from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
from sklearn.cluster import AgglomerativeClustering

vectorizer = TfidfVectorizer(stop_words='english')
X = vectorizer.fit_transform(data)
C = 1 - cosine_similarity(X.T)
ward = AgglomerativeClustering(n_clusters=k, linkage='ward').fit(C)
label = ward.labels_

from sklearn.cluster import KMeans

km = KMeans(n_clusters=k, init='k-means++', max_iter=100, n_init=1)
km.fit(X)
order_centroids = km.cluster_centers_.argsort()[:, ::-1]
terms = vectorizer.get_feature_names()
for i in range(k):
    print("Cluster %d:" % i, end='')
    for ind in order_centroids[i, :10]:
        print(' %s' % terms[ind], end='')

from sklearn.decomposition import NMF
nmf = NMF(n_components=k, random_state=1).fit(X)

feature_names = vectorizer.get_feature_names()

for topic_idx, topic in enumerate(nmf.components_):
    print("Topic #%d:" % topic_idx)
    print(" ".join([feature_names[i]
                    for i in topic.argsort()[:-10-1:-1]]))
    print()