Braindecode 1.3.0.dev176089716__tar.gz → 1.3.0.dev176122045__tar.gz

{braindecode-1.3.0.dev176089716/braindecode.egg-info → braindecode-1.3.0.dev176122045}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: braindecode
-Version: 1.3.0.dev176089716
+Version: 1.3.0.dev176122045
 Summary: Deep learning software to decode EEG, ECG or MEG signals
 Author-email: Robin Tibor Schirrmeister <robintibor@gmail.com>
 Maintainer-email: Alexandre Gramfort <agramfort@meta.com>, Bruno Aristimunha Pinto <b.aristimunha@gmail.com>, Robin Tibor Schirrmeister <robintibor@gmail.com>

{braindecode-1.3.0.dev176089716 → braindecode-1.3.0.dev176122045}/braindecode/models/__init__.py

@@ -28,7 +28,6 @@ from .fbmsnet import FBMSNet
 from .hybrid import HybridNet
 from .ifnet import IFNet
 from .labram import Labram
-from .medformer import MEDFormer
 from .msvtnet import MSVTNet
 from .patchedtransformer import PBT
 from .sccnet import SCCNet
@@ -83,7 +82,6 @@ __all__ = [
     "HybridNet",
     "IFNet",
     "Labram",
-    "MEDFormer",
     "MSVTNet",
     "PBT",
     "SCCNet",

{braindecode-1.3.0.dev176089716 → braindecode-1.3.0.dev176122045}/braindecode/models/summary.csv

@@ -41,4 +41,3 @@ IFNet,Motor Imagery,Classification,250,"n_chans, n_outputs, n_times, sfreq",9860
 PBT,General,Classification,250,"n_chans, n_outputs, n_times",818948,"PBT(n_chans=22, n_outputs=4, n_times=1000, sfreq=250)","Large Brain Model"
 SSTDPN,Motor Imagery,Classification,250,"n_chans, n_outputs, n_times",19502,"SSTDPN(n_chans=22, n_outputs=4, n_times=1000)","Convolution,Small Attention"
 BENDR,General,"Classification,Embedding",250,"n_chans, n_times, n_outputs",157141049,"BENDR(n_chans=22, n_outputs=4, n_times=1000)","Large Brain Model,Convolution"
-MEDFormer,General,Classification,250,"n_chans, n_outputs, n_times",5313924,"MEDFormer(n_chans=22, n_outputs=4, n_times=1000)","Large Brain Model,Convolution"

{braindecode-1.3.0.dev176089716 → braindecode-1.3.0.dev176122045}/braindecode/models/util.py

@@ -99,7 +99,6 @@ models_mandatory_parameters = [
     ("PBT", ["n_chans", "n_outputs", "n_times"], None),
     ("SSTDPN", ["n_chans", "n_outputs", "n_times", "sfreq"], None),
     ("BENDR", ["n_chans", "n_outputs", "n_times"], None),
-    ("MEDFormer", ["n_chans", "n_outputs", "n_times"], None),
 ]
 
 ################################################################

braindecode-1.3.0.dev176122045/braindecode/preprocessing/__init__.py

@@ -0,0 +1,61 @@
+from .eegprep_preprocess import (
+    EEGPrep,
+    ReinterpolateRemovedChannels,
+    RemoveBadChannels,
+    RemoveBadChannelsNoLocs,
+    RemoveBadWindows,
+    RemoveBursts,
+    RemoveCommonAverageReference,
+    RemoveDCOffset,
+    RemoveDrifts,
+    RemoveFlatChannels,
+    Resampling,
+)
+from .mne_preprocess import (  # type: ignore[attr-defined]
+    Crop,
+    DropChannels,
+    Filter,
+    Pick,
+    Resample,
+    SetEEGReference,
+)
+from .preprocess import (
+    Preprocessor,
+    exponential_moving_demean,
+    exponential_moving_standardize,
+    filterbank,
+    preprocess,
+)
+from .windowers import (
+    create_fixed_length_windows,
+    create_windows_from_events,
+    create_windows_from_target_channels,
+)
+
+__all__ = [
+    "exponential_moving_demean",
+    "exponential_moving_standardize",
+    "filterbank",
+    "preprocess",
+    "Preprocessor",
+    "Resample",
+    "DropChannels",
+    "SetEEGReference",
+    "Filter",
+    "Pick",
+    "Crop",
+    "EEGPrep",
+    "RemoveDCOffset",
+    "Resampling",
+    "RemoveFlatChannels",
+    "RemoveDrifts",
+    "RemoveBadChannels",
+    "RemoveBadChannelsNoLocs",
+    "RemoveBursts",
+    "RemoveBadWindows",
+    "ReinterpolateRemovedChannels",
+    "RemoveCommonAverageReference",
+    "create_windows_from_events",
+    "create_fixed_length_windows",
+    "create_windows_from_target_channels",
+]

