# -*- coding: utf-8 -*-
"""
.. _ex-xdawn-decoding:

============================
XDAWN Decoding From EEG data
============================

ERP decoding with Xdawn :footcite:`RivetEtAl2009,RivetEtAl2011`. For each event
type, a set of spatial Xdawn filters are trained and applied on the signal.
Channels are concatenated and rescaled to create features vectors that will be
fed into a logistic regression.
"""
# Authors: Alexandre Barachant <alexandre.barachant@gmail.com>
#
# License: BSD-3-Clause

# %%

import numpy as np
import matplotlib.pyplot as plt

from sklearn.model_selection import StratifiedKFold
from sklearn.pipeline import make_pipeline
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report, confusion_matrix
from sklearn.preprocessing import MinMaxScaler

from mne import io, pick_types, read_events, Epochs, EvokedArray, create_info
from mne.datasets import sample
from mne.preprocessing import Xdawn
from mne.decoding import Vectorizer


print(__doc__)

data_path = sample.data_path()

# %%
# Set parameters and read data
meg_path = data_path / 'MEG' / 'sample'
raw_fname = meg_path / 'sample_audvis_filt-0-40_raw.fif'
event_fname = meg_path / 'sample_audvis_filt-0-40_raw-eve.fif'
tmin, tmax = -0.1, 0.3
event_id = {'Auditory/Left': 1, 'Auditory/Right': 2,
            'Visual/Left': 3, 'Visual/Right': 4}
n_filter = 3

# Setup for reading the raw data
raw = io.read_raw_fif(raw_fname, preload=True)
raw.filter(1, 20, fir_design='firwin')
events = read_events(event_fname)

picks = pick_types(raw.info, meg=False, eeg=True, stim=False, eog=False,
                   exclude='bads')

epochs = Epochs(raw, events, event_id, tmin, tmax, proj=False,
                picks=picks, baseline=None, preload=True,
                verbose=False)

# Create classification pipeline
clf = make_pipeline(Xdawn(n_components=n_filter),
                    Vectorizer(),
                    MinMaxScaler(),
                    LogisticRegression(penalty='l1', solver='liblinear',
                                       multi_class='auto'))

# Get the labels
labels = epochs.events[:, -1]

# Cross validator
cv = StratifiedKFold(n_splits=10, shuffle=True, random_state=42)

# Do cross-validation
preds = np.empty(len(labels))
for train, test in cv.split(epochs, labels):
    clf.fit(epochs[train], labels[train])
    preds[test] = clf.predict(epochs[test])

# Classification report
target_names = ['aud_l', 'aud_r', 'vis_l', 'vis_r']
report = classification_report(labels, preds, target_names=target_names)
print(report)

# Normalized confusion matrix
cm = confusion_matrix(labels, preds)
cm_normalized = cm.astype(float) / cm.sum(axis=1)[:, np.newaxis]

# Plot confusion matrix
fig, ax = plt.subplots(1)
im = ax.imshow(cm_normalized, interpolation='nearest', cmap=plt.cm.Blues)
ax.set(title='Normalized Confusion matrix')
fig.colorbar(im)
tick_marks = np.arange(len(target_names))
plt.xticks(tick_marks, target_names, rotation=45)
plt.yticks(tick_marks, target_names)
fig.tight_layout()
ax.set(ylabel='True label', xlabel='Predicted label')

# %%
# The ``patterns_`` attribute of a fitted Xdawn instance (here from the last
# cross-validation fold) can be used for visualization.

fig, axes = plt.subplots(nrows=len(event_id), ncols=n_filter,
                         figsize=(n_filter, len(event_id) * 2))
fitted_xdawn = clf.steps[0][1]
info = create_info(epochs.ch_names, 1, epochs.get_channel_types())
info.set_montage(epochs.get_montage())
for ii, cur_class in enumerate(sorted(event_id)):
    cur_patterns = fitted_xdawn.patterns_[cur_class]
    pattern_evoked = EvokedArray(cur_patterns[:n_filter].T, info, tmin=0)
    pattern_evoked.plot_topomap(
        times=np.arange(n_filter),
        time_format='Component %d' if ii == 0 else '', colorbar=False,
        show_names=False, axes=axes[ii], show=False)
    axes[ii, 0].set(ylabel=cur_class)
fig.tight_layout(h_pad=1.0, w_pad=1.0, pad=0.1)

# %%
# References
# ----------
# .. footbibliography::