.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/plot_dataset_example.py"
.. LINE NUMBERS ARE GIVEN BELOW.
.. only:: html
.. note::
:class: sphx-glr-download-link-note
Click :ref:`here <sphx_glr_download_auto_examples_plot_dataset_example.py>`
to download the full example code
.. rst-class:: sphx-glr-example-title
.. _sphx_glr_auto_examples_plot_dataset_example.py:
MOABB Dataset Example
========================
In this example, we show how to fetch and prepare a MOABB dataset for usage
with Braindecode.
.. GENERATED FROM PYTHON SOURCE LINES 7-21
.. code-block:: default
# Authors: Lukas Gemein <l.gemein@gmail.com>
# Hubert Banville <hubert.jbanville@gmail.com>
# Simon Brandt <simonbrandt@protonmail.com>
#
# License: BSD (3-clause)
import matplotlib.pyplot as plt
from braindecode.datasets import MOABBDataset
from braindecode.preprocessing import \
create_windows_from_events, create_fixed_length_windows
from braindecode.preprocessing import preprocess, Preprocessor
.. GENERATED FROM PYTHON SOURCE LINES 22-23
First, we create a dataset based on BCIC IV 2a fetched with MOABB,
.. GENERATED FROM PYTHON SOURCE LINES 23-25
.. code-block:: default
dataset = MOABBDataset(dataset_name="BNCI2014001", subject_ids=[1])
.. GENERATED FROM PYTHON SOURCE LINES 26-27
ds has a pandas DataFrame with additional description of its internal datasets
.. GENERATED FROM PYTHON SOURCE LINES 27-29
.. code-block:: default
dataset.description
.. raw:: html
<div class="output_subarea output_html rendered_html output_result">
<div>
<style scoped>
.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}
.dataframe tbody tr th {
vertical-align: top;
}
.dataframe thead th {
text-align: right;
}
</style>
<table border="1" class="dataframe">
<thead>
<tr style="text-align: right;">
<th></th>
<th>subject</th>
<th>session</th>
<th>run</th>
</tr>
</thead>
<tbody>
<tr>
<th>0</th>
<td>1</td>
<td>session_T</td>
<td>run_0</td>
</tr>
<tr>
<th>1</th>
<td>1</td>
<td>session_T</td>
<td>run_1</td>
</tr>
<tr>
<th>2</th>
<td>1</td>
<td>session_T</td>
<td>run_2</td>
</tr>
<tr>
<th>3</th>
<td>1</td>
<td>session_T</td>
<td>run_3</td>
</tr>
<tr>
<th>4</th>
<td>1</td>
<td>session_T</td>
<td>run_4</td>
</tr>
<tr>
<th>5</th>
<td>1</td>
<td>session_T</td>
<td>run_5</td>
</tr>
<tr>
<th>6</th>
<td>1</td>
<td>session_E</td>
<td>run_0</td>
</tr>
<tr>
<th>7</th>
<td>1</td>
<td>session_E</td>
<td>run_1</td>
</tr>
<tr>
<th>8</th>
<td>1</td>
<td>session_E</td>
<td>run_2</td>
</tr>
<tr>
<th>9</th>
<td>1</td>
<td>session_E</td>
<td>run_3</td>
</tr>
<tr>
<th>10</th>
<td>1</td>
<td>session_E</td>
<td>run_4</td>
</tr>
<tr>
<th>11</th>
<td>1</td>
<td>session_E</td>
<td>run_5</td>
</tr>
</tbody>
</table>
</div>
</div>
<br />
<br />
.. GENERATED FROM PYTHON SOURCE LINES 30-33
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).
.. GENERATED FROM PYTHON SOURCE LINES 33-37
.. code-block:: default
for x, y in dataset:
print(x.shape, y)
break
.. rst-class:: sphx-glr-script-out
Out:
.. code-block:: none
(26, 1) None
.. GENERATED FROM PYTHON SOURCE LINES 38-40
We can apply preprocessing transforms that are defined in mne and work
in-place, such as resampling, bandpass filtering, or electrode selection.
