Filter bank classes

docs/source/api.rst

@@ -215,8 +215,7 @@ P300 Paradigms
     :toctree: generated/
     :template: class.rst
 
-     SinglePass
-     P300
+    P300
 
 ---------------
 SSVEP Paradigms
@@ -270,8 +269,6 @@ Base & Utils
     :template: class.rst
 
     motor_imagery.BaseMotorImagery
-    motor_imagery.SinglePass
-    motor_imagery.FilterBank
     p300.BaseP300
     ssvep.BaseSSVEP
     BaseFixedIntervalWindowsProcessing

docs/source/whats_new.rst

@@ -39,6 +39,7 @@ Enhancements
 
 API changes
 ~~~~~~~~~~~
+- Removed ``SinglePass`` and ``FilterBank`` intermediate classes from motor imagery and P300 paradigms. ``FilterBankLeftRightImagery`` now inherits from ``LeftRightImagery``, ``FilterBankMotorImagery`` inherits from ``MotorImagery``, and ``P300`` inherits directly from ``BaseP300``. ``RestingStateToP300Adapter`` now inherits from ``BaseP300``. Docstring inheritance is handled via ``NumpyDocstringInheritanceInitMeta`` (:gh:`467` by `Bruno Aristimunha`_).
 - Allow CodeCarbon script level configurations when instantiating a :class:`moabb.evaluations.base.BaseEvaluation` child class (:gh:`866` by `Ethan Davis`_).
 - When CodeCarbon is installed, MOABB HDF5 results have an additional column `codecarbon_task_name`. If CodeCarbon is configured to save to file, its own tabular results have a column `task_name`. These columns are unique UUID4s. Related rows can be joined to see detailed costs and benefits of predictive performance and computing profiling metrics (:gh:`866` by `Ethan Davis`_).
 - Isolated model fitting, duration tracking, and CodeCarbon compute profiling tracking. New and consistent ordering of duration and CodeCarbon tracking across all evaluations: (Higher priority, closest to model fitting) required duration tracking, (lower priority, second closest to model fitting) optional CodeCarbon tracking (:gh:`866` by `Ethan Davis`_).

moabb/paradigms/base.py

@@ -27,6 +27,7 @@
     get_resample_pipeline,
     make_fixed_pipeline,
 )
+from moabb.utils import MoabbMetaClass
 
 
 log = logging.getLogger(__name__)
@@ -188,7 +189,7 @@ def _is_valid_scorer_item(item):
     return scorer
 
 
-class BaseProcessing(metaclass=abc.ABCMeta):
+class BaseProcessing(metaclass=MoabbMetaClass):
     """Base Processing.
 
     Please use one of the child classes
@@ -744,7 +745,7 @@ class BaseParadigm(BaseProcessing):
     ----------
 
     events: List of str | None (default None)
-        event to use for epoching. If None, default to all events defined in
+        events to use for epoching. If None, default to all events defined in
         the dataset.
 
     scorer: sklearn-compatible string or a compatible sklearn scorer | None (default None)

moabb/paradigms/cvep.py

@@ -36,35 +36,6 @@ class BaseCVEP(BaseParadigm):
     n_classes: int or None (default None)
         Number of classes each dataset must have. All dataset classes if None.
 
-    tmin: float (default 0.0)
-        Start time (in second) of the epoch, relative to the dataset specific
-        task interval e.g. tmin = 1 would mean the epoch will start 1 second
-        after the beginning of the task as defined by the dataset.
-
-    tmax: float | None (default None)
-        End time (in second) of the epoch, relative to the beginning of the
-        dataset specific task interval. tmax = 5 would mean the epoch will end
-        5 second after the beginning of the task as defined in the dataset. If
-        None, use the dataset value.
-
-    baseline: None | tuple of length 2 (default None)
-        The time interval to consider as “baseline” when applying baseline
-        correction. If None, do not apply baseline correction.
-        If a tuple (a, b), the interval is between a and b (in seconds),
-        including the endpoints.
-        Correction is applied by computing the mean of the baseline period
-        and subtracting it from the data (see mne.Epochs)
-
-    channels: list of str | None (default None)
-        list of channel to select. If None, use all EEG channels available in
-        the dataset.
-
-    resample: float | None (default None)
-        If not None, resample the eeg data with the sampling rate provided.
-
-    scorer: sklearn-compatible string or a compatible sklearn scorer | None (default None)
-        If None, and n_classes==2 use the roc_auc, else use accuracy.
-
     Notes
     -----
 
@@ -176,7 +147,6 @@ class CVEP(BaseCVEP):
     the target code. The code value is between 0  (i.e., stimulation off)
     and 1 (i.e., maximal stimulation).
 
-
     Parameters
     ----------
     fmin: float (default 1.0)
@@ -185,55 +155,40 @@ class CVEP(BaseCVEP):
     fmax: float (default 45.0)
         cutoff frequency (Hz) for the lowpass filter
 
-    events: List of str | None (default None)
-        Event to use for epoching. Note, we stick to a convention where the
-        intensity level is encoded as float. For example, a binary sequence
