dbscan.py 文件源码

def dbscan(userid,X):

    db = DBSCAN(eps=0.15,min_samples=4).fit(X)
    # print db.labels_     zeros_like
    core_samples_mask = np.zeros_like(db.labels_,dtype=bool)
    core_samples_mask[db.core_sample_indices_] = True
    lables = db.labels_ 
    labels_list = list(lables)
    # print labels_list.count(-1)
    out_user.setdefault(userid,0)
    out_user[userid] = labels_list.count(-1)
    print out_user

    # print labels_list.index(-1)
    print lables
    n_clusters_ = len(set(lables)) -(1 if -1 in lables else 0)
    unique_lables = set(lables)
    cols = plt.cm.Spectral(np.linspace(0,1,len(unique_lables)))
    # center_points = []
    for k,col in zip(unique_lables,cols):
        if k == -1:
            col = 'k'
        class_member_mask = (lables == k)
        k_x = X[class_member_mask & core_samples_mask]
        plt.plot(k_x[:,0],k_x[:,1],'o',markerfacecolor = col,
            markeredgecolor = 'k' , markersize = 5)
        center_points.append([np.mean(k_x[:,1]),np.mean(k_x[:,0])])
    plt.title('DBSCAN :Estimated number of clusters: %d' % n_clusters_)
    # plt.show()