braindecode-1.3.0.dev176122045/braindecode/preprocessing/mne_preprocess.py

@@ -0,0 +1,77 @@
+"""Preprocessor objects based on mne methods."""
+
+# Authors: Bruna Lopes <brunajaflopes@gmail.com>
+#          Bruno Aristimunha <b.aristimunha@gmail.com>
+#
+# License: BSD-3
+import inspect
+
+import mne.io
+
+from braindecode.preprocessing.preprocess import Preprocessor
+from braindecode.util import _update_moabb_docstring
+
+
+def _generate_init_method(func):
+    """
+    Generate an __init__ method for a class based on the function's signature.
+    """
+    parameters = list(inspect.signature(func).parameters.values())
+    param_names = [param.name for param in parameters]
+
+    def init_method(self, *args, **kwargs):
+        for name, value in zip(param_names, args):
+            setattr(self, name, value)
+        for name, value in kwargs.items():
+            setattr(self, name, value)
+        self.kwargs = kwargs
+
+    init_method.__signature__ = inspect.signature(func)
+    return init_method
+
+
+def _generate_mne_pre_processor(function):
+    """
+    Generate a class based on an MNE function for preprocessing.
+    """
+    class_name = "".join(word.title() for word in function.__name__.split("_")).replace(
+        "Eeg", "EEG"
+    )
+    import_path = f"{function.__module__}.{function.__name__}"
+    doc = f" See more details in {import_path}"
+
+    base_classes = (Preprocessor,)
+    class_attrs = {
+        "__init__": _generate_init_method(function),
+        "__doc__": _update_moabb_docstring(function, doc),
+        "fn": function.__name__,
+    }
+    generated_class = type(class_name, base_classes, class_attrs)
+
+    return generated_class
+
+
+# List of MNE functions to generate classes for
+mne_functions = [
+    mne.filter.resample,
+    mne.io.Raw.drop_channels,
+    mne.io.Raw.filter,
+    mne.io.Raw.crop,
+    mne.io.Raw.pick,
+    mne.io.Raw.set_eeg_reference,
+]
+
+# Automatically generate and add classes to the global namespace
+for function in mne_functions:
+    class_obj = _generate_mne_pre_processor(function)
+    globals()[class_obj.__name__] = class_obj
+
+# Define __all__ based on the generated class names
+__all__ = [
+    class_obj.__name__
+    for class_obj in globals().values()
+    if isinstance(class_obj, type)
+]
+
+# Clean up unnecessary variables
+del mne_functions, function, class_obj

{braindecode-1.3.0.dev176089716 → braindecode-1.3.0.dev176122045}/braindecode/preprocessing/preprocess.py

