solr-similarity.py 文件源码

def sk_kmeans(core): #, kval=3

    solrURL = "http://localhost:8983/solr/" + core
    solrInstance = Solr(solrURL)

    list_of_points = []
    docs = solrInstance.query_iterator(query="*:*", start=0)

    for doc in docs:
        list_of_points.append(Vector(doc['id'], doc))

    list_of_Dicts = (point.features for point in list_of_points)

    df = pd.DataFrame(list_of_Dicts)
    df = df.fillna(0)

    silhouettes = {}
    for k in range(2, 10):

        kmeans = KMeans(n_clusters=k,
                    init='k-means++',
                    max_iter=300,  # k-means convergence
                    n_init=10,  # find global minima
                    n_jobs=-2,  # parallelize
                    )

        labels = kmeans.fit_predict(df)
        silhouettes[k] = silhouette_score(df, labels)


    return str(silhouettes)