reduced logging

utils/gram2vec_feat_utils.py

@@ -172,6 +172,8 @@ def show_combined_spans_all(selected_feature_llm, selected_feature_g2v,
         # print(llm_style_feats_analysis)
         print(f"{len(llm_style_feats_analysis['spans'].values())}")
         author_list = list(llm_style_feats_analysis['spans'].values())
+        # print(f"Author list length: {len(author_list)}")
+        # print(f"Author list: {author_list}")
         llm_spans_list = []
         for i, (_, txt) in enumerate(texts):
             print(f"{i}/{len(texts)}")
@@ -228,12 +230,12 @@ def show_combined_spans_all(selected_feature_llm, selected_feature_g2v,
     bg_start = 4
     bg_indices = list(range(bg_start, len(texts)))
     kept_indices = [i for i in bg_indices if gram_spans_list[i]]
-    print(f"\n---> {kept_indices}")
+    # print(f"\n---> {kept_indices}")
     filtered_texts_bg = [texts[i] for i in kept_indices]
     filtered_llm_bg   = [llm_spans_list[i] for i in kept_indices]
     filtered_gram_bg  = [gram_spans_list[i] for i in kept_indices]
 
-    print(filtered_texts_bg)
+    # print(filtered_texts_bg)
 
     html_background_authors = create_html(
         filtered_texts_bg,
@@ -279,7 +281,7 @@ def get_label(label: str, predicted_author=None, ground_truth_author=None, bg_id
 def create_html(texts, llm_spans_list, gram_spans_list, selected_feature_llm, selected_feature_g2v, short=None, background = False, predicted_author=None, ground_truth_author=None):
     html = []
     for i, (label, txt) in enumerate(texts):
-        print(i, label, txt[:30])
+        # print(i, label, txt[:30])
         label = get_label(label, predicted_author, ground_truth_author,  i) if background else get_label(label, predicted_author, ground_truth_author)
         combined = highlight_both_spans(txt, llm_spans_list[i], gram_spans_list[i])
         notice = ""

utils/visualizations.py

@@ -309,7 +309,7 @@ def handle_zoom(event_json, bg_proj, bg_lbls, clustered_authors_df, task_authors
 
     task_texts = [_to_text(x) for x in task_only_df['fullText'].tolist()]
 
-    print(f"task_texts: {task_texts}")
+    print(f"len task_texts: {len(task_texts)}")
     filtered_g2v_feats = []
     for feat in g2v_feats:
         try:
@@ -333,7 +333,7 @@ def handle_zoom(event_json, bg_proj, bg_lbls, clustered_authors_df, task_authors
     HR_g2v_list = []
     for feat in filtered_g2v_feats:
         HR_g2v = get_fullform(feat[0])
-        print(f"\n\n feat: {feat} ---> Human Readable: {HR_g2v}")
+        # print(f"\n\n feat: {feat} ---> Human Readable: {HR_g2v}")
         if HR_g2v is None:
             print(f"Skipping Gram2Vec feature without human readable form: {feat}")
         else:
@@ -342,11 +342,11 @@ def handle_zoom(event_json, bg_proj, bg_lbls, clustered_authors_df, task_authors
     HR_g2v_list = [("None", None)] + HR_g2v_list
 
     print(f"[INFO] Found {len(llm_feats)} LLM features and {len(g2v_feats)} Gram2Vec features in the zoomed region.")   
-    print(f"[INFO] unfiltered g2v features: {g2v_feats}")
+    # print(f"[INFO] unfiltered g2v features: {g2v_feats}")
 
     print(f"[INFO] LLM features: {llm_feats}")
     HR_g2v_list, _ = format_g2v_features_for_display(HR_g2v_list)
-    print(f"[INFO] Gram2Vec features: {HR_g2v_list}")
+    # print(f"[INFO] Gram2Vec features: {HR_g2v_list}")
 
     return (
         gr.update(choices=llm_feats, value=llm_feats[0]),
@@ -386,7 +386,7 @@ def handle_zoom_with_retries(event_json, bg_proj, bg_lbls, clustered_authors_df,
 def visualize_clusters_plotly(iid, cfg, instances, model_radio, custom_model_input, task_authors_df, background_authors_embeddings_df, pred_idx=None, gt_idx=None):
     model_name = model_radio if model_radio != "Other" else custom_model_input
     embedding_col_name = f'{model_name.split("/")[-1]}_style_embedding'
-    print(background_authors_embeddings_df.columns)
+    # print(background_authors_embeddings_df.columns)
     print("Generating cluster visualization")
     iid = int(iid)
     #interp      = load_interp_space(cfg)