Cont fixing proportion plot

utils.py

@@ -491,12 +491,15 @@ def build_multifile_category_df(validNames, results, summaries, categories, cate
         df6_dict.setdefault(category, [])
 
     # Second pass: compute proportions per file
-    for fn in validNames:
+    for row_idx, fn in enumerate(validNames):
         currAnnotation, totalSeconds = results[fn]
         safe_total = max(totalSeconds, 1)
         prefix = fn + ": "
         renames = speakerRenames.get(fn, {})
 
+        # Track which allCategories columns get a value this row
+        filled = set()
+
         # For each role: union all assigned speakers into one subset, then sum.
         # su.sumTimes uses get_timeline(False).duration() which merges overlaps.
         for i, category in enumerate(categories):
@@ -505,13 +508,13 @@ def build_multifile_category_df(validNames, results, summaries, categories, cate
                 for t in categorySelect[i]
                 if t.startswith(prefix)
             ] if i < len(categorySelect) else []
-            # Filter to speakers that actually exist in this annotation
             valid_sps = [sp for sp in assigned_sps if sp in currAnnotation.labels()]
             if valid_sps:
                 val = su.sumTimes(currAnnotation.subset(valid_sps)) / safe_total
             else:
                 val = 0.0
             df6_dict[category].append(min(val, 1.0))
+            filled.add(category)
 
         # For unassigned speakers: each gets their own column
         assigned_all = {
@@ -525,10 +528,11 @@ def build_multifile_category_df(validNames, results, summaries, categories, cate
             display = renames.get(sp, sp)
             val = su.sumTimes(currAnnotation.subset([sp])) / safe_total
             df6_dict[display].append(min(val, 1.0))
+            filled.add(display)
 
-        # Fill 0 for any extra columns this file doesn't have
+        # Fill 0 for every allCategories column not touched this row
         for category in allCategories:
-            if len(df6_dict[category]) < len(df6_dict["files"]):
+            if category not in filled:
                 df6_dict[category].append(0)
 
     return pd.DataFrame(df6_dict), allCategories