def test_TSclassifier_classifier(get_covmats, get_labels):
"""Test TS Classifier"""
n_trials, n_channels, n_classes = 6, 3, 2
covmats = get_covmats(n_trials, n_channels)
labels = get_labels(n_trials, n_classes)
clf = TSclassifier(clf=DummyClassifier())
clf.fit(covmats, labels).predict(covmats)
class wrapper_TSclassifier(machine_learning_method):
"""wrapper for pyriemann TSclassifier"""
def __init__(self, method_name, method_args):
super(wrapper_TSclassifier, self).__init__(method_name, method_args)
self.init_method()
def init_method(self):
self.classifier = TSclassifier(metric=self.method_args['metric'],
tsupdate=self.method_args['tsupdate'])
def fit(self, X, y):
return self.classifier.fit(X, y)
def predict(self, X):
return self.classifier.predict(X)
def test_tsclassifier_clf_error(get_covmats, get_labels):
"""Test TS if not Classifier"""
n_matrices, n_channels, n_classes = 6, 3, 2
covmats = get_covmats(n_matrices, n_channels)
labels = get_labels(n_matrices, n_classes)
with pytest.raises(TypeError):
TSclassifier(clf=Covariances()).fit(covmats, labels)
def test_TSclassifier():
"""Test TS Classifier"""
covset = generate_cov(40, 3)
labels = np.array([0, 1]).repeat(20)
with pytest.raises(TypeError):
TSclassifier(clf='666')
clf = TSclassifier()
clf.fit(covset, labels)
assert_array_equal(clf.classes_, np.array([0, 1]))
clf.predict(covset)
clf.predict_proba(covset)
def test_TSclassifier():
"""Test TS Classifier"""
covset = generate_cov(40, 3)
labels = np.array([0, 1]).repeat(20)
assert_raises(TypeError, TSclassifier, clf='666')
clf = TSclassifier()
clf.fit(covset, labels)
clf.predict(covset)
clf.predict_proba(covset)
def main(state, freq):
"""Where the magic happens"""
print(state, freq)
if FULL_TRIAL:
labels = np.concatenate((np.ones(18), np.zeros(18)))
groups = range(36)
elif SUBSAMPLE:
info_data = pd.read_csv(SAVE_PATH.parent / "info_data.csv")[STATE_LIST]
n_trials = info_data.min().min()
n_subs = len(info_data) - 1
groups = [i for i in range(n_subs) for _ in range(n_trials)]
n_total = n_trials * n_subs
labels = [0 if i < n_total / 2 else 1 for i in range(n_total)]
else:
labels = loadmat(LABEL_PATH / state + "_labels.mat")["y"].ravel()
labels, groups = create_groups(labels)
file_path = (SAVE_PATH / "results" / PREFIX + NAME +
"_{}_{}_{}_{:.2f}.mat".format(state, freq, WINDOW, OVERLAP))
if not file_path.isfile():
file_name = NAME + "_{}_{}_{}_{:.2f}.mat".format(
state, freq, WINDOW, OVERLAP)
data_file_path = SAVE_PATH / file_name
if data_file_path.isfile():
final_save = {}
random_seed = 0
data = loadmat(data_file_path)
if FULL_TRIAL:
data = data["data"]
elif SUBSAMPLE:
data = prepare_data(data,
n_trials=n_trials,
random_state=random_seed)
else:
data = prepare_data(data)
sl2go = StratifiedLeave2GroupsOut()
lda = LDA()
clf = TSclassifier(clf=lda)
best_combin, best_score = backward_selection(
clf, data, labels, sl2go, groups)
final_save = {
"best_combin_index": best_combin,
"best_combin": CHANNEL_NAMES[best_combin],
"score": best_score,
}
savemat(file_path, final_save)
print(
f"Best combin: {CHANNEL_NAMES[best_combin]}, score: {best_score}"