@@ -85,7 +85,7 @@ class Preprocessor(object):
 
     def apply(self, raw_or_epochs: BaseRaw | BaseEpochs):
         try:
-            return self._try_apply(raw_or_epochs)
+            self._try_apply(raw_or_epochs)
         except RuntimeError:
             # Maybe the function needs the data to be loaded and the data was
             # not loaded yet. Not all MNE functions need data to be loaded,
@@ -93,20 +93,15 @@ class Preprocessor(object):
             # without preloading data which can make the overall preprocessing
             # pipeline substantially faster.
             raw_or_epochs.load_data()
-            return self._try_apply(raw_or_epochs)
+            self._try_apply(raw_or_epochs)
 
     def _try_apply(self, raw_or_epochs):
         if callable(self.fn):
-            result = self.fn(raw_or_epochs, **self.kwargs)
-            # For standalone functions that return a new object, propagate it back
-            if result is not None and result is not raw_or_epochs:
-                return result
-            return raw_or_epochs
+            self.fn(raw_or_epochs, **self.kwargs)
         else:
             if not hasattr(raw_or_epochs, self.fn):
                 raise AttributeError(f"MNE object does not have a {self.fn} method.")
             getattr(raw_or_epochs, self.fn)(**self.kwargs)
-            return raw_or_epochs
 
 
 def preprocess(
@@ -256,21 +251,16 @@ def _preprocess(
         if raw_or_epochs.preload and copy_data:
             raw_or_epochs._data = raw_or_epochs._data.copy()
         for preproc in preprocessors:
-            raw_or_epochs = preproc.apply(raw_or_epochs)
-        return raw_or_epochs
+            preproc.apply(raw_or_epochs)
 
     if hasattr(ds, "raw"):
         if isinstance(ds, EEGWindowsDataset):
             warn(
                 f"Applying preprocessors {preprocessors} to the mne.io.Raw of an EEGWindowsDataset."
             )
-        processed = _preprocess_raw_or_epochs(ds.raw, preprocessors)
-        if processed is not ds.raw:
-            ds.raw = processed
+        _preprocess_raw_or_epochs(ds.raw, preprocessors)
     elif hasattr(ds, "windows"):
-        processed = _preprocess_raw_or_epochs(ds.windows, preprocessors)
-        if processed is not ds.windows:
-            ds.windows = processed
+        _preprocess_raw_or_epochs(ds.windows, preprocessors)
     else:
         raise ValueError(
             "Can only preprocess concatenation of RecordDataset, "

braindecode-1.3.0.dev176122045/braindecode/version.py

@@ -0,0 +1 @@
+__version__ = "1.3.0.dev176122045"

{braindecode-1.3.0.dev176089716 → braindecode-1.3.0.dev176122045/braindecode.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: braindecode
-Version: 1.3.0.dev176089716
+Version: 1.3.0.dev176122045
 Summary: Deep learning software to decode EEG, ECG or MEG signals
 Author-email: Robin Tibor Schirrmeister <robintibor@gmail.com>
 Maintainer-email: Alexandre Gramfort <agramfort@meta.com>, Bruno Aristimunha Pinto <b.aristimunha@gmail.com>, Robin Tibor Schirrmeister <robintibor@gmail.com>

{braindecode-1.3.0.dev176089716 → braindecode-1.3.0.dev176122045}/braindecode.egg-info/SOURCES.txt

@@ -66,7 +66,6 @@ braindecode/models/fbmsnet.py
 braindecode/models/hybrid.py
 braindecode/models/ifnet.py
 braindecode/models/labram.py
-braindecode/models/medformer.py
 braindecode/models/msvtnet.py
 braindecode/models/patchedtransformer.py
 braindecode/models/sccnet.py

{braindecode-1.3.0.dev176089716 → braindecode-1.3.0.dev176122045}/docs/api.rst

@@ -80,7 +80,6 @@ save and load models from the Hugging Face Hub, if the ``braindecode[hug]`` pack
     FBMSNet
     IFNet
     Labram
-    MEDFormer
     MSVTNet
     PBT
     SCCNet
@@ -365,28 +364,37 @@ Preprocessing
 
 .. currentmodule:: braindecode.preprocessing
 
-Core Functions
-''''''''''''''
-
 .. autosummary::
    :toctree: generated/
 
-    preprocess
-    Preprocessor
     create_windows_from_events
     create_fixed_length_windows
     create_windows_from_target_channels
     exponential_moving_demean
     exponential_moving_standardize
     filterbank
+    preprocess
+    Preprocessor
+    EEGPrep
 
