def _auto_low_rank_model(data, mode, n_jobs, method_params, cv,
stop_early=True, verbose=None):
"""compute latent variable models."""
method_params = cp.deepcopy(method_params)
iter_n_components = method_params.pop('iter_n_components')
if iter_n_components is None:
iter_n_components = np.arange(5, data.shape[1], 5)
from sklearn.decomposition import PCA, FactorAnalysis
if mode == 'factor_analysis':
est = FactorAnalysis
elif mode == 'pca':
est = PCA
else:
raise ValueError('Come on, this is not a low rank estimator: %s' %
mode)
est = est(**method_params)
est.n_components = 1
scores = np.empty_like(iter_n_components, dtype=np.float64)
scores.fill(np.nan)
# make sure we don't empty the thing if it's a generator
max_n = max(list(cp.deepcopy(iter_n_components)))
if max_n > data.shape[1]:
warn('You are trying to estimate %i components on matrix '
'with %i features.' % (max_n, data.shape[1]))
for ii, n in enumerate(iter_n_components):
est.n_components = n
try: # this may fail depending on rank and split
score = _cross_val(data=data, est=est, cv=cv, n_jobs=n_jobs)
except ValueError:
score = np.inf
if np.isinf(score) or score > 0:
logger.info('... infinite values encountered. stopping estimation')
break
logger.info('... rank: %i - loglik: %0.3f' % (n, score))
if score != -np.inf:
scores[ii] = score
if (ii >= 3 and np.all(np.diff(scores[ii - 3:ii]) < 0.) and
stop_early is True):
# early stop search when loglik has been going down 3 times
logger.info('early stopping parameter search.')
break
# happens if rank is too low right form the beginning
if np.isnan(scores).all():
raise RuntimeError('Oh no! Could not estimate covariance because all '
'scores were NaN. Please contact the MNE-Python '
'developers.')
i_score = np.nanargmax(scores)
best = est.n_components = iter_n_components[i_score]
logger.info('... best model at rank = %i' % best)
runtime_info = {'ranks': np.array(iter_n_components),
'scores': scores,
'best': best,
'cv': cv}
return est, runtime_info
