import pysparnn.cluster_index as ci
from sklearn.feature_extraction.text import TfidfVectorizer

data = [
    "hello world",
    "oh hello there",
    "Play it",
    "Play it again Sam",
]


tv = TfidfVectorizer()
tv.fit(data)
#特征向量
features_vec = tv.transform(data)

#建立搜索索引
cp = ci.MultiClusterIndex(features_vec,data)

#搜索带有索引的
search_data = [
    "oh there",
    "Play it again Frank"
]

search_feature_vec = tv.transform(search_data)

#k是返回的个数，k_clusters代表聚类的个数
print(cp.search(search_feature_vec,k = 1,k_clusters=2,return_distance=False))

[['oh hello there'], ['Play it again Sam']]