Add app.py

app.py

@@ -0,0 +1,140 @@
+"""
+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.
+"""
+
+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.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")
+    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)
+    return df
+
+
+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 "?")
+
+tab1, tab2, tab3, tab4 = st.tabs(["Process Model", "Variants", "Statistics", "Raw Data"])
+
+with tab1:
+    st.subheader("Directly-Follows Graph")
+    try:
+        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,
+            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)
+    except Exception as e:
+        st.warning(f"Could not render DFG: {e}")
+        st.info("Try the Variants or Statistics tabs instead.")
+
+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}%)"
+            )
+
+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]:,}")
+
+    if "time:timestamp" in df.columns:
+        st.subheader("Events Over Time")
+        daily = df.set_index("time:timestamp").resample("W").size()
+        st.line_chart(daily)
+
+with tab4:
+    st.subheader("Raw Event Data")
+    st.dataframe(df.head(100), 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)"
+)