Fix: correct column names (activity_name, case_id) for OCEL dataset

app.py

@@ -1,47 +1,25 @@
-"""
-VynFi × pm4py: Interactive Process Mining Demo
-
-Deployed as a HuggingFace Space (Streamlit SDK). Embeddable on vynfi.com
-via iframe for the /process-mining-data pillar page.
-
-Loads the VynFi Supply Chain OCEL dataset from HF, runs pm4py process
-discovery + variant analysis, and renders interactive visualizations.
-"""
+"""VynFi × pm4py: Interactive Process Mining Demo"""
 
 import streamlit as st
 import pandas as pd
-import pm4py
-from pm4py.objects.conversion.log import converter as log_converter
 from collections import Counter
-import io
 
 st.set_page_config(page_title="VynFi Process Mining", page_icon="📊", layout="wide")
-
 st.title("📊 VynFi × pm4py: Process Mining Demo")
-st.caption("Synthetic supply-chain event log from [VynFi](https://vynfi.com) — explore interactively")
+st.caption("Synthetic supply-chain event log from [VynFi](https://vynfi.com)")
 
 
 @st.cache_data
 def load_data():
-    """Load the VynFi OCEL dataset from HuggingFace."""
     from datasets import load_dataset
-
-    ds = load_dataset("VynFi/vynfi-supply-chain-ocel", "events", split="train", download_mode="force_redownload")
+    ds = load_dataset("VynFi/vynfi-supply-chain-ocel", "events", split="train")
     df = ds.to_pandas()
-    if "timestamp" in df.columns:
-        df["timestamp"] = pd.to_datetime(df["timestamp"], errors="coerce")
-
-    # Rename for pm4py
-    rename = {}
-    if "case_id" in df.columns:
-        rename["case_id"] = "case:concept:name"
-    if "activity_name" in df.columns:
-        rename["activity_name"] = "concept:name"
-    elif "activity" in df.columns:
-        rename["activity"] = "concept:name"
-    if "timestamp" in df.columns:
-        rename["timestamp"] = "time:timestamp"
-    df = df.rename(columns=rename)
+    df["timestamp"] = pd.to_datetime(df["timestamp"], errors="coerce")
+    df = df.rename(columns={
+        "case_id": "case:concept:name",
+        "activity_name": "concept:name",
+        "timestamp": "time:timestamp",
+    })
     return df
 
 
@@ -49,92 +27,55 @@ df = load_data()
 
 st.sidebar.header("Dataset")
 st.sidebar.metric("Events", f"{len(df):,}")
-st.sidebar.metric("Activities", df["concept:name"].nunique() if "concept:name" in df.columns else "?")
-st.sidebar.metric("Cases", df["case:concept:name"].nunique() if "case:concept:name" in df.columns else "?")
+st.sidebar.metric("Activities", df["concept:name"].nunique())
+st.sidebar.metric("Cases", df["case:concept:name"].nunique())
 
 tab1, tab2, tab3, tab4 = st.tabs(["Process Model", "Variants", "Statistics", "Raw Data"])
 
 with tab1:
     st.subheader("Directly-Follows Graph")
     try:
+        import pm4py
         event_log = pm4py.convert_to_event_log(df)
-        dfg, start_activities, end_activities = pm4py.discover_dfg(event_log)
-
-        # Render DFG as dot → SVG
-        from pm4py.visualization.dfg import visualizer as dfg_visualizer
-
-        gviz = dfg_visualizer.apply(
-            dfg,
-            log=event_log,
-            variant=dfg_visualizer.Variants.FREQUENCY,
+        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,
             parameters={
-                dfg_visualizer.Variants.FREQUENCY.value.Parameters.START_ACTIVITIES: start_activities,
-                dfg_visualizer.Variants.FREQUENCY.value.Parameters.END_ACTIVITIES: end_activities,
-                dfg_visualizer.Variants.FREQUENCY.value.Parameters.FORMAT: "svg",
-            },
-        )
-        svg = dfg_visualizer.serialize(gviz).decode("utf-8")
-        st.image(svg, use_container_width=True)
+                dfg_vis.Variants.FREQUENCY.value.Parameters.START_ACTIVITIES: sa,
+                dfg_vis.Variants.FREQUENCY.value.Parameters.END_ACTIVITIES: ea,
+                dfg_vis.Variants.FREQUENCY.value.Parameters.FORMAT: "svg",
+            })
+        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("Try the Variants or Statistics tabs instead.")
+        st.info("pm4py or graphviz may not be available. Try the Variants tab.")
 
