cluster.py 文件源码

def kmeans(reduced_data, n_clusters):
    #----Do KMeans clustering and return relevant graphing/performance data
    kmeans = cluster.KMeans(n_clusters=n_clusters, random_state=42)
    kmeans = kmeans.fit(reduced_data)
    sil_score = metrics.silhouette_score(reduced_data, kmeans.labels_, metric='euclidean')

    data_dictionary = {
        "labels": kmeans.labels_,
        "centroids": kmeans.cluster_centers_,
        "silhouette_score": sil_score
    }

    return data_dictionary