# Extract text from the document text = [] for para in doc.paragraphs: text.append(para.text) text = '\n'.join(text)
import docx import nltk from nltk.tokenize import word_tokenize from nltk.corpus import stopwords J Pollyfan Nicole PusyCat Set docx
# Calculate word frequency word_freq = nltk.FreqDist(tokens) # Extract text from the document text = [] for para in doc
Here are some features that can be extracted or generated: J Pollyfan Nicole PusyCat Set docx