plt.close()
else:
weights = pd.DataFrame(weights.reshape(-1, len(weights)),
columns=areas)
visualize.plot_connectivity(weights)
plt.title(part + " " + mode)
pdf.savefig()
plt.close()
X_part_1 = LinearDiscriminantAnalysis(n_components=1).fit(
X_part, label_part).transform(X_part)
data_one = pd.DataFrame(
np.transpose(np.vstack((X_part_1.flatten(), label_part))))
data_one.columns = ['LDA_1D', 'label']
oneD.append(data_one)
for i, p in enumerate(participants):
data = oneD[i]
a = sns.displot(data=data, x="LDA_1D", hue="label", kind="kde", fill=True)
a._legend.set_title(p)
pdf.savefig()
plt.close()
toplot = pd.DataFrame()
toplot['accuracies'] = acc
toplot['ID'] = participants
toplot['outcome'] = outcome
