def test_dict_mf_reconstruction(backend):
X, Q = generate_synthetic()
dict_mf = DictMF(
n_components=4, alpha=1e-4, max_n_iter=300, l1_ratio=0, backend=backend, random_state=rng_global, reduction=1
)
dict_mf.fit(X)
P = dict_mf.transform(X)
Y = P.T.dot(dict_mf.components_)
assert_array_almost_equal(X, Y, decimal=1)
def test_dict_mf_reconstruction_reduction(backend):
X, Q = generate_synthetic(n_features=20, n_samples=400, dictionary_rank=5)
dict_mf = DictMF(
n_components=4, alpha=1e-6, max_n_iter=800, l1_ratio=0, backend=backend, random_state=rng_global, reduction=2
)
dict_mf.fit(X)
P = dict_mf.transform(X)
Y = P.T.dot(dict_mf.components_)
rel_error = np.sum((X - Y) ** 2) / np.sum(X ** 2)
assert rel_error < 0.06
def test_dict_mf_reconstruction_reduction_batch(backend):
X, Q = generate_synthetic(n_features=20, n_samples=400, dictionary_rank=5)
dict_mf = DictMF(
n_components=4,
alpha=1e-6,
max_n_iter=800,
l1_ratio=0,
backend=backend,
random_state=rng_global,
batch_size=2,
reduction=2,
)
dict_mf.fit(X)
P = dict_mf.transform(X)
Y = P.T.dot(dict_mf.Q_)
rel_error = np.sum((X - Y)**2) / np.sum(X**2)
assert (rel_error < 0.02)
def test_dict_mf_reconstruction_sparse_dict(backend, var_red):
X, Q = generate_sparse_synthetic(300, 4)
rng = check_random_state(0)
dict_init = Q + rng.randn(*Q.shape) * 0.01
dict_mf = DictMF(n_components=4, alpha=1e-4, max_n_iter=400, l1_ratio=1,
dict_init=dict_init,
backend=backend,
var_red=var_red,
random_state=rng_global)
dict_mf.fit(X)
Q_rec = dict_mf.components_
Q_rec /= np.sqrt(np.sum(Q_rec ** 2, axis=1))[:, np.newaxis]
Q /= np.sqrt(np.sum(Q ** 2, axis=1))[:, np.newaxis]
G = np.abs(Q_rec.dot(Q.T))
recovered_maps = min(np.sum(np.any(G > 0.95, axis=1)),
np.sum(np.any(G > 0.95, axis=0)))
assert (recovered_maps >= 4)
P = dict_mf.transform(X)
Y = P.T.dot(dict_mf.components_)
def single_run(n_components, var_red, projection, offset, learning_rate,
reduction, alpha, data):
cb = Callback(data)
estimator = DictMF(n_components=n_components,
batch_size=10,
reduction=reduction,
l1_ratio=1,
alpha=alpha,
max_n_iter=20000,
projection=projection,
var_red=var_red,
backend='python',
verbose=3,
learning_rate=learning_rate,
offset=offset,
random_state=0,
callback=cb)
estimator.fit(data)
return cb, estimator
def test_dict_mf_reconstruction_sparse_dict(backend):
X, Q = generate_sparse_synthetic(300, 4)
rng = check_random_state(0)
dict_init = Q + rng.randn(*Q.shape) * 0.01
dict_mf = DictMF(n_components=4,
alpha=1e-4,
max_n_iter=400,
l1_ratio=1,
dict_init=dict_init,
backend=backend,
random_state=rng_global)
dict_mf.fit(X)
Q_rec = dict_mf.components_
Q_rec /= np.sqrt(np.sum(Q_rec**2, axis=1))[:, np.newaxis]
Q /= np.sqrt(np.sum(Q**2, axis=1))[:, np.newaxis]
G = np.abs(Q_rec.dot(Q.T))
recovered_maps = min(np.sum(np.any(G > 0.95, axis=1)),
np.sum(np.any(G > 0.95, axis=0)))
assert (recovered_maps >= 4)
P = dict_mf.transform(X)
Y = P.T.dot(dict_mf.components_)
