diff --git a/sklearn/datasets/base.py b/sklearn/datasets/base.py index 2ad2bdb16cbfad129997a586d2d41e546a3a1a85..58762a2fce5cc779950b8f6f0dadabaad0b3e0b4 100644 --- a/sklearn/datasets/base.py +++ b/sklearn/datasets/base.py @@ -568,14 +568,19 @@ def load_diabetes(return_X_y=False): .. versionadded:: 0.18 """ - base_dir = join(dirname(__file__), 'data') + + module_path = dirname(__file__) + base_dir = join(module_path, 'data') data = np.loadtxt(join(base_dir, 'diabetes_data.csv.gz')) target = np.loadtxt(join(base_dir, 'diabetes_target.csv.gz')) + with open(join(module_path, 'descr', 'diabetes.rst')) as rst_file: + fdescr = rst_file.read() + if return_X_y: return data, target - return Bunch(data=data, target=target, + return Bunch(data=data, target=target, DESCR=fdescr, feature_names=['age', 'sex', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']) diff --git a/sklearn/datasets/tests/test_base.py b/sklearn/datasets/tests/test_base.py index c0dd5101904d911f55bb5df2efe704ef48fe8f32..5c171561bd58c8837ad2fc5ce8473a317b3ac954 100644 --- a/sklearn/datasets/tests/test_base.py +++ b/sklearn/datasets/tests/test_base.py @@ -173,6 +173,7 @@ def test_load_diabetes(): assert_equal(res.data.shape, (442, 10)) assert_true(res.target.size, 442) assert_equal(len(res.feature_names), 10) + assert_true(res.DESCR) # test return_X_y option X_y_tuple = load_diabetes(return_X_y=True)