Function main

nlp_class2/rntn_tensorflow_rnn.py:300–336

(is_binary=True)

def main(is_binary=True):
    train, test, word2idx = get_ptb_data()

    for t in train:
        add_idx_to_tree(t, 0)
    train = [tree2list(t, -1, is_binary) for t in train]
    if is_binary:
        train = [t for t in train if t[3][-1] >= 0] # for filtering binary labels

    for t in test:
        add_idx_to_tree(t, 0)
    test = [tree2list(t, -1, is_binary) for t in test]
    if is_binary:
        test = [t for t in test if t[3][-1] >= 0] # for filtering binary labels



    train = shuffle(train)
    # train = train[:5000]
    # n_pos = sum(t[3][-1] for t in train)
    # print("n_pos train:", n_pos)
    test = shuffle(test)
    smalltest = test[:1000]
    # n_pos = sum(t[3][-1] for t in test)
    # print("n_pos test:", n_pos)

    V = len(word2idx)
    print("vocab size:", V)
    D = 10
    K = 2 if is_binary else 5

    model = RecursiveNN(V, D, K)
    model.fit(train, smalltest, reg=1e-3, epochs=20, train_inner_nodes=True)
    print("train accuracy:", model.score(train))
    print("test accuracy:", model.score(test))
    print("train f1:", model.f1_score(train))
    print("test f1:", model.f1_score(test))


if __name__ == '__main__':