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 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)
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)
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)) CSP_lr_record.append(np.sum(pred == test_label) / box_length) print('-----------------------------------------')