def _poly_drift(order, frame_times):
"""Create a polynomial drift matrix
Parameters
----------
order : int,
Number of polynomials in the drift model.
frame_times : array of shape(n_scans),
Time stamps used to sample polynomials.
Returns
-------
pol : ndarray, shape(n_scans, order + 1)
Estimated polynomial drifts plus a constant regressor.
"""
order = int(order)
pol = np.zeros((np.size(frame_times), order + 1))
tmax = float(frame_times.max())
for k in range(order + 1):
pol[:, k] = (frame_times / tmax)**k
pol = _orthogonalize(pol)
pol = np.hstack((pol[:, 1:], pol[:, :1]))
return pol
def test_orthogonalize_trivial():
""" test that the orthogonalization is OK """
rng = np.random.RandomState(42)
X = rng.standard_normal(size=100)
Y = X.copy()
X = _orthogonalize(X)
assert_array_equal(Y, X)
def test_orthogonalize():
""" test that the orthogonalization is OK """
X = np.random.randn(100, 5)
X = _orthogonalize(X)
K = np.dot(X.T, X)
K -= np.diag(np.diag(K))
assert_almost_equal((K ** 2).sum(), 0, 15)
def test_orthogonalize():
""" test that the orthogonalization is OK """
rng = np.random.RandomState(42)
X = rng.standard_normal(size=(100, 5))
X = _orthogonalize(X)
K = np.dot(X.T, X)
K -= np.diag(np.diag(K))
assert_almost_equal((K**2).sum(), 0, 15)
def test_orthogonalize_trivial():
""" test that the orthogonalization is OK """
X = np.random.randn(100)
Y = X.copy()
X = _orthogonalize(X)
assert_array_equal(Y, X)
