test_sap.py 文件源码

def clusterSimilarityWithSklearnAPC(data_file,damping=0.9,max_iter=200,convergence_iter=15,preference='min'):
    """
    Compare Sparse Affinity Propagation (SAP) result with SKlearn Affinity Propagation (AP) Clustering result.
    Please note that convergence condition for Sklearn AP is "no change in the number of estimated clusters",
    for SAP the condition is "no change in the cluster assignment". 
    So SAP may take more iterations and the there will be slightly difference in final cluster assignment (exemplars for each sample).
    """
    # loading data
    simi_mat=loadMatrix(data_file)
    simi_mat_dense=simi_mat.todense()

    # get preference
    if preference=='min':
        preference=np.min(simi_mat_dense)
    elif preference=='median':
        preference=np.median(simi_mat_dense)

    print('{0}, start SKlearn Affinity Propagation'.format(datetime.now()))
    af=AffinityPropagation(damping=damping, preference=preference, affinity='precomputed',verbose=True)
    af.fit(simi_mat_dense)
    cluster_centers_indices,labels = af.cluster_centers_indices_,af.labels_
    sk_exemplars=np.asarray([cluster_centers_indices[i] for i in labels])
    print('{0}, start Fast Sparse Affinity Propagation Cluster'.format(datetime.now()))
    sap=SAP(preference=preference,convergence_iter=convergence_iter,max_iter=max_iter,damping=damping,verboseIter=100)
    sap_exemplars=sap.fit_predict(simi_mat_dense)

    # Caculate similarity between sk_exemplars and sap_exemplars
    exemplars_similarity=sparseAP_cy.arrSamePercent(np.array(sk_exemplars), np.array(sap_exemplars))

    return exemplars_similarity