research(wave-0822): VOL-SIZE — il p-value del null di permutazione si cita col segno, non col decimale (3 ancore su 23)

scripts/research/r0822_basis_calendar.py

@@ -318,6 +318,14 @@ def certify(asset: str, wide: pd.DataFrame, vwide: pd.DataFrame, meta: pd.DataFr
         print(f"  convergenza a scadenza |ln(F/indice)| ultima ora: "
               f"mediana {np.median(conv):.1f} bps, max {np.max(conv):.1f} bps  (n={len(conv)})")
 
+    # (c-bis) scarto PERP vs INDICE: la gamba FvP lo assume piccolo, quindi si misura
+    pj = perp.reindex(fund.set_index("ts").index).dropna()
+    if len(pj) > 1000:
+        ii = fund.set_index("ts")["index"].reindex(pj.index)
+        pb = (np.log(pj / ii) * 1e4).replace([np.inf, -np.inf], np.nan).dropna()
+        print(f"  perp vs indice: mediana {pb.median():+.1f} bps, p95 |scarto| "
+              f"{pb.abs().quantile(0.95):.1f} bps  (n={len(pb):,}) — la gamba FvP e' sul PERP")
+
     # (d) CROSS-CHECK INDIPENDENTE: il forward implicito nella catena opzioni
     xchk = cross_check_option_forward(asset, wide, ok)
     return dict(flat=fb, vol=vb, conv=conv, xchk=xchk)
@@ -370,7 +378,8 @@ def cross_check_option_forward(asset: str, wide: pd.DataFrame, meta: pd.DataFram
 # 2. CURVA — front/back trimestrali, basis annualizzato, slope forward
 # ==========================================================================
 def curve_frame(asset: str, wide: pd.DataFrame, meta: pd.DataFrame,
-                fund: pd.DataFrame, roll_dte: int) -> pd.DataFrame:
+                fund: pd.DataFrame, roll_dte: int,
+                perp: pd.Series | None = None) -> pd.DataFrame:
     """Per ogni ora: front = trimestrale piu' vicino con dte >= roll_dte, back = il successivo.
     Ritorna prezzi, tau, basis annualizzati, slope forward e funding."""
     ok = meta[meta.status == "ok"].sort_values("exp")
@@ -408,6 +417,15 @@ def curve_frame(asset: str, wide: pd.DataFrame, meta: pd.DataFrame,
     out["tau_front_h"], out["tau_back_h"] = tf, tb
     out["index"] = F["index"].values
     out["f1h"] = F["f1h"].values
+    # gamba perp: il PERP CERTIFICATO, non l'indice (l'indice non si compra).
+    # fallback all'indice solo se il perp non copre l'ora, e lo si dichiara.
+    if perp is not None:
+        pp = perp.reindex(idx)
+        out["perp"] = pp.where(pp.notna(), out["index"]).values
+        out["perp_from_index"] = pp.isna().values
+    else:
+        out["perp"] = out["index"].values
+        out["perp_from_index"] = True
     # basis annualizzato di ciascuna gamba vs INDICE
     out["c_front"] = np.log(Ff / out["index"]) * HOURS_Y / tf
     out["c_back"] = np.log(Fb / out["index"]) * HOURS_Y / tb
@@ -532,7 +550,7 @@ def run_strategy(cv: pd.DataFrame, ctx: dict, family: str, sig: str,
     turn = np.abs(dP).sum(axis=1)
 
     if family == "FvP":
-        perp_r = np.nan_to_num(cv["index"].pct_change().values, nan=0.0)
+        perp_r = np.nan_to_num(cv["perp"].pct_change().values, nan=0.0)
         f1h = np.nan_to_num(cv["f1h"].values, nan=0.0)
         wheld = held.sum(axis=1)                        # una sola gamba datata
         # long datato => short perp: guadagna -w*perp_r e INCASSA w*funding
@@ -609,11 +627,14 @@ def main() -> None:
 
     # ---------------- STEP 2: certificazione ----------------
     print("\n[2] CERTIFICAZIONE (regola 4: un edge su un book fermo non e' un edge)")
-    certs = {}
+    certs, perps = {}, {}
     for a in ASSETS:
-        perp = A.get(a, "1h").set_index(pd.DatetimeIndex(
-            pd.to_datetime(A.get(a, "1h")["datetime"], utc=True)))["close"]
-        certs[a] = certