MTNN.py 文件源码

def find_nearest_instance_thread(test_instance_start_index, test_instance_end_index):

    print test_instance_start_index, test_instance_end_index

    for test_instance_index in range(test_instance_start_index, test_instance_end_index):

        # find the nearest training instance with cosine similarity
        maximal_cosine_similarity = -1
        maximal_cosine_similarity_index = 0
        for training_instance, training_instance_index in zip(training_data, range(len(training_data))):
            # compute the cosine similarity
            # first, compute the inner product
            inner_product = np.inner(test_data[test_instance_index][0].reshape(-1), training_instance[0].reshape(-1))
            normalized_inner_product = inner_product / test_data_lengths[test_instance_index] / training_data_lengths[training_instance_index]

            if normalized_inner_product > maximal_cosine_similarity:
                maximal_cosine_similarity = normalized_inner_product
                maximal_cosine_similarity_index = training_instance_index

        classified_results[test_instance_index] = maximal_cosine_similarity_index