-        would have events 1.0 (i.e., on) and 0.0 (i.e., off). If None, default
-        to all events defined in the dataset.
-
-    n_classes: int or None (default None)
-        Number of classes each dataset must have. All dataset classes if None
-
-    tmin: float (default 0.0)
-        Start time (in second) of the epoch, relative to the dataset specific
-        task interval e.g. tmin = 1 would mean the epoch will start 1 second
-        after the beginning of the task as defined by the dataset.
-
-    tmax: float | None, (default None)
-        End time (in second) of the epoch, relative to the beginning of the
-        dataset specific task interval. tmax = 5 would mean the epoch will end
-        5 second after the beginning of the task as defined in the dataset. If
-        None, use the dataset value.
-
-    baseline: None | tuple of length 2 (default None)
-        The time interval to consider as “baseline” when applying baseline
-        correction. If None, do not apply baseline correction.
-        If a tuple (a, b), the interval is between a and b (in seconds),
-        including the endpoints.
-        Correction is applied by computing the mean of the baseline period
-        and subtracting it from the data (see mne.Epochs)
-
-    channels: list of str | None (default None)
-        List of channel to select. If None, use all EEG channels available in
-        the dataset.
-
-    resample: float | None (default None)
-        If not None, resample the eeg data with the sampling rate provided.
-
-    scorer: sklearn-compatible string or a compatible sklearn scorer | None (default None)
-        If None, and n_classes==2 use the roc_auc, else use accuracy.
-
     Notes
     -----
 
     .. versionadded:: 1.0.0
 
     """
 
-    def __init__(self, fmin=1.0, fmax=45.0, **kwargs):
-        if "filters" in kwargs.keys():
-            raise (ValueError("c-VEP does not take argument filters"))
-        super().__init__(filters=((fmin, fmax),), **kwargs)
+    def __init__(
+        self,
+        fmin=1.0,
+        fmax=45.0,
+        filters=None,
+        events=None,
+        n_classes=None,
+        tmin=0.0,
+        tmax=None,
+        baseline=None,
+        channels=None,
+        resample=None,
+        scorer=None,
+    ):
+        if filters is not None:
+            raise ValueError("c-VEP does not take argument filters")
+        super().__init__(
+            filters=((fmin, fmax),),
+            events=events,
+            n_classes=n_classes,
+            tmin=tmin,
+            tmax=tmax,
+            baseline=baseline,
+            channels=channels,
+            resample=resample,
+            scorer=scorer,
+        )
 
 
 class FilterBankCVEP(BaseCVEP):
@@ -251,36 +206,6 @@ class FilterBankCVEP(BaseCVEP):
     ----------
     filters: tuple of tuple | None (default ((1., 45.), (12., 45.), (30., 45.)))
         Bank of bandpass filter to apply.
-    events: List of str | None (default None)
-        Event to use for epoching. Note, we stick to a convention where the
-        intensity level is encoded as float. For example, a binary sequence
-        would have events 1.0 (i.e., on) and 0.0 (i.e., off). If None, default
-        to all events defined in the dataset.
-    n_classes: int or None (default None)
-        Number of classes each dataset must have. All dataset classes if None
-    tmin: float (default 0.0)
-        Start time (in second) of the epoch, relative to the dataset specific
-        task interval e.g. tmin = 1 would mean the epoch will start 1 second
-        after the beginning of the task as defined by the dataset.
-    tmax: float | None, (default None)
-        End time (in second) of the epoch, relative to the beginning of the
-        dataset specific task interval. tmax = 5 would mean the epoch will end
-        5 second after the beginning of the task as defined in the dataset. If
-        None, use the dataset value.
-    baseline: None | tuple of length 2 (default None)
-        The time interval to consider as “baseline” when applying baseline
-        correction. If None, do not apply baseline correction.
-        If a tuple (a, b), the interval is between a and b (in seconds),
-        including the endpoints.
-        Correction is applied by computing the mean of the baseline period
-        and subtracting it from the data (see mne.Epochs)
-    channels: list of str | None (default None)
-        List of channel to select. If None, use all EEG channels available in
-        the dataset.
-    resample: float | None (default None)
-        If not None, resample the eeg data with the sampling rate provided.
-    scorer: sklearn-compatible string or a compatible sklearn scorer | None (default None)
-        If None, and n_classes==2 use the roc_auc, else use accuracy.
 
     Notes
     -----
@@ -289,8 +214,29 @@ class FilterBankCVEP(BaseCVEP):
 
     """
 
