def test_multivariate_input_shape():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 7
n_dims_w = 6
Xw = [rng_global.randn(n_features, n_dims_w) for i in range(n_samples)]
dico = MultivariateDictLearning(n_kernels=n_kernels).fit(X)
for i in range(n_kernels):
assert dico.kernels_[i].shape == (n_features, n_dims)
dico = MultivariateDictLearning(n_kernels=n_kernels)
assert_raises(ValueError, dico.fit, Xw)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels).fit(X)
for i in range(n_kernels):
assert dico.kernels_[i].shape == (n_features, n_dims)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels)
assert_raises(ValueError, dico.fit, Xw)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels).partial_fit(X)
for i in range(n_kernels):
assert dico.kernels_[i].shape == (n_features, n_dims)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels)
assert_raises(ValueError, dico.partial_fit, Xw)
def test_dict_init():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 8
d = [rng_global.randn(n_features, n_dims) for i in range(n_kernels)]
for i in range(len(d)):
d[i] /= np.linalg.norm(d[i], "fro")
dico = MultivariateDictLearning(
n_kernels=n_kernels,
random_state=0,
max_iter=1,
n_nonzero_coefs=1,
learning_rate=0.0,
dict_init=d,
verbose=5,
).fit(X)
dico = dico.fit(X)
for i in range(n_kernels):
assert_array_almost_equal(dico.kernels_[i], d[i])
# code = dico.fit(X).transform(X[0])
# assert (len(code[0]) > 1)
dico = MiniBatchMultivariateDictLearning(
n_kernels=n_kernels,
random_state=0,
n_iter=1,
n_nonzero_coefs=1,
dict_init=d,
verbose=1,
learning_rate=0.0,
).fit(X)
dico = dico.fit(X)
for i in range(n_kernels):
assert_array_almost_equal(dico.kernels_[i], d[i])
def test_callback():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 8
def my_callback(loc):
_ = loc["dict_obj"]
dico = MultivariateDictLearning(
n_kernels=n_kernels,
random_state=0,
max_iter=2,
n_nonzero_coefs=1,
callback=my_callback,
)
code = dico.fit(X).transform(X[0])
assert len(code[0]) <= 1
dico = MiniBatchMultivariateDictLearning(
n_kernels=n_kernels,
random_state=0,
n_iter=2,
n_nonzero_coefs=1,
callback=my_callback,
)
code = dico.fit(X).transform(X[0])
assert len(code[0]) <= 1
def test_sparse_encode():
n_kernels = 8
dico = MultivariateDictLearning(n_kernels=n_kernels, random_state=0,
max_iter=2, n_nonzero_coefs=1)
dico = dico.fit(X)
_, code = multivariate_sparse_encode(X, dico, n_nonzero_coefs=1,
n_jobs=-1, verbose=3)
assert_true(len(code[0]) <= 1)
def test_sparse_encode():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 8
dico = MultivariateDictLearning(
n_kernels=n_kernels, random_state=0, max_iter=2, n_nonzero_coefs=1
)
dico = dico.fit(X)
_, code = multivariate_sparse_encode(X, dico, n_nonzero_coefs=1, n_jobs=-1, verbose=3)
assert len(code[0]) <= 1
def test_mdla_nonzero_coefs():
n_kernels = 8
dico = MultivariateDictLearning(n_kernels=n_kernels, random_state=0,
max_iter=3, n_nonzero_coefs=3, verbose=5)
code = dico.fit(X).transform(X[0])
assert_true(len(code[0]) <= 3)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
random_state=0, n_iter=3, n_nonzero_coefs=3, verbose=5)
code = dico.fit(X).transform(X[0])
assert_true(len(code[0]) <= 3)
def test_X_array():
n_kernels = 8
X = rng_global.randn(n_samples, n_features, n_dims)
dico = MultivariateDictLearning(n_kernels=n_kernels, random_state=0,
max_iter=3, n_nonzero_coefs=3, verbose=5)
code = dico.fit(X).transform(X[0])
assert_true(len(code[0]) <= 3)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
random_state=0, n_iter=3, n_nonzero_coefs=3, verbose=5)
code = dico.fit(X).transform(X[0])
assert_true(len(code[0]) <= 3)
def test_X_array():
n_samples, n_features, n_dims = 10, 5, 3
n_kernels = 8
X = rng_global.randn(n_samples, n_features, n_dims)
dico = MultivariateDictLearning(
n_kernels=n_kernels, random_state=0, max_iter=3, n_nonzero_coefs=3, verbose=5
)
code = dico.fit(X).transform(X[0])
assert len(code[0]) <= 3
