你有四份文档，编号从1到4，每份文档包含一个句子。请确定与第一份文档最相似的文档的标识符，相似度根据TF-IDF得分计算得出。

My name is Ankit,Ankit name is very famous,Ankit like his nameIndia has a lot of beautiful cities

输出一个整数（可能是2、3或4），输出时前后不要有空格。

回答：

import numpy as npfrom sklearn.feature_extraction.text import TfidfVectorizervect = TfidfVectorizer(min_df=1)tfidf = vect.fit_transform(["My name is Ankit",                             "Ankit name is very famous",                             "Ankit like his name",                             "India has a lot of beautiful cities"])print ((tfidf * tfidf.T).A)