Upload 2 files

app.py

@@ -0,0 +1,82 @@
+
+import streamlit as st
+import json, os
+
+st.set_page_config(
+    page_title="Hybrid AI Fraud Detection",
+    page_icon="shield",
+    layout="wide",
+    initial_sidebar_state="expanded"
+)
+
+@st.cache_resource
+def load_results():
+    results = {}
+    for name, path in [
+        ("p1", "models/p1_lgbm_results.json"),
+        ("p2", "models/p2_stacking_results.json"),
+        ("p3", "models/p3_pipeline_results.json"),
+    ]:
+        if os.path.exists(path):
+            with open(path) as f:
+                results[name] = json.load(f)
+    return results
+
+results = load_results()
+
+st.title("Hybrid AI Architectures for Proactive Fraud Detection")
+st.subheader("An XAI-Driven Optimization Framework")
+st.markdown("**Master MAII | FSTH - Universite Abdelmalek Essaadi | Latif SINARE**")
+st.divider()
+
+col1, col2, col3, col4 = st.columns(4)
+with col1:
+    st.metric("Recall cible", ">= 90%")
+with col2:
+    st.metric("FPR cible", "< 0,01%")
+with col3:
+    st.metric("AUPRC cible", "> 0,85")
+with col4:
+    st.metric("Precision min", ">= 10%")
+
+st.divider()
+
+col_a, col_b = st.columns(2)
+with col_a:
+    st.markdown("### Architecture des Pipelines")
+    table_lines = [
+        "| Phase | Dataset | Modeles | Optimiseur | XAI |",
+        "|-------|---------|---------|------------|-----|",
+        "| 1 - Baseline | Kaggle CC | LightGBM | CMA-ES | SHAP |",
+        "| 2 - Prototype | PaySim | LSTM + RGAT + Stacking | PSO Async | GNNExplainer |",
+        "| 3 - Production | IEEE-CIS | LSTM + RGAT + Stacking | PSO Async | SHAP + GNN |",
+        "| 4 - Extension | AMLSim | RGAT | - | GNNExplainer |",
+    ]
+    st.markdown(chr(10).join(table_lines))
+
+with col_b:
+    st.markdown("### Fonction de Fitness Penalisee")
+    st.latex(r"fitness(	heta) = AUPRC - 10\cdot\max(0, 0.90 - Recall) - 10\cdot\max(0, FPR - 0.0001)")
+    st.markdown("Cette fonction garantit simultanement le Recall >= 90 pourcent et le FPR < 0,01 pourcent.")
+
+st.divider()
+
+if results:
+    st.markdown("### Resultats disponibles")
+    cols = st.columns(len(results))
+    labels = {"p1": "Phase 1 - Kaggle CC", "p2": "Phase 2 - PaySim", "p3": "Phase 3 - IEEE-CIS"}
+    for i, (k, res) in enumerate(results.items()):
+        with cols[i]:
+            th = res.get("test_holdout", res.get("fusion_test", {}))
+            st.markdown(f"**{labels.get(k, k)}**")
+            auprc_val = th.get("auprc", 0)
+            recall_val = th.get("recall", 0)
+            fpr_val = th.get("fpr", 0)
+            st.metric("AUPRC", f"{auprc_val:.4f}")
+            st.metric("Recall", f"{recall_val:.4f}")
+            st.metric("FPR", f"{fpr_val:.6f}")
+else:
+    st.info("Les resultats apparaitront ici au fur et a mesure de execution des notebooks 03, 08 et 11.")
+
+st.divider()
+st.info("Utilisez la barre laterale pour naviguer entre les pipelines et analyser des transactions individuelles.")

requirements.txt

@@ -1,3 +1,8 @@
-altair
-pandas
-streamlit
+streamlit>=1.28.0
+numpy>=1.24.0
+pandas>=2.0.0
+scikit-learn>=1.3.0
+lightgbm>=4.0.0
+shap>=0.43.0
+matplotlib>=3.7.0
+seaborn>=0.12.0