def estimate_components_orthomax(d):
"""
Compute the PCA/FA components based on the input data d
as returned by GeoField bootstrap constructor.
"""
U, s, _ = pca_components_gf(d)
U = U[:, :NUM_COMPONENTS]
if not ROTATE_NORMALIZED:
U *= s[np.newaxis, :NUM_COMPONENTS]
Ur, _, _ = orthomax(U, gamma=GAMMA, norm_rows=True)
Ur /= np.sum(Ur**2, axis=0)**0.5
return Ur
def estimate_components_orthomax(d):
"""
Compute the PCA/FA components based on the input data d
as returned by GeoField bootstrap constructor.
"""
U, s, _ = pca_components_gf(d)
U = U[:, :NUM_COMPONENTS]
if not ROTATE_NORMALIZED:
U *= s[np.newaxis, :NUM_COMPONENTS]
Ur, _, _ = orthomax(U, gamma = GAMMA, norm_rows=True)
Ur /= np.sum(Ur**2, axis = 0) ** 0.5
return Ur
def estimate_components_orthomax(d):
"""
Compute the PCA/FA components based on the input data d
as returned by GeoField bootstrap constructor.
"""
U, s, _ = pca_components_gf(d)
U = U[:, :NUM_COMPONENTS]
if not ROTATE_NORMALIZED:
U *= s[np.newaxis, :NUM_COMPONENTS]
Ur, _, iters = orthomax(U, rtol = np.finfo(np.float32).eps ** 0.5,
gamma = GAMMA,
maxiter = 500,
norm_rows = ROTATE_NORM_ROWS)
Ur /= np.sum(Ur**2, axis = 0) ** 0.5
if iters >= 499:
print('Warning: max iters reached.')
return None
else:
return Ur
def estimate_components_orthomax(d):
"""
Compute the PCA/FA components based on the input data d
as returned by GeoField bootstrap constructor.
"""
U, s, _ = pca_components_gf(d)
U = U[:, :NUM_COMPONENTS]
if not ROTATE_NORMALIZED:
U *= s[np.newaxis, :NUM_COMPONENTS]
Ur, _, iters = orthomax(U,
rtol=np.finfo(np.float32).eps**0.5,
gamma=GAMMA,
maxiter=500,
norm_rows=ROTATE_NORM_ROWS)
Ur /= np.sum(Ur**2, axis=0)**0.5
if iters >= 499:
print('Warning: max iters reached.')
return None
else:
return Ur
def estimate_components_orthomax(d):
"""
Compute the PCA/FA components based on the input data d
as returned by GeoField bootstrap constructor.
"""
try:
U, s, _ = pca_components_gf(d)
U = U[:, :NUM_COMPONENTS]
Ur, T, iters = orthomax(U,
rtol = np.finfo(np.float32).eps ** 0.5,
gamma = GAMMA,
maxiter = 500)
if iters >= 499:
return None
else:
return Ur, T
except LinAlgError as e:
print("**LINALG ERROR** code: %d text : %s" % (e.errno, e.strerror))
except:
print("**UNEXPECTED ERROR** %s" % sys.exc_info()[0])
def compute_lno_sample_components(x):
gf, Urd, i, j = x
b = gf.data()
b = np.vstack([b[:i, ...], b[j:, ...]])
U, _, _ = pca_components_gf(b)
Ur, _, _ = orthomax(U[:, :NUM_COMPONENTS])
# compute closeness of components
C = np.dot(Ur.T, Urd)
# find optimal matching of components
m = Munkres()
match = m.compute(1.0 - np.abs(C))
perm = np.zeros((NUM_COMPONENTS, ), dtype=np.int)
for i in range(len(match)):
m_i = match[i]
perm[m_i[0]] = m_i[1]
# flip the sign in the matched boostrap component if the correlation was negative
Ur[m_i[1]] = -Ur[m_i[1]] if C[m_i[0], m_i[1]] < 0.0 else Ur[m_i[1]]
# reorder the bootstrap components according to the best matching
Ur = Ur[:, perm]
return Ur
def compute_lno_sample_components(x):
gf, Urd, i, j = x
b = gf.data()
b = np.vstack([b[:i,...], b[j:,...]])
