def get_roc_auc()

in autogluon/tabular-prediction/AutoGluon-Tabular-with-SageMaker/container-training/train.py [0:0]

• 37 lines of code
• 7 McCabe index (conditional complexity)

def get_roc_auc(y_test_true, y_test_pred, labels, class_labels_internal, model_output_dir):
    from sklearn.preprocessing import label_binarize
    from sklearn.metrics import roc_curve, auc

    from itertools import cycle
        
    y_test_true_binalized = label_binarize(y_test_true, classes=labels)
    
    if len(labels) == 2:
        # binary classification
        true_label_index = class_labels_internal.index(1)
        y_test_pred = y_test_pred[:,true_label_index]
        y_test_pred = np.reshape(y_test_pred, (-1, 1))
        labels = labels[true_label_index:true_label_index+1]
        n_classes = 1
    else:
        # multiclass classification
        n_classes = len(labels)
    
    # Compute ROC curve and ROC area for each class
    fpr = dict()
    tpr = dict()
    roc_auc = dict()

    for i in range(n_classes):
        fpr[i], tpr[i], _ = roc_curve(y_test_true_binalized[:, i], y_test_pred[:, i])
        roc_auc[i] = auc(fpr[i], tpr[i])

    # Compute micro-average ROC curve and ROC area
    fpr["micro"], tpr["micro"], _ = roc_curve(y_test_true_binalized.ravel(), y_test_pred.ravel())
    roc_auc["micro"] = auc(fpr["micro"], tpr["micro"])
    
    sns.set(font_scale=1)
    plt.figure()
    lw = 2
    colors = cycle(['aqua', 'darkorange', 'cornflowerblue'])

    for i, color in zip(range(n_classes), colors):
        plt.plot(fpr[i], tpr[i], color=color,
                 lw=lw, label=f'ROC curve for {labels[i]} (area = %0.2f)' % roc_auc[i])
    plt.plot([0, 1], [0, 1], color='navy', lw=lw, linestyle='--')
    plt.xlim([0.0, 1.0])
    plt.ylim([0.0, 1.05])
    plt.xlabel('False Positive Rate')
    plt.ylabel('True Positive Rate')
    plt.title('Receiver operating characteristic example')
    plt.legend(loc="lower right")
    plt.show()
    plt.savefig(f'{model_output_dir}/roc_auc_curve.png')