evaluation.py 文件源码

def bio_classification_report(y_gold,y_pred):
    #y_gold: [[],[],[]]
    #y_pred:
    lb = LabelBinarizer()
    y_gold_combined = lb.fit_transform(list(chain.from_iterable(y_gold)))
    y_pred_combined = lb.fit_transform(list(chain.from_iterable(y_pred)))

    tagset = set(lb.classes_) - {'O'}
    tagset = sorted(tagset,key=lambda tag: tag.split('-',1)[::-1])
    class_indices = {cls:idx for idx,cls in enumerate(lb.classes_)}
    return classification_report(
        y_gold_combined,
        y_pred_combined,
        labels=[class_indices[cls] for cls in tagset],
        target_names=tagset
    )