def test_iterative_imputer_early_stopping():
rng = np.random.RandomState(0)
n = 50
d = 5
A = rng.rand(n, 1)
B = rng.rand(1, d)
X = np.dot(A, B)
nan_mask = rng.rand(n, d) < 0.5
X_missing = X.copy()
X_missing[nan_mask] = np.nan
imputer = IterativeImputer(max_iter=100,
tol=1e-2,
sample_posterior=False,
verbose=1,
random_state=rng)
X_filled_100 = imputer.fit_transform(X_missing)
assert len(imputer.imputation_sequence_) == d * imputer.n_iter_
imputer = IterativeImputer(max_iter=imputer.n_iter_,
sample_posterior=False,
verbose=1,
random_state=rng)
X_filled_early = imputer.fit_transform(X_missing)
assert_allclose(X_filled_100, X_filled_early, atol=1e-7)
imputer = IterativeImputer(max_iter=100,
tol=0,
sample_posterior=False,
verbose=1,
random_state=rng)
imputer.fit(X_missing)
assert imputer.n_iter_ == imputer.max_iter
def test_iterative_imputer_imputation_order(imputation_order):
rng = np.random.RandomState(0)
n = 100
d = 10
max_iter = 2
X = _sparse_random_matrix(n, d, density=0.10, random_state=rng).toarray()
X[:, 0] = 1 # this column should not be discarded by IterativeImputer
imputer = IterativeImputer(missing_values=0,
max_iter=max_iter,
n_nearest_features=5,
sample_posterior=False,
skip_complete=True,
min_value=0,
max_value=1,
verbose=1,
imputation_order=imputation_order,
random_state=rng)
imputer.fit_transform(X)
ordered_idx = [i.feat_idx for i in imputer.imputation_sequence_]
assert (len(ordered_idx) // imputer.n_iter_ ==
imputer.n_features_with_missing_)
if imputation_order == 'roman':
assert np.all(ordered_idx[:d-1] == np.arange(1, d))
elif imputation_order == 'arabic':
assert np.all(ordered_idx[:d-1] == np.arange(d-1, 0, -1))
elif imputation_order == 'random':
ordered_idx_round_1 = ordered_idx[:d-1]
ordered_idx_round_2 = ordered_idx[d-1:]
assert ordered_idx_round_1 != ordered_idx_round_2
elif 'ending' in imputation_order:
assert len(ordered_idx) == max_iter * (d - 1)
def test_iterative_imputer_truncated_normal_posterior():
# test that the values that are imputed using `sample_posterior=True`
# with boundaries (`min_value` and `max_value` are not None) are drawn
# from a distribution that looks gaussian via the Kolmogorov Smirnov test.
# note that starting from the wrong random seed will make this test fail
# because random sampling doesn't occur at all when the imputation
# is outside of the (min_value, max_value) range
pytest.importorskip("scipy", minversion="0.17.0")
rng = np.random.RandomState(42)
X = rng.normal(size=(5, 5))
X[0][0] = np.nan
imputer = IterativeImputer(min_value=0,
max_value=0.5,
sample_posterior=True,
random_state=rng)
imputer.fit_transform(X)
# generate multiple imputations for the single missing value
imputations = np.array([imputer.transform(X)[0][0] for _ in range(100)])
assert all(imputations >= 0)
assert all(imputations <= 0.5)
mu, sigma = imputations.mean(), imputations.std()
ks_statistic, p_value = kstest((imputations - mu) / sigma, 'norm')
if sigma == 0:
sigma += 1e-12
ks_statistic, p_value = kstest((imputations - mu) / sigma, 'norm')
# we want to fail to reject null hypothesis
# null hypothesis: distributions are the same
assert ks_statistic < 0.2 or p_value > 0.1, \
"The posterior does appear to be normal"
def test_iterative_imputer_all_missing():
n = 100
d = 3
X = np.zeros((n, d))
imputer = IterativeImputer(missing_values=0, max_iter=1)
X_imputed = imputer.fit_transform(X)
assert_allclose(X_imputed, imputer.initial_imputer_.transform(X))
def test_iterative_imputer_no_missing():
rng = np.random.RandomState(0)
X = rng.rand(100, 100)
X[:, 0] = np.nan
m1 = IterativeImputer(max_iter=10, random_state=rng)
m2 = IterativeImputer(max_iter=10, random_state=rng)
pred1 = m1.fit(X).transform(X)
pred2 = m2.fit_transform(X)
# should exclude the first column entirely
assert_allclose(X[:, 1:], pred1)
# fit and fit_transform should both be identical
assert_allclose(pred1, pred2)
def test_imputation_shape(strategy):
