def test_shrunk_covariance():
# Tests ShrunkCovariance module on a simple dataset.
# compare shrunk covariance obtained from data and from MLE estimate
cov = ShrunkCovariance(shrinkage=0.5)
cov.fit(X)
assert_array_almost_equal(
shrunk_covariance(empirical_covariance(X), shrinkage=0.5),
cov.covariance_, 4)
# same test with shrinkage not provided
cov = ShrunkCovariance()
cov.fit(X)
assert_array_almost_equal(shrunk_covariance(empirical_covariance(X)),
cov.covariance_, 4)
# same test with shrinkage = 0 (<==> empirical_covariance)
cov = ShrunkCovariance(shrinkage=0.)
cov.fit(X)
assert_array_almost_equal(empirical_covariance(X), cov.covariance_, 4)
# test with n_features = 1
X_1d = X[:, 0].reshape((-1, 1))
cov = ShrunkCovariance(shrinkage=0.3)
cov.fit(X_1d)
assert_array_almost_equal(empirical_covariance(X_1d), cov.covariance_, 4)
# test shrinkage coeff on a simple data set (without saving precision)
cov = ShrunkCovariance(shrinkage=0.5, store_precision=False)
cov.fit(X)
assert (cov.precision_ is None)
def test_graphical_lasso_iris_singular():
# Small subset of rows to test the rank-deficient case
# Need to choose samples such that none of the variances are zero
indices = np.arange(10, 13)
# Hard-coded solution from R glasso package for alpha=0.01
cov_R = np.array([
[0.08, 0.056666662595, 0.00229729713223, 0.00153153142149],
[0.056666662595, 0.082222222222, 0.00333333333333, 0.00222222222222],
[0.002297297132, 0.003333333333, 0.00666666666667, 0.00009009009009],
[0.001531531421, 0.002222222222, 0.00009009009009, 0.00222222222222]
])
icov_R = np.array([
[24.42244057, -16.831679593, 0.0, 0.0],
[-16.83168201, 24.351841681, -6.206896552, -12.5],
[0.0, -6.206896171, 153.103448276, 0.0],
[0.0, -12.499999143, 0.0, 462.5]
])
X = datasets.load_iris().data[indices, :]
emp_cov = empirical_covariance(X)
for method in ('cd', 'lars'):
cov, icov = graphical_lasso(emp_cov, alpha=0.01, return_costs=False,
mode=method)
assert_array_almost_equal(cov, cov_R, decimal=5)
assert_array_almost_equal(icov, icov_R, decimal=5)
def launch_mcd_on_dataset(n_samples, n_features, n_outliers, tol_loc, tol_cov,
tol_support):
rand_gen = np.random.RandomState(0)
data = rand_gen.randn(n_samples, n_features)
# add some outliers
outliers_index = rand_gen.permutation(n_samples)[:n_outliers]
outliers_offset = 10. * \
(rand_gen.randint(2, size=(n_outliers, n_features)) - 0.5)
data[outliers_index] += outliers_offset
inliers_mask = np.ones(n_samples).astype(bool)
inliers_mask[outliers_index] = False
pure_data = data[inliers_mask]
# compute MCD by fitting an object
mcd_fit = MinCovDet(random_state=rand_gen).fit(data)
T = mcd_fit.location_
S = mcd_fit.covariance_
H = mcd_fit.support_
# compare with the estimates learnt from the inliers
error_location = np.mean((pure_data.mean(0) - T)**2)
assert (error_location < tol_loc)
error_cov = np.mean((empirical_covariance(pure_data) - S)**2)
assert (error_cov < tol_cov)
assert (np.sum(H) >= tol_support)
assert_array_almost_equal(mcd_fit.mahalanobis(data), mcd_fit.dist_)
def test_covariance():