.. GENERATED FROM PYTHON SOURCE LINES 40-48
.. code-block:: default
preprocessors = [
Preprocessor('pick_types', eeg=True, meg=False, stim=True),
Preprocessor('resample', sfreq=100)
]
print(dataset.datasets[0].raw.info["sfreq"])
preprocess(dataset, preprocessors)
print(dataset.datasets[0].raw.info["sfreq"])
.. rst-class:: sphx-glr-script-out
Out:
.. code-block:: none
250.0
100.0
.. GENERATED FROM PYTHON SOURCE LINES 49-51
We can easily split ds based on a criteria applied to the description
DataFrame:
.. GENERATED FROM PYTHON SOURCE LINES 51-54
.. code-block:: default
subsets = dataset.split("session")
print({subset_name: len(subset) for subset_name, subset in subsets.items()})
.. rst-class:: sphx-glr-script-out
Out:
.. code-block:: none
{'session_E': 232164, 'session_T': 232164}
.. GENERATED FROM PYTHON SOURCE LINES 55-56
Next, we use a windower to extract events from the dataset based on events:
.. GENERATED FROM PYTHON SOURCE LINES 56-61
.. code-block:: default
windows_dataset = create_windows_from_events(
dataset, trial_start_offset_samples=0, trial_stop_offset_samples=100,
window_size_samples=400, window_stride_samples=100,
drop_last_window=False)
.. GENERATED FROM PYTHON SOURCE LINES 62-66
We can iterate through the windows_ds which yields a window x,
a target y, and window_ind (which itself contains ``i_window_in_trial``,
``i_start_in_trial``, and ``i_stop_in_trial``, which are required for
combining window predictions in the scorer).
.. GENERATED FROM PYTHON SOURCE LINES 66-70
.. code-block:: default
for x, y, window_ind in windows_dataset:
print(x.shape, y, window_ind)
break
.. rst-class:: sphx-glr-script-out
Out:
.. code-block:: none
(23, 400) 3 [0, 300, 700]
.. GENERATED FROM PYTHON SOURCE LINES 71-72
We visually inspect the windows:
.. GENERATED FROM PYTHON SOURCE LINES 72-84
.. code-block:: default
max_i = 2
fig, ax_arr = plt.subplots(1, max_i + 1, figsize=(3.5 * (max_i + 1), 3.5),
sharex=True, sharey=True)
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()
.. image-sg:: /auto_examples/images/sphx_glr_plot_dataset_example_001.png
:alt: label=3, label=3, label=0
:srcset: /auto_examples/images/sphx_glr_plot_dataset_example_001.png
:class: sphx-glr-single-img
.. GENERATED FROM PYTHON SOURCE LINES 85-87
Alternatively, we can create evenly spaced ("sliding") windows using a
different windower.
.. GENERATED FROM PYTHON SOURCE LINES 87-99
.. code-block:: default
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
.. rst-class:: sphx-glr-script-out
Out:
.. code-block:: none
/home/runner/work/braindecode/braindecode/braindecode/preprocessing/windowers.py:597: UserWarning: Meaning of `trial_stop_offset_samples`=0 has changed, use `None` to indicate end of trial/recording. Using `None`.
