Hello everyone:
I am a beginner in EEG processing.I following the example CSPto write my own code，but I had some problems.
In tutorial of CSP, he doesn’t use ica.But someting wrong when I after ICA.
After ICA, I use the raw data to make epoch, in tutorial he dosen’t use baseline, But I let it use the default settings. Later I got the error
I try many times, and find
if ICA + mne.Epochs(baseline=None) = no error
if no ICA + mne.Epochs(baseline = (None,0) ) = no error
if ICA + mne.Epochs(baseline = (None,0)) = error ‘‘SVD did not converge’’
What’s wrong with my code, or is my thinking wrong？
Forgive me my English is too bad, I hope you can understand 
- MNE version:1.0.3
- operating system:Windows 10
- dataset: BCI Competition datasets IV-2a
import mne
import numpy as np
import scipy.io as sio
import matplotlib.pyplot as plt
from mne.decoding import CSP
from sklearn.svm import SVC
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import cross_val_score, StratifiedKFold
from sklearn.metrics import cohen_kappa_score
mne.set_log_level('warning')
sfreq = 250
tmin, tmax = -1., 4.
event_id = dict(left=1, right=2, foot=3, tougue=4)
eog = ['EOG-left', 'EOG-central', 'EOG-right']
input_fname = "D:\BCI Competition\week16\A01T.gdf"
raw = mne.io.read_raw_gdf(input_fname, eog=eog, preload=True)
old_chans_name = raw.info.get('ch_names')[:-3]
standard_chans_name = ['Fz', 'FC3', 'FC1', 'FCz', 'FC2',
'FC4', 'C5', 'C3', 'C1', 'Cz',
'C2', 'C4', 'C6', 'CP3', 'CP1',
'CPz', 'CP2', 'CP4', 'P1', 'Pz',
'P2', 'POz']
rename_dict = {old_chans_name[i]:standard_chans_name[i] for i in range(len(old_chans_name))}
raw.rename_channels(rename_dict)
raw.set_montage('standard_1020')
raw.filter(7., 30., fir_design='firwin', skip_by_annotation='edge')
ica = mne.preprocessing.ICA(n_components=15,
random_state=97)
ica.fit(raw)
# ica.plot_sources(raw)
# ica.plot_components(outlines = "skirt")
bad_idx, scores =ica.find_bads_eog(raw)
# print(bad_idx)
ica.exclude = bad_idx
# ica.plot_overlay(raw, picks='eeg')
raw_data = ica.apply(raw,exclude = ica.exclude)
mapping = {'769': 1, '770': 2, '771': 3, '772': 4}
events,_ = mne.events_from_annotations(raw_data, event_id=mapping)
picks = mne.pick_types(raw_data.info, eeg=True)
epochs = mne.Epochs(raw_data,
events,
event_id,
tmin, tmax,
proj=True,
picks=picks,
# baseline=None,
preload=True
)
epochs_train = epochs.copy().crop(tmin=1, tmax=4)
labels = epochs.events[:, -1]
scores = []
epochs_data = epochs.get_data()
epochs_data_train = epochs_train.get_data()
kf = StratifiedKFold(n_splits=5,
shuffle=True,
random_state=10
)
cv_split = kf.split(epochs_data_train,
labels)
svm = SVC()
mms = MinMaxScaler()
csp = CSP(n_components=4,
reg=None,
log=False,
norm_trace=False
)
clf = Pipeline([('CSP', csp), ('MMS', mms), ('SVM', svm)])
scores = cross_val_score(clf,
epochs_data_train,
labels,
cv=kf,
n_jobs=-1
)
print("Classification accuracy: {:.4f}".format(np.mean(scores)))
csp.fit_transform(epochs_data, labels)
csp.plot_patterns(epochs.info,
ch_type='eeg',
units='Patterns (AU)',
size=1.5
)
ValueError Traceback (most recent call last)
Input In [13], in <cell line: 19>()
13 csp = CSP(n_components=4,
14 reg=None,
15 log=False,
16 norm_trace=False
17 )
18 clf = Pipeline([('CSP', csp), ('MMS', mms), ('SVM', svm)])
---> 19 scores = cross_val_score(clf,
20 epochs_data_train,
21 labels,
22 cv=kf,
23 n_jobs=-1
24 )
25 print("Classification accuracy: {:.4f}".format(np.mean(scores)))
26 csp.fit_transform(epochs_data, labels)
File ~\.conda\envs\pytorch\lib\site-packages\sklearn\model_selection\_validation.py:515, in cross_val_score(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, error_score)
512 # To ensure multimetric format is not supported
513 scorer = check_scoring(estimator, scoring=scoring)
--> 515 cv_results = cross_validate(
516 estimator=estimator,
517 X=X,
518 y=y,
519 groups=groups,
520 scoring={"score": scorer},
521 cv=cv,
522 n_jobs=n_jobs,
523 verbose=verbose,
524 fit_params=fit_params,
525 pre_dispatch=pre_dispatch,
526 error_score=error_score,
527 )
528 return cv_results["test_score"]
File ~\.conda\envs\pytorch\lib\site-packages\sklearn\model_selection\_validation.py:285, in cross_validate(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, return_train_score, return_estimator, error_score)
265 parallel = Parallel(n_jobs=n_jobs, verbose=verbose, pre_dispatch=pre_dispatch)
266 results = parallel(
267 delayed(_fit_and_score)(
268 clone(estimator),
(...)
