def fit(self, X, y):
# validate
X, y = check_X_y(X, y, allow_nd=True)
X = check_array(X, allow_nd=True)
# set internal vars
self.classes_ = unique_labels(y)
self.X_ = X
self.y_ = y
##################################################
# split X into train and test sets, so that
# grid search can be performed on train set only
seed = 7
np.random.seed(seed)
#X_TRAIN, X_TEST, y_TRAIN, y_TEST = train_test_split(X, y, test_size=0.25, random_state=seed)
for epoch_trim in self.epoch_bounds:
for bandpass in self.bandpass_filters:
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.25, random_state=seed)
# X_train = np.copy(X_TRAIN)
# X_test = np.copy(X_TEST)
# y_train = np.copy(y_TRAIN)
# y_test = np.copy(y_TEST)
# separate out inputs that are tuples
bandpass_start, bandpass_end = bandpass
epoch_trim_start, epoch_trim_end = epoch_trim
# bandpass filter coefficients
b, a = butter(
5,
np.array([bandpass_start, bandpass_end]) /
(self.sfreq * 0.5), 'bandpass')
# filter and crop TRAINING SET
X_train = self.preprocess_X(X_train, b, a, epoch_trim_start,
epoch_trim_end)
# validate
X_train, y_train = check_X_y(X_train, y_train, allow_nd=True)
X_train = check_array(X_train, allow_nd=True)
# filter and crop TEST SET
X_test = self.preprocess_X(X_test, b, a, epoch_trim_start,
epoch_trim_end)
# validate
X_test, y_test = check_X_y(X_test, y_test, allow_nd=True)
X_test = check_array(X_test, allow_nd=True)
###########################################################################
# self-tune CSP to find optimal number of filters to use at these settings
#[best_num_filters, best_num_filters_score] = self.self_tune(X_train, y_train)
best_num_filters = 5
# as an option, we could tune optimal CSP filter num against complete train set
#X_tune = self.preprocess_X(X, b, a, epoch_trim_start, epoch_trim_end)
#[best_num_filters, best_num_filters_score] = self.self_tune(X_tune, y)
# now use this insight to really fit with optimal CSP spatial filters
"""
reg : float | str | None (default None)
if not None, allow regularization for covariance estimation
if float, shrinkage covariance is used (0 <= shrinkage <= 1).
if str, optimal shrinkage using Ledoit-Wolf Shrinkage ('ledoit_wolf')
or Oracle Approximating Shrinkage ('oas').
"""
transformer = CSP(n_components=best_num_filters,
reg='ledoit_wolf')
transformer.fit(X_train, y_train)
# use these CSP spatial filters to transform train and test
spatial_filters_train = transformer.transform(X_train)
spatial_filters_test = transformer.transform(X_test)
# put this back in as failsafe if NaN or inf starts cropping up
# spatial_filters_train = np.nan_to_num(spatial_filters_train)
# check_X_y(spatial_filters_train, y_train)
# spatial_filters_test = np.nan_to_num(spatial_filters_test)
# check_X_y(spatial_filters_test, y_test)
# train LDA
classifier = LinearDiscriminantAnalysis()
classifier.fit(spatial_filters_train, y_train)
score = classifier.score(spatial_filters_test, y_test)
#print "current score",score
print "bandpass:"******"epoch window:", epoch_trim_start, epoch_trim_end
#print best_num_filters,"filters chosen"
# put in ranked order Top 10 list
idx = bisect(self.ranked_scores, score)
self.ranked_scores.insert(idx, score)
self.ranked_scores_opts.insert(
idx,
dict(bandpass=bandpass,
epoch_trim=epoch_trim,
filters=best_num_filters))
self.ranked_classifiers.insert(idx, classifier)
self.ranked_transformers.insert(idx, transformer)
if len(self.ranked_scores) > self.num_votes:
