Extract token2idf mapper from TfidfVectorizer.

tfidf_token2idf.py

from sklearn.feature_extraction.text import TfidfVectorizer

# data
corpus = [
    'This is the first document.',
    'This document is the second document.',
    'And this is the third one.',
    'Is this the first document?',
]

# fit
tfidf_vectorizer = TfidfVectorizer()
tfidf_vectorizer.fit(corpus)

# token2idf
token2idf = {token: tfidf_vectorizer.idf_[idx] for token, idx in tfidf_vectorizer.vocabulary_.items()}

# sorted token2idf
sorted_token2idf = sorted(
    token2idf.items(),
    key=lambda x: x[1],
)