def plot_contours(self, ax, show=False):
COV = self.emp_cov
COV_slice = EmpiricalCovariance()
COV_slice.location_ = np.array([ COV.location_[0], COV.location_[1] ])
COV_slice.covariance_ = np.array([ COV.covariance_[ 0,0 ], COV.covariance_[ 0,1 ],
COV.covariance_[ 1,0 ], COV.covariance_[ 1,1 ] ])
COV_slice.covariance_ = COV_slice.covariance_.reshape((2,2))
COV_slice.precision_ = np.array([ COV.precision_[ 0,0 ], COV.precision_[ 0,1 ],
COV.precision_[ 1,0 ], COV.precision_[ 1,1 ] ])
COV_slice.precision_ = COV_slice.precision_.reshape((2,2))
# Show contours of the distance functions
xx, yy = np.meshgrid(
np.linspace(COV_slice.location_[0]-5*math.sqrt(COV_slice.covariance_[0,0]), COV_slice.location_[0]+5*math.sqrt(COV_slice.covariance_[0,0]), 100),
np.linspace(COV_slice.location_[1]-5*math.sqrt(COV_slice.covariance_[1,1]), COV_slice.location_[1]+5*math.sqrt(COV_slice.covariance_[1,1]), 100),
)
zz = np.c_[xx.ravel(), yy.ravel()]
# Empirical fit is not so good. Don't plot this
if False: # keep for debugging
mahal_emp_cov = COV_slice.mahalanobis(zz)
mahal_emp_cov = mahal_emp_cov.reshape(xx.shape)
emp_cov_contour = ax.contour(xx, yy, np.sqrt(mahal_emp_cov),
levels=[1.,2.,3.,4.,5.],
#cmap=plt.cm.PuBu_r,
cmap=plt.cm.cool_r,
linestyles='dashed')
COV = self.rob_cov
COV_slice = EmpiricalCovariance()
COV_slice.location_ = np.array([ COV.location_[0], COV.location_[1] ])
COV_slice.covariance_ = np.array([ COV.covariance_[ 0,0 ], COV.covariance_[ 0,1 ],
COV.covariance_[ 1,0 ], COV.covariance_[ 1,1 ] ])
COV_slice.covariance_ = COV_slice.covariance_.reshape((2,2))
COV_slice.precision_ = np.array([ COV.precision_[ 0,0 ], COV.precision_[ 0,1 ],
COV.precision_[ 1,0 ], COV.precision_[ 1,1 ] ])
COV_slice.precision_ = COV_slice.precision_.reshape((2,2))
self.robust_model_XY = COV_slice
# robust is better
if show:
mahal_robust_cov = COV_slice.mahalanobis(zz)
mahal_robust_cov = mahal_robust_cov.reshape(xx.shape)
robust_contour = ax.contour(xx, yy, np.sqrt(mahal_robust_cov),
levels=[1.,2.,3.,4.,5.],
#cmap=plt.cm.YlOrBr_r,
cmap=plt.cm.spring_r,
linestyles='dotted')
def test_suffstat_sk_tied():
# use equation Nk * Sk / N = S_tied
rng = np.random.RandomState(0)
n_samples, n_features, n_components = 500, 2, 2
resp = rng.rand(n_samples, n_components)
resp = resp / resp.sum(axis=1)[:, np.newaxis]
X = rng.rand(n_samples, n_features)
nk = resp.sum(axis=0)
xk = np.dot(resp.T, X) / nk[:, np.newaxis]
covars_pred_full = _estimate_gaussian_covariances_full(resp, X, nk, xk, 0)
covars_pred_full = np.sum(nk[:, np.newaxis, np.newaxis] * covars_pred_full,
0) / n_samples
covars_pred_tied = _estimate_gaussian_covariances_tied(resp, X, nk, xk, 0)
ecov = EmpiricalCovariance()
ecov.covariance_ = covars_pred_full
assert_almost_equal(ecov.error_norm(covars_pred_tied, norm='frobenius'), 0)
assert_almost_equal(ecov.error_norm(covars_pred_tied, norm='spectral'), 0)
# check the precision computation
precs_chol_pred = _compute_precision_cholesky(covars_pred_tied, 'tied')
