def windows_ds():
raws, description = fetch_data_with_moabb(
dataset_name='BNCI2014001', subject_ids=4)
ds = [BaseDataset(raws[i], description.iloc[i]) for i in range(3)]
concat_ds = BaseConcatDataset(ds)
windows_ds = create_fixed_length_windows(
concat_ds=concat_ds, start_offset_samples=0, stop_offset_samples=None,
window_size_samples=500, window_stride_samples=500,
drop_last_window=False, preload=False)
return windows_ds
def test_multi_target_dataset(set_up):
_, base_dataset, _, _, _, _ = set_up
base_dataset.target_name = ['pathological', 'gender', 'age']
x, y = base_dataset[0]
assert len(y) == 3
assert base_dataset.description.to_list() == y
concat_ds = BaseConcatDataset([base_dataset])
windows_ds = create_fixed_length_windows(
concat_ds,
window_size_samples=100,
window_stride_samples=100,
start_offset_samples=0,
stop_offset_samples=None,
drop_last_window=False,
mapping={True: 1, False: 0, 'M': 0, 'F': 1}, # map non-digit targets
)
x, y, ind = windows_ds[0]
assert len(y) == 3
assert y == [1, 0, 48] # order matters: pathological, gender, age
for rec_i, tuh_subset in tuh_splits.items():
# implement preprocess for BaseDatasets? Would remove necessity
# to split above
preprocess(tuh_subset, preprocessors)
# update description of the recording(s)
tuh_subset.description.sfreq = len(tuh_subset.datasets) * [sfreq]
tuh_subset.description.reference = len(tuh_subset.datasets) * ['ar']
tuh_subset.description.n_samples = [len(d) for d in tuh_subset.datasets]
if create_compute_windows:
# generate compute windows here and store them to disk
tuh_windows = create_fixed_length_windows(
tuh_subset,
start_offset_samples=0,
stop_offset_samples=None,
window_size_samples=window_size_samples,
window_stride_samples=window_stride_samples,
drop_last_window=False)
# save memory by deleting raw recording
del tuh_subset
# store the number of windows required for loading later on
tuh_windows.description["n_windows"] = [
len(d) for d in tuh_windows.datasets
]
# create one directory for every recording
rec_path = os.path.join(OUT_PATH, str(rec_i))
if not os.path.exists(rec_path):
os.makedirs(rec_path)
save_concat_dataset(rec_path, tuh_windows)
from braindecode.preprocessing.preprocess import (
preprocess, zscore, Preprocessor, filterbank, exponential_moving_demean,
exponential_moving_standardize, MNEPreproc, NumpyPreproc, _replace_inplace,
_set_preproc_kwargs)
from braindecode.preprocessing.preprocess import scale as deprecated_scale
from braindecode.preprocessing.windowers import create_fixed_length_windows
from braindecode.datautil.serialization import load_concat_dataset
# 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)
@pytest.fixture
def windows_concat_ds():
return copy.deepcopy(windows_ds)
def modify_windows_object(epochs, factor=1):
epochs._data *= factor
for i, (x, y, window_ind) in enumerate(windows_dataset):
ax_arr[i].plot(x.T)
ax_arr[i].set_ylim(-4e-5, 4e-5)
ax_arr[i].set_title(f"label={y}")
if i == max_i:
break
fig.tight_layout()
###############################################################################
# Alternatively, we can create evenly spaced ("sliding") windows using a
# different windower.
sliding_windows_dataset = create_fixed_length_windows(
dataset,
start_offset_samples=0,
stop_offset_samples=0,
window_size_samples=1200,
window_stride_samples=1000,
drop_last_window=False)
print(len(sliding_windows_dataset))
for x, y, window_ind in sliding_windows_dataset:
print(x.shape, y, window_ind)
break
sliding_windows_dataset.description
###############################################################################
# Transforms can also be applied on windows in the same way as shown
# above on continuous data:
x, y = tuh[-1]
print('x:', x)
print('y:', y)
###############################################################################
# We will skip preprocessing steps for now, since it is not the aim of this
# example. Instead, we will directly create compute windows. We specify a
# mapping from genders 'M' and 'F' to integers, since this is required for
# decoding.
tuh_windows = create_fixed_length_windows(
tuh,
start_offset_samples=0,
stop_offset_samples=None,
window_size_samples=1000,
window_stride_samples=1000,
drop_last_window=False,
mapping={
'M': 0,
'F': 1
}, # map non-digit targets
)
# store the number of windows required for loading later on
tuh_windows.set_description(
{"n_windows": [len(d) for d in tuh_windows.datasets]})
###############################################################################
# Iterating through the dataset gives x as ndarray(n_channels x 1000), y as
# [age, gender], and ind. Let's look at the last example again.
x, y, ind = tuh_windows[-1]
print('x:', x)
print('y:', y)