Fix: drop NaT timestamps, avoid colon in altair column names

app.py

@@ -15,10 +15,13 @@ 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"])
+    # Rename for pm4py — use safe names without colons for display
     df = df.rename(columns={
-        "case_id": "case:concept:name",
-        "activity_name": "concept:name",
-        "timestamp": "time:timestamp",
+        "case_id": "case_id_pm",
+        "activity_name": "activity",
+        "timestamp": "ts",
     })
     return df
 
@@ -27,8 +30,8 @@ df = load_data()
 
 st.sidebar.header("Dataset")
 st.sidebar.metric("Events", f"{len(df):,}")
-st.sidebar.metric("Activities", df["concept:name"].nunique())
-st.sidebar.metric("Cases", df["case:concept:name"].nunique())
+st.sidebar.metric("Activities", df["activity"].nunique())
+st.sidebar.metric("Cases", df["case_id_pm"].nunique())
 
 tab1, tab2, tab3, tab4 = st.tabs(["Process Model", "Variants", "Statistics", "Raw Data"])
 
@@ -36,7 +39,13 @@ with tab1:
     st.subheader("Directly-Follows Graph")
     try:
         import pm4py
-        event_log = pm4py.convert_to_event_log(df)
+        # Convert to pm4py format
+        pm_df = df.rename(columns={
+            "case_id_pm": "case:concept:name",
+            "activity": "concept:name",
+            "ts": "time:timestamp",
+        })
+        event_log = pm4py.convert_to_event_log(pm_df)
         dfg, sa, ea = pm4py.discover_dfg(event_log)
         from pm4py.visualization.dfg import visualizer as dfg_vis
         gviz = dfg_vis.apply(dfg, log=event_log, variant=dfg_vis.Variants.FREQUENCY,
@@ -48,13 +57,13 @@ with tab1:
         st.image(dfg_vis.serialize(gviz).decode("utf-8"), use_container_width=True)
     except Exception as e:
         st.warning(f"Could not render DFG: {e}")
-        st.info("pm4py or graphviz may not be available. Try the Variants tab.")
+        st.info("Try the Variants or Statistics tabs instead.")
 
 with tab2:
     st.subheader("Process Variants")
     variants = {}
-    for cid, grp in df.sort_values("time:timestamp").groupby("case:concept:name"):
-        variants[cid] = tuple(grp["concept:name"].tolist())
+    for cid, grp in df.sort_values("ts").groupby("case_id_pm"):
+        variants[cid] = tuple(grp["activity"].tolist())
     vc = Counter(variants.values())
     total = len(variants)
     st.metric("Unique Variants", len(vc))
@@ -66,12 +75,16 @@ with tab2:
         st.info(f"**Happy path**: {' → '.join(hp[0])} ({hp[1]} cases, {hp[1]/total*100:.1f}%)")
 
 with tab3:
-    st.subheader("Activity Statistics")
-    ac = df["concept:name"].value_counts()
-    st.bar_chart(ac)
-    if "time:timestamp" in df.columns:
-        st.subheader("Events Over Time")
-        st.line_chart(df.set_index("time:timestamp").resample("W").size())
+    st.subheader("Activity Frequency")
+    ac = df["activity"].value_counts().reset_index()
+    ac.columns = ["Activity", "Count"]
+    st.bar_chart(ac, x="Activity", y="Count")
+
+    st.subheader("Events Over Time")
+    if "ts" in df.columns:
+        weekly = df.set_index("ts").resample("W").size().reset_index()
+        weekly.columns = ["Week", "Events"]
+        st.line_chart(weekly, x="Week", y="Events")
 
 with tab4:
     st.subheader("Raw Event Data")