precs_pred = np.dot(precs_chol_pred, precs_chol_pred.T)
precs_est = linalg.inv(covars_pred_tied)
assert_array_almost_equal(precs_est, precs_pred)
def test_suffstat_sk_tied():
# use equation Nk * Sk / N = S_tied
rng = np.random.RandomState(0)
n_samples, n_features, n_components = 500, 2, 2
resp = rng.rand(n_samples, n_components)
resp = resp / resp.sum(axis=1)[:, np.newaxis]
X = rng.rand(n_samples, n_features)
nk = resp.sum(axis=0)
xk = np.dot(resp.T, X) / nk[:, np.newaxis]
covars_pred_full = _estimate_gaussian_covariances_full(resp, X, nk, xk, 0)
covars_pred_full = np.sum(nk[:, np.newaxis, np.newaxis] * covars_pred_full,
0) / n_samples
covars_pred_tied = _estimate_gaussian_covariances_tied(resp, X, nk, xk, 0)
ecov = EmpiricalCovariance()
ecov.covariance_ = covars_pred_full
assert_almost_equal(ecov.error_norm(covars_pred_tied, norm='frobenius'), 0)
assert_almost_equal(ecov.error_norm(covars_pred_tied, norm='spectral'), 0)
# check the precision computation
precs_chol_pred = _compute_precision_cholesky(covars_pred_tied, 'tied')
precs_pred = np.dot(precs_chol_pred, precs_chol_pred.T)
precs_est = linalg.inv(covars_pred_tied)
assert_array_almost_equal(precs_est, precs_pred)
def test_suffstat_sk_diag():
# test against 'full' case
rng = np.random.RandomState(0)
n_samples, n_features, n_components = 500, 2, 2
resp = rng.rand(n_samples, n_components)
resp = resp / resp.sum(axis=1)[:, np.newaxis]
X = rng.rand(n_samples, n_features)
nk = resp.sum(axis=0)
xk = np.dot(resp.T, X) / nk[:, np.newaxis]
precs_pred_full = _estimate_gaussian_precisions_cholesky_full(
resp, X, nk, xk, 0)
covars_pred_full = [
linalg.inv(np.dot(precision_chol, precision_chol.T))
for precision_chol in precs_pred_full
]
precs_pred_diag = _estimate_gaussian_precisions_cholesky_diag(
resp, X, nk, xk, 0)
covars_pred_diag = np.array([np.diag(1. / d)**2 for d in precs_pred_diag])
ecov = EmpiricalCovariance()
for (cov_full, cov_diag) in zip(covars_pred_full, covars_pred_diag):
ecov.covariance_ = np.diag(np.diag(cov_full))
assert_almost_equal(ecov.error_norm(cov_diag, norm='frobenius'), 0)
assert_almost_equal(ecov.error_norm(cov_diag, norm='spectral'), 0)
def test_suffstat_sk_diag():
# test against 'full' case
rng = np.random.RandomState(0)
n_samples, n_features, n_components = 500, 2, 2
resp = rng.rand(n_samples, n_components)
resp = resp / resp.sum(axis=1)[:, np.newaxis]
X = rng.rand(n_samples, n_features)
nk = resp.sum(axis=0)
xk = np.dot(resp.T, X) / nk[:, np.newaxis]
precs_pred_full = _estimate_gaussian_precisions_cholesky_full(resp, X,
nk, xk, 0)
covars_pred_full = [linalg.inv(np.dot(precision_chol, precision_chol.T))
for precision_chol in precs_pred_full]
precs_pred_diag = _estimate_gaussian_precisions_cholesky_diag(resp, X,
nk, xk, 0)
covars_pred_diag = np.array([np.diag(1. / d) ** 2
for d in precs_pred_diag])
ecov = EmpiricalCovariance()
for (cov_full, cov_diag) in zip(covars_pred_full, covars_pred_diag):
ecov.covariance_ = np.diag(np.diag(cov_full))
assert_almost_equal(ecov.error_norm(cov_diag, norm='frobenius'), 0)