-EEGPrep Pipeline
-''''''''''''''''
+
+Preprocessing Transform
+''''''''''''''''''''''''
+
+These modules implement various preprocessing transforms that can be applied
+to EEG data, including cropping, filtering, resampling, and channel selection.
+
+:py:mod:`braindecode.preprocessing`:
+
+.. currentmodule:: braindecode.preprocessing
 
 .. autosummary::
    :toctree: generated/
 
-    EEGPrep
+    Crop
+    DropChannels
+    Filter
+    Pick
     ReinterpolateRemovedChannels
     RemoveBadChannels
     RemoveBadChannelsNoLocs
@@ -396,107 +404,9 @@ EEGPrep Pipeline
     RemoveDCOffset
     RemoveDrifts
     RemoveFlatChannels
-
-Signal Processing
-'''''''''''''''''
-
-.. autosummary::
-   :toctree: generated/
-
     Resample
     Resampling
-    Filter
-    FilterData
-    NotchFilter
-    SavgolFilter
-    ApplyHilbert
-    Rescale
-    OversampledTemporalProjection
-
-Channel Management
-''''''''''''''''''
-
-.. autosummary::
-   :toctree: generated/
-
-    Pick
-    PickChannels
-    PickTypes
-    DropChannels
-    AddChannels
-    CombineChannels
-    RenameChannels
-    ReorderChannels
-    SetChannelTypes
-    InterpolateBads
-    InterpolateTo
-    InterpolateBridgedElectrodes
-    ComputeBridgedElectrodes
-    EqualizeChannels
-    EqualizeBads
-    FindBadChannelsLof
-
-Reference & Montage
-'''''''''''''''''''
-
-.. autosummary::
-   :toctree: generated/
-
     SetEEGReference
-    SetBipolarReference
-    AddReferenceChannels
-    SetMontage
-
-SSP Projections
-'''''''''''''''
-
-.. autosummary::
-   :toctree: generated/
-
-    AddProj
-    ApplyProj
-    DelProj
-
-Data Transformation
-'''''''''''''''''''
-
-.. autosummary::
-   :toctree: generated/
-
-    Crop
-    CropByAnnotations
-    ComputeCurrentSourceDensity
-    FixStimArtifact
-    MaxwellFilter
-    RealignRaw
-    RegressArtifact
-
-Artifact Detection & Annotation
-''''''''''''''''''''''''''''''''
-
-.. autosummary::
-   :toctree: generated/
-
-    AnnotateAmplitude
-    AnnotateBreak
-    AnnotateMovement
-    AnnotateMuscleZscore
-    AnnotateNan
-
-Metadata & Configuration
-'''''''''''''''''''''''''
-
-.. autosummary::
-   :toctree: generated/
-
-    Anonymize
-    SetAnnotations
-    SetMeasDate
-    AddEvents
-    FixMagCoilTypes
-    ApplyGradientCompensation
-
-
 
 
 Data Utils

{braindecode-1.3.0.dev176089716 → braindecode-1.3.0.dev176122045}/docs/conf.py

@@ -22,7 +22,6 @@ import inspect
 import os
 import os.path as op
 import sys
-import warnings
 
 import matplotlib
 
@@ -34,32 +33,6 @@ import sphinx_gallery  # noqa
 from numpydoc import docscrape, numpydoc  # noqa
 from sphinx_gallery.sorting import ExplicitOrder, FileNameSortKey
 
-# Merge MNE-Python references during build
-try:
-    import logging
-    import sys
-    from pathlib import Path
-
-    # Add current directory to path so we can import download_mne_references
-    docs_dir = Path(__file__).parent.absolute()
-    if str(docs_dir) not in sys.path:
-        sys.path.insert(0, str(docs_dir))
-
-    logger = logging.getLogger(__name__)
-    from download_mne_references import update_references
-
-    logger.info("Attempting to merge MNE-Python references...")
-    result = update_references()
-    if result:
-        logger.info("MNE-Python references merged successfully or skipped gracefully")
-    else:
-        logger.warning("MNE references update returned False")
-except ImportError as e:
-    warnings.warn(f"Could not import download_mne_references module: {e}")
-except Exception as e:
-    # Don't fail the build if updating references fails; emit a warning
-    warnings.warn(f"MNE references update encountered an issue: {e}")
-
 # -- General configuration ------------------------------------------------
 
