def call_data(dataset_name, subject_ids):
'''
:param dataset_name: (String) data name to be entered in MOABBDataset
(e.g. "BNCI2014001", "BNCI2014004")
:param subject_ids: (list) A list of subject numbers to call
BNCI2014001: 1~9
BNCI2014004: 1~9
:return: (list) a list of braindecode.datasets.moabb.MOABBDataset
'''
datasets = [
MOABBDataset(dataset_name=dataset_name, subject_ids=[i])
for i in subject_ids
]
return datasets
In this example, we show multiple ways of how to split datasets.
"""
# Authors: Lukas Gemein <*****@*****.**>
#
# License: BSD (3-clause)
from IPython.display import display
from braindecode.datasets import MOABBDataset
from braindecode.preprocessing.windowers import create_windows_from_events
###############################################################################
# First, we create a dataset based on BCIC IV 2a fetched with MOABB,
ds = MOABBDataset(dataset_name="BNCI2014001", subject_ids=[1])
###############################################################################
# ds has a pandas DataFrame with additional description of its internal datasets
display(ds.description)
###############################################################################
# We can split the dataset based on the info in the description, for example
# based on different runs. The returned dictionary will have string keys
# corresponding to unique entries in the description DataFrame column
splits = ds.split("run")
display(splits)
display(splits["run_4"].description)
###############################################################################
# We can also split the dataset based on a list of integers corresponding to
import copy
import pytest
import numpy as np
from braindecode.datasets import MOABBDataset
from braindecode.datautil.preprocess import preprocess, zscore, scale, \
Preprocessor, filterbank, exponential_moving_demean, \
exponential_moving_standardize, MNEPreproc, NumpyPreproc
from braindecode.datautil.windowers import create_fixed_length_windows
# We can't use fixtures with scope='module' as the dataset objects are modified
# inplace during preprocessing. To avoid the long setup time caused by calling
# the dataset/windowing functions multiple times, we instantiate the dataset
# objects once and deep-copy them in fixture.
raw_ds = MOABBDataset(dataset_name='BNCI2014001', subject_ids=[1, 2])
windows_ds = create_fixed_length_windows(raw_ds,
start_offset_samples=100,
stop_offset_samples=None,
window_size_samples=1000,
window_stride_samples=1000,
drop_last_window=True,
mapping=None,
preload=True)
@pytest.fixture
def base_concat_ds():
return copy.deepcopy(raw_ds)
def base_concat_ds():
return MOABBDataset(dataset_name="BNCI2014001", subject_ids=[1, 2])
######################################################################
# Loading and preprocessing the dataset
# -------------------------------------
######################################################################
# Loading
# ~~~~~~~
#
from braindecode import EEGClassifier
from skorch.helper import predefined_split
from skorch.callbacks import LRScheduler
from braindecode.datasets import MOABBDataset
subject_id = 3
dataset = MOABBDataset(dataset_name="BNCI2014001", subject_ids=[subject_id])
######################################################################
# Preprocessing
# ~~~~~~~~~~~~~
#
from braindecode.preprocessing import (exponential_moving_standardize,
preprocess, Preprocessor)
low_cut_hz = 4. # low cut frequency for filtering
high_cut_hz = 38. # high cut frequency for filtering
# Parameters for exponential moving standardization
factor_new = 1e-3
init_block_size = 1000
def setup_concat_raw_dataset():
return MOABBDataset(dataset_name="BNCI2014001", subject_ids=[1])
# Authors: Lukas Gemein <*****@*****.**>
# Hubert Banville <*****@*****.**>
# Simon Brandt <*****@*****.**>
#
# License: BSD (3-clause)
import matplotlib.pyplot as plt
from braindecode.datasets import MOABBDataset
from braindecode.preprocessing.windowers import \
create_windows_from_events, create_fixed_length_windows
from braindecode.preprocessing.preprocess import preprocess, Preprocessor
###############################################################################
# First, we create a dataset based on BCIC IV 2a fetched with MOABB,
dataset = MOABBDataset(dataset_name="BNCI2014001", subject_ids=[1])
