# custom frequency bands for calculating power band features **URL:** \ **Category:** Support & Discussions\ **Tags:** time-frequency, preprocessing\ **Created:** [November 14, 2021, 8:29pm UTC](https://mne.discourse.group/t/custom-frequency-bands-for-calculating-power-band-features/3951 "2021-11-14T20:29:11Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![FRSHT](https://yyz2.discourse-cdn.com/free1/user_avatar/mne.discourse.group/frsht/32/139_2.png) [@FRSHT](https://mne.discourse.group/u/FRSHT)\ **Post date:** [November 14, 2021, 8:29pm UTC](https://mne.discourse.group/t/custom-frequency-bands-for-calculating-power-band-features/3951/1 "2021-11-14T20:29:11Z")
Dear community members, I’m extracting band power features from single channel eeg data with mne\_features and I need to know if it is possible to create custom frequency bands for calculating power. For example, I’d like to have normalised and relative power over these ranges: “delta”: [0.5, 3.5], “theta”: [3.5, 7.5], “alpha1”: [7.5, 9.5],“alpha2”: [9.5,12.5], “beta1”: [12.5, 17.5], “beta1”: [17.5, 25], “gamma”: [25,40] I tried this code, and it returned 6 final results for each epoch, whereas I expected 7 data points based on the frequency band definition. . bands = {“delta”: [0.5, 3.5], “theta”: [3.5, 7.5], “alpha1”: [7.5, 9.5],“alpha2”: [9.5,12.5], “beta1”: [12.5, 17.5], “beta1”: [17.5, 25], “gamma”: [25,40]} X\_psd\_2 = extract\_features(X = epochs.get\_data([‘F7’]), sfreq = epochs.info[‘sfreq’], selected\_funcs = [‘pow\_freq\_bands’], funcs\_params = {‘pow\_freq\_bands\_\_freq\_bands’: bands, ‘pow\_freq\_bands\_\_normalize’ : True}) ---
**Author:** ![richard](https://yyz2.discourse-cdn.com/free1/user_avatar/mne.discourse.group/richard/32/15_2.png) [@richard](https://mne.discourse.group/u/richard)\ **Post date:** [November 14, 2021, 8:54pm UTC](https://mne.discourse.group/t/custom-frequency-bands-for-calculating-power-band-features/3951/2 "2021-11-14T20:54:48Z")
Hello, > [@FRSHT](#): > > bands = {“delta”: [0.5, 3.5], “theta”: [3.5, 7.5], “alpha1”: [7.5, 9.5],“alpha2”: [9.5,12.5], “beta1”: [12.5, 17.5], “beta1”: [17.5, 25], “gamma”: [25,40]} `beta1` occurs twice, I suppose the second one needs to be `beta2` instead. Best wishes, Richard ---
**Author:** ![FRSHT](https://yyz2.discourse-cdn.com/free1/user_avatar/mne.discourse.group/frsht/32/139_2.png) [@FRSHT](https://mne.discourse.group/u/FRSHT)\ **Post date:** [November 15, 2021, 8:46pm UTC](https://mne.discourse.group/t/custom-frequency-bands-for-calculating-power-band-features/3951/3 "2021-11-15T20:46:28Z")
Thanks for your response @richard , I fixed that and it worked but now I am faced with this error while using the same code: **\_check\_input() missing 1 required keyword-only argument: 'reset’** I have no idea what had happened. ---
**Author:** ![mscheltienne](https://yyz2.discourse-cdn.com/free1/user_avatar/mne.discourse.group/mscheltienne/32/827_2.png) [@mscheltienne](https://mne.discourse.group/u/mscheltienne)\ **Post date:** [November 16, 2021, 9:26am UTC](https://mne.discourse.group/t/custom-frequency-bands-for-calculating-power-band-features/3951/4 "2021-11-16T09:26:45Z")
Can you give the full traceback of the error? It suggests the private method `_check_input()` is used with an argument provided as a positional argument instead of a keyword argument somewhere. i.e. it should be `_check_input(positional_arguments, reset=..., other_keword_argument)` ---
