问K模:最优k

EN

def matching_disimilarity(a, b):
    return np.sum(a != b, axis=1)

silhouette_dict = dict()
cluster_labels = [...]
distinct_cluster_label_predictions = unique cluster_labels

for i in m_array:
    other_records_in_cluster = m_array_(with cluster_prediction == cluster_prediction of i) - i
    other_records_outside_cluster = m_array_(with cluster_prediction != cluster_prediction of i)
    other_records_outside_cluster_labels = cluster labels of record in other_records_outside_cluster

    sum_a = 0
    sum_b = 0
    sum_cluster_dist = dict()
    avg_cluster_dist = dict()

    for c in distinct_cluster_label_predictions:
        sum_cluster_dist[c] = 0

    # finding a(i) - for each observation i, calculate the average dissimilarity ai between i and all other 
    # points of the cluster to which i belongs.
    for j in other_records_in_cluster:
        sum_a += matching_disimilarity(i, j)
    a = sum_a/len(other_records_in_cluster)

    dict_b = dict()

    # find average of inter-cluster distance with nearest neighbour
    for j in other_records_outside_cluster:
        dist_i_to_j = matching_disimilarity(i,j)
        dict_b[j] = dist_i_to_j
        sum_till_now = sum_cluster_dist[other_records_outside_cluster_labels[j]]
        sum_cluster_dist[other_records_outside_cluster_labels[j]] = sum_till_now+dist_i_to_j

    for c in distinct_cluster_label_predictions:
        avg_cluster_dist[c] = sum_cluster_dist[c]/(length of elements_belonging_to_c)

    # nearest_neighbour is the with smallest average distance
    # for more than one nearest neighbour? Break randomly?
    nearest_cluster_label = key of minimum avg_cluster_dist value

    neighbouring_cluster_records = records with cluster_prediction == nearest_cluster_label

    for k in neighbouring_cluster_records:
        sum_b += dict_b[k]
    b = sum_b/len(neighbouring_cluster_records)

    if (a