import sklearn
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
text1 = 'A smiling costumed woman is holding an umbrella'
text2 = 'A happy woman in a fairy costume holds an umbrella'
vectorizer = TfidfVectorizer()
vectors = vectorizer.fit_transform([text1,text2])
similarity = cosine_similarity(vectors)
print(similarity)
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