self.ranked_scores.pop(0)
if len(self.ranked_scores_opts) > self.num_votes:
self.ranked_scores_opts.pop(0)
if len(self.ranked_classifiers) > self.num_votes:
self.ranked_classifiers.pop(0)
if len(self.ranked_transformers) > self.num_votes:
self.ranked_transformers.pop(0)
"""
Covariance computation
"""
# compute covariance matrices
cov_data_train = covariances(X=X_train)
cov_data_test = covariances(X=X_test)
clf_mdm = MDM(metric=dict(mean='riemann', distance='riemann'))
clf_mdm.fit(cov_data_train, y_train)
score_mdm = clf_mdm.score(cov_data_test, y_test)
# print "MDM prediction score:",score_mdm
# put in ranked order Top 10 list
idx = bisect(self.ranked_scores_mdm, score_mdm)
self.ranked_scores_mdm.insert(idx, score_mdm)
self.ranked_scores_opts_mdm.insert(
idx,
dict(bandpass=bandpass,
epoch_trim=epoch_trim,
filters=best_num_filters))
self.ranked_classifiers_mdm.insert(idx, clf_mdm)
if len(self.ranked_scores_mdm) > self.num_votes:
self.ranked_scores_mdm.pop(0)
if len(self.ranked_scores_opts_mdm) > self.num_votes:
self.ranked_scores_opts_mdm.pop(0)
if len(self.ranked_classifiers_mdm) > self.num_votes:
self.ranked_classifiers_mdm.pop(0)
clf_ts = TSclassifier()
clf_ts.fit(cov_data_train, y_train)
score_ts = clf_ts.score(cov_data_test, y_test)
# put in ranked order Top 10 list
idx = bisect(self.ranked_scores_ts, score_ts)
self.ranked_scores_ts.insert(idx, score_ts)
self.ranked_scores_opts_ts.insert(
idx,
dict(bandpass=bandpass,
epoch_trim=epoch_trim,
filters=best_num_filters))
self.ranked_classifiers_ts.insert(idx, clf_ts)
if len(self.ranked_scores_ts) > self.num_votes:
self.ranked_scores_ts.pop(0)
if len(self.ranked_scores_opts_ts) > self.num_votes:
self.ranked_scores_opts_ts.pop(0)
if len(self.ranked_classifiers_ts) > self.num_votes:
self.ranked_classifiers_ts.pop(0)
print "CSP+LDA score:", score, "Tangent space w/LR score:", score_ts
print "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~"
print "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
print " T O P ", self.num_votes, " C L A S S I F I E R S"
print
#j=1
for i in xrange(len(self.ranked_scores)):
print i, ",", round(self.ranked_scores[i], 4), ",",
print self.ranked_scores_opts[i]
print "-------------------------------------"
for i in xrange(len(self.ranked_scores_ts)):
print i, ",", round(self.ranked_scores_ts[i], 4), ",",
print self.ranked_scores_opts_ts[i]
print "-------------------------------------"
for i in xrange(len(self.ranked_scores_mdm)):
print i, ",", round(self.ranked_scores_mdm[i], 4), ",",
print self.ranked_scores_opts_mdm[i]
# finish up, set the flag to indicate "fitted" state
self.fit_ = True
# Return the classifier
return self
kf = KFold(n_splits=n_splits)
for train_index, test_index in tqdm(kf.split(covs), total=n_splits):
# split into training and testing datasets
covs_train = covs[train_index]
labs_train = labels[train_index]
covs_test = covs[test_index]
labs_test = labels[test_index]
# reduce the dimensions with ['covpca', 'gpcaRiemann']
for meth in ['covpca', 'gpcaRiemann']:
trf = DR.RDR(n_components=pred, method=meth)
trf.fit(covs_train)
covs_train_red = trf.transform(covs_train)
covs_test_red = trf.transform(covs_test)
clf.fit(covs_train_red, labs_train)
scores[meth].append(clf.score(covs_test_red, labs_test))
# reduce the dimensions with [SELg, SELb]
for meth, sel in zip(['SELg', 'SELb'], [SELg, SELb]):
covs_train_red = covs_train[:, sel, :][:, :, sel]
covs_test_red = covs_test[:, sel, :][:, :, sel]
