Update clustering.py

clustering.py

@@ -626,7 +626,7 @@ def perform_clustering(
     embeddings_matrix = np.array(data[embeddings_col].tolist())
 
     if not threshold_values:
-        threshold_values = np.round(np.linspace(min_eps, max_eps, n), 6)
+        threshold_values = np.round(np.linspace(min_eps, max_eps, n), 6).astype(float)
         log_message(f"perform_clustering {threshold_values}")
         # threshold_values = np.linspace(min_eps, max_eps, n)
 
@@ -637,7 +637,6 @@ def perform_clustering(
     most_similar_comments = {}
 
     for distance_threshold in threshold_values:
-        distance_threshold = round(distance_threshold, 6)
         log_message(distance_threshold)
         clustering = AgglomerativeClustering(
             n_clusters=None,
@@ -645,6 +644,7 @@ def perform_clustering(
             linkage="complete",
             metric="cosine",
         )
+
         data[f"cluster_{distance_threshold}"] = clustering.fit_predict(
             embeddings_matrix
         )