updated app.py and models section

app.py

@@ -622,7 +622,18 @@ st.markdown("<div style='margin-top:2rem'></div>", unsafe_allow_html=True)
 with st.expander("Model Details"):
     st.markdown(f"**Best Model:** {metadata['best_model_name']}")
     st.markdown(f"**Splits:** Train {metadata['train_seasons']} · Val {metadata['val_seasons']} · Test {metadata['test_seasons']}")
-    st.markdown("**Model Comparison:**")
+
+    if metadata.get("iteration_summary"):
+        st.markdown("**CV Iteration Comparison (5-fold, all models):**")
+        iter_df = pd.DataFrame(metadata["iteration_summary"])
+        iter_df = iter_df.rename(columns={
+            "iteration": "Iteration", "model": "Model",
+            "cv_f1": "CV F1", "cv_std": "± Std", "cv_acc": "CV Acc",
+        })
+        iter_df[["CV F1", "± Std", "CV Acc"]] = iter_df[["CV F1", "± Std", "CV Acc"]].round(4)
+        st.dataframe(iter_df.set_index("Iteration"), use_container_width=True)
+
+    st.markdown("**Final Holdout Evaluation (Val 2024 · Test 2025):**")
     for name, r in metadata["results"].items():
         val  = r.get("val_2024",  {})
         test = r.get("test_2025", {})

models/metadata.json

@@ -45,6 +45,19 @@
   "threshold_config": {
     "Lost": 1.0
   },
+  "iteration_summary": [
+    {"iteration": "1 – Baseline",    "model": "Logistic Regression",   "cv_f1": 0.3605, "cv_std": 0.0225, "cv_acc": 0.3942},
+    {"iteration": "1 – Baseline",    "model": "RF (n=100)",             "cv_f1": 0.5380, "cv_std": 0.0198, "cv_acc": 0.5600},
+    {"iteration": "2 – Weather",     "model": "Logistic Regression",   "cv_f1": 0.3624, "cv_std": 0.0171, "cv_acc": 0.3888},
+    {"iteration": "2 – Weather",     "model": "RF (n=200)",             "cv_f1": 0.5275, "cv_std": 0.0180, "cv_acc": 0.5542},
+    {"iteration": "2 – Weather",     "model": "XGBoost (n=200)",        "cv_f1": 0.5358, "cv_std": 0.0175, "cv_acc": 0.5439},
+    {"iteration": "3 – History",     "model": "RF (n=300)",             "cv_f1": 0.5358, "cv_std": 0.0184, "cv_acc": 0.5772},
+    {"iteration": "3 – History",     "model": "XGBoost (n=300)",        "cv_f1": 0.5406, "cv_std": 0.0304, "cv_acc": 0.5523},
+    {"iteration": "3 – History",     "model": "GradBoost (n=200)",      "cv_f1": 0.5551, "cv_std": 0.0241, "cv_acc": 0.5772},
+    {"iteration": "4 – Quali/Pace",  "model": "RF (n=300)",             "cv_f1": 0.5200, "cv_std": 0.0183, "cv_acc": 0.5642},
+    {"iteration": "4 – Quali/Pace",  "model": "XGBoost (n=300)",        "cv_f1": 0.5414, "cv_std": 0.0310, "cv_acc": 0.5535},
+    {"iteration": "4 – Quali/Pace",  "model": "GradBoost (n=200)",      "cv_f1": 0.5497, "cv_std": 0.0204, "cv_acc": 0.5718}
+  ],
   "results": {
     "RF (n=300)": {
       "val_2024": {