def test_resample_stratified_replace():
# Make sure stratified resampling supports the replace parameter
rng = np.random.RandomState(0)
n_samples = 100
X = rng.normal(size=(n_samples, 1))
y = rng.randint(0, 2, size=n_samples)
X_replace, _ = resample(X,
y,
replace=True,
n_samples=50,
random_state=rng,
stratify=y)
X_no_replace, _ = resample(X,
y,
replace=False,
n_samples=50,
random_state=rng,
stratify=y)
assert np.unique(X_replace).shape[0] < 50
assert np.unique(X_no_replace).shape[0] == 50
# make sure n_samples can be greater than X.shape[0] if we sample with
# replacement
X_replace, _ = resample(X,
y,
replace=True,
n_samples=1000,
random_state=rng,
stratify=y)
assert X_replace.shape[0] == 1000
assert np.unique(X_replace).shape[0] == 100
def test_resample():
# Border case not worth mentioning in doctests
assert resample() is None
# Check that invalid arguments yield ValueError
assert_raises(ValueError, resample, [0], [0, 1])
assert_raises(ValueError,
resample, [0, 1], [0, 1],
replace=False,
n_samples=3)
assert_raises(ValueError, resample, [0, 1], [0, 1], meaning_of_life=42)
# Issue:6581, n_samples can be more when replace is True (default).
assert len(resample([1, 2], n_samples=5)) == 5
def test_resample_stratify_2dy():
# Make sure y can be 2d when stratifying
rng = np.random.RandomState(0)
n_samples = 100
X = rng.normal(size=(n_samples, 1))
y = rng.randint(0, 2, size=(n_samples, 2))
X, y = resample(X, y, n_samples=50, random_state=rng, stratify=y)
assert y.ndim == 2
def test_resample_stratified():
# Make sure resample can stratify
rng = np.random.RandomState(0)
n_samples = 100
p = .9
X = rng.normal(size=(n_samples, 1))
y = rng.binomial(1, p, size=n_samples)
_, y_not_stratified = resample(X,
y,
n_samples=10,
random_state=0,
stratify=None)
assert np.all(y_not_stratified == 1)
_, y_stratified = resample(X, y, n_samples=10, random_state=0, stratify=y)
assert not np.all(y_stratified == 1)
assert np.sum(y_stratified) == 9 # all 1s, one 0
def test_resample_stratify_sparse_error():
# resample must be ndarray
rng = np.random.RandomState(0)
n_samples = 100
X = rng.normal(size=(n_samples, 2))
y = rng.randint(0, 2, size=n_samples)
stratify = sp.csr_matrix(y)
with pytest.raises(TypeError, match='A sparse matrix was passed'):
X, y = resample(X,
y,
n_samples=50,
random_state=rng,
stratify=stratify)