Fix DFG tab: drop case-less events before pm4py conversion

The native OCEL 2.0 events parquet has ~33% case-less events
(shared-resource activities); pm4py's discover_dfg requires a
case ID per event. Dropping them in load_data() so the first
tab renders cleanly without affecting the other tabs.

app.py

@@ -15,8 +15,9 @@ def load_data():
     ds = load_dataset("VynFi/vynfi-supply-chain-ocel", "events", split="train")
     df = ds.to_pandas()
     df["timestamp"] = pd.to_datetime(df["timestamp"], errors="coerce")
-    # Drop rows with NaT timestamps (pm4py can't handle them)
-    df = df.dropna(subset=["timestamp"])
+    # pm4py needs both timestamp and case_id present; native OCEL 2.0 has
+    # case-less events for shared-resource activities, drop them here.
+    df = df.dropna(subset=["timestamp", "case_id"])
     # Rename for pm4py — use safe names without colons for display
     df = df.rename(columns={
         "case_id": "case_id_pm",