# Tests Covariance module on a simple dataset.
# test covariance fit from data
cov = EmpiricalCovariance()
cov.fit(X)
emp_cov = empirical_covariance(X)
assert_array_almost_equal(emp_cov, cov.covariance_, 4)
assert_almost_equal(cov.error_norm(emp_cov), 0)
assert_almost_equal(cov.error_norm(emp_cov, norm='spectral'), 0)
assert_almost_equal(cov.error_norm(emp_cov, norm='frobenius'), 0)
assert_almost_equal(cov.error_norm(emp_cov, scaling=False), 0)
assert_almost_equal(cov.error_norm(emp_cov, squared=False), 0)
with pytest.raises(NotImplementedError):
cov.error_norm(emp_cov, norm='foo')
# Mahalanobis distances computation test
mahal_dist = cov.mahalanobis(X)
assert np.amin(mahal_dist) > 0
# test with n_features = 1
X_1d = X[:, 0].reshape((-1, 1))
cov = EmpiricalCovariance()
cov.fit(X_1d)
assert_array_almost_equal(empirical_covariance(X_1d), cov.covariance_, 4)
assert_almost_equal(cov.error_norm(empirical_covariance(X_1d)), 0)
assert_almost_equal(
cov.error_norm(empirical_covariance(X_1d), norm='spectral'), 0)
# test with one sample
# Create X with 1 sample and 5 features
X_1sample = np.arange(5).reshape(1, 5)
cov = EmpiricalCovariance()
assert_warns(UserWarning, cov.fit, X_1sample)
assert_array_almost_equal(cov.covariance_,
np.zeros(shape=(5, 5), dtype=np.float64))
# test integer type
X_integer = np.asarray([[0, 1], [1, 0]])
result = np.asarray([[0.25, -0.25], [-0.25, 0.25]])
assert_array_almost_equal(empirical_covariance(X_integer), result)
# test centered case
cov = EmpiricalCovariance(assume_centered=True)
cov.fit(X)
assert_array_equal(cov.location_, np.zeros(X.shape[1]))
def test_graph_lasso_2D():
# Hard-coded solution from Python skggm package
# obtained by calling `quic(emp_cov, lam=.1, tol=1e-8)`
cov_skggm = np.array([[3.09550269, 1.186972],
[1.186972, 0.57713289]])
icov_skggm = np.array([[1.52836773, -3.14334831],
[-3.14334831, 8.19753385]])
X = datasets.load_iris().data[:, 2:]
emp_cov = empirical_covariance(X)
for method in ('cd', 'lars'):
cov, icov = graphical_lasso(emp_cov, alpha=.1, return_costs=False,
mode=method)
assert_array_almost_equal(cov, cov_skggm)
assert_array_almost_equal(icov, icov_skggm)
def test_graphical_lasso(random_state=0):
# Sample data from a sparse multivariate normal
dim = 20
n_samples = 100
random_state = check_random_state(random_state)
prec = make_sparse_spd_matrix(dim, alpha=.95,
random_state=random_state)
cov = linalg.inv(prec)
X = random_state.multivariate_normal(np.zeros(dim), cov, size=n_samples)
emp_cov = empirical_covariance(X)
for alpha in (0., .1, .25):
covs = dict()
icovs = dict()
for method in ('cd', 'lars'):
cov_, icov_, costs = graphical_lasso(emp_cov, return_costs=True,
alpha=alpha, mode=method)
covs[method] = cov_
icovs[method] = icov_
costs, dual_gap = np.array(costs).T
# Check that the costs always decrease (doesn't hold if alpha == 0)
if not alpha == 0:
assert_array_less(np.diff(costs), 0)
# Check that the 2 approaches give similar results
assert_array_almost_equal(covs['cd'], covs['lars'], decimal=4)
assert_array_almost_equal(icovs['cd'], icovs['lars'], decimal=4)
# Smoke test the estimator
model = GraphicalLasso(alpha=.25).fit(X)
model.score(X)
assert_array_almost_equal(model.covariance_, covs['cd'], decimal=4)
assert_array_almost_equal(model.covariance_, covs['lars'], decimal=4)
# For a centered matrix, assume_centered could be chosen True or False
# Check that this returns indeed the same result for centered data
Z = X - X.mean(0)
precs = list()
for assume_centered in (False, True):
prec_ = GraphicalLasso(
assume_centered=assume_centered).fit(Z).precision_
precs.append(prec_)
assert_array_almost_equal(precs[0], precs[1])
def _naive_ledoit_wolf_shrinkage(X):
# A simple implementation of the formulas from Ledoit & Wolf
# The computation below achieves the following computations of the
# "O. Ledoit and M. Wolf, A Well-Conditioned Estimator for
# Large-Dimensional Covariance Matrices"
# beta and delta are given in the beginning of section 3.2
n_samples, n_features = X.shape
emp_cov = empirical_covariance(X, assume_centered=False)
mu = np.trace(emp_cov) / n_features
delta_ = emp_cov.copy()
delta_.flat[::n_features + 1] -= mu
delta = (delta_**2).sum() / n_features
X2 = X**2
beta_ = 1. / (n_features * n_samples) \
* np.sum(np.dot(X2.T, X2) / n_samples - emp_cov ** 2)
beta = min(beta_, delta)
shrinkage = beta / delta
return shrinkage
def test_graphical_lasso_iris():
# Hard-coded solution from R glasso package for alpha=1.0
# (need to set penalize.diagonal to FALSE)
cov_R = np.array([