# Verify the shapes of the imputed matrix for different strategies.
X = np.random.randn(10, 2)
X[::2] = np.nan
imputer = SimpleImputer(strategy=strategy)
X_imputed = imputer.fit_transform(sparse.csr_matrix(X))
assert X_imputed.shape == (10, 2)
X_imputed = imputer.fit_transform(X)
assert X_imputed.shape == (10, 2)
iterative_imputer = IterativeImputer(initial_strategy=strategy)
X_imputed = iterative_imputer.fit_transform(X)
assert X_imputed.shape == (10, 2)
def test_iterative_imputer_estimators(estimator):
rng = np.random.RandomState(0)
n = 100
d = 10
X = _sparse_random_matrix(n, d, density=0.10, random_state=rng).toarray()
imputer = IterativeImputer(missing_values=0,
max_iter=1,
estimator=estimator,
random_state=rng)
imputer.fit_transform(X)
# check that types are correct for estimators
hashes = []
for triplet in imputer.imputation_sequence_:
expected_type = (type(estimator) if estimator is not None
else type(BayesianRidge()))
assert isinstance(triplet.estimator, expected_type)
hashes.append(id(triplet.estimator))
# check that each estimator is unique
assert len(set(hashes)) == len(hashes)
def test_iterative_imputer_rank_one():
rng = np.random.RandomState(0)
d = 50
A = rng.rand(d, 1)
B = rng.rand(1, d)
X = np.dot(A, B)
nan_mask = rng.rand(d, d) < 0.5
X_missing = X.copy()
X_missing[nan_mask] = np.nan
imputer = IterativeImputer(max_iter=5,
verbose=1,
random_state=rng)
X_filled = imputer.fit_transform(X_missing)
assert_allclose(X_filled, X, atol=0.02)
def test_iterative_imputer_clip():
rng = np.random.RandomState(0)
n = 100
d = 10
X = _sparse_random_matrix(n, d, density=0.10,
random_state=rng).toarray()
imputer = IterativeImputer(missing_values=0,
max_iter=1,
min_value=0.1,
max_value=0.2,
random_state=rng)
Xt = imputer.fit_transform(X)
assert_allclose(np.min(Xt[X == 0]), 0.1)
assert_allclose(np.max(Xt[X == 0]), 0.2)
assert_allclose(Xt[X != 0], X[X != 0])
def test_iterative_imputer_clip_truncnorm():
rng = np.random.RandomState(0)
n = 100
d = 10
X = _sparse_random_matrix(n, d, density=0.10, random_state=rng).toarray()
X[:, 0] = 1
imputer = IterativeImputer(missing_values=0,
max_iter=2,
n_nearest_features=5,
sample_posterior=True,
min_value=0.1,
max_value=0.2,
verbose=1,
imputation_order='random',
random_state=rng)
Xt = imputer.fit_transform(X)
assert_allclose(np.min(Xt[X == 0]), 0.1)
assert_allclose(np.max(Xt[X == 0]), 0.2)
assert_allclose(Xt[X != 0], X[X != 0])
def test_iterative_imputer_catch_warning():
# check that we catch a RuntimeWarning due to a division by zero when a
# feature is constant in the dataset
X, y = load_boston(return_X_y=True)
n_samples, n_features = X.shape
# simulate that a feature only contain one category during fit
X[:, 3] = 1
# add some missing values
rng = np.random.RandomState(0)
missing_rate = 0.15
for feat in range(n_features):
sample_idx = rng.choice(
np.arange(n_samples), size=int(n_samples * missing_rate),
replace=False
)
X[sample_idx, feat] = np.nan
imputer = IterativeImputer(n_nearest_features=5, sample_posterior=True)
with pytest.warns(None) as record:
X_fill = imputer.fit_transform(X, y)
assert not record.list
assert not np.any(np.isnan(X_fill))
def test_iterative_imputer_zero_iters():
rng = np.random.RandomState(0)
n = 100
d = 10
X = _sparse_random_matrix(n, d, density=0.10, random_state=rng).toarray()
missing_flag = X == 0
X[missing_flag] = np.nan
imputer = IterativeImputer(max_iter=0)
X_imputed = imputer.fit_transform(X)
# with max_iter=0, only initial imputation is performed
assert_allclose(X_imputed, imputer.initial_imputer_.transform(X))
# repeat but force n_iter_ to 0
imputer = IterativeImputer(max_iter=5).fit(X)
# transformed should not be equal to initial imputation
assert not np.all(imputer.transform(X) ==
imputer.initial_imputer_.transform(X))
imputer.n_iter_ = 0
# now they should be equal as only initial imputation is done
assert_allclose(imputer.transform(X),
imputer.initial_imputer_.transform(X))
def test_iterative_imputer_error_param(max_iter, tol, error_type, warning):
X = np.zeros((100, 2))
imputer = IterativeImputer(max_iter=max_iter, tol=tol)
with pytest.raises(error_type, match=warning):
imputer.fit_transform(X)