from bertopic import BERTopic
from umap import UMAP
from sklearn.feature_extraction.text import CountVectorizer
from nltk.corpus import stopwords
import nltk
from nltk import word_tokenize          
from nltk.stem import WordNetLemmatizer
import pandas as pd
import re

nltk.download('stopwords')

# create a list of speeches
docs = data['text'].tolist()