def test_mdla_shuffle():
n_kernels = 8
dico = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
random_state=0, n_iter=3, n_nonzero_coefs=1,
verbose=5, shuffle=False)
code = dico.fit(X).transform(X[0])
assert_true(len(code[0]) <= 1)
def test_mdla_shuffle():
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 = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
random_state=0,
n_iter=3,
n_nonzero_coefs=1,
verbose=5,
shuffle=False)
code = dico.fit(X).transform(X[0])
assert_true(len(code[0]) <= 1)
n_nonzero_coefs = 2
learning_rate = 5.0
n_iter = 40 # 100
n_jobs, batch_size = -1, None # n_cpu, 5*n_cpu
figname = "-60ker-K3-klen80-lr5.0-emm-all"
d = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
batch_size=batch_size,
n_iter=n_iter,
n_nonzero_coefs=n_nonzero_coefs,
n_jobs=n_jobs,
learning_rate=learning_rate,
kernel_init_len=kernel_init_len,
verbose=1,
random_state=rng_global)
d = d.fit(X)
plot_objective_func(d.error_, n_iter, figname)
n_jobs = 4
plot_atom_usage(X, d.kernels_, n_nonzero_coefs, n_jobs, figname)
with open('EEG-savedico' + figname + '.pkl', 'wb') as f:
o = {
'kernels': d.kernels_,
'error': d.error_,
'kernel_init_len': d.kernel_init_len,
'learning_rate': d.learning_rate,
'n_iter': d.n_iter,
'n_jobs': d.n_jobs,
'n_kernels': d.n_kernels,
g, X, code = _generate_testbed(kernel_init_len,
n_nonzero_coefs, n_kernels, n_samples, n_features,
n_dims, s)
d = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
batch_size=batch_size, n_iter=n_iter,
n_nonzero_coefs=n_nonzero_coefs, callback=callback_recovery,
n_jobs=n_jobs, learning_rate=learning_rate,
kernel_init_len=kernel_init_len, verbose=1,
random_state=rng_global)
d.generating_dict = list(g)
d.wc, d.wfs, d.hc, d.hfs = list(), list(), list(), list()
d.wcpa, d.wbc, d.wg, d.wfb = list(), list(), list(), list()
d.hcpa, d.hbc, d.hg, d.hfb = list(), list(), list(), list()
d.dr99, d.dr97 = list(), list()
print ('\nExperiment', e+1, 'on', n_experiments)
d = d.fit(X)
wc[i, e, :] = array(d.wc); wfs[i, e, :] = array(d.wfs)
hc[i, e, :] = array(d.hc); hfs[i, e, :] = array(d.hfs)
wcpa[i, e, :] = array(d.wcpa); wbc[i, e, :] = array(d.wbc)
wg[i, e, :] = array(d.wg); wfb[i, e, :] = array(d.wfb)
hcpa[i, e, :] = array(d.hcpa); hbc[i, e, :] = array(d.hbc)
hg[i, e, :] = array(d.hg); hfb[i, e, :] = array(d.hfb)
dr99[i, e, :] = array(d.dr99); dr97[i, e, :] = array(d.dr97)
with open(backup_fname, "w") as f:
o = {'wc':wc, 'wfs':wfs, 'hc':hc, 'hfs':hfs, 'dr99':dr99, 'dr97':dr97,
'wcpa':wcpa, 'wbc':wbc, 'wg':wg, 'wfb':wfb, 'hcpa':hcpa,
'hbc':hbc, 'hg':hg, 'hfb':hfb}
pickle.dump(o, f)
# plot_recov(wc, wfs, hc, hfs, dr99, dr97, n_iter, "multivariate_recov")
plot_recov_all(wc, wfs, wcpa, wbc, wg, wfb, hc, hfs, hcpa, hbc, hg, hfb, dr99, dr97, n_iter, "multivariate_recov_all")
'without multiprocessing:',
end='')
batch_size, n_jobs = n_samples, 1
learned_dict = MiniBatchMultivariateDictLearning(
n_kernels=n_kernels,
batch_size=batch_size,
n_iter=max_iter,
n_nonzero_coefs=n_nonzero_coefs,
n_jobs=n_jobs,
learning_rate=learning_rate,
kernel_init_len=kernel_init_len,
verbose=1,
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)
# Online with mini-batch
minibatch_range = [cpu_count()]
minibatch_range.extend([cpu_count() * i for i in range(3, 10, 2)])
n_jobs = -1
for mb in minibatch_range:
print('\nProcessing ',
max_iter,