clf.fit(covs_train_red, labs_train)
scores[meth].append(clf.score(covs_test_red, labs_test))
print('subject ', subject)
# print the scores
for meth in scores.keys():
print(meth, np.mean(scores[meth]))
print('')
def score_pooling_rct(settings, subject_target, ntop):
dataset = settings['dataset']
paradigm = settings['paradigm']
session = settings['session']
storage = settings['storage']
filepath = '../results/' + dataset + '/TL_intra-subject_scores.pkl'
acc_intra_dict = joblib.load(filepath)
scores = []
subject_sources = []
for subject in settings['subject_list']:
if subject == subject_target:
continue
else:
scores.append(acc_intra_dict[subject])
subject_sources.append(subject)
scores = np.array(scores)
subject_sources = np.array(subject_sources)
idx_sort = scores.argsort()[::-1]
scores = scores[idx_sort]
subject_sources = subject_sources[idx_sort]
subject_sources_ntop = subject_sources[:ntop]
# get the geometric means for each subject (each class and also the center)
filename = '../results/' + dataset + '/subject_means.pkl'
subj_means = joblib.load(filename)
# get the data for the target subject
target_org = GD.get_dataset(dataset, subject_target, session, storage)
if paradigm == 'MI':
# things here are only implemented for MI for now
target_org['covs'] = Covariances(estimator='oas').fit_transform(
target_org['signals'])
target_org['labels'] = target_org['labels']
ncovs = settings['ncovs_list'][0]
score_rzt = 0.0
nrzt = 10
for rzt in range(nrzt):
# split randomly the target dataset
target_org_train, target_org_test = get_target_split_motorimagery(
target_org, ncovs)
# get the data from the sources and pool it all together
class_mean_1 = []
class_mean_2 = []
for subj_source in subject_sources_ntop:
MC_source = subj_means[subj_source]['center']
M1_source = subj_means[subj_source]['left_hand']
M2_source = subj_means[subj_source]['right_hand']
M1_source_rct = np.dot(invsqrtm(MC_source),
np.dot(M1_source, invsqrtm(MC_source)))
class_mean_1.append(M1_source_rct)
M2_source_rct = np.dot(invsqrtm(MC_source),
np.dot(M2_source, invsqrtm(MC_source)))
class_mean_2.append(M2_source_rct)
class_mean_1_source = np.stack(class_mean_1)
class_mean_2_source = np.stack(class_mean_2)
covs_train_source = np.concatenate(
[class_mean_1_source, class_mean_2_source])
labs_train_source = np.concatenate([
len(class_mean_1_source) * ['left_hand'],
len(class_mean_2_source) * ['right_hand']
])
# re-center data for the target
covs_train_target = target_org['covs']
MC_target = mean_riemann(covs_train_target)
labs_train_target = target_org['labels']
class_mean_1_target = mean_riemann(
covs_train_target[labs_train_target == 'left_hand'])
class_mean_1_target = np.dot(
invsqrtm(MC_target),
np.dot(class_mean_1_target, invsqrtm(MC_target)))
class_mean_2_target = mean_riemann(
covs_train_target[labs_train_target == 'right_hand'])
class_mean_2_target = np.dot(
invsqrtm(MC_target),
np.dot(class_mean_2_target, invsqrtm(MC_target)))
covs_train_target = np.stack(
[class_mean_1_target, class_mean_2_target])
labs_train_target = np.array(['left_hand', 'right_hand'])
covs_train = np.concatenate([covs_train_source, covs_train_target])
labs_train = np.concatenate([labs_train_source, labs_train_target])
covs_test = target_org_test['covs']
labs_test = target_org_test['labels']
# do the classification
clf = MDM()
clf.fit(covs_train, labs_train)
score_rzt = score_rzt + clf.score(covs_test, labs_test)
score = score_rzt / nrzt
return score