dico = MiniBatchMultivariateDictLearning(
n_kernels=n_kernels, random_state=0, n_iter=3, n_nonzero_coefs=3, verbose=5
)
code = dico.fit(X).transform(X[0])
assert len(code[0]) <= 3
def test_callback():
n_kernels = 8
def my_callback(loc):
d = loc['dict_obj']
dico = MultivariateDictLearning(n_kernels=n_kernels, random_state=0,
max_iter=2, n_nonzero_coefs=1,
callback=my_callback)
code = dico.fit(X).transform(X[0])
assert_true(len(code[0]) <= 1)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
random_state=0, n_iter=2, n_nonzero_coefs=1,
callback=my_callback)
code = dico.fit(X).transform(X[0])
assert_true(len(code[0]) <= 1)
def test_mdla_dict_update():
n_kernels = 10
# n_samples, n_features, n_dims = 100, 5, 3
n_samples, n_features, n_dims = 80, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
dico = MultivariateDictLearning(
n_kernels=n_kernels, random_state=0, max_iter=10, n_jobs=-1
).fit(X)
first_epoch = list(dico.kernels_)
dico = dico.fit(X)
second_epoch = list(dico.kernels_)
for k, c in zip(first_epoch, second_epoch):
assert (k - c).sum() != 0.0
dico = MiniBatchMultivariateDictLearning(
n_kernels=n_kernels, random_state=0, n_iter=10, n_jobs=-1
).fit(X)
first_epoch = list(dico.kernels_)
dico = dico.fit(X)
second_epoch = list(dico.kernels_)
for k, c in zip(first_epoch, second_epoch):
assert (k - c).sum() != 0.0
dico = MiniBatchMultivariateDictLearning(
n_kernels=n_kernels, random_state=0, n_iter=10, n_jobs=-1
).partial_fit(X)
first_epoch = list(dico.kernels_)
dico = dico.partial_fit(X)
second_epoch = list(dico.kernels_)
for k, c in zip(first_epoch, second_epoch):
assert (k - c).sum() != 0.0
def test_mdla_nonzero_coefs():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 8
dico = MultivariateDictLearning(n_kernels=n_kernels,
random_state=0,
max_iter=3,
n_nonzero_coefs=3,
verbose=5)
code = dico.fit(X).transform(X[0])
assert_true(len(code[0]) <= 3)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
random_state=0,
n_iter=3,
n_nonzero_coefs=3,
verbose=5)
code = dico.fit(X).transform(X[0])
assert_true(len(code[0]) <= 3)
def test_dict_init():
n_kernels = 8
d = [rng_global.randn(n_features, n_dims) for i in range(n_kernels)]
for i in range(len(d)):
d[i] /= np.linalg.norm(d[i], 'fro')
dico = MultivariateDictLearning(n_kernels=n_kernels, random_state=0,
max_iter=1, n_nonzero_coefs=1, learning_rate=0.,
dict_init=d, verbose=5).fit(X)
dico = dico.fit(X)
for i in range(n_kernels):
assert_array_almost_equal(dico.kernels_[i], d[i])
# code = dico.fit(X).transform(X[0])
# assert_true(len(code[0]) > 1)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
random_state=0, n_iter=1, n_nonzero_coefs=1,
dict_init=d, verbose=1, learning_rate=0.).fit(X)
dico = dico.fit(X)
for i in range(n_kernels):
assert_array_almost_equal(dico.kernels_[i], d[i])
def test_mdla_dict_init():
n_kernels = 10
n_samples, n_features, n_dims = 20, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
dict_init = [np.random.randn(n_features, n_dims) for i in range(n_kernels)]
dico = MultivariateDictLearning(
n_kernels=n_kernels, random_state=0, max_iter=10, dict_init=dict_init
).fit(X)
diff = 0.0
for i in range(n_kernels):
diff = diff + (dico.kernels_[i] - dict_init[i]).sum()
assert diff != 0
def test_mdla_dict_update():
n_kernels = 10
# n_samples, n_features, n_dims = 100, 5, 3
n_samples, n_features, n_dims = 80, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
dico = MultivariateDictLearning(n_kernels=n_kernels, random_state=0,
max_iter=10, n_jobs=-1).fit(X)
first_epoch = list(dico.kernels_)
dico = dico.fit(X)
second_epoch = list(dico.kernels_)
for k, c in zip(first_epoch, second_epoch):
assert_true((k-c).sum() != 0.)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
random_state=0, n_iter=10, n_jobs=-1).fit(X)
first_epoch = list(dico.kernels_)
dico = dico.fit(X)
second_epoch = list(dico.kernels_)
for k, c in zip(first_epoch, second_epoch):
assert_true((k-c).sum() != 0.)