-    def __init__(self, filters=((1.0, 45.0), (12.0, 45.0), (30.0, 45.0)), **kwargs):
-        super().__init__(filters=filters, **kwargs)
+    def __init__(
+        self,
+        filters=((1.0, 45.0), (12.0, 45.0), (30.0, 45.0)),
+        events=None,
+        n_classes=None,
+        tmin=0.0,
+        tmax=None,
+        baseline=None,
+        channels=None,
+        resample=None,
+        scorer=None,
+    ):
+        super().__init__(
+            filters=filters,
+            events=events,
+            n_classes=n_classes,
+            tmin=tmin,
+            tmax=tmax,
+            baseline=baseline,
+            channels=channels,
+            resample=resample,
+            scorer=scorer,
+        )
 
 
 class FakeCVEPParadigm(BaseCVEP):

moabb/paradigms/fixed_interval_windows.py

@@ -12,24 +12,6 @@ class BaseFixedIntervalWindowsProcessing(BaseProcessing):
     Parameters
     ----------
 
-    filters: list of list (default [[7, 45]])
-        bank of bandpass filter to apply.
-
-    baseline: None | tuple of length 2
-        The time interval to consider as “baseline” when applying baseline
-        correction. If None, do not apply baseline correction.
-        If a tuple (a, b), the interval is between a and b (in seconds),
-        including the endpoints.
-        Correction is applied by computing the mean of the baseline period
-        and subtracting it from the data (see mne.Epochs)
-
-    channels: list of str | None (default None)
-        list of channel to select. If None, use all EEG channels available in
-        the dataset.
-
-    resample: float | None (default None)
-        If not None, resample the eeg data with the sampling rate provided.
-
     length: float (default 5.0)
         Length of the epochs in seconds.
 
@@ -133,45 +115,13 @@ class FixedIntervalWindowsProcessing(BaseFixedIntervalWindowsProcessing):
     Paradigm for creating epochs at fixed interval,
     ignoring the stim channel and events of the dataset.
 
-     Parameters
-     ----------
-
+    Parameters
+    ----------
     fmin: float (default 7)
         cutoff frequency (Hz) for the high pass filter
 
     fmax: float (default 45)
         cutoff frequency (Hz) for the low pass filter
-
-    baseline: None | tuple of length 2
-        The time interval to consider as “baseline” when applying baseline
-        correction. If None, do not apply baseline correction.
-        If a tuple (a, b), the interval is between a and b (in seconds),
-        including the endpoints.
-        Correction is applied by computing the mean of the baseline period
-        and subtracting it from the data (see mne.Epochs)
-
-    channels: list of str | None (default None)
-        list of channel to select. If None, use all EEG channels available in
-        the dataset.
-
-    resample: float | None (default None)
-        If not None, resample the eeg data with the sampling rate provided.
-
-    length: float (default 5.0)
-        Length of the epochs in seconds.
-
-    stride: float (default 10.0)
-        Stride between epochs in seconds.
-
-    start_offset: float (default 0.0)
-        Start from the beginning of the raw recordings in seconds.
-
-    stop_offset: float | None (default None)
-        Stop offset from beginning of raw recordings in seconds.
-        If None, set to be the end of the recording.
-
-    marker: int (default -1)
-        Marker to use for the events created.
     """
 
     def __init__(
@@ -212,37 +162,6 @@ class FilterBankFixedIntervalWindowsProcessing(BaseFixedIntervalWindowsProcessin
 
     filters: list of list (default ((8, 12), (12, 16), (16, 20), (20, 24), (24, 28), (28, 32)))
         bank of bandpass filter to apply.
-
-    baseline: None | tuple of length 2
-        The time interval to consider as “baseline” when applying baseline
-        correction. If None, do not apply baseline correction.
-        If a tuple (a, b), the interval is between a and b (in seconds),
-        including the endpoints.
-        Correction is applied by computing the mean of the baseline period
-        and subtracting it from the data (see mne.Epochs)
-
-    channels: list of str | None (default None)
-        list of channel to select. If None, use all EEG channels available in
-        the dataset.
-
-    resample: float | None (default None)
-        If not None, resample the eeg data with the sampling rate provided.
-
-    length: float (default 5.0)
-        Length of the epochs in seconds.
-
-    stride: float (default 10.0)
-        Stride between epochs in seconds.
-
-    start_offset: float (default 0.0)
-        Start from the beginning of the raw recordings in seconds.
-
-    stop_offset: float | None (default None)
-        Stop offset from beginning of raw recordings in seconds.
-        If None, set to be the end of the recording.
-
-    marker: int (default -1)
-        Marker to use for the events created.
     """
 
     def __init__(