import numpy as np
import pandas as pd
from sentence_transformers import SentenceTransformer
from turftopic import KeyNMF

# Create corpus from text summaries (not original texts)
corpus = list(summary_df["summary"])

# Collect key points by segmenting at double line breaks
points = []

for doc in corpus:
  _points = doc.split("\n\n")
  doc_points = [p for p in _points if len(p.strip().removeprefix(" - "))]
  points.extend(doc_points)

# Tell KeyNMF to automatically detect the number of topics using BIC
model = KeyNMF("auto", encoder="paraphrase-mpnet-base-v2")
doc_topic = model.fit_transform(points)

# Print topic IDs with top words
model.print_topics()