)
else:
print(data_file_path.NAME + " Not found")
def check_other_classifiers(train_X, train_y, test_X, test_y):
from pyriemann.classification import MDM, TSclassifier
from sklearn.linear_model import LogisticRegression
from pyriemann.estimation import Covariances
from sklearn.pipeline import Pipeline
from mne.decoding import CSP
import seaborn as sns
import pandas as pd
train_y = [np.where(i == 1)[0][0] for i in train_y]
test_y = [np.where(i == 1)[0][0] for i in test_y]
cov_data_train = Covariances().transform(train_X)
cov_data_test = Covariances().transform(test_X)
cv = KFold(n_splits=10, random_state=42)
clf = TSclassifier()
scores = cross_val_score(clf, cov_data_train, train_y, cv=cv, n_jobs=1)
print("Tangent space Classification accuracy: ", np.mean(scores))
clf = TSclassifier()
clf.fit(cov_data_train, train_y)
print(clf.score(cov_data_test, test_y))
mdm = MDM(metric=dict(mean='riemann', distance='riemann'))
scores = cross_val_score(mdm, cov_data_train, train_y, cv=cv, n_jobs=1)
print("MDM Classification accuracy: ", np.mean(scores))
mdm = MDM()
mdm.fit(cov_data_train, train_y)
fig, axes = plt.subplots(1, 2)
ch_names = [ch for ch in range(8)]
df = pd.DataFrame(data=mdm.covmeans_[0], index=ch_names, columns=ch_names)
g = sns.heatmap(df,
ax=axes[0],
square=True,
cbar=False,
xticklabels=2,
yticklabels=2)
g.set_title('Mean covariance - feet')
df = pd.DataFrame(data=mdm.covmeans_[1], index=ch_names, columns=ch_names)
g = sns.heatmap(df,
ax=axes[1],
square=True,
cbar=False,
xticklabels=2,
yticklabels=2)
plt.xticks(rotation='vertical')
plt.yticks(rotation='horizontal')
g.set_title('Mean covariance - hands')
# dirty fix
plt.sca(axes[0])
plt.xticks(rotation='vertical')
plt.yticks(rotation='horizontal')
plt.savefig("meancovmat.png")
plt.show()
def test_TSclassifier():
"""Test TS Classifier"""
covset = generate_cov(40, 3)
labels = np.array([0, 1]).repeat(20)
assert_raises(TypeError, TSclassifier, clf='666')
clf = TSclassifier()
clf.fit(covset, labels)
clf.predict(covset)
clf.predict_proba(covset)
def RHvsLH_cross(out_dir, pipelines):
name = 'RHvsLH_cross'
datasets = utils.dataset_search('imagery',
events=['right_hand', 'left_hand'],
has_all_events=True,
min_subjects=2,
multi_session=False)
print(datasets)
pipelines = OrderedDict()
pipelines['TS'] = make_pipeline(Covariances('oas'), TSclassifier())
pipelines['CSP+LDA'] = make_pipeline(Covariances('oas'), CSP(6), LDA())
pipelines['CSP+SVM'] = make_pipeline(Covariances('oas'), CSP(6), SVC()) #
context = LeftRightImagery(pipelines, CrossSubjectEvaluation(n_jobs=10),
datasets)
results = context.process()
def test_TSclassifier_classifier_error():
"""Test TS if not Classifier"""
with pytest.raises(TypeError):
TSclassifier(clf=Covariances())
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
def get_score(subject=7):
###############################################################################
# Set parameters and read data
# avoid classification of evoked responses by using epochs that start 1s after
# cue onset.
tmin, tmax = 1., 2.