U, _, _ = pca_components_gf(b)
Ur, _, _ = orthomax(U[:, :NUM_COMPONENTS])
# compute closeness of components
C = np.dot(Ur.T, Urd)
# find optimal matching of components
m = Munkres()
match = m.compute(1.0 - np.abs(C))
perm = np.zeros((NUM_COMPONENTS,), dtype = np.int)
for i in range(len(match)):
m_i = match[i]
perm[m_i[0]] = m_i[1]
# flip the sign in the matched boostrap component if the correlation was negative
Ur[m_i[1]] = - Ur[m_i[1]] if C[m_i[0], m_i[1]] < 0.0 else Ur[m_i[1]]
# reorder the bootstrap components according to the best matching
Ur = Ur[:, perm]
return Ur
#gf.slice_months([12, 1, 2])
#S = np.zeros(shape = (5, 10), dtype = np.int32)
#S[1:4, 0:2] = 1
#S[0:3, 6:9] = 2
#v, Sr = constructVAR(S, [0.0, 0.191, 0.120], [-0.1, 0.1], [0.00, 0.00], [0.01, 0.01])
#ts = v.simulate(768)
#gf = make_model_geofield(S, ts)
# initialize a parallel pool
pool = Pool(POOL_SIZE)
# compute components for data
Ud, sd, Vtd = pca_components_gf(gf.data())
Ud = Ud[:, :NUM_COMPONENTS]
Ur, _, its = orthomax(Ud)
print("Finished after %d iterations." % its)
t_start = datetime.now()
LNO_COUNT = len(gf.tm) // LNO_PAR
#LNO_COUNT = 4
print("Running leave one out analysis [%d samples] at %s" %
(LNO_COUNT, str(t_start)))
# initialize maximal and minimal boostraps
EXTREMA_MEMORY = math.ceil(DISCARD_RATE * LNO_COUNT)
max_comp = np.tile(np.abs(Ur.copy()), (EXTREMA_MEMORY + BULK_STEP, 1, 1))
min_comp = np.tile(np.abs(Ur.copy()), (EXTREMA_MEMORY + BULK_STEP, 1, 1))
mean_comp = np.zeros_like(Ur)
var_comp = np.zeros_like(Ur)
v_sel = [0, 0, 0, 0, 1, 1, 1, 1, 2, 2]
for i in range(10):
X[:, i] = V[:, v_sel[i]] + np.random.normal(size=(N, ), scale=sigma)
return X
if __name__ == '__main__':
# program the prolific test example used by everybody
X = make_test_data1(1000, 1.0)
C = spca_meng.extract_sparse_components(X.T, 3, 3)
PC, _, _ = component_analysis.pca_components(X.T)
PC = PC[:, :3]
UR, _, _ = component_analysis.orthomax(PC)
print C
plt.figure()
plt.subplot(311)
plt.plot(C)
plt.title('Sparse PCA')
plt.subplot(312)
plt.plot(PC)
plt.title('PCA components')
plt.subplot(313)
plt.plot(UR)
plt.title('Rotated components')
plt.show()
v_sel = [0, 0, 0, 0, 1, 1, 1, 1, 2, 2]
for i in range(10):
X[:,i] = V[:,v_sel[i]] + np.random.normal(size = (N,), scale = sigma)
return X
if __name__ == '__main__':
# program the prolific test example used by everybody
X = make_test_data1(1000, 1.0)
C = spca_meng.extract_sparse_components(X.T, 3, 3)
PC,_,_ = component_analysis.pca_components(X.T)
PC = PC[:,:3]
UR, _, _ = component_analysis.orthomax(PC)
print C
plt.figure()
plt.subplot(311)
plt.plot(C)
plt.title('Sparse PCA')
plt.subplot(312)
plt.plot(PC)
plt.title('PCA components')
plt.subplot(313)
plt.plot(UR)
plt.title('Rotated components')
plt.show()
#S = np.zeros(shape = (5, 10), dtype = np.int32)
#S[1:4, 0:2] = 1
#S[0:3, 6:9] = 2
#v, Sr = constructVAR(S, [0.0, 0.191, 0.120], [-0.1, 0.1], [0.00, 0.00], [0.01, 0.01])
#ts = v.simulate(768)
#gf = make_model_geofield(S, ts)
# initialize a parallel pool
pool = Pool(POOL_SIZE)
# compute components for data
Ud, sd, Vtd = pca_components_gf(gf.data())
Ud = Ud[:, :NUM_COMPONENTS]
Ur, _, its = orthomax(Ud)
print("Finished after %d iterations." % its)
t_start = datetime.now()
LNO_COUNT = len(gf.tm) // LNO_PAR
#LNO_COUNT = 4
print("Running leave one out analysis [%d samples] at %s" % (LNO_COUNT, str(t_start)))
# initialize maximal and minimal boostraps
EXTREMA_MEMORY = math.ceil(DISCARD_RATE * LNO_COUNT)
max_comp = np.tile(np.abs(Ur.copy()), (EXTREMA_MEMORY + BULK_STEP, 1, 1))
min_comp = np.tile(np.abs(Ur.copy()), (EXTREMA_MEMORY + BULK_STEP, 1, 1))
mean_comp = np.zeros_like(Ur)
var_comp = np.zeros_like(Ur)