assert_almost_equal(ecov.error_norm(cov_diag, norm='spectral'), 0)
def test_gaussian_mixture_fit():
# recover the ground truth
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
n_features = rand_data.n_features
n_components = rand_data.n_components
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
g = GaussianMixture(
n_components=n_components,
n_init=20,
reg_covar=0,
random_state=rng,
covariance_type=covar_type,
)
g.fit(X)
# needs more data to pass the test with rtol=1e-7
assert_allclose(np.sort(g.weights_),
np.sort(rand_data.weights),
rtol=0.1,
atol=1e-2)
arg_idx1 = g.means_[:, 0].argsort()
arg_idx2 = rand_data.means[:, 0].argsort()
assert_allclose(g.means_[arg_idx1],
rand_data.means[arg_idx2],
rtol=0.1,
atol=1e-2)
if covar_type == "full":
prec_pred = g.precisions_
prec_test = rand_data.precisions["full"]
elif covar_type == "tied":
prec_pred = np.array([g.precisions_] * n_components)
prec_test = np.array([rand_data.precisions["tied"]] * n_components)
elif covar_type == "spherical":
prec_pred = np.array(
[np.eye(n_features) * c for c in g.precisions_])
prec_test = np.array([
np.eye(n_features) * c
for c in rand_data.precisions["spherical"]
])
elif covar_type == "diag":
prec_pred = np.array([np.diag(d) for d in g.precisions_])
prec_test = np.array(
[np.diag(d) for d in rand_data.precisions["diag"]])
arg_idx1 = np.trace(prec_pred, axis1=1, axis2=2).argsort()
arg_idx2 = np.trace(prec_test, axis1=1, axis2=2).argsort()
for k, h in zip(arg_idx1, arg_idx2):
ecov = EmpiricalCovariance()
ecov.covariance_ = prec_test[h]
# the accuracy depends on the number of data and randomness, rng
assert_allclose(ecov.error_norm(prec_pred[k]), 0, atol=0.15)
def test_gaussian_mixture_fit():
# recover the ground truth
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
n_features = rand_data.n_features
n_components = rand_data.n_components
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
g = GaussianMixture(n_components=n_components, n_init=20,
reg_covar=0, random_state=rng,
covariance_type=covar_type)
g.fit(X)
# needs more data to pass the test with rtol=1e-7
assert_allclose(np.sort(g.weights_), np.sort(rand_data.weights),
rtol=0.1, atol=1e-2)
arg_idx1 = g.means_[:, 0].argsort()
arg_idx2 = rand_data.means[:, 0].argsort()
assert_allclose(g.means_[arg_idx1], rand_data.means[arg_idx2],
rtol=0.1, atol=1e-2)
if covar_type == 'full':
prec_pred = g.precisions_
prec_test = rand_data.precisions['full']
elif covar_type == 'tied':
prec_pred = np.array([g.precisions_] * n_components)
prec_test = np.array([rand_data.precisions['tied']] * n_components)
elif covar_type == 'spherical':
prec_pred = np.array([np.eye(n_features) * c
for c in g.precisions_])
prec_test = np.array([np.eye(n_features) * c for c in
rand_data.precisions['spherical']])
elif covar_type == 'diag':
prec_pred = np.array([np.diag(d) for d in g.precisions_])
prec_test = np.array([np.diag(d) for d in
rand_data.precisions['diag']])
arg_idx1 = np.trace(prec_pred, axis1=1, axis2=2).argsort()