def test_dict_mf_reconstruction_sparse(backend):
X, Q = generate_synthetic(n_features=20, n_samples=200, dictionary_rank=5)
sp_X = np.zeros((X.shape[0] * 2, X.shape[1]))
# Generate a sparse simple problem
for i in range(X.shape[0]):
perm = rng_global.permutation(X.shape[1])
even_range = perm[::2]
odd_range = perm[1::2]
sp_X[2 * i, even_range] = X[i, even_range]
sp_X[2 * i, odd_range] = X[i, odd_range]
sp_X = sp.csr_matrix(sp_X)
dict_mf = DictMF(n_components=4,
alpha=1e-6,
max_n_iter=500,
l1_ratio=0,
backend=backend,
random_state=rng_global)
dict_mf.fit(sp_X)
P = dict_mf.transform(X)
Y = P.T.dot(dict_mf.Q_)
rel_error = np.sum((X - Y)**2) / np.sum(X**2)
assert (rel_error < 0.02)
def test_dict_mf_reconstruction_sparse_dict(backend):
X, Q = generate_sparse_synthetic(300, 4)
dict_init = Q + rng_global.randn(*Q.shape) * 0.01
dict_mf = DictMF(n_components=4,
alpha=1e-2,
max_n_iter=300,
l1_ratio=1,
dict_init=dict_init,
backend=backend,
random_state=rng_global)
dict_mf.fit(X)
Q_rec = dict_mf.Q_
Q_rec /= np.sqrt(np.sum(Q_rec**2, axis=1))[:, np.newaxis]
Q /= np.sqrt(np.sum(Q**2, axis=1))[:, np.newaxis]
G = np.abs(Q_rec.dot(Q.T))
recovered_maps = min(np.sum(np.any(G > 0.95, axis=1)),
np.sum(np.any(G > 0.95, axis=0)))
assert (recovered_maps >= 4)
P = compute_code(X, dict_mf.Q_, alpha=1e-3)
Y = P.T.dot(dict_mf.Q_)
assert_array_almost_equal(X, Y, decimal=2)
# Much stronger
assert_array_almost_equal(X, Y, decimal=2)
data = faces_centered
cb = Callback(data)
estimator = DictMF(n_components=n_components, batch_size=10,
reduction=10,
l1_ratio=1,
alpha=0.001,
max_n_iter=10000,
projection='partial',
backend='c',
verbose=3,
learning_rate=.8,
offset=0,
random_state=2,
callback=cb)
estimator.fit(data)
train_time = (time.time() - t0)
print("done in %0.3fs" % train_time)
import matplotlib.pyplot as plt
components_ = estimator.components_
plot_gallery('%s - Train time %.1fs' % (name, train_time),
components_[:n_components])
P = estimator.transform(data)
# plot_gallery('Original faces',
# data[:n_components])
plot_gallery('Residual',
data[:n_components] - P.T.dot(estimator.components_)[:n_components])
fig, ax = plt.subplots(1, 1, sharex=True)
ax.plot(cb.iter, cb.obj, label='P')
cb = Callback(data)
estimator = DictMF(n_components=n_components,
batch_size=10,
reduction=10,
l1_ratio=1,
alpha=0.001,
max_n_iter=10000,
projection='partial',
backend='c',
verbose=3,
learning_rate=.8,
offset=0,
random_state=2,
callback=cb)
estimator.fit(data)
train_time = (time.time() - t0)
print("done in %0.3fs" % train_time)
import matplotlib.pyplot as plt
components_ = estimator.components_
plot_gallery('%s - Train time %.1fs' % (name, train_time),
components_[:n_components])
P = estimator.transform(data)
# plot_gallery('Original faces',
# data[:n_components])
plot_gallery(
'Residual',
data[:n_components] - P.T.dot(estimator.components_)[:n_components])
fig, ax = plt.subplots(1, 1, sharex=True)
