analyze_clustering.py 文件源码

def comparative_exp():
    """
    Runs a series of clustering experiments for different parameter settings.
    """
    data_path = sys.argv[1]    # path to data set
    stem_dict_path = sys.argv[2]    # path to stemming dictionary
    parameters = ['SPLIT', 'noUF']
    d = data(data_path, stem_dict_path, parameters)
    #
    #
    clustering_algos = [(a,m,k) for a in ['hierarchical', 'ward', 'ap', 'kmeans']
                for m in [None,'complete','average','single']
                for k in [None,2,3,4,5,6,7,8,9,10]
                if (m != None and k == None and a == 'hierarchical') or
                (m == None and k != None and a == 'kmeans') or
                (m == None and k == None and a in ['ward', 'ap'])]
    for onto_cat in ['thing', 'body']:
        parameters_i = parameters + ['onto:%s' % onto_cat]
        oix = sorted(set(np.where(d.ontological == onto_cat)[0]))
        similarity_matrix = get_similarity_matrix(d, parameters_i, oix, association = 'associated')
        for a,m,k in clustering_algos:
            parameters_j = parameters_i + ['algo:%s' % a]
            if m != None: parameters_j.append('method:%s' % m)
            if k != None: parameters_j.append('k:%r' % k)
            print(parameters_j)
            cluster_assignments = get_cluster_assignments(similarity_matrix, parameters_j)
            print(set(cluster_assignments))
            print(evaluate_clustering(cluster_assignments, d.annotation[oix]))
            print_confusion_matrix(cluster_assignments, d.annotation[oix])