'iterations in online mode, with ',
'minibatch size',
mb,
'and',
generating_dict, X, code = _generate_testbed(kernel_init_len, n_nonzero_coefs,
n_kernels, n_samples, n_features,
n_dims)
# Online without mini-batch
print ('Processing ', max_iter, 'iterations in online mode, '
'without multiprocessing:', end='')
batch_size, n_jobs =n_samples, 1
learned_dict = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
batch_size=batch_size, n_iter=max_iter,
n_nonzero_coefs=n_nonzero_coefs,
n_jobs=n_jobs, learning_rate=learning_rate,
kernel_init_len=kernel_init_len, verbose=1,
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)
# Online with mini-batch
minibatch_range = [cpu_count()]
minibatch_range.extend([cpu_count()*i for i in range(3, 10, 2)])
n_jobs = -1
for mb in minibatch_range:
print ('\nProcessing ', max_iter, 'iterations in online mode, with ',
'minibatch size', mb, 'and', cpu_count(), 'processes:', end='')
batch_size = mb
learned_dict = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
batch_size=batch_size, n_iter=max_iter,
n_nonzero_coefs=n_nonzero_coefs,
n_batches = loc['n_batches']
if np.mod((ii-iter_offset)/int(n_batches), n_iter) == 0:
# Compute distance only every 5 iterations, as in previous case
d = loc['dict_obj']
d.wasserstein.append(emd(loc['dictionary'], d.generating_dict,
'chordal', scale=True))
d.detect_rate.append(detection_rate(loc['dictionary'],
d.generating_dict, 0.99))
d.objective_error.append(loc['current_cost'])
# reinitializing the random generator
learned_dict2 = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
batch_size=batch_size, n_iter=max_iter*n_iter,
n_nonzero_coefs=n_nonzero_coefs,
callback=callback_distance,
n_jobs=n_jobs, learning_rate=learning_rate,
kernel_init_len=kernel_init_len, verbose=1,
dict_init=dict_init, random_state=rng_global)
learned_dict2.generating_dict = list(generating_dict)
learned_dict2.wasserstein = list()
learned_dict2.detect_rate = list()
learned_dict2.objective_error = list()
learned_dict2 = learned_dict2.fit(X)
plot_univariate(array(learned_dict2.objective_error),
array(learned_dict2.detect_rate),
array(learned_dict2.wasserstein),
n_iter=1, figname='univariate-case-callback')
n_batches = loc['n_batches']
if np.mod((ii-iter_offset)/int(n_batches), n_iter) == 0:
# Compute distance only every 5 iterations, as in previous case
d = loc['dict_obj']
d.wasserstein.append(emd(loc['dictionary'], d.generating_dict,
'chordal', scale=True))
d.detection_rate.append(detectionRate(loc['dictionary'],
d.generating_dict, 0.99))
d.objective_error.append(loc['current_cost'])
# reinitializing the random generator
learned_dict2 = MiniBatchMultivariateDictLearning(n_kernels=n_kernels,
batch_size=batch_size, n_iter=max_iter*n_iter,
n_nonzero_coefs=n_nonzero_coefs,
callback=callback_distance,
n_jobs=n_jobs, learning_rate=learning_rate,
kernel_init_len=kernel_init_len, verbose=1,
dict_init=dict_init, random_state=rng_global)
learned_dict2.generating_dict = list(generating_dict)
learned_dict2.wasserstein = list()
learned_dict2.detection_rate = list()
learned_dict2.objective_error = list()
learned_dict2 = learned_dict2.fit(X)
plot_multivariate(array(learned_dict2.objective_error),
array(learned_dict2.detection_rate),
100.-array(learned_dict2.wasserstein),
n_iter=1, figname='multivariate-case-callback')