**Author:** ![FRSHT](https://yyz2.discourse-cdn.com/free1/user_avatar/mne.discourse.group/frsht/32/139_2.png) [@FRSHT](https://mne.discourse.group/u/FRSHT)\ **Post date:** [November 16, 2021, 5:43pm UTC](https://mne.discourse.group/t/custom-frequency-bands-for-calculating-power-band-features/3951/5 "2021-11-16T17:43:41Z")
@mscheltienne, Thanks for your response, Of course, I’ll share the entire error trace back, which consists of 21 frames: Specifically, I’d like to extract spectral and temporal properties from “F7” eeg channel data. bands = {“delta”: [0.5, 3.5], “theta”: [3.5, 7.5],“alpha1”: [7.5, 9.5],“alpha2”: [9.5,12.5], “beta1”: [12.5, 17.5], “beta2”: [17.5, 25], “gamma”: [25,40], ‘total’:[0.5,40]} X\_psd\_2 = extract\_features(X = epochs.get\_data([‘F7’]), sfreq = epochs.info[‘sfreq’], selected\_funcs = [‘pow\_freq\_bands’] , funcs\_params = {‘pow\_freq\_bands\_\_freq\_bands’: bands, ‘pow\_freq\_bands\_\_normalize’ : True}) * * * TypeError Traceback (most recent call last) in () 4 selected\_funcs = [‘pow\_freq\_bands’] , 5 funcs\_params = {‘pow\_freq\_bands\_\_freq\_bands’: bands, ----\> 6 ‘pow\_freq\_bands\_\_normalize’ : True}) 21 frames /usr/local/lib/python3.7/dist-packages/mne\_features/feature\_extraction.py in extract\_features(X, sfreq, selected\_funcs, funcs\_params, n\_jobs, return\_as\_df) 433 extractor.set\_params(\*\*funcs\_params) 434 res = joblib.Parallel(n\_jobs=n\_jobs)(joblib.delayed(\_apply\_extractor)( → 435 extractor, X[j, :, :], return\_as\_df) for j in range(n\_epochs)) 436 feature\_names = res[0][1] 437 res = list(zip(\*res))[0] /usr/local/lib/python3.7/dist-packages/joblib/parallel.py in **call** (self, iterable) 1041 # remaining jobs. 1042 self.\_iterating = False → 1043 if self.dispatch\_one\_batch(iterator): 1044 self.\_iterating = self.\_original\_iterator is not None 1045 /usr/local/lib/python3.7/dist-packages/joblib/parallel.py in dispatch\_one\_batch(self, iterator) 859 return False 860 else: → 861 self.\_dispatch(tasks) 862 return True 863 /usr/local/lib/python3.7/dist-packages/joblib/parallel.py in \_dispatch(self, batch) 777 with self.\_lock: 778 job\_idx = len(self.\_jobs) → 779 job = self.\_backend.apply\_async(batch, callback=cb) 780 # A job can complete so quickly than its callback is 781 # called before we get here, causing self.\_jobs to /usr/local/lib/python3.7/dist-packages/joblib/\_parallel\_backends.py in apply\_async(self, func, callback) 206 def apply\_async(self, func, callback=None): 207 “”“Schedule a func to be run”"" → 208 result = ImmediateResult(func) 209 if callback: 210 callback(result) /usr/local/lib/python3.7/dist-packages/joblib/\_parallel\_backends.py in **init** (self, batch) 570 # Don’t delay the application, to avoid keeping the input 571 # arguments in memory → 572 self.results = batch() 573 574 def get(self): /usr/local/lib/python3.7/dist-packages/joblib/parallel.py in **call** (self) 261 with parallel\_backend(self.\_backend, n\_jobs=self.\_n\_jobs): 262 return [func(\*args, \*\*kwargs) → 263 for func, args, kwargs in self.items] 264 265 def **reduce** (self): /usr/local/lib/python3.7/dist-packages/joblib/parallel.py in (.0) 261 with parallel\_backend(self.\_backend, n\_jobs=self.\_n\_jobs): 262 return [func(\*args, \*\*kwargs) → 263 for func, args, kwargs in self.items] 264 265 def **reduce** (self): /usr/local/lib/python3.7/dist-packages/mne\_features/feature\_extraction.py in \_apply\_extractor(extractor, X, return\_as\_df) 199 Not None, only if `return_as_df` is True. 200 “”" → 201 X = extractor.fit\_transform(X) 202 feature\_names = None 203 if return\_as\_df: /usr/local/lib/python3.7/dist-packages/sklearn/pipeline.py in fit\_transform(self, X, y, \*\*fit\_params) 1170 sum of `n_components` (output dimension) over transformers. 1171 “”" → 1172 results = self.\_parallel\_func(X, y, fit\_params, \_fit\_transform\_one) 1173 if not results: 1174 # All transformers are None /usr/local/lib/python3.7/dist-packages/sklearn/pipeline.py in \_parallel\_func(self, X, y, fit\_params, func) 1202 \*\*fit\_params, 1203 ) → 1204 for idx, (name, transformer, weight) in enumerate(transformers, 1) 1205 ) 1206 /usr/local/lib/python3.7/dist-packages/joblib/parallel.py in **call** (self, iterable) 1041 # remaining jobs. 1042 self.\_iterating = False → 1043 if self.dispatch\_one\_batch(iterator): 1044 self.\_iterating = self.