def test_multivariate_OMP():
n_samples = 10
n_features = 100
n_dims = 90
n_kernels = 8
n_nonzero_coefs = 3
kernel_init_len = n_features
verbose = False
dico, signals, decomposition = _generate_testbed(
kernel_init_len, n_nonzero_coefs, n_kernels, n_samples, n_features, n_dims
)
r, d = multivariate_sparse_encode(signals, dico, n_nonzero_coefs, n_jobs=1)
if verbose is True:
for i in range(n_samples):
# original signal decomposition, sorted by amplitude
sorted_decomposition = np.zeros_like(decomposition[i]).view("float, int, int")
for j in range(decomposition[i].shape[0]):
sorted_decomposition[j] = tuple(decomposition[i][j, :].tolist())
sorted_decomposition.sort(order=["f0"], axis=0)
for j in reversed(sorted_decomposition):
print(j)
# decomposition found by OMP, also sorted
sorted_d = np.zeros_like(d[i]).view("float, int, int")
for j in range(d[i].shape[0]):
sorted_d[j] = tuple(d[i][j, :].tolist())
sorted_d.sort(order=["f0"], axis=0)
for j in reversed(sorted_d):
print(j)
assert_array_almost_equal(
reconstruct_from_code(d, dico, n_features), signals, decimal=3
)
def _verif_OMP():
n_samples = 1000
n_nonzero_coefs = 3
for n_features in range(5, 50, 5):
kernel_init_len = n_features - n_features / 2
n_dims = n_features / 2
n_kernels = n_features * 5
dico, signals, _ = _generate_testbed(
kernel_init_len, n_nonzero_coefs, n_kernels, n_samples, n_features, n_dims
)
r, d = multivariate_sparse_encode(signals, dico, n_nonzero_coefs, n_jobs=1)
reconstructed = reconstruct_from_code(d, dico, n_features)
residual_energy = 0.0
for sig, rec in zip(signals, reconstructed):
residual_energy += ((sig - rec) ** 2).sum(1).mean()
print(
"Mean energy of the",
n_samples,
"residuals for",
(n_features, n_dims),
"features and",
n_kernels,
"kernels of",
(kernel_init_len, n_dims),
" is",
residual_energy / n_samples,
)
def test_multivariate_OMP():
n_samples = 10
n_features = 100
n_dims = 90
n_kernels = 8
n_nonzero_coefs = 3
kernel_init_len = n_features
verbose = False
dico, signals, decomposition = _generate_testbed(kernel_init_len,
n_nonzero_coefs,
n_kernels,
n_samples, n_features,
n_dims)
r, d = multivariate_sparse_encode(signals, dico, n_nonzero_coefs,
n_jobs = 1)
if verbose == True:
for i in range(n_samples):
# original signal decomposition, sorted by amplitude
sorted_decomposition = np.zeros_like(decomposition[i]).view('float, int, int')
for j in range(decomposition[i].shape[0]):
sorted_decomposition[j] = tuple(decomposition[i][j,:].tolist())
sorted_decomposition.sort(order=['f0'], axis=0)
for j in reversed(sorted_decomposition): print (j)
# decomposition found by OMP, also sorted
sorted_d = np.zeros_like(d[i]).view('float, int, int')
for j in range(d[i].shape[0]):
sorted_d[j] = tuple(d[i][j,:].tolist())
sorted_d.sort(order=['f0'], axis=0)
for j in reversed(sorted_d): print (j)
assert_array_almost_equal(reconstruct_from_code(d, dico, n_features),
signals, decimal=3)
def test_mdla_reconstruction():
n_samples, n_features, n_dims = 10, 5, 3
n_kernels = 8
n_nonzero_coefs = 3
kernel_init_len = n_features
dico, signals, decomposition = _generate_testbed(kernel_init_len,
n_nonzero_coefs,
n_kernels)
assert_array_almost_equal(
reconstruct_from_code(decomposition, dico, n_features), signals)
def test_mdla_reconstruction():
n_kernels = 8
n_nonzero_coefs = 3
kernel_init_len = n_features
dico, signals, decomposition = _generate_testbed(kernel_init_len,
n_nonzero_coefs,
n_kernels)
assert_array_almost_equal(reconstruct_from_code(decomposition,
dico, n_features),
signals)
def plot_reconstruction_samples(X, r, code, kernels, n, figname):