[0.68112222, 0.0000000, 0.265820, 0.02464314],
[0.00000000, 0.1887129, 0.000000, 0.00000000],
[0.26582000, 0.0000000, 3.095503, 0.28697200],
[0.02464314, 0.0000000, 0.286972, 0.57713289]
])
icov_R = np.array([
[1.5190747, 0.000000, -0.1304475, 0.0000000],
[0.0000000, 5.299055, 0.0000000, 0.0000000],
[-0.1304475, 0.000000, 0.3498624, -0.1683946],
[0.0000000, 0.000000, -0.1683946, 1.8164353]
])
X = datasets.load_iris().data
emp_cov = empirical_covariance(X)
for method in ('cd', 'lars'):
cov, icov = graphical_lasso(emp_cov, alpha=1.0, return_costs=False,
mode=method)
assert_array_almost_equal(cov, cov_R)
assert_array_almost_equal(icov, icov_R)
X_test = np.dot(base_X_test, coloring_matrix)
# #############################################################################
# Compute the likelihood on test data
# spanning a range of possible shrinkage coefficient values
shrinkages = np.logspace(-2, 0, 30)
negative_logliks = [
-ShrunkCovariance(shrinkage=s).fit(X_train).score(X_test)
for s in shrinkages
]
# under the ground-truth model, which we would not have access to in real
# settings
real_cov = np.dot(coloring_matrix.T, coloring_matrix)
emp_cov = empirical_covariance(X_train)
loglik_real = -log_likelihood(emp_cov, linalg.inv(real_cov))
# #############################################################################
# Compare different approaches to setting the parameter
# GridSearch for an optimal shrinkage coefficient
tuned_parameters = [{'shrinkage': shrinkages}]
cv = GridSearchCV(ShrunkCovariance(), tuned_parameters)
cv.fit(X_train)
# Ledoit-Wolf optimal shrinkage coefficient estimate
lw = LedoitWolf()
loglik_lw = lw.fit(X_train).score(X_test)
# OAS coefficient estimate
def test_oas():
# Tests OAS module on a simple dataset.
# test shrinkage coeff on a simple data set
X_centered = X - X.mean(axis=0)
oa = OAS(assume_centered=True)
oa.fit(X_centered)
shrinkage_ = oa.shrinkage_
score_ = oa.score(X_centered)
# compare shrunk covariance obtained from data and from MLE estimate
oa_cov_from_mle, oa_shrinkage_from_mle = oas(X_centered,
assume_centered=True)
assert_array_almost_equal(oa_cov_from_mle, oa.covariance_, 4)
assert_almost_equal(oa_shrinkage_from_mle, oa.shrinkage_)
# compare estimates given by OAS and ShrunkCovariance
scov = ShrunkCovariance(shrinkage=oa.shrinkage_, assume_centered=True)
scov.fit(X_centered)
assert_array_almost_equal(scov.covariance_, oa.covariance_, 4)
# test with n_features = 1
X_1d = X[:, 0:1]
oa = OAS(assume_centered=True)
oa.fit(X_1d)
oa_cov_from_mle, oa_shrinkage_from_mle = oas(X_1d, assume_centered=True)
assert_array_almost_equal(oa_cov_from_mle, oa.covariance_, 4)
assert_almost_equal(oa_shrinkage_from_mle, oa.shrinkage_)
assert_array_almost_equal((X_1d**2).sum() / n_samples, oa.covariance_, 4)
# test shrinkage coeff on a simple data set (without saving precision)
oa = OAS(store_precision=False, assume_centered=True)
oa.fit(X_centered)
assert_almost_equal(oa.score(X_centered), score_, 4)
assert (oa.precision_ is None)
# Same tests without assuming centered data--------------------------------
# test shrinkage coeff on a simple data set
oa = OAS()
oa.fit(X)
assert_almost_equal(oa.shrinkage_, shrinkage_, 4)
assert_almost_equal(oa.score(X), score_, 4)
# compare shrunk covariance obtained from data and from MLE estimate
oa_cov_from_mle, oa_shrinkage_from_mle = oas(X)
assert_array_almost_equal(oa_cov_from_mle, oa.covariance_, 4)
assert_almost_equal(oa_shrinkage_from_mle, oa.shrinkage_)
# compare estimates given by OAS and ShrunkCovariance
scov = ShrunkCovariance(shrinkage=oa.shrinkage_)
scov.fit(X)
assert_array_almost_equal(scov.covariance_, oa.covariance_, 4)
# test with n_features = 1
X_1d = X[:, 0].reshape((-1, 1))
oa = OAS()
oa.fit(X_1d)
oa_cov_from_mle, oa_shrinkage_from_mle = oas(X_1d)
assert_array_almost_equal(oa_cov_from_mle, oa.covariance_, 4)
assert_almost_equal(oa_shrinkage_from_mle, oa.shrinkage_)
assert_array_almost_equal(empirical_covariance(X_1d), oa.covariance_, 4)
# test with one sample
# warning should be raised when using only 1 sample
X_1sample = np.arange(5).reshape(1, 5)
oa = OAS()
assert_warns(UserWarning, oa.fit, X_1sample)
assert_array_almost_equal(oa.covariance_,
np.zeros(shape=(5, 5), dtype=np.float64))
# test shrinkage coeff on a simple data set (without saving precision)
oa = OAS(store_precision=False)
oa.fit(X)
assert_almost_equal(oa.score(X), score_, 4)
assert (oa.precision_ is None)
def test_ledoit_wolf():