arg_idx2 = np.trace(prec_test, axis1=1, axis2=2).argsort()
for k, h in zip(arg_idx1, arg_idx2):
ecov = EmpiricalCovariance()
ecov.covariance_ = prec_test[h]
# the accuracy depends on the number of data and randomness, rng
assert_allclose(ecov.error_norm(prec_pred[k]), 0, atol=0.1)
def test_suffstat_sk_tied():
# use equation Nk * Sk / N = S_tied
rng = np.random.RandomState(0)
n_samples, n_features, n_components = 500, 2, 2
resp = rng.rand(n_samples, n_components)
resp = resp / resp.sum(axis=1)[:, np.newaxis]
X = rng.rand(n_samples, n_features)
nk = resp.sum(axis=0)
xk = np.dot(resp.T, X) / nk[:, np.newaxis]
covars_pred_full = _estimate_gaussian_covariance_full(resp, X, nk, xk, 0)
covars_pred_full = np.sum(nk[:, np.newaxis, np.newaxis] * covars_pred_full,
0) / n_samples
covars_pred_tied = _estimate_gaussian_covariance_tied(resp, X, nk, xk, 0)
ecov = EmpiricalCovariance()
ecov.covariance_ = covars_pred_full
assert_almost_equal(ecov.error_norm(covars_pred_tied, norm='frobenius'), 0)
assert_almost_equal(ecov.error_norm(covars_pred_tied, norm='spectral'), 0)
def test_suffstat_sk_diag():
# test against 'full' case
rng = np.random.RandomState(0)
n_samples, n_features, n_components = 500, 2, 2
resp = rng.rand(n_samples, n_components)
resp = resp / resp.sum(axis=1)[:, np.newaxis]
X = rng.rand(n_samples, n_features)
nk = resp.sum(axis=0)
xk = np.dot(resp.T, X) / nk[:, np.newaxis]
covars_pred_full = _estimate_gaussian_covariances_full(resp, X, nk, xk, 0)
covars_pred_diag = _estimate_gaussian_covariances_diag(resp, X, nk, xk, 0)
ecov = EmpiricalCovariance()
for (cov_full, cov_diag) in zip(covars_pred_full, covars_pred_diag):
ecov.covariance_ = np.diag(np.diag(cov_full))
cov_diag = np.diag(cov_diag)
assert_almost_equal(ecov.error_norm(cov_diag, norm='frobenius'), 0)
assert_almost_equal(ecov.error_norm(cov_diag, norm='spectral'), 0)
# check the precision computation
precs_chol_pred = _compute_precision_cholesky(covars_pred_diag, 'diag')
assert_almost_equal(covars_pred_diag, 1. / precs_chol_pred**2)
def test_suffstat_sk_diag():
# test against 'full' case
rng = np.random.RandomState(0)
n_samples, n_features, n_components = 500, 2, 2
resp = rng.rand(n_samples, n_components)
resp = resp / resp.sum(axis=1)[:, np.newaxis]
X = rng.rand(n_samples, n_features)
nk = resp.sum(axis=0)
xk = np.dot(resp.T, X) / nk[:, np.newaxis]
covars_pred_full = _estimate_gaussian_covariances_full(resp, X, nk, xk, 0)
covars_pred_diag = _estimate_gaussian_covariances_diag(resp, X, nk, xk, 0)
ecov = EmpiricalCovariance()
for (cov_full, cov_diag) in zip(covars_pred_full, covars_pred_diag):
ecov.covariance_ = np.diag(np.diag(cov_full))
cov_diag = np.diag(cov_diag)
assert_almost_equal(ecov.error_norm(cov_diag, norm='frobenius'), 0)
assert_almost_equal(ecov.error_norm(cov_diag, norm='spectral'), 0)
# check the precision computation
precs_chol_pred = _compute_precision_cholesky(covars_pred_diag, 'diag')
assert_almost_equal(covars_pred_diag, 1. / precs_chol_pred ** 2)
