Only one class present in y_true. ROC AUC score is not defined in that case.

ROC AUC score is a performance metric used to evaluate the performance of classification models. It is calculated based on the true positive rate (TPR) and false positive rate (FPR) at various threshold values. However, when there is only one class present in the true labels `y_true`, ROC AUC score is not defined because there is no distinction between positive and negative cases.

In such cases, you can use alternative performance metrics such as accuracy, precision, recall, or F1-score to evaluate your model's performance. These metrics can be easily calculated using scikit-learn's `metrics` module. Here's an example code snippet:

from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score

y_true = [0, 0, 0, 0]  # Only one class present
y_pred = [0, 1, 0, 0]  # Example predictions

acc = accuracy_score(y_true, y_pred)
prec = precision_score(y_true, y_pred)
rec = recall_score(y_true, y_pred)
f1 = f1_score(y_true, y_pred)

print("Accuracy: {:.2f}".format(acc))
print("Precision: {:.2f}".format(prec))
print("Recall: {:.2f}".format(rec))
print("F1-score: {:.2f}".format(f1))

This will output the accuracy, precision, recall, and F1-score of the model on the given predictions. Note that these metrics are only applicable when there is more than one class present in the true labels.