Update src/streamlit_app.py

src/streamlit_app.py

@@ -329,49 +329,47 @@ def load_data(csv_path=CSV_PATH, meta_path=META_PATH):
 df, meta_df = load_data()
 
 
-# Sidebar filters & UI (safe against minimal metadata)
+# -------------------------
+# Sidebar filters & UI (fault-tolerant for minimal metadata)
 # -------------------------
 st.sidebar.title("Feature Explorer - Advanced + SHAP")
 
-# Handle metadata safely — not all runs have detailed feature info
-if "source_type" in meta_df.columns:
-    feat_types = sorted(meta_df["source_type"].dropna().unique().tolist())
-    selected_types = st.sidebar.multiselect("Feature type", feat_types, default=feat_types)
-    filtered_meta = meta_df[meta_df["source_type"].isin(selected_types)]
-else:
-    st.sidebar.warning("Metadata file has no feature-level info. Showing all features.")
-    selected_types = []
-    filtered_meta = pd.DataFrame({
-        "feature_name": df.columns,
-        "source_type": "synthetic",
-        "formula": "",
-        "remarks": ""
-    })
+# Ensure meta_df always has at least placeholder columns
+required_cols = ["feature_name", "source_type", "formula", "remarks"]
+for col in required_cols:
+    if col not in meta_df.columns:
+        meta_df[col] = None
+
+# Populate placeholders if file is just run summaries
+if meta_df["feature_name"].isna().all():
+    meta_df["feature_name"] = df.columns
+    meta_df["source_type"] = [
+        "engineered" if any(x in c for x in ["poly", "pca", "roll", "lag"]) else "measured"
+        for c in df.columns
+    ]
+    meta_df["formula"] = ""
+    meta_df["remarks"] = "auto-inferred synthetic feature metadata"
 
-numeric_cols = df.select_dtypes(include=[np.number]).columns.tolist()
+# Build sidebar safely
+feat_types = sorted(meta_df["source_type"].dropna().unique().tolist())
+selected_types = st.sidebar.multiselect("Feature type", feat_types, default=feat_types)
+filtered_meta = meta_df[meta_df["source_type"].isin(selected_types)]
 
+numeric_cols = df.select_dtypes(include=[np.number]).columns.tolist()
 
 # -------------------------
-# Main tabs
+# Features tab (robust)
 # -------------------------
-st.title("Steel Authority of India Limited (SHAP-enabled)")
-tabs = st.tabs([
-    "Features",
-    "Visualize",
-    "Correlations",
-    "Stats",
-    "Ensemble + SHAP",
-    "Target & Business Impact",
-    "Bibliography"
-])
-
-# ----- Features tab
 with tabs[0]:
     st.subheader("Feature metadata")
-    filtered_meta = meta_df[meta_df["source_type"].isin(selected_types)]
-    st.dataframe(filtered_meta[["feature_name","source_type","formula","remarks"]].rename(columns={"feature_name":"Feature"}), height=400)
+    st.dataframe(
+        filtered_meta[["feature_name", "source_type", "formula", "remarks"]]
+        .rename(columns={"feature_name": "Feature"}),
+        height=400
+    )
     st.markdown(f"Total features loaded: **{df.shape[1]}**  |  Rows: **{df.shape[0]}**")
 
+
 # ----- Visualize tab
 with tabs[1]:
     st.subheader("Feature visualization")