与@larsman相同，但有一些预处理

import nltk, string
from sklearn.feature_extraction.text import TfidfVectorizer

nltk.download('punkt') # if necessary...


stemmer = nltk.stem.porter.PorterStemmer()
remove_punctuation_map = dict((ord(char), None) for char in string.punctuation)

def stem_tokens(tokens):
    return [stemmer.stem(item) for item in tokens]

'''remove punctuation, lowercase, stem'''
def normalize(text):
    return stem_tokens(nltk.word_tokenize(text.lower().translate(remove_punctuation_map)))

vectorizer = TfidfVectorizer(tokenizer=normalize, stop_words='english')

def cosine_sim(text1, text2):
    tfidf = vectorizer.fit_transform([text1, text2])
    return ((tfidf * tfidf.T).A)[0,1]


print cosine_sim('a little bird', 'a little bird')
print cosine_sim('a little bird', 'a little bird chirps')
print cosine_sim('a little bird', 'a big dog barks')

你可能想尝试一下cos文档相似度的在线服务http://www.scurtu.it/documentSimilarity.html

import urllib,urllib2
import json
API_URL="http://www.scurtu.it/apis/documentSimilarity"
inputDict={}
inputDict['doc1']='Document with some text'
inputDict['doc2']='Other document with some text'
params = urllib.urlencode(inputDict)    
f = urllib2.urlopen(API_URL, params)
response= f.read()
responseObject=json.loads(response)  
print responseObject

为了用更少的数据集找到句子的相似性，并获得更高的精度，你可以使用下面的python包，它使用预训练的BERT模型，

pip install similar-sentences

句法相似性 有3种简单的方法来检测相似性。

Word2Vec 手套 Tfidf或countvectorizer

语义相似性 可以使用BERT嵌入和尝试不同的词池策略来获得文档嵌入，然后在文档嵌入上应用余弦相似度。

一种先进的方法是利用BERT分数来获得相似度。

研究论文链接:https://arxiv.org/abs/1904.09675

这里有一个小应用程序让你开始…

import difflib as dl

a = file('file').read()
b = file('file1').read()

sim = dl.get_close_matches

s = 0
wa = a.split()
wb = b.split()

for i in wa:
    if sim(i, wb):
        s += 1

n = float(s) / float(len(wa))
print '%d%% similarity' % int(n * 100)

与@larsman相同，但有一些预处理

import nltk, string
from sklearn.feature_extraction.text import TfidfVectorizer

nltk.download('punkt') # if necessary...


stemmer = nltk.stem.porter.PorterStemmer()
remove_punctuation_map = dict((ord(char), None) for char in string.punctuation)

def stem_tokens(tokens):
    return [stemmer.stem(item) for item in tokens]

'''remove punctuation, lowercase, stem'''
def normalize(text):
    return stem_tokens(nltk.word_tokenize(text.lower().translate(remove_punctuation_map)))

vectorizer = TfidfVectorizer(tokenizer=normalize, stop_words='english')

def cosine_sim(text1, text2):
    tfidf = vectorizer.fit_transform([text1, text2])
    return ((tfidf * tfidf.T).A)[0,1]


print cosine_sim('a little bird', 'a little bird')
print cosine_sim('a little bird', 'a little bird chirps')
print cosine_sim('a little bird', 'a big dog barks')