Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,4 +1,4 @@
-# sail_modex_stable.py
+
 import os
 import json
 import time
@@ -654,7 +654,7 @@ with tabs[4]:
                 result = tune_family(fam, X, y, n_trials=max_trials)
                 model_obj = result.get("model_obj")
             
-                # ✅ Fix: ensure model is safe to access before fitting
+                # Fix: ensure model is safe to access before fitting
                 if hasattr(model_obj, "estimators_"):
                     delattr(model_obj, "estimators_")  # clear stale ref if any
                 result["model_obj"] = model_obj
@@ -768,11 +768,39 @@ with tabs[4]:
             try:
                 top_base = next((b for b in base_models if b["family"] == selected[0]), None)
                 if top_base and hasattr(top_base["model"], "predict"):
-                    sample_X = X_val.sample(min(300, len(X_val)), random_state=42)
+                    # --- Ensure numeric dtypes for SHAP ---
+                    sample_X = X_val.sample(min(300, len(X_val)), random_state=42).copy()
+                    for col in sample_X.columns:
+                        if sample_X[col].dtype == object:
+                            # Clean any bracketed, comma, or sci-notation strings
+                            sample_X[col] = (
+                                sample_X[col]
+                                .astype(str)
+                                .str.replace("[", "", regex=False)
+                                .str.replace("]", "", regex=False)
+                                .str.replace(",", "", regex=False)
+                                .str.replace("E", "e", regex=False)
+                                .str.replace("nan", "0", regex=False)
+                                .str.strip()
+                            )
+                        # Force numeric conversion for all columns
+                        sample_X[col] = pd.to_numeric(sample_X[col], errors="coerce")
+                    
+                    # Replace NaN with 0 for SHAP stability
+                    sample_X = sample_X.fillna(0)
+                    
+                    # Optional: show columns that were coerced
+                    non_numeric_cols = [c for c in sample_X.columns if not np.issubdtype(sample_X[c].dtype, np.number)]
+                    if non_numeric_cols:
+                        st.warning(f"Non-numeric columns coerced: {non_numeric_cols}")
+
+            
+                    # --- SHAP computation ---
                     model = top_base["model"]
                     expl = shap.TreeExplainer(model)
                     shap_vals = expl.shap_values(sample_X)
-                    if isinstance(shap_vals, list): shap_vals = shap_vals[0]
+                    if isinstance(shap_vals, list):
+                        shap_vals = shap_vals[0]
                     shap_vals = np.array(shap_vals)
                     mean_abs = np.abs(shap_vals).mean(axis=0)
                     mean_sign = np.sign(shap_vals).mean(axis=0)
@@ -781,17 +809,24 @@ with tabs[4]:
                         "Mean |SHAP|": mean_abs,
                         "Mean SHAP Sign": mean_sign
                     }).sort_values("Mean |SHAP|", ascending=False)
+            
                     st.markdown("### Top 5 Operational Drivers")
                     st.dataframe(importance.head(5))
+            
                     recommendations = []
                     for _, row in importance.head(5).iterrows():
                         f, s = row["Feature"], row["Mean SHAP Sign"]
-                        if s > 0.05: recommendations.append(f"Increase `{f}` likely increases `{target}`")
-                        elif s < -0.05: recommendations.append(f"Decrease `{f}` likely increases `{target}`")
-                        else: recommendations.append(f"`{f}` neutral for `{target}`")
+                        if s > 0.05:
+                            recommendations.append(f"Increase `{f}` likely increases `{target}`")
+                        elif s < -0.05:
+                            recommendations.append(f"Decrease `{f}` likely increases `{target}`")
+                        else:
+                            recommendations.append(f"`{f}` neutral for `{target}`")
+            
                     st.markdown("### Suggested Operator Adjustments")
                     st.write("\n".join(recommendations))
 
+
                     # --- Call HF Llama-3-70B-Instruct API for summary ---
                     import requests
                     HF_TOKEN = st.secrets.get("HF_TOKEN", os.getenv("HF_TOKEN"))