 with tab2:
     st.subheader("Process Variants")
-    if "case:concept:name" in df.columns and "concept:name" in df.columns:
-        variants = {}
-        for case_id, group in df.sort_values("time:timestamp").groupby("case:concept:name"):
-            trace = tuple(group["concept:name"].tolist())
-            variants[case_id] = trace
-
-        variant_counts = Counter(variants.values())
-        total = len(variants)
-
-        st.metric("Unique Variants", len(variant_counts))
-
-        rows = []
-        for trace, count in variant_counts.most_common(20):
-            rows.append({
-                "Trace": " → ".join(trace),
-                "Count": count,
-                "Frequency": f"{count / total * 100:.1f}%",
-            })
-        st.dataframe(pd.DataFrame(rows), use_container_width=True, hide_index=True)
-
-        # Happy path
-        if variant_counts:
-            happy_path = variant_counts.most_common(1)[0]
-            st.info(
-                f"**Happy path**: {' → '.join(happy_path[0])} "
-                f"({happy_path[1]} cases, {happy_path[1] / total * 100:.1f}%)"
-            )
+    variants = {}
+    for cid, grp in df.sort_values("time:timestamp").groupby("case:concept:name"):
+        variants[cid] = tuple(grp["concept:name"].tolist())
+    vc = Counter(variants.values())
+    total = len(variants)
+    st.metric("Unique Variants", len(vc))
+    rows = [{"Trace": " → ".join(t), "Count": c, "Frequency": f"{c/total*100:.1f}%"}
+            for t, c in vc.most_common(20)]
+    st.dataframe(pd.DataFrame(rows), use_container_width=True, hide_index=True)
+    if vc:
+        hp = vc.most_common(1)[0]
+        st.info(f"**Happy path**: {' → '.join(hp[0])} ({hp[1]} cases, {hp[1]/total*100:.1f}%)")
 
 with tab3:
     st.subheader("Activity Statistics")
-    if "concept:name" in df.columns:
-        act_counts = df["concept:name"].value_counts()
-        st.bar_chart(act_counts)
-
-        col1, col2 = st.columns(2)
-        with col1:
-            st.metric("Most frequent", act_counts.index[0])
-            st.metric("Count", f"{act_counts.iloc[0]:,}")
-        with col2:
-            st.metric("Least frequent", act_counts.index[-1])
-            st.metric("Count", f"{act_counts.iloc[-1]:,}")
-
+    ac = df["concept:name"].value_counts()
+    st.bar_chart(ac)
     if "time:timestamp" in df.columns:
         st.subheader("Events Over Time")
-        daily = df.set_index("time:timestamp").resample("W").size()
-        st.line_chart(daily)
+        st.line_chart(df.set_index("time:timestamp").resample("W").size())
 
 with tab4:
     st.subheader("Raw Event Data")
-    st.dataframe(df.head(100), use_container_width=True)
+    st.dataframe(df.head(200), use_container_width=True)
 
 st.divider()
-st.caption(
-    "Data: [VynFi/vynfi-supply-chain-ocel](https://huggingface.co/datasets/VynFi/vynfi-supply-chain-ocel) · "
-    "Engine: [pm4py](https://pm4py.fit.fraunhofer.de/) · "
-    "Platform: [vynfi.com](https://vynfi.com)"
-)
+st.caption("[VynFi](https://vynfi.com) · [pm4py](https://pm4py.fit.fraunhofer.de/) · [Dataset](https://huggingface.co/datasets/VynFi/vynfi-supply-chain-ocel)")