Add a new cross file chart

utils.py

@@ -538,6 +538,63 @@ def build_multifile_category_df(validNames, results, summaries, categories, cate
     return pd.DataFrame(df6_dict), allCategories
 
 
+def build_multifile_role_voice_df(validNames, results, summaries, categories,
+                                  categorySelect, speakerRenames=None):
+    """Build df8: per-file proportions split by role for single voice, plus
+    Multi Voice and No Voice.
+
+    Single Voice time is broken down into each role and an Unassigned bucket
+    (speakers in single-voice segments that haven't been assigned to any role).
+    Multi Voice and No Voice come from df5 percentiles (0-100 scale) converted
+    to 0-1 proportions.
+
+    This is the combination of df6 (role proportions) and df7 (voice categories)
+    where Single Voice is replaced by its constituent roles.
+    """
+    speakerRenames = speakerRenames or {}
+    col_names = list(categories) + ["Unassigned", "Multi Voice", "No Voice"]
+    df8_dict  = {"files": validNames}
+    for col in col_names:
+        df8_dict[col] = []
+
+    for fn in validNames:
+        currAnnotation, totalSeconds = results[fn]
+        safe_total = max(totalSeconds, 1)
+        prefix     = fn + ": "
+        renames    = speakerRenames.get(fn, {})
+
+        # Role proportions — same logic as build_multifile_category_df
+        assigned_all = set()
+        for i, category in enumerate(categories):
+            assigned_sps = [
+                t[len(prefix):]
+                for t in (categorySelect[i] if i < len(categorySelect) else [])
+                if t.startswith(prefix)
+            ]
+            valid_sps = [sp for sp in assigned_sps if sp in currAnnotation.labels()]
+            assigned_all.update(valid_sps)
+            if valid_sps:
+                val = su.sumTimes(currAnnotation.subset(valid_sps)) / safe_total
+            else:
+                val = 0.0
+            df8_dict[category].append(min(val, 1.0))
+
+        # Unassigned speakers
+        unassigned_sps = [sp for sp in currAnnotation.labels() if sp not in assigned_all]
+        if unassigned_sps:
+            val = su.sumTimes(currAnnotation.subset(unassigned_sps)) / safe_total
+        else:
+            val = 0.0
+        df8_dict["Unassigned"].append(min(val, 1.0))
+
+        # Multi Voice and No Voice from df5 percentiles (0-100 → 0-1)
+        partial = summaries[fn]["df5"]
+        df8_dict["No Voice"].append(partial["percentiles"][0] / 100)
+        df8_dict["Multi Voice"].append(partial["percentiles"][2] / 100)
+
+    return pd.DataFrame(df8_dict), col_names
+
+
 def build_multifile_voice_df(validNames, summaries):
     """Build df7 (no/one/multi voice percentages per file) for the multi-file expander."""
     voiceNames = ["No Voice", "Single Voice", "Multi Voice"]