282 for train, test in cv.split(X, y, groups)
283 )
--> 285 _warn_or_raise_about_fit_failures(results, error_score)
287 # For callabe scoring, the return type is only know after calling. If the
288 # return type is a dictionary, the error scores can now be inserted with
289 # the correct key.
290 if callable(scoring):
File ~\.conda\envs\pytorch\lib\site-packages\sklearn\model_selection\_validation.py:367, in _warn_or_raise_about_fit_failures(results, error_score)
360 if num_failed_fits == num_fits:
361 all_fits_failed_message = (
362 f"\nAll the {num_fits} fits failed.\n"
363 "It is very likely that your model is misconfigured.\n"
364 "You can try to debug the error by setting error_score='raise'.\n\n"
365 f"Below are more details about the failures:\n{fit_errors_summary}"
366 )
--> 367 raise ValueError(all_fits_failed_message)
369 else:
370 some_fits_failed_message = (
371 f"\n{num_failed_fits} fits failed out of a total of {num_fits}.\n"
372 "The score on these train-test partitions for these parameters"
(...)
376 f"Below are more details about the failures:\n{fit_errors_summary}"
377 )
ValueError:
All the 5 fits failed.
It is very likely that your model is misconfigured.
You can try to debug the error by setting error_score='raise'.
Below are more details about the failures:
--------------------------------------------------------------------------------
5 fits failed with the following error:
Traceback (most recent call last):
File "C:\Users\Admin\.conda\envs\pytorch\lib\site-packages\sklearn\model_selection\_validation.py", line 686, in _fit_and_score
estimator.fit(X_train, y_train, **fit_params)
File "C:\Users\Admin\.conda\envs\pytorch\lib\site-packages\sklearn\pipeline.py", line 378, in fit
Xt = self._fit(X, y, **fit_params_steps)
File "C:\Users\Admin\.conda\envs\pytorch\lib\site-packages\sklearn\pipeline.py", line 336, in _fit
X, fitted_transformer = fit_transform_one_cached(
File "C:\Users\Admin\.conda\envs\pytorch\lib\site-packages\joblib\memory.py", line 349, in __call__
return self.func(*args, **kwargs)
File "C:\Users\Admin\.conda\envs\pytorch\lib\site-packages\sklearn\pipeline.py", line 870, in _fit_transform_one
res = transformer.fit_transform(X, y, **fit_params)
File "C:\Users\Admin\.conda\envs\pytorch\lib\site-packages\mne\decoding\csp.py", line 236, in fit_transform
return super().fit_transform(X, y=y, **fit_params)
File "C:\Users\Admin\.conda\envs\pytorch\lib\site-packages\mne\decoding\mixin.py", line 33, in fit_transform
return self.fit(X, y, **fit_params).transform(X)
File "C:\Users\Admin\.conda\envs\pytorch\lib\site-packages\mne\decoding\csp.py", line 184, in fit
self.patterns_ = pinv(eigen_vectors)
File "C:\Users\Admin\.conda\envs\pytorch\lib\site-packages\mne\fixes.py", line 1056, in pinv
u, s, vh = np.linalg.svd(a, full_matrices=False)
File "<__array_function__ internals>", line 180, in svd
File "C:\Users\Admin\.conda\envs\pytorch\lib\site-packages\numpy\linalg\linalg.py", line 1648, in svd
u, s, vh = gufunc(a, signature=signature, extobj=extobj)
File "C:\Users\Admin\.conda\envs\pytorch\lib\site-packages\numpy\linalg\linalg.py", line 97, in _raise_linalgerror_svd_nonconvergence
raise LinAlgError("SVD did not converge")
numpy.linalg.LinAlgError: SVD did not converge