named entity recognition.py

from collections import Counter
import en_core_web_sm

# preprocessing
    nlp = en_core_web_sm.load()
    tweet_article = nlp('|'.join(tweets.tweets))
    # make sure the entities we need are persons
    items = [x.text for x in tweet_article.ents if x.label_ == 'PERSON']
    # exclude the obvious misclassified entities
    items = [celebrity[0] for celebrity in Counter(items).most_common(20) if
             'http' not in celebrity[0] and '@' not in celebrity[0]
             and '#' not in celebrity[0]]