###############################################################################
# ds has a pandas DataFrame with additional description of its internal datasets
dataset.description
##############################################################################
# We can iterate through ds which yields one time point of a continuous signal x,
# and a target y (which can be None if targets are not defined for the entire
# continuous signal).
for x, y in dataset:
print(x.shape, y)
break
##############################################################################
# We can apply preprocessing transforms that are defined in mne and work
with torch.no_grad():
dummy_input = torch.tensor(
np.ones((1, n_chans, input_time_length, 1), dtype=np.float32),
device=device,
)
n_preds_per_input = model(dummy_input).shape[2]
dataset = MOABBDataset(
"BNCI2014001",
subject_ids=[1],
trial_start_offset_samples=-125,
trial_stop_offset_samples=1000,
supercrop_size_samples=1000,
supercrop_stride_samples=n_preds_per_input,
drop_samples=False,
mapping={
1: 0,
2: 1,
3: 2,
4: 3
},
)
class TrainTestBCICIV2aSplit(object):
def __call__(self, dataset, y, **kwargs):
splitted = dataset.split('session')
return splitted['session_T'], splitted['session_E']
Split Dataset Example
=====================
In this example, we show multiple ways of how to split datasets.
"""
# Authors: Lukas Gemein <*****@*****.**>
#
# License: BSD (3-clause)
from braindecode.datasets import MOABBDataset
from braindecode.preprocessing import create_windows_from_events
###############################################################################
# First, we create a dataset based on BCIC IV 2a fetched with MOABB,
dataset = MOABBDataset(dataset_name="BNCI2014001", subject_ids=[1])
###############################################################################
# ds has a pandas DataFrame with additional description of its internal datasets
dataset.description
###############################################################################
# We can split the dataset based on the info in the description, for example
# based on different runs. The returned dictionary will have string keys
# corresponding to unique entries in the description DataFrame column
splits = dataset.split("run")
print(splits)
splits["run_4"].description
###############################################################################
# We can also split the dataset based on a list of integers corresponding to
# Authors: Lukas Gemein <*****@*****.**>
#
# License: BSD (3-clause)
import tempfile
from braindecode.datasets import MOABBDataset
from braindecode.preprocessing import preprocess, Preprocessor
from braindecode.datautil import load_concat_dataset
from braindecode.preprocessing import create_windows_from_events
###############################################################################
# First, we load some dataset using MOABB.
dataset = MOABBDataset(
dataset_name='BNCI2014001',
subject_ids=[1],
)
###############################################################################
# We can apply preprocessing steps to the dataset. It is also possible to skip
# this step and not apply any preprocessing.
preprocess(
concat_ds=dataset,
preprocessors=[Preprocessor(fn='resample', sfreq=10)]
)
###############################################################################
# We save the dataset to a an existing directory. It will create a '.fif' file
# for every dataset in the concat dataset. Additionally it will create two
# JSON files, the first holding the description of the dataset, the second
# holding the name of the target. If you want to store to the same directory
Simple Moabb Dataset Example
=========================
Showcasing how to fetch and crop a moabb dataset.
"""
# Authors: Lukas Gemein <*****@*****.**>
#
# License: BSD (3-clause)
from braindecode.datasets import MOABBDataset
# create a dataset based on BCIC IV 2a fetched with moabb
ds = MOABBDataset(dataset_name="BNCI2014001",
subject_ids=[4],
trial_start_offset_samples=0,
trial_stop_offset_samples=1000,
supercrop_size_samples=1000,
supercrop_stride_samples=1000)
# we can iterate through ds which yields an example x, target y,
# and info as i_supercrop_in_trial, i_start_in_trial, and i_stop_in_trial
# which is required for combining supercrop predictions in the scorer
for x, y, info in ds:
print(x.shape, y, info)
break
# each base_ds in ds has its own info DataFrame
print(ds.datasets[-1].info)
# ds has a concattenation of all DataFrames of its datasets
print(ds.info)
