Y_pred = y_pred.tolist()
Y_pred = np.array(Y_pred)
Y_test = np.array(y_test)
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split

# multi-class classification
from sklearn.multiclass import OneVsRestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import roc_curve
from sklearn.metrics import roc_auc_score

fpr = {}
tpr = {}
thresh ={}



for i in range(n_class):
    fpr[i], tpr[i], thresh[i] = roc_curve(Y_test, Y_pred[:,i], pos_label=i)
colors = ['orange', 'green', 'blue', 'purple', 'cyan']
# plotting
for i in range(n_class):
    plt.plot(fpr[i], tpr[i], linestyle='--',color=colors[i], label=f'Class {i} vs Rest')
plt.title('Multiclass ROC curve')
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive rate')
plt.legend(loc='best')
plt.savefig('Multiclass ROC',dpi=300);