exp_svmstruct.py 文件源码

def svmstruct_cv_score(dataset, C, class_weight, constraints,
                       compat_features, second_order_features):

    fn = cache_fname("svmstruct_cv_score", (dataset, C, class_weight,
                                            constraints, compat_features,
                                            second_order_features))

    if os.path.exists(fn):
        logging.info("Cached file already exists.")
        with open(fn, "rb") as f:
            return dill.load(f)

    load, ids = get_dataset_loader(dataset, split="train")

    n_folds = 5 if dataset == 'ukp' else 3

    # below are boolean logical ops
    grandparents = second_order_features and dataset == 'ukp'
    coparents = second_order_features
    siblings = second_order_features and dataset == 'cdcp'

    scores = []
    all_Y_pred = []

    for k, (tr, val) in enumerate(KFold(n_folds).split(ids)):
        train_docs = list(load(ids[tr]))
        val_docs = list(load(ids[val]))

        clf, Y_val, Y_pred = fit_predict(train_docs, val_docs, dataset, C,
                                         class_weight,
                                         constraints, compat_features,
                                         second_order_features, grandparents,
                                         coparents, siblings)
        all_Y_pred.extend(Y_pred)
        scores.append(clf.model._score(Y_val, Y_pred))

    with open(fn, "wb") as f:
        dill.dump((scores, all_Y_pred), f)

    return scores, all_Y_pred