n_features = X[0].shape[0]
energy_residual = zeros(len(r))
for i in range(len(r)):
energy_residual[i] = norm(r[i], 'fro')
energy_sample = zeros(len(X))
for i in range(len(X)):
energy_sample[i] = norm(X[i], 'fro')
energy_explained = energy_residual / energy_sample
index = argsort(energy_explained) # 0 =worse, end=best
fig = plt.figure(figsize=(15, 9))
k = fig.add_subplot(3, 2 * n, 1)
k.set_xticklabels([])
k.set_yticklabels([])
for i in range(n):
if i != 0: ka = fig.add_subplot(3, 2 * n, i + 1, sharex=k, sharey=k)
else: ka = k
ka.plot(X[index[i]])
ka.set_title('s%d: %.1f%%' % (index[i], 100. *
(1 - energy_explained[index[i]])))
ka = fig.add_subplot(3, 2 * n, 2 * n + i + 1, sharex=k, sharey=k)
ka.plot(r[index[i]])
ka = fig.add_subplot(3, 2 * n, 4 * n + i + 1, sharex=k, sharey=k)
s = reconstruct_from_code([code[index[i]]], kernels, n_features)
ka.plot(s[0, :, :])
for j, i in zip(range(n, 2 * n), range(n, 0, -1)):
ka = fig.add_subplot(3, 2 * n, j + 1, sharex=k, sharey=k)
ka.plot(X[index[-i]])
ka.set_title('s%d: %.1f%%' % (index[-i], 100. *
(1 - energy_explained[index[-i]])))
ka = fig.add_subplot(3, 2 * n, 2 * n + j + 1, sharex=k, sharey=k)
ka.plot(r[index[-i]])
ka = fig.add_subplot(3, 2 * n, 4 * n + j + 1, sharex=k, sharey=k)
s = reconstruct_from_code([code[index[-i]]], kernels, n_features)
ka.plot(s[0, :, :])
plt.tight_layout(.5)
plt.savefig('EEG-reconstruction' + figname + '.png')
def plot_reconstruction_samples(X, r, code, kernels, n, figname):
n_features = X[0].shape[0]
energy_residual = zeros(len(r))
for i in range(len(r)):
energy_residual[i] = norm(r[i], 'fro')
energy_sample = zeros(len(X))
for i in range(len(X)):
energy_sample[i] = norm(X[i], 'fro')
energy_explained=energy_residual/energy_sample
index = argsort(energy_explained) # 0 =worse, end=best
fig = plt.figure(figsize=(15, 9))
k = fig.add_subplot(3, 2*n, 1)
k.set_xticklabels([])
k.set_yticklabels([])
for i in range(n):
if i != 0: ka = fig.add_subplot(3, 2*n, i+1, sharex=k, sharey=k)
else: ka = k
ka.plot(X[index[i]])
ka.set_title('s%d: %.1f%%' % (index[i], 100.*(1-energy_explained[index[i]])))
ka = fig.add_subplot(3, 2*n, 2*n+i+1, sharex=k, sharey=k)
ka.plot(r[index[i]])
ka = fig.add_subplot(3, 2*n, 4*n+i+1, sharex=k, sharey=k)
s = reconstruct_from_code([code[index[i]]], kernels, n_features)
ka.plot(s[0,:,:])
for j, i in zip(range(n, 2*n), range(n, 0, -1)):
ka = fig.add_subplot(3, 2*n, j+1, sharex=k, sharey=k)
ka.plot(X[index[-i]])
ka.set_title('s%d: %.1f%%' % (index[-i], 100.*(1-energy_explained[index[-i]])))
ka = fig.add_subplot(3, 2*n, 2*n+j+1, sharex=k, sharey=k)
ka.plot(r[index[-i]])
ka = fig.add_subplot(3, 2*n, 4*n+j+1, sharex=k, sharey=k)
s = reconstruct_from_code([code[index[-i]]], kernels, n_features)
ka.plot(s[0,:,:])
plt.tight_layout(.5)
plt.savefig('EEG-reconstruction'+figname+'.png')
def _verif_OMP():
n_samples = 1000
n_nonzero_coefs = 3
for n_features in range (5, 50, 5):
kernel_init_len = n_features - n_features/2
n_dims = n_features/2
n_kernels = n_features*5
dico, signals, decomposition = _generate_testbed(kernel_init_len,
n_nonzero_coefs,
n_kernels,
n_samples, n_features,
n_dims)
r, d = multivariate_sparse_encode(signals, dico, n_nonzero_coefs,
n_jobs = 1)
reconstructed = reconstruct_from_code(d, dico, n_features)
residual_energy = 0.
for sig, rec in zip(signals, reconstructed):
residual_energy += ((sig-rec)**2).sum(1).mean()
print ('Mean energy of the', n_samples, 'residuals for', (n_features, n_dims), 'features and', n_kernels, 'kernels of', (kernel_init_len, n_dims),' is', residual_energy/n_samples)