event_id = dict(hands=2, feet=3)
runs = [6, 10, 14] # motor imagery: hands vs feet
raw_files = [
read_raw_edf(f, preload=True) for f in eegbci.load_data(subject, runs)
]
raw = concatenate_raws(raw_files)
picks = pick_types(raw.info,
meg=False,
eeg=True,
stim=False,
eog=False,
exclude='bads')
# subsample elecs
picks = picks[::2]
# Apply band-pass filter
raw.filter(7., 35., method='iir', picks=picks)
events = find_events(raw, shortest_event=0, stim_channel='STI 014')
# Read epochs (train will be done only between 1 and 2s)
# Testing will be done with a running classifier
epochs = Epochs(raw,
events,
event_id,
tmin,
tmax,
proj=True,
picks=picks,
baseline=None,
preload=True,
verbose=False)
labels = epochs.events[:, -1] - 2
# cross validation
cv = KFold(len(labels), 10, shuffle=True, random_state=42)
# get epochs
epochs_data_train = 1e6 * epochs.get_data()
# compute covariance matrices
cov_data_train = Covariances().transform(epochs_data_train)
###############################################################################
# Classification with Minimum distance to mean
mdm = MDM(metric=dict(mean='riemann', distance='riemann'))
# Use scikit-learn Pipeline with cross_val_score function
mdm.fit(cov_data_train, labels)
print(123)
###############################################################################
# Classification with Tangent Space Logistic Regression
clf = TSclassifier()
# Use scikit-learn Pipeline with cross_val_score function
scores = cross_val_score(clf, cov_data_train, labels, cv=cv, n_jobs=1)
# Printing the results
class_balance = np.mean(labels == labels[0])
class_balance = max(class_balance, 1. - class_balance)
ts_score = np.mean(scores)
print("Tangent space Classification accuracy: %f / Chance level: %f" %
(ts_score, class_balance))
###############################################################################
return [subject, mdm_score, ts_score]
def init_method(self):
self.classifier = TSclassifier(metric=self.method_args['metric'],
tsupdate=self.method_args['tsupdate'])
import logging
import coloredlogs
logging.basicConfig(level=logging.DEBUG)
logger = logging.getLogger()
coloredlogs.install(level=logging.DEBUG)
datasets = utils.dataset_search('imagery',
events=['supination', 'hand_close'],
has_all_events=False,
min_subjects=2,
multi_session=False)
for d in datasets:
d.subject_list = d.subject_list[:10]
paradigm = ImageryNClass(2)
context = WithinSessionEvaluation(paradigm=paradigm,
datasets=datasets,
random_state=42)
pipelines = OrderedDict()
pipelines['av+TS'] = make_pipeline(Covariances(estimator='oas'),
TSclassifier())
pipelines['av+CSP+LDA'] = make_pipeline(Covariances(estimator='oas'), CSP(8),
LDA())
results = context.process(pipelines, overwrite=True)
analyze(results, './')
N_SUBS = len(info_data) - 1
groups = [i for i in range(N_SUBS) for _ in range(N_TRIALS)]
N_TOTAL = N_TRIALS * N_SUBS
labels = [0 if i < N_TOTAL / 2 else 1 for i in range(N_TOTAL)]
file_name = prefix + name + "n153_{}.mat".format(state)
save_file_path = SAVE_PATH / "results" / file_name
data_file_path = SAVE_PATH / name + "_{}.mat".format(state)
final_save = None
data = loadmat(data_file_path)
data = prepare_data(data, n_trials=N_TRIALS, random_state=0)
sl2go = StratifiedLeave2GroupsOut()
lda = LDA()
clf = TSclassifier(clf=lda)
score = cross_val_score(clf, data, labels, groups, cv=sl2go, n_jobs=-1)
print(score)
# save['acc_bootstrap'] = [save['acc_score']]
# save['auc_bootstrap'] = [save['auc_score']]
# if final_save is None:
# final_save = save
# else:
# for key, value in final_save.items():
# final_save[key] = final_save[key] + save[key]
# savemat(save_file_path, final_save)
def classif_cov(state):
"""Where the magic happens"""
