""".. _moabb-dataset-example:

MOABB Dataset Example
========================

In this example, we show how to fetch and prepare a MOABB dataset for usage
with Braindecode.
"""

# Authors: Lukas Gemein <l.gemein@gmail.com>
#          Hubert Banville <hubert.jbanville@gmail.com>
#          Simon Brandt <simonbrandt@protonmail.com>
#          Daniel Wilson <dan.c.wil@gmail.com>
#
# License: BSD (3-clause)

from braindecode.datasets import MOABBDataset
from braindecode.preprocessing import preprocess

###############################################################################
# First, we create a dataset based on BCIC IV 2a fetched with MOABB,
dataset = MOABBDataset(dataset_name="BNCI2014_001", subject_ids=[1])

###############################################################################
# The dataset has a pandas DataFrame with additional description of its internal datasets
dataset.description

##############################################################################
# We can iterate through dataset 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
# in-place. Braindecode provides dedicated preprocessing classes for common
# operations, or you can use the generic Preprocessor class.

# Using the new dedicated preprocessing classes (recommended):
from braindecode.preprocessing import Pick, Resample

preprocessors = [
    Pick(picks="eeg", exclude=()),  # Keep only EEG channels
    Resample(sfreq=100),  # Resample to 100 Hz
]

# Alternative: using the generic Preprocessor class (legacy approach):
# 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"])

###############################################################################
# We can easily split the dataset based on a criteria applied to the description
# DataFrame:
subsets = dataset.split("session")
print({subset_name: len(subset) for subset_name, subset in subsets.items()})

##############################################################################
# See our :ref:`Trialwise Decoding <bcic-iv-2a-moabb-trial>` and
# :ref:`Cropped Decoding <bcic-iv-2a-moabb-cropped>` examples for
# training with this dataset.