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
random_state=0, n_iter=10, n_jobs=-1).partial_fit(X)
first_epoch = list(dico.kernels_)
dico = dico.partial_fit(X)
second_epoch = list(dico.kernels_)
for k, c in zip(first_epoch, second_epoch):
assert_true((k-c).sum() != 0.)
def test_mdla_nonzero_coef_errors():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 8
dico = MultivariateDictLearning(
n_kernels=n_kernels, random_state=0, max_iter=2, n_nonzero_coefs=0
)
assert_raises(ValueError, dico.fit, X)
dico = MiniBatchMultivariateDictLearning(
n_kernels=n_kernels, random_state=0, n_iter=2, n_nonzero_coefs=n_kernels + 1
)
assert_raises(ValueError, dico.fit, X)
def test_mdla_normalization():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 8
dico = MultivariateDictLearning(
n_kernels=n_kernels, random_state=0, max_iter=2, verbose=1
).fit(X)
for k in dico.kernels_:
assert_almost_equal(np.linalg.norm(k, "fro"), 1.0)
dico = MiniBatchMultivariateDictLearning(
n_kernels=n_kernels, random_state=0, n_iter=2, verbose=1
).fit(X)
for k in dico.kernels_:
assert_almost_equal(np.linalg.norm(k, "fro"), 1.0)
def test_mdla_shapes():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
n_kernels = 8
dico = MultivariateDictLearning(
n_kernels=n_kernels, random_state=0, max_iter=10, verbose=5
).fit(X)
for i in range(n_kernels):
assert dico.kernels_[i].shape == (n_features, n_dims)
dico = MiniBatchMultivariateDictLearning(
n_kernels=n_kernels, random_state=0, verbose=5, n_iter=10
).fit(X)
for i in range(n_kernels):
assert dico.kernels_[i].shape == (n_features, n_dims)
def test_n_kernels():
n_samples, n_features, n_dims = 10, 5, 3
X = [rng_global.randn(n_features, n_dims) for i in range(n_samples)]
dico = MultivariateDictLearning(
random_state=0, max_iter=2, n_nonzero_coefs=1, verbose=5
).fit(X)
assert len(dico.kernels_) == 2 * n_features
dico = MiniBatchMultivariateDictLearning(
random_state=0, n_iter=2, n_nonzero_coefs=1, verbose=5
).fit(X)
assert len(dico.kernels_) == 2 * n_features
dico = MiniBatchMultivariateDictLearning(
random_state=0, n_iter=2, n_nonzero_coefs=1, verbose=5
).partial_fit(X)
assert len(dico.kernels_) == 2 * n_features
# Batch learning
mp_range = range(1, cpu_count() + 1)
for p in mp_range:
print('\nProcessing ',
max_iter,
'iterations in batch mode, with',
p,
'processes:',
end='')
n_jobs = p
learned_dict = MultivariateDictLearning(n_kernels=n_kernels,
max_iter=max_iter,
verbose=1,
n_nonzero_coefs=n_nonzero_coefs,
n_jobs=n_jobs,
learning_rate=learning_rate,
kernel_init_len=kernel_init_len,
dict_init=None,
random_state=rng_global)
ts = time()
learned_dict = learned_dict.fit(X)
iter_time.append((time() - ts) / max_iter)
it_separator += 1
plot_separator.append(it_separator)
print('Done benchmarking')
figname = 'minibatch-performance'
print('Plotting results in', figname)
benchmarking_plot(figname, iter_time, plot_separator, minibatch_range,
mp_range)