# create stopwords list
standard_stopwords = list(stopwords.words('english'))

# extended list of English stopwords
stopwords_extended = [ "0o",  ..]      

# additional tokens to remove
additional_stopwords = ['blue','buffalo','dog','food','ha','month','ago'] 

# combine standard, extended stopwords, and additional tokens
full_stopwords = standard_stopwords 
                 + additional_stopwords
                 + stopwords_extended

# define tokenizer retrurning lemmatized text without numbers
class LemmaTokenizer:
    def __init__(self):
        self.wnl = WordNetLemmatizer()
    def __call__(self, doc):
        doc = re.sub(r'd+', '', doc)  # clean numbers
        return [self.wnl.lemmatize(t) for t in word_tokenize(doc)] # lemmatize

# vectorizer makes data processing and generates bigrams
vectorizer_model = CountVectorizer(tokenizer=LemmaTokenizer(),
                                  ngram_range=(2, 2),
                                  stop_words=full_stopwords)

# set-up model
model = BERTopic(n_gram_range=(2,2), # returns bigrams
                nr_topics=9,         # generate 9 topics, leave -1 for outliers
                top_n_words=20,      # return top 20 bigrams
                min_topic_size=20,   # topics contains at least 20 tokens
                vectorizer_model=vectorizer_model,
                umap_model = UMAP(random_state=1))  # setting seed topics reproduce

# fit model to data
topics, probabilities = model.fit_transform(docs)