import docx import nltk from nltk.tokenize import word_tokenize from nltk.corpus import stopwords
# Calculate word frequency word_freq = nltk.FreqDist(tokens) J Pollyfan Nicole PusyCat Set docx
# Remove stopwords and punctuation stop_words = set(stopwords.words('english')) tokens = [t for t in tokens if t.isalpha() and t not in stop_words] import docx import nltk from nltk