main.py 文件源码

def knowsim_experiment(scope, scope_name, type_list, count, newLabels, tau=1, kNeighbors=10, label_num = 5):
    split_path = 'data/local/split/' + scope_name + '/'
    with open('data/local/' + scope_name + '.dmp') as f:
        hin = pk.load(f)

    repeats = 50
    tf_param = {'word': True, 'entity': False, 'we_weight': 0.1}
    X_word, newIds, entityIds = GraphGenerator.getTFVectorX(hin, tf_param)
    n = X_word.shape[0]

    knowsim = sparse.lil_matrix((n, n))
    for t in type_list:
        tf_param = {'word': True, 'entity': True, 'we_weight': 0.1}
        X_typed, newIds, entityIds = GraphGenerator.getTFVectorX(hin, tf_param, t)

        # make similarity graph
        cosX = cosine_similarity(X_typed)
        graph = sparse.lil_matrix((n, n))
        for i in range(n):
            for j in np.argpartition(cosX[i], -kNeighbors)[-kNeighbors:]:
                if j == i:
                    continue
                graph[i, j] = cosX[i, j]  # np.exp(- (1 - cosX[i, j]) / 0.03) #
                graph[j, i] = cosX[i, j]  # np.exp(- (1 - cosX[i, j]) / 0.03) #

        # calculate laplacian scores
        row_sum = graph.sum(axis=1)
        laplacian_score = generate_laplacian_score(row_sum, X_word, kNeighbors)

        # add meta-path-based similarity to the knowsim
        knowsim = knowsim + np.exp(-tau * laplacian_score) * graph

    knowsim = knowsim.tocsr()
    print 'running lp'
    lp_param = {'alpha':0.98, 'normalization_factor':5}

    ssl = SSLClassifier(knowsim, newLabels, scope, lp_param, repeatTimes=50, trainNumbers=label_num, classCount=count)
    ssl.repeatedFixedExperimentwithNewIds(pathPrefix=split_path + 'lb' + str(label_num).zfill(3) + '_', newIds=newIds)
    return ssl.get_mean()