\_original\_iterator is not None 1045 /usr/local/lib/python3.7/dist-packages/joblib/parallel.py in dispatch\_one\_batch(self, iterator) 859 return False 860 else: → 861 self.\_dispatch(tasks) 862 return True 863 /usr/local/lib/python3.7/dist-packages/joblib/parallel.py in \_dispatch(self, batch) 777 with self.\_lock: 778 job\_idx = len(self.\_jobs) → 779 job = self.\_backend.apply\_async(batch, callback=cb) 780 # A job can complete so quickly than its callback is 781 # called before we get here, causing self.\_jobs to /usr/local/lib/python3.7/dist-packages/joblib/\_parallel\_backends.py in apply\_async(self, func, callback) 206 def apply\_async(self, func, callback=None): 207 “”“Schedule a func to be run”"" → 208 result = ImmediateResult(func) 209 if callback: 210 callback(result) /usr/local/lib/python3.7/dist-packages/joblib/\_parallel\_backends.py in **init** (self, batch) 570 # Don’t delay the application, to avoid keeping the input 571 # arguments in memory → 572 self.results = batch() 573 574 def get(self): /usr/local/lib/python3.7/dist-packages/joblib/parallel.py in **call** (self) 261 with parallel\_backend(self.\_backend, n\_jobs=self.\_n\_jobs): 262 return [func(\*args, \*\*kwargs) → 263 for func, args, kwargs in self.items] 264 265 def **reduce** (self): /usr/local/lib/python3.7/dist-packages/joblib/parallel.py in (.0) 261 with parallel\_backend(self.\_backend, n\_jobs=self.\_n\_jobs): 262 return [func(\*args, \*\*kwargs) → 263 for func, args, kwargs in self.items] 264 265 def **reduce** (self): /usr/local/lib/python3.7/dist-packages/sklearn/utils/fixes.py in **call** (self, \*args, \*\*kwargs) 209 def **call** (self, \*args, \*\*kwargs): 210 with config\_context(\*\*self.config): → 211 return self.function(\*args, \*\*kwargs) 212 213 /usr/local/lib/python3.7/dist-packages/sklearn/pipeline.py in \_fit\_transform\_one(transformer, X, y, weight, message\_clsname, message, \*\*fit\_params) 891 with \_print\_elapsed\_time(message\_clsname, message): 892 if hasattr(transformer, “fit\_transform”): → 893 res = transformer.fit\_transform(X, y, \*\*fit\_params) 894 else: 895 res = transformer.fit(X, y, \*\*fit\_params).transform(X) /usr/local/lib/python3.7/dist-packages/sklearn/base.py in fit\_transform(self, X, y, \*\*fit\_params) 845 if y is None: 846 # fit method of arity 1 (unsupervised transformation) → 847 return self.fit(X, \*\*fit\_params).transform(X) 848 else: 849 # fit method of arity 2 (supervised transformation) /usr/local/lib/python3.7/dist-packages/mne\_features/feature\_extraction.py in fit(self, X, y) 85 self 86 “”" —\> 87 self.\_check\_input(X) 88 \_feature\_func = \_get\_python\_func(self.func) 89 if hasattr(\_feature\_func, ‘get\_feature\_names’): TypeError: \_check\_input() missing 1 required keyword-only argument: ‘reset’ ---
**Author:** ![mscheltienne](https://yyz2.discourse-cdn.com/free1/user_avatar/mne.discourse.group/mscheltienne/32/827_2.png) [@mscheltienne](https://mne.discourse.group/u/mscheltienne)\ **Post date:** [November 17, 2021, 10:27am UTC](https://mne.discourse.group/t/custom-frequency-bands-for-calculating-power-band-features/3951/6 "2021-11-17T10:27:42Z")
This bug has been fix on the github repository: > in this commit: [passing reset=True in \_check\_input() · mne-tools/mne-features@629f5d4 · GitHub](https://github.com/mne-tools/mne-features/commit/629f5d48f03e5facf0280c989b26cbebab4d199d) To get rid of it, you could update to the development version, either by cloning the repository and then doing: `python setup.py install` Or by using the pip command: `pip install git+https://github.com/mne-tools/mne-features.git#egg=mne_features` ---
**Author:** ![FRSHT](https://yyz2.discourse-cdn.com/free1/user_avatar/mne.discourse.group/frsht/32/139_2.png) [@FRSHT](https://mne.discourse.group/u/FRSHT)\ **Post date:** [November 18, 2021, 12:25pm UTC](https://mne.discourse.group/t/custom-frequency-bands-for-calculating-power-band-features/3951/7 "2021-11-18T12:25:28Z")
@mscheltienne Many thanks for your help.