fix: entity_count fallback + globe SQLite loading

- entity_count: fallback from ClusterResult sizes when PCA is skipped
- globe_view: load from SQLite table (_data_N) instead of csv_glob path

analysis/views.py

@@ -816,6 +816,13 @@ def _run_clustering_pipeline(run, store, entity_ds_id, feature_columns, algorith
             except Exception as pca_err:
                 logger.warning(f'PCA-2D embedding skipped: {pca_err}')
 
+        # Fallback: if entity_count not set (PCA skipped), derive from cluster sizes
+        if run.entity_count is None:
+            from django.db.models import Sum
+            total = run.clusters.aggregate(total=Sum('size'))['total'] or 0
+            run.entity_count = total
+            run.save(update_fields=['entity_count'])
+
         # ── Done ──
         run.status = 'completed'
         run.progress_pct = 100
@@ -1358,7 +1365,7 @@ def _extract_flows_from_df(df, MAX_ROWS):
 def globe_view(request):
     import json
     from analysis.geoip import lookup as geo_lookup
-    from analysis.data_loader import load_csv_directory
+    from analysis.data_loader import load_csv_directory, load_from_db
     from analysis.models import AnalysisRun
     from analysis.session_store import SessionStore
 
@@ -1412,7 +1419,11 @@ def globe_view(request):
 
     for run in selected_runs:
         try:
-            lf, schema, rc, fc, mem = load_csv_directory(run.csv_glob)
+            lf = None
+            if run.sqlite_table:
+                lf = load_from_db(run.sqlite_table)
+            if lf is None:
+                lf, schema, rc, fc, mem = load_csv_directory(run.csv_glob)
             df = lf.head(MAX_ROWS_PER_RUN).collect()
             flows.extend(_extract_flows_from_df(df, MAX_ROWS_PER_RUN))
             all_selected_failed = False
@@ -1422,25 +1433,22 @@ def globe_view(request):
             continue
 
     if all_selected_failed or not flows:
-        # Fallback: latest completed run with valid files
+        # Fallback: latest completed run with valid data (SQLite or CSV)
         for latest in AnalysisRun.objects.filter(status='completed').order_by('-id'):
-            if not latest.csv_glob:
+            if not latest.csv_glob and not latest.sqlite_table:
                 continue
-            glob_path = Path(latest.csv_glob)
             try:
-                if '/*' in latest.csv_glob:
-                    if glob_path.parent.is_dir():
-                        lf, schema, rc, fc, mem = load_csv_directory(latest.csv_glob)
-                        df = lf.head(MAX_ROWS_PER_RUN).collect()
-                        flows.extend(_extract_flows_from_df(df, MAX_ROWS_PER_RUN))
-                        selected_runs = [latest]
-                        break
-                elif glob_path.exists():
+                lf = None
+                if latest.sqlite_table:
+                    lf = load_from_db(latest.sqlite_table)
+                if lf is None:
+                    if not latest.csv_glob:
+                        continue
                     lf, schema, rc, fc, mem = load_csv_directory(latest.csv_glob)
-                    df = lf.head(MAX_ROWS_PER_RUN).collect()
-                    flows.extend(_extract_flows_from_df(df, MAX_ROWS_PER_RUN))
-                    selected_runs = [latest]
-                    break
+                df = lf.head(MAX_ROWS_PER_RUN).collect()
+                flows.extend(_extract_flows_from_df(df, MAX_ROWS_PER_RUN))
+                selected_runs = [latest]
+                break
             except Exception:
                 continue