sklearn之kmeans文本聚类主题输出

from sklearn import feature_extraction
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.cluster import KMeans
corpus = []
tfidfdict = {}
seg_ty = open('E:\\kmeans.txt', 'r')
for line in seg_ty:
    corpus.append(line.strip())
    vectorizer=CountVectorizer()
    transformer=TfidfTransformer()
    tfidf=transformer.fit_transform(vectorizer.fit_transform(corpus))
    word=vectorizer.get_feature_names()
    weight=tfidf.toarray()
    
for i in range(len(weight)):
    for j in range(len(word)):
        getword = word[j]
        getvalue = weight[i][j]
K = range(1,15)
for k in K:
    print("第几次聚类:"+ str(k) + "\n")
    clf = KMeans(n_clusters = k)                      
    s = clf.fit(weight)                    
    order_centroids = clf.cluster_centers_.argsort()[:, ::-1]
    terms = vectorizer.get_feature_names()    
    for ss in range(k):
        print("/n")
        print("Cluster %d:" % ss, end='')
        for ind in order_centroids[ss, :10]:
            print(' %s' % terms[ind], end='')