 # If your documentation needs a minimal Sphinx version, state it here.

{braindecode-1.3.0.dev176089716 → braindecode-1.3.0.dev176122045}/docs/whats_new.rst

@@ -27,7 +27,6 @@ Enhancements
 - Adding :class:`braindecode.models.SSTDPN`  (:gh:`790` by `Can Han`_ and `Bruno Aristimunha`_ )
 - Added :class:`braindecode.models.BENDR`  (:gh:`802` by `Bruno Aristimunha`_ )
 - Adding a tutorial for fine-tuning a pre-trained foundation model (:gh:`794` by `Pierre Guetschel`_)
-- Added 25 new MNE preprocessing functions, expanding from 6 to 31 total preprocessing classes. New functions include: :class:`braindecode.preprocessing.NotchFilter`, :class:`braindecode.preprocessing.SavgolFilter`, :class:`braindecode.preprocessing.ApplyHilbert`, :class:`braindecode.preprocessing.InterpolateBads`, :class:`braindecode.preprocessing.InterpolateTo`, :class:`braindecode.preprocessing.RenameChannels`, :class:`braindecode.preprocessing.ReorderChannels`, :class:`braindecode.preprocessing.EqualizeChannels`, :class:`braindecode.preprocessing.AddChannels`, :class:`braindecode.preprocessing.SetMontage`, :class:`braindecode.preprocessing.AddReferenceChannels`, :class:`braindecode.preprocessing.AddProj`, :class:`braindecode.preprocessing.ApplyProj`, :class:`braindecode.preprocessing.DelProj`, :class:`braindecode.preprocessing.ComputeCurrentSourceDensity`, :class:`braindecode.preprocessing.FixStimArtifact`, :class:`braindecode.preprocessing.CropByAnnotations`, :class:`braindecode.preprocessing.Anonymize`, :class:`braindecode.preprocessing.SetAnnotations`, :class:`braindecode.preprocessing.SetChannelTypes`, :class:`braindecode.preprocessing.SetMeasDate`, :class:`braindecode.preprocessing.FixMagCoilTypes`, :class:`braindecode.preprocessing.ApplyGradientCompensation`, :class:`braindecode.preprocessing.AddEvents`, and :class:`braindecode.preprocessing.Rescale` (:gh:`801` by `Bruno Aristimunha`_)
 - Adding artifact removal preprocessing steps, incl. :class:`braindecode.preprocessing.EEGPrep` (:gh:`796` by `Christian Kothe`_)
 - Including huggingface hub mixin to all models (:gh:`795` by `Kuntal Kokate`_ )
 - Better inheritance between the different dataset classes (:gh:`806` by `Pierre Guetschel`_ )
@@ -35,9 +34,7 @@ Enhancements
 - Including missed tag in all the models and creating some test for it (:gh:`811` by `Bruno Aristimunha`_ )
 - Modify verbosity of create_window_from_events (:gh:`814` by `Matthew Chen`_)
 - Modify the interface of FBMSNet for consistency with FBCNet + Unit Tests (:gh:`819` by `Matthew Chen`_)
-- Adding :class:`braindecode.models.MEDFormer`  (:gh:`821` by `Bruno Aristimunha`_ )
 - Adding :class:`braindecode.models.EEGSym` model (:gh:`697` by `Pierre Guetschel`_ and `Bruno Aristimunha`_ )
-- Adding tutorial for :func:`braindecode.preprocessing.windowers.create_fixed_length_windows` (:gh:`746` by `Aniela Bulicz` and `Arina Schippers` and `Aron van Zuijlen`)
 
 
 API changes
@@ -425,4 +422,3 @@ Authors
 .. _Christian Kothe: https://github.com/chkothe
 .. _Kuntal Kokate: https://github.com/Kkuntal990
 .. _Matthew Chen: https://github.com/MatthewChen37
-.. _Aniela Bulicz: github.com/AryaDro