def generate_statistics_with_weighted_majorityvote_ensamble(
        startingpoint=5, endpoint=50, skips=5, iterations=5, topn=10):
    results = []
    for i in range(startingpoint, endpoint, skips):
        for j in range(0, iterations):
            if (os.path.isfile(
                    "weighted_majority_vote_Ensamble_test_results.csv")):
                f = open("weighted_majority_vote_Ensamble_test_results.csv",
                         "a")
            else:
                f = open("weighted_majority_vote_Ensamble_test_results.csv",
                         "w")

            ensamble_model = BS.boot_strap_aggregator()
            dir_path = "questions-words.txt"
            right, wrong = ensamble_model.accuracy(dir_path,
                                                   number_of_models=i,
                                                   predictor_method=3)
            res = [[i, topn, right, wrong]]
            print(res)
            results.append(res)
            np.savetxt(f, res, delimiter=',')
            f.close()
            print('iteration finished')

    print(results)
    return results
def generate_statistics_weight_based_on_total_oov_ignore_oov_human_similarity(
        startingpoint=5, endpoint=50, skips=5, iterations=5, topn=10):
    results = []
    for i in range(startingpoint, endpoint, skips):
        for j in range(0, iterations):
            if (os.path.isfile(
                    "weight_based_on_total_oov_ignore_oov_human_similarity_stats.csv"
            )):
                f = open(
                    "weight_based_on_total_oov_ignore_oov_human_similarity_stats.csv",
                    "a")
            else:
                f = open(
                    "weight_based_on_total_oov_ignore_oov_human_similarity_stats.csv",
                    "w")

            ensamble_model = BS.boot_strap_aggregator()
            dir_path = "wordsim353.tsv"
            spearman_result, pearson_result = ensamble_model.evaluate_word_pairs(
                dir_path, number_of_models=i, similarity_model_type=3)
            res = [[
                i, topn, spearman_result[0], spearman_result[1],
                pearson_result[0], pearson_result[1]
            ]]
            print(res)
            results.append(res)
            np.savetxt(f, res, delimiter=',')
            f.close()
            print('iteration finished')

    print(results)
    return results
def oov_test(startingpoint, endpoint, skips, iterations):
    results = []
    for i in range(startingpoint, endpoint, skips):
        for j in range(0, iterations):
            if (os.path.isfile("oov_test.csv")):
                f = open("oov_test.csv", "a")
            else:
                f = open("oov_test.csv", "w")

            ensamble_model = BS.boot_strap_aggregator()
            dir_path = "questions-words.txt"
            oov = ensamble_model.oov_test(questions=dir_path,
                                          number_of_models=i)
            res = [[i, oov]]
            print(res)
            results.append(res)
            np.savetxt(f, res, delimiter=',')
            f.close()
            print('iteration finished')
示例#4
0
def word_sim_test():
    ensamble = EP.simple_ensamble(
        generate_array_of_all_trained_model_specification)
    dir_path = os.path.dirname(
        os.path.realpath(__file__)) + "/TestingSet/wordsim353.tsv"
    ensamble.evaluate_word_pairs(dir_path, similarity_model_type=0)
示例#5
0
def question_word_test():
    ensamble = EP.boot_strap_aggregator(
        generate_array_of_all_trained_model_specification())
    dir_path = "questions-words.txt"
    #ensamble.set_weights([1, 0.5])
    ensamble.accuracy(dir_path, predictor_method=3, number_of_models=2)