model.py

def features(sentence):
    stop_words = stopwords.words('english') + list(punctuation)
    words = word_tokenize(sentence)
    words = [w.lower() for w in words]
    filtered = [w for w in words if w not in stop_words and not w.isdigit()]
    words = {}
    for word in filtered:
        if word in words:
            words[word] += 1.0
        else:
            words[word] = 1.0
    return words