup99(data_home=data_home, shuffle=shuffle, + percent10=percent10, download_if_missing=download_if_missing) data = kddcup99.data