Update app.py

app.py

@@ -1,5 +1,5 @@
 # app.py
-import os, io, math, time, warnings, json
+import os, io, math, time, warnings
 warnings.filterwarnings("ignore")
 
 from typing import List, Tuple, Dict, Optional
@@ -163,7 +163,7 @@ def estimate_all_moments_aligned(symbols: List[str], years: int, rf_ann: float):
         betas[s] = cov_sm / var_m
     betas[MARKET_TICKER] = 1.0
 
-    # >>> FIX: include MARKET_TICKER in covariance so σ for portfolios holding VOO is correct
+    # include market in covariance so σ for portfolios holding VOO is correct
     asset_cols_all = list(R.columns)  # includes market
     cov_m_all = np.cov(R[asset_cols_all].values.T, ddof=1) if asset_cols_all else np.zeros((0, 0))
     covA = pd.DataFrame(cov_m_all * 12.0, index=asset_cols_all, columns=asset_cols_all)
@@ -222,7 +222,7 @@ def plot_cml(rf_ann, erp_ann, sigma_mkt,
     plt.scatter([_pct(0)], [_pct(rf_ann)], label="Risk-free")
     plt.scatter([_pct(sigma_mkt)], [_pct(rf_ann + erp_ann)], label="Market")
 
-    # Your CAPM point (y is clamped under CML at your σ for display)
+    # Your CAPM point (y clamped to CML at your σ for display)
     y_cml_at_sigma_p = rf_ann + slope * max(0.0, float(sigma_hist_p))
     y_you = min(float(mu_capm_p), y_cml_at_sigma_p)
     plt.scatter([_pct(sigma_hist_p)], [_pct(y_you)], label="Your CAPM point")
@@ -260,7 +260,7 @@ def build_synthetic_dataset(universe_user: List[str],
     Generate long-only mixes **from exactly the user's tickers** (VOO included only if the user holds it).
     """
     rng = np.random.default_rng(12345)
-    assets = list(universe_user)  # <-- allow VOO if present
+    assets = list(universe_user)
     if len(assets) == 0:
         return pd.DataFrame(columns=["tickers", "weights", "beta", "mu_capm", "sigma_hist"])
 
@@ -328,7 +328,6 @@ def rerank_and_pick_one(df_band: pd.DataFrame,
         embs_ok = False
         q = None
 
-    # exposure similarity
     def _cos(a, b):
         an = np.linalg.norm(a) + 1e-12
         bn = np.linalg.norm(b) + 1e-12
@@ -360,11 +359,25 @@ def suggest_one_per_band(synth: pd.DataFrame, sigma_mkt: float, universe_user: L
     out: Dict[str, pd.Series] = {}
     for band in ["Low", "Medium", "High"]:
         lo, hi = _band_bounds(sigma_mkt, band)
-        pick_pool = synth[(synth["sigma_hist"] >= lo) & (synth["sigma_hist"] <= hi)].copy()
-        if pick_pool.empty:
-            pick_pool = synth.copy()
-        pick_pool = pick_pool.sort_values("mu_capm", ascending=False).head(50).reset_index(drop=True)
-        chosen = rerank_and_pick_one(pick_pool, universe_user, band)
+        pool = synth[(synth["sigma_hist"] >= lo) & (synth["sigma_hist"] <= hi)].copy()
+        note = ""
+        if pool.empty:
+            # Closest-available logic to prevent "Low" showing a high-vol pick
+            if band.lower() == "low":
+                pool = synth.nsmallest(50, "sigma_hist").copy()
+                note = " (closest available: min σ)"
+            elif band.lower() == "high":
+                pool = synth.nlargest(50, "sigma_hist").copy()
+                note = " (closest available: max σ)"
+            else:  # medium
+                tmp = synth.copy()
+                tmp["dist_med"] = (tmp["sigma_hist"] - sigma_mkt).abs()
+                pool = tmp.nsmallest(100, "dist_med").drop(columns=["dist_med"])
+                note = " (closest to market σ)"
+        chosen = rerank_and_pick_one(pool, universe_user, band)
+        if not chosen.empty:
+            chosen = chosen.copy()
+            chosen["__note__"] = note
         out[band.lower()] = chosen
     return out
 
@@ -458,15 +471,15 @@ def compute(
     symbols = [t for t in df["ticker"].tolist() if t]
     if len(symbols) == 0:
         return None, "Add at least one ticker.", "Universe empty.", empty_positions_df(), empty_suggestion_df(), None, \
-               "", "", "", None, None, None, None, None, None, None
+               "", "", "", None, None, None, None, None, None, None, None, None
 
     symbols = validate_tickers(symbols, years_lookback)
     if len(symbols) == 0:
         return None, "Could not validate any tickers.", "Universe invalid.", empty_positions_df(), empty_suggestion_df(), None, \
-               "", "", "", None, None, None, None, None, None, None
+               "", "", "", None, None, None, None, None, None, None, None, None
 
     global UNIVERSE
-    UNIVERSE = list(sorted(set(symbols)))[:MAX_TICKERS]  # keep market if present
+    UNIVERSE = list(sorted(set(symbols)))[:MAX_TICKERS]
 
     df = df[df["ticker"].isin(symbols)].copy()
     amounts = {r["ticker"]: float(r["amount_usd"]) for _, r in df.iterrows()}
@@ -480,7 +493,7 @@ def compute(
     gross = sum(abs(v) for v in amounts.values())
     if gross <= 1e-12:
         return None, "All amounts are zero.", "Universe ok.", empty_positions_df(), empty_suggestion_df(), None, \
-               "", "", "", None, None, None, None, None, None, None
+               "", "", "", None, None, None, None, None, None, None, None, None
     weights = {k: v / gross for k, v in amounts.items()}
 
     # Portfolio CAPM stats
@@ -504,7 +517,8 @@ def compute(
     def _fmt(row: pd.Series) -> str:
         if row is None or row.empty:
             return "No pick available."
-        return f"CAPM E[r] {row['mu_capm']*100:.2f}%, σ(h) {row['sigma_hist']*100:.2f}%"
+        note = str(row.get("__note__", "") or "")
+        return f"CAPM E[r] {row['mu_capm']*100:.2f}%, σ(h) {row['sigma_hist']*100:.2f}%{note}"
 
     txt_low   = _fmt(picks.get("low", pd.Series(dtype=object)))
     txt_med   = _fmt(picks.get("medium", pd.Series(dtype=object)))
@@ -519,6 +533,7 @@ def compute(
     else:
         chosen_sigma = float(chosen["sigma_hist"])
         chosen_mu = float(chosen["mu_capm"])
+        # holdings table from chosen suggestion
         sugg_table = _holdings_table_from_row(chosen, budget=gross)
 
     pos_table = pd.DataFrame(