clustering.py

if reduce_size:
  # reduce embedding dimensionality
  embeddings = UMAP(n_neighbors=15, 
                    n_components=10, 
                    min_dist=0.0, 
                    metric='cosine', 
                    random_state=42
                   ).fit_transform(embeddings)

# clustering, here we set 5 clusters, i.e. 5 topics
kmeans = KMeans(5)
documents = kmeans.fit(embeddings)