def test_chained_imputer_imputation_order(imputation_order):
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 # this column should not be discarded by ChainedImputer
imputer = ChainedImputer(missing_values=0,
n_imputations=1,
n_burn_in=1,
n_nearest_features=5,
min_value=0,
max_value=1,
verbose=False,
imputation_order=imputation_order,
random_state=rng)
imputer.fit_transform(X)
ordered_idx = [i.feat_idx for i in imputer.imputation_sequence_]
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) == 2 * (d - 1)
def test_chained_imputer_additive_matrix():
rng = np.random.RandomState(0)
n = 100
d = 10
A = rng.randn(n, d)
B = rng.randn(n, d)
X_filled = np.zeros(A.shape)
for i in range(d):
for j in range(d):
X_filled[:, (i+j) % d] += (A[:, i] + B[:, j]) / 2
# a quarter is randomly missing
nan_mask = rng.rand(n, d) < 0.25
X_missing = X_filled.copy()
X_missing[nan_mask] = np.nan
# split up data
n = n // 2
X_train = X_missing[:n]
X_test_filled = X_filled[n:]
X_test = X_missing[n:]
imputer = ChainedImputer(n_imputations=25,
n_burn_in=10,
verbose=True,
random_state=rng).fit(X_train)
X_test_est = imputer.transform(X_test)
assert_allclose(X_test_filled, X_test_est, atol=0.01)
def test_chained_imputer_no_missing():
rng = np.random.RandomState(0)
X = rng.rand(100, 100)
X[:, 0] = np.nan
m1 = ChainedImputer(n_imputations=10, random_state=rng)
m2 = ChainedImputer(n_imputations=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():
# Verify the shapes of the imputed matrix for different strategies.
X = np.random.randn(10, 2)
X[::2] = np.nan
for strategy in ['mean', 'median', 'most_frequent', "constant"]:
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)
chained_imputer = ChainedImputer(initial_strategy=strategy)
X_imputed = chained_imputer.fit_transform(X)
assert X_imputed.shape == (10, 2)
def test_chained_imputer_rank_one():
rng = np.random.RandomState(0)
d = 100
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 = ChainedImputer(n_imputations=5,
n_burn_in=5,
verbose=True,
random_state=rng)
X_filled = imputer.fit_transform(X_missing)
assert_allclose(X_filled, X, atol=0.001)
def test_chained_imputer_transform_stochasticity():
rng = np.random.RandomState(0)
n = 100
d = 10
X = sparse_random_matrix(n, d, density=0.10,
random_state=rng).toarray()
imputer = ChainedImputer(missing_values=0,
n_imputations=1,
n_burn_in=1,
random_state=rng)
imputer.fit(X)
X_fitted_1 = imputer.transform(X)
X_fitted_2 = imputer.transform(X)
# sufficient to assert that the means are not the same
assert np.mean(X_fitted_1) != pytest.approx(np.mean(X_fitted_2))
def test_chained_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 = ChainedImputer(missing_values=0,
n_imputations=1,
n_burn_in=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_chained_imputer_missing_at_transform(strategy):
rng = np.random.RandomState(0)
n = 100
d = 10
X_train = rng.randint(low=0, high=3, size=(n, d))
X_test = rng.randint(low=0, high=3, size=(n, d))
X_train[:, 0] = 1 # definitely no missing values in 0th column
X_test[0, 0] = 0 # definitely missing value in 0th column
imputer = ChainedImputer(missing_values=0,
n_imputations=1,
n_burn_in=1,
initial_strategy=strategy,
random_state=rng).fit(X_train)
initial_imputer = SimpleImputer(missing_values=0,
strategy=strategy).fit(X_train)
# if there were no missing values at time of fit, then imputer will
# only use the initial imputer for that feature at transform
assert np.all(imputer.transform(X_test)[:, 0] ==
initial_imputer.transform(X_test)[:, 0])
def test_chained_imputer_predictors(predictor):
rng = np.random.RandomState(0)
n = 100
d = 10
X = sparse_random_matrix(n, d, density=0.10, random_state=rng).toarray()
imputer = ChainedImputer(missing_values=0,
n_imputations=1,
n_burn_in=1,
predictor=predictor,
random_state=rng)
imputer.fit_transform(X)
# check that types are correct for predictors
hashes = []
for triplet in imputer.imputation_sequence_:
assert triplet.predictor
hashes.append(id(triplet.predictor))
# check that each predictor is unique
assert len(set(hashes)) == len(hashes)
def test_chained_imputer_transform_recovery(rank):
rng = np.random.RandomState(0)
n = 100
d = 100
A = rng.rand(n, rank)
B = rng.rand(rank, d)
X_filled = np.dot(A, B)
# half is randomly missing
nan_mask = rng.rand(n, d) < 0.5
X_missing = X_filled.copy()
X_missing[nan_mask] = np.nan
# split up data in half
n = n // 2
X_train = X_missing[:n]
X_test_filled = X_filled[n:]
X_test = X_missing[n:]
imputer = ChainedImputer(n_imputations=10,
n_burn_in=10,
verbose=True,
random_state=rng).fit(X_train)
X_test_est = imputer.transform(X_test)
assert_allclose(X_test_filled, X_test_est, rtol=1e-5, atol=0.1)
def test_chained_imputer_missing_at_transform(strategy):
rng = np.random.RandomState(0)
n = 100
d = 10
X_train = rng.randint(low=0, high=3, size=(n, d))
X_test = rng.randint(low=0, high=3, size=(n, d))
X_train[:, 0] = 1 # definitely no missing values in 0th column
X_test[0, 0] = 0 # definitely missing value in 0th column
imputer = ChainedImputer(missing_values=0,
n_imputations=1,
n_burn_in=1,
initial_strategy=strategy,
random_state=rng).fit(X_train)
initial_imputer = SimpleImputer(missing_values=0,
strategy=strategy).fit(X_train)
# if there were no missing values at time of fit, then imputer will
# only use the initial imputer for that feature at transform
assert np.all(
imputer.transform(X_test)[:,
0] == initial_imputer.transform(X_test)[:,
0])
def test_chained_imputer_transform_recovery(rank):
rng = np.random.RandomState(0)
n = 100
d = 100
A = rng.rand(n, rank)
B = rng.rand(rank, d)
X_filled = np.dot(A, B)
# half is randomly missing
nan_mask = rng.rand(n, d) < 0.5
X_missing = X_filled.copy()
X_missing[nan_mask] = np.nan
# split up data in half
n = n // 2
X_train = X_missing[:n]
X_test_filled = X_filled[n:]
X_test = X_missing[n:]
imputer = ChainedImputer(n_imputations=10,
n_burn_in=10,
verbose=True,
random_state=rng).fit(X_train)
X_test_est = imputer.transform(X_test)
assert_allclose(X_test_filled, X_test_est, rtol=1e-5, atol=0.1)
def test_chained_imputer_no_missing():
rng = np.random.RandomState(0)
X = rng.rand(100, 100)
X[:, 0] = np.nan
m1 = ChainedImputer(n_imputations=10, random_state=rng)
m2 = ChainedImputer(n_imputations=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)