Update clustering.py

clustering.py

@@ -28,18 +28,6 @@ from wordcloud import WordCloud
 
 from concurrent.futures import ThreadPoolExecutor
 
-import logging
-
-logging.basicConfig(
-    level=logging.INFO,
-    format='%(asctime)s - %(levelname)s - %(message)s',
-    datefmt='%Y-%m-%d %H:%M:%S'
-)
-
-def log_message(message):
-    """"""
-    logging.info(message)
-
 try:
     import torch
     device = 0 if torch.cuda.is_available() else -1
@@ -627,7 +615,6 @@ def perform_clustering(
 
     if threshold_values is None:
         threshold_values = np.round(np.linspace(min_eps, max_eps, n), 6).astype(float)
-        log_message(f"perform_clustering {threshold_values}")
 
     cluster_assignments = {}
     cluster_counts = {}
@@ -636,7 +623,6 @@ def perform_clustering(
     most_similar_comments = {}
 
     for distance_threshold in threshold_values:
-        log_message(distance_threshold)
         rounded_distance_threshold = round(distance_threshold, 6)
         clustering = AgglomerativeClustering(
             n_clusters=None,
@@ -704,11 +690,9 @@ def build_sankey_data(
     comments = []
 
     sorted_threshold_values = sorted(cluster_assignments.keys())
-    log_message(f"build_sankey_data {sorted_threshold_values}")
     valid_clusters = {}
 
     for threshold in sorted_threshold_values:
-        print(threshold)
         valid_clusters[threshold] = [
             j
             for j in np.unique(cluster_assignments[threshold])