# Tests LedoitWolf module on a simple dataset.
# test shrinkage coeff on a simple data set
X_centered = X - X.mean(axis=0)
lw = LedoitWolf(assume_centered=True)
lw.fit(X_centered)
shrinkage_ = lw.shrinkage_
score_ = lw.score(X_centered)
assert_almost_equal(
ledoit_wolf_shrinkage(X_centered, assume_centered=True), shrinkage_)
assert_almost_equal(
ledoit_wolf_shrinkage(X_centered, assume_centered=True, block_size=6),
shrinkage_)
# compare shrunk covariance obtained from data and from MLE estimate
lw_cov_from_mle, lw_shrinkage_from_mle = ledoit_wolf(X_centered,
assume_centered=True)
assert_array_almost_equal(lw_cov_from_mle, lw.covariance_, 4)
assert_almost_equal(lw_shrinkage_from_mle, lw.shrinkage_)
# compare estimates given by LW and ShrunkCovariance
scov = ShrunkCovariance(shrinkage=lw.shrinkage_, assume_centered=True)
scov.fit(X_centered)
assert_array_almost_equal(scov.covariance_, lw.covariance_, 4)
# test with n_features = 1
X_1d = X[:, 0].reshape((-1, 1))
lw = LedoitWolf(assume_centered=True)
lw.fit(X_1d)
lw_cov_from_mle, lw_shrinkage_from_mle = ledoit_wolf(X_1d,
assume_centered=True)
assert_array_almost_equal(lw_cov_from_mle, lw.covariance_, 4)
assert_almost_equal(lw_shrinkage_from_mle, lw.shrinkage_)
assert_array_almost_equal((X_1d**2).sum() / n_samples, lw.covariance_, 4)
# test shrinkage coeff on a simple data set (without saving precision)
lw = LedoitWolf(store_precision=False, assume_centered=True)
lw.fit(X_centered)
assert_almost_equal(lw.score(X_centered), score_, 4)
assert (lw.precision_ is None)
# Same tests without assuming centered data
# test shrinkage coeff on a simple data set
lw = LedoitWolf()
lw.fit(X)
assert_almost_equal(lw.shrinkage_, shrinkage_, 4)
assert_almost_equal(lw.shrinkage_, ledoit_wolf_shrinkage(X))
assert_almost_equal(lw.shrinkage_, ledoit_wolf(X)[1])
assert_almost_equal(lw.score(X), score_, 4)
# compare shrunk covariance obtained from data and from MLE estimate
lw_cov_from_mle, lw_shrinkage_from_mle = ledoit_wolf(X)
assert_array_almost_equal(lw_cov_from_mle, lw.covariance_, 4)
assert_almost_equal(lw_shrinkage_from_mle, lw.shrinkage_)
# compare estimates given by LW and ShrunkCovariance
scov = ShrunkCovariance(shrinkage=lw.shrinkage_)
scov.fit(X)
assert_array_almost_equal(scov.covariance_, lw.covariance_, 4)
# test with n_features = 1
X_1d = X[:, 0].reshape((-1, 1))
lw = LedoitWolf()
lw.fit(X_1d)
lw_cov_from_mle, lw_shrinkage_from_mle = ledoit_wolf(X_1d)
assert_array_almost_equal(lw_cov_from_mle, lw.covariance_, 4)
assert_almost_equal(lw_shrinkage_from_mle, lw.shrinkage_)
assert_array_almost_equal(empirical_covariance(X_1d), lw.covariance_, 4)
# test with one sample
# warning should be raised when using only 1 sample
X_1sample = np.arange(5).reshape(1, 5)
lw = LedoitWolf()
assert_warns(UserWarning, lw.fit, X_1sample)
assert_array_almost_equal(lw.covariance_,
np.zeros(shape=(5, 5), dtype=np.float64))
# test shrinkage coeff on a simple data set (without saving precision)
lw = LedoitWolf(store_precision=False)
lw.fit(X)
assert_almost_equal(lw.score(X), score_, 4)
assert (lw.precision_ is None)