Lines of Questioning

nanogenmo-2025.py

import re
import json
import random
from textblob import TextBlob
import nltk
from nltk.tag import pos_tag

nltk.download('punkt')
nltk.download('averaged_perceptron_tagger')
nltk.download('averaged_perceptron_tagger_eng')
nltk.download('brown')
nltk.download('punkt_tab')


text = "\n".join([k['s'] for k in data_list])
blob = TextBlob(text)
sentences = blob.sentences

questions = []

for sentence in sentences:
  if (str(sentence)[-1] == '?'):
    cleaner = re.sub(r'["\'“`\[\]\(\)_]', '', str(sentence))
    cleaner = re.sub(r"\n([A-Z]\w+)",lambda x: " " + x.group(1).lower(),cleaner)
    cleaner = re.sub(r"\n"," ",cleaner)
    if (cleaner[0].islower()):
      cleaner = cleaner.split()[0][0].upper() + cleaner[1:]
      
    questions.append(cleaner)

questions = set(questions)

book = '# Lines of Questioning\n\n\n'
fib = [1,1]
while (len(fib) < 10):
  fib.append(fib[-2] + fib[-1])

chapter = 0

while (len(book) < 50000):
  chapter += 1
  book += "## Chapter " + str(chapter) + "\n\n"
  for i in range(len(fib)):
    book += " " + random.choice([str(q) for q in questions if len(q.split(" ")) == fib[i]]) + "\n"
  book += "\n\n"


with open("/content/book.md","w") as f:
  f.write(book)