how-to-make-qa-bot-4.py

from sklearn.feature_extraction.text import TfidfVectorizer

sentences = [sentence
             for datum in squad['data']
             for paragraph in datum['paragraphs']
             for sentence in paragraph['context'].split('. ')
            ]

tf_idf_vect = TfidfVectorizer(tokenizer=tokenize_and_stem)
tf_idf_vect.fit(sentences)
question_repr = tf_idf_vect.transform([question])

context_sentences = context.split('. ')
sentence_repr = tf_idf_vect.transform(context_sentences)
sentence_repr

'''<4x76188 sparse matrix of type '<class 'numpy.float64'>'
	with 71 stored elements in Compressed Sparse Row format>'''