'Meaning of `trial_stop_offset_samples`=0 has changed, use `None` '
468
(23, 1200) -1 [0, 0, 1200]
.. raw:: html
<div class="output_subarea output_html rendered_html output_result">
<div>
<style scoped>
.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}
.dataframe tbody tr th {
vertical-align: top;
}
.dataframe thead th {
text-align: right;
}
</style>
<table border="1" class="dataframe">
<thead>
<tr style="text-align: right;">
<th></th>
<th>subject</th>
<th>session</th>
<th>run</th>
</tr>
</thead>
<tbody>
<tr>
<th>0</th>
<td>1</td>
<td>session_T</td>
<td>run_0</td>
</tr>
<tr>
<th>1</th>
<td>1</td>
<td>session_T</td>
<td>run_1</td>
</tr>
<tr>
<th>2</th>
<td>1</td>
<td>session_T</td>
<td>run_2</td>
</tr>
<tr>
<th>3</th>
<td>1</td>
<td>session_T</td>
<td>run_3</td>
</tr>
<tr>
<th>4</th>
<td>1</td>
<td>session_T</td>
<td>run_4</td>
</tr>
<tr>
<th>5</th>
<td>1</td>
<td>session_T</td>
<td>run_5</td>
</tr>
<tr>
<th>6</th>
<td>1</td>
<td>session_E</td>
<td>run_0</td>
</tr>
<tr>
<th>7</th>
<td>1</td>
<td>session_E</td>
<td>run_1</td>
</tr>
<tr>
<th>8</th>
<td>1</td>
<td>session_E</td>
<td>run_2</td>
</tr>
<tr>
<th>9</th>
<td>1</td>
<td>session_E</td>
<td>run_3</td>
</tr>
<tr>
<th>10</th>
<td>1</td>
<td>session_E</td>
<td>run_4</td>
</tr>
<tr>
<th>11</th>
<td>1</td>
<td>session_E</td>
<td>run_5</td>
</tr>
</tbody>
</table>
</div>
</div>
<br />
<br />
.. GENERATED FROM PYTHON SOURCE LINES 100-102
Transforms can also be applied on windows in the same way as shown
above on continuous data:
.. GENERATED FROM PYTHON SOURCE LINES 102-136
.. code-block:: default
def crop_windows(windows, start_offset_samples, stop_offset_samples):
fs = windows.info["sfreq"]
windows.crop(tmin=start_offset_samples / fs, tmax=stop_offset_samples / fs,
include_tmax=False)
epochs_preprocessors = [
Preprocessor('pick_types', eeg=True, meg=False, stim=False),
Preprocessor(crop_windows, apply_on_array=False, start_offset_samples=100,
stop_offset_samples=900)
]
print(windows_dataset.datasets[0].windows.info["ch_names"],
len(windows_dataset.datasets[0].windows.times))
preprocess(windows_dataset, epochs_preprocessors)
print(windows_dataset.datasets[0].windows.info["ch_names"],
len(windows_dataset.datasets[0].windows.times))
max_i = 2
fig, ax_arr = plt.subplots(1, max_i + 1, figsize=(3.5 * (max_i + 1), 3.5),
sharex=True, sharey=True)
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()
plt.show()
.. image-sg:: /auto_examples/images/sphx_glr_plot_dataset_example_002.png
:alt: label=3, label=3, label=0
:srcset: /auto_examples/images/sphx_glr_plot_dataset_example_002.png
:class: sphx-glr-single-img
.. rst-class:: sphx-glr-script-out
Out:
.. code-block:: none
['Fz', 'FC3', 'FC1', 'FCz', 'FC2', 'FC4', 'C5', 'C3', 'C1', 'Cz', 'C2', 'C4', 'C6', 'CP3', 'CP1', 'CPz', 'CP2', 'CP4', 'P1', 'Pz', 'P2', 'POz', 'stim'] 400
['Fz', 'FC3', 'FC1', 'FCz', 'FC2', 'FC4', 'C5', 'C3', 'C1', 'Cz', 'C2', 'C4', 'C6', 'CP3', 'CP1', 'CPz', 'CP2', 'CP4', 'P1', 'Pz', 'P2', 'POz'] 300
.. GENERATED FROM PYTHON SOURCE LINES 137-139
Again, we can easily split windows_ds based on some criteria in the
description DataFrame:
.. GENERATED FROM PYTHON SOURCE LINES 139-141
.. code-block:: default
subsets = windows_dataset.split("session")
print({subset_name: len(subset) for subset_name, subset in subsets.items()})
.. rst-class:: sphx-glr-script-out
Out:
.. code-block:: none
{'session_E': 576, 'session_T': 576}
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 0 minutes 8.463 seconds)
**Estimated memory usage:** 371 MB
.. _sphx_glr_download_auto_examples_plot_dataset_example.py:
.. only :: html
.. container:: sphx-glr-footer
:class: sphx-glr-footer-example
.. container:: sphx-glr-download sphx-glr-download-python
:download:`Download Python source code: plot_dataset_example.py <plot_dataset_example.py>`
.. container:: sphx-glr-download sphx-glr-download-jupyter
:download:`Download Jupyter notebook: plot_dataset_example.ipynb <plot_dataset_example.ipynb>`
.. only:: html
.. rst-class:: sphx-glr-signature
`Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_