Function main

nlp_class2/rntn_theano.py:296–353

(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

    # check imbalance
    # pos = 0
    # neg = 0
    # mid = 0
    # label_counts = np.zeros(5)
    # for t in train + test:
    #     words, left_child, right_child, labels = t
    #     # for l in labels:
    #     #     if l == 0:
    #     #         neg += 1
    #     #     elif l == 1:
    #     #         pos += 1
    #     #     else:
    #     #         mid += 1
    #     for l in labels:
    #         label_counts[l] += 1
    # # print("pos / total:", float(pos) / (pos + neg + mid))
    # # print("mid / total:", float(mid) / (pos + neg + mid))
    # # print("neg / total:", float(neg) / (pos + neg + mid))
    # print("label proportions:", label_counts / label_counts.sum())
    # exit()


    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 = 20
    K = 2 if is_binary else 5

    model = RecursiveNN(V, D, K)
    model.fit(train, smalltest, 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))