print(state)
if FULL_TRIAL:
labels = np.concatenate((np.ones(18), np.zeros(18)))
groups = range(36)
elif SUBSAMPLE:
info_data = pd.read_csv(SAVE_PATH.parent / "info_data.csv")[STATE_LIST]
n_trials = info_data.min().min()
n_subs = len(info_data) - 1
groups = [i for i in range(n_subs) for _ in range(n_trials)]
n_total = n_trials * n_subs
labels = [0 if i < n_total / 2 else 1 for i in range(n_total)]
else:
labels = loadmat(LABEL_PATH / state + "_labels.mat")["y"].ravel()
labels, groups = create_groups(labels)
file_path = SAVE_PATH / "results" / PREFIX + NAME + "_{}.mat".format(state)
if not file_path.isfile():
n_rep = 0
else:
final_save = proper_loadmat(file_path)
n_rep = final_save["n_rep"]
print("starting from i={}".format(n_rep))
file_name = NAME + "_{}.mat".format(state)
data_file_path = SAVE_PATH / file_name
if data_file_path.isfile():
data_og = loadmat(data_file_path)
for i in range(n_rep, N_BOOTSTRAPS):
if FULL_TRIAL:
data = data_og["data"]
elif SUBSAMPLE:
data = prepare_data(data_og, n_trials=n_trials, random_state=i)
else:
data = prepare_data(data_og)
if REDUCED:
reduced_data = []
for submat in data:
temp_a = np.delete(submat, i, 0)
temp_b = np.delete(temp_a, i, 1)
reduced_data.append(temp_b)
data = np.asarray(reduced_data)
if FULL_TRIAL:
crossval = SSS(9)
else:
crossval = StratifiedLeave2GroupsOut()
lda = LDA()
clf = TSclassifier(clf=lda)
save = classification(clf,
crossval,
data,
labels,
groups,
N_PERM,
n_jobs=-1)
print(save["acc_score"])
if i == 0:
final_save = save
elif BOOTSTRAP or REDUCED:
for key, value in save.items():
final_save[key] += value
final_save["n_rep"] = i + 1
savemat(file_path, final_save)
final_save["n_rep"] = N_BOOTSTRAPS
if BOOTSTRAP:
final_save["auc_score"] = np.mean(final_save["auc_score"])
final_save["acc_score"] = np.mean(final_save["acc_score"])
savemat(file_path, final_save)
print("accuracy for %s %s : %0.2f (+/- %0.2f)" %
(state, np.mean(save["acc_score"]), np.std(save["acc"])))
if PERM:
print("pval = {}".format(save["acc_pvalue"]))
else:
print(data_file_path.name + " Not found")
def main(state):
"""Where the magic happens"""
print(state)
if FULL_TRIAL:
labels = np.concatenate((np.ones(18), np.zeros(18)))
groups = range(36)
elif SUBSAMPLE:
info_data = pd.read_csv(SAVE_PATH.parent / "info_data.csv")[STATE_LIST]
##### FOR A TEST #####
info_data = info_data["SWS"]
##### FOR A TEST #####
N_TRIALS = info_data.min().min()
N_SUBS = len(info_data) - 1
groups = [i for _ in range(N_TRIALS) for i in range(N_SUBS)]
N_TOTAL = N_TRIALS * N_SUBS
labels = [0 if i < N_TOTAL / 2 else 1 for i in range(N_TOTAL)]
else:
labels = loadmat(LABEL_PATH / state + "_labels.mat")["y"].ravel()
labels, groups = create_groups(labels)
file_name = prefix + name + "n153_{}.mat".format(state)
save_file_path = SAVE_PATH / "results" / file_name
if not save_file_path.isfile():
data_file_path = SAVE_PATH / name + "_{}.mat".format(state)
if data_file_path.isfile():
final_save = None
for i in range(N_BOOTSTRAPS):
data = loadmat(data_file_path)
if FULL_TRIAL:
data = data["data"]
elif SUBSAMPLE:
data = prepare_data(data,
n_trials=N_TRIALS,
random_state=i)
else:
data = prepare_data(data)
sl2go = StratifiedLeave2GroupsOut()
lda = LDA()
clf = TSclassifier(clf=lda)
save = classification(clf,
sl2go,
data,
labels,
groups,
N_PERM,
n_jobs=-1)
save["acc_bootstrap"] = [save["acc_score"]]
save["auc_bootstrap"] = [save["auc_score"]]
if final_save is None:
final_save = save
else:
for key, value in final_save.items():
final_save[key] = final_save[key] + save[key]
savemat(save_file_path, final_save)
print("accuracy for %s : %0.2f (+/- %0.2f)" %
(state, save["acc_score"], np.std(save["acc"])))
else:
print(data_file_path.name + " Not found")
##
## # make kernels
# K_train = np.dot(training_data, np.transpose(training_data))
# K_test = np.dot(testing_data, np.transpose(training_data))
## K_train = K_lin_timecourse[train_index, :][:, train_index]
## K_test = K_lin_timecourse[test_index, :][:, train_index]
#
#
# # train classifier and predict
# clf.fit(K_train, training_labels)
# preds_rep = np.append(preds_rep, clf.predict(K_test))
# labels_rep = np.append(labels_rep, testing_labels)
#print np.transpose(np.vstack((np.transpose(labels), np.transpose(preds_rep))))
print metrics.accuracy_score(labels_rep, preds_rep)
# try pyriemann's tangent space classifier
# adapted from http://pythonhosted.org/pyriemann/auto_examples/motor-imagery/plot_single.html#sphx-glr-auto-examples-motor-imagery-plot-single-py
# reshape data for TSclassifier
timecourse_connectivity_data_TSclassifier = np.reshape(timecourse_connectivity_data, (100, 90, 90))
clf = TSclassifier()
clf = MDM()
#cv = cross_validation.KFold(len(labels), 10, shuffle=True, random_state=42)
cv = cross_validation.StratifiedShuffleSplit(labels, n_iter=100, test_size=0.1)
scores = cross_validation.cross_val_score(clf, timecourse_connectivity_data_TSclassifier, labels, cv=cv, n_jobs=1)
print scores
print np.mean(scores)
def classif_cosp(state, n_jobs=-1):
global CHANGES
print(state, "multif")
if SUBSAMPLE or ADAPT:
info_data = pd.read_csv(SAVE_PATH.parent / "info_data.csv")[STATE_LIST]
if SUBSAMPLE:
n_trials = info_data.min().min()
# n_trials = 30
elif ADAPT:
n_trials = info_data.min()[state]
elif FULL_TRIAL:
groups = range(36)
labels_og = INIT_LABELS
file_path = (SAVE_PATH / "results" / PREFIX + NAME +
"_{}_{}_{:.2f}.mat".format(state, WINDOW, OVERLAP))
if not file_path.isfile():
n_rep = 0
else:
final_save = proper_loadmat(file_path)
n_rep = int(final_save["n_rep"])
n_splits = int(final_save["n_splits"])
print("Starting from i={}".format(n_rep))
if FULL_TRIAL:
crossval = SSS(9)
else:
crossval = StratifiedShuffleGroupSplit(2)
lda = LDA()
clf = TSclassifier(clf=lda)
for i in range(n_rep, N_BOOTSTRAPS):
CHANGES = True
data_freqs = []
for freq in FREQ_DICT:
file_name = NAME + "_{}_{}_{}_{:.2f}.mat".format(
state, freq, WINDOW, OVERLAP)
data_file_path = SAVE_PATH / file_name
data_og = loadmat(data_file_path)["data"].ravel()
data_og = np.asarray([sub.squeeze() for sub in data_og])
if SUBSAMPLE or ADAPT:
data, labels, groups = prepare_data(data_og,
labels_og,
n_trials=n_trials,
random_state=i)
else:
data, labels, groups = prepare_data(data_og, labels_og)
data_freqs.append(data)
n_splits = crossval.get_n_splits(None, labels, groups)
data_freqs = np.asarray(data_freqs).swapaxes(0, 1).swapaxes(
1, 3).swapaxes(1, 2)
save = classification(clf,
crossval,
data,
labels,
groups,
N_PERM,
n_jobs=n_jobs)
if i == 0:
final_save = save
elif BOOTSTRAP:
for key, value in save.items():
if key != "n_splits":
final_save[key] += value
final_save["n_rep"] = i + 1
if n_jobs == -1:
savemat(file_path, final_save)
final_save["auc_score"] = np.mean(final_save.get("auc_score", 0))
final_save["acc_score"] = np.mean(final_save["acc_score"])
if CHANGES:
savemat(file_path, final_save)
to_print = "accuracy for {} {} : {:.2f}".format(state, freq,
final_save["acc_score"])
if BOOTSTRAP:
standev = np.std([
np.mean(final_save["acc"][i * n_splits:(i + 1) * n_splits])
for i in range(N_BOOTSTRAPS)
])
to_print += " (+/- {:.2f})".format(standev)
print(to_print)
if PERM:
print("pval = {}".format(final_save["acc_pvalue"]))
from pyriemann.spatialfilters import CSP
from pyriemann.classification import TSclassifier, MDM
from sklearn.pipeline import make_pipeline
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from collections import OrderedDict
context = BNCI2014001MIHands()
pipelines = OrderedDict()
pipelines['MDM'] = make_pipeline(Covariances('oas'), MDM())
pipelines['TS'] = make_pipeline(Covariances('oas'), TSclassifier())
pipelines['CSP+LDA'] = make_pipeline(Covariances('oas'), CSP(8), LDA())
results = context.evaluate(pipelines, verbose=True)
for p in results.keys():
results[p].to_csv('../../results/MotorImagery/BNCI_2014_001/%s.csv' % p)
results = pd.concat(results.values())
print(results.groupby('Pipeline').mean())
res = results.pivot(values='Score', columns='Pipeline', index='Subject')
sns.lmplot(data=res, x='CSP+LDA', y='TS', fit_reg=False)
plt.xlim(0.4, 1)
plt.ylim(0.4, 1)
plt.plot([0.4, 1], [0.4, 1], ls='--', c='k')
def classif_subcosp(state, freq, elec, n_jobs=-1):
global CHANGES
print(state, freq)
if SUBSAMPLE or ADAPT:
info_data = pd.read_csv(SAVE_PATH.parent / "info_data.csv")[STATE_LIST]
if SUBSAMPLE:
n_trials = info_data.min().min()
n_trials = 61
elif ADAPT:
n_trials = info_data.min()[state]
elif FULL_TRIAL:
groups = range(36)
labels_og = INIT_LABELS
file_path = (
SAVE_PATH / "results" / PREFIX + NAME +
"_{}_{}_{}_{}_{:.2f}.npy".format(state, freq, elec, WINDOW, OVERLAP))
if not file_path.isfile():
n_rep = 0
else:
final_save = np.load(file_path)
n_rep = int(final_save["n_rep"])
n_splits = int(final_save["n_splits"])
print("Starting from i={}".format(n_rep))
file_name = NAME + "_{}_{}_{}_{}_{:.2f}.npy".format(
state, freq, elec, WINDOW, OVERLAP)
data_file_path = SAVE_PATH / file_name
data_og = np.load(data_file_path)
if FULL_TRIAL:
cv = SSS(9)
else:
cv = StratifiedShuffleGroupSplit(2)
lda = LDA()
clf = TSclassifier(clf=lda)
for i in range(n_rep, N_BOOTSTRAPS):
CHANGES = True
if FULL_TRIAL:
data = data_og["data"]
elif SUBSAMPLE or ADAPT:
data, labels, groups = prepare_data(data_og,
labels_og,
n_trials=n_trials,
random_state=i)
else:
data, labels, groups = prepare_data(data_og, labels_og)
n_splits = cv.get_n_splits(None, labels, groups)
save = classification(clf,
cv,
data,
labels,
groups,
N_PERM,
n_jobs=n_jobs)
if i == 0:
final_save = save
elif BOOTSTRAP:
for key, value in save.items():
if key != "n_splits":
final_save[key] += value
final_save["n_rep"] = i + 1
np.save(file_path, final_save)
final_save["auc_score"] = np.mean(final_save.get("auc_score", 0))
final_save["acc_score"] = np.mean(final_save["acc_score"])
if CHANGES:
np.save(file_path, final_save)
to_print = "accuracy for {} {} : {:.2f}".format(state, freq,
final_save["acc_score"])
if BOOTSTRAP:
standev = np.std([
np.mean(final_save["acc"][i * n_splits:(i + 1) * n_splits])
for i in range(N_BOOTSTRAPS)
])
to_print += " (+/- {:.2f})".format(standev)
print(to_print)
if PERM:
print("pval = {}".format(final_save["acc_pvalue"]))
print('MDM: {:4f}'.format(np.sum(pred == test_label) / box_length))
MDM_record.append(np.sum(pred == test_label) / box_length)
print('-----------------------------------------')
Fgmdm = FgMDM(metric=dict(mean='riemann', distance='riemann'))
Fgmdm.fit(train, train_label)
pred = Fgmdm.predict(test)
print('FGMDM: {:4f}'.format(
np.sum(pred == test_label) / box_length))
FGMDM_record.append(np.sum(pred == test_label) / box_length)
print('-----------------------------------------')
clf = TSclassifier()
clf.fit(train, train_label)
pred = clf.predict(test)
print('TSC: {:4f}'.format(np.sum(pred == test_label) / box_length))
TSC_record.append(np.sum(pred == test_label) / box_length)
print('-----------------------------------------')
lr = LogisticRegression()
csp = CSP(n_components=4, reg='ledoit_wolf', log=True)
clf = Pipeline([('CSP', csp), ('LogisticRegression', lr)])
clf.fit(train_CSP, train_label)
pred = clf.predict(test_CSP)
print('CSP_lr: {:4f}'.format(
np.sum(pred == test_label) / box_length))