clustering-fin-news-bertopic.py

from bertopic import BERTopic
from umap import UMAP
from hdbscan import HDBSCAN

# Use Hierarchical DBSCAN as clustering model
hdbscan_model = HDBSCAN(min_cluster_size=15, metric='euclidean', cluster_selection_method='eom', prediction_data=True)

# Use UMAP for dimensionality reduction
umap_model = UMAP(n_neighbors=15, n_components=5, min_dist=0.0, metric='cosine', random_state=42)

# Build the topic model
topic_model = BERTopic(
    verbose=True,
    embedding_model=finbert,
    hdbscan_model=hdbscan_model,
    nr_topics=10,
    umap_model=umap_model
)

# Fit
headline_topics, _ = topic_model.fit_transform(headline_texts)

# View topics
freq = topic_model.get_topic_info()
print("Number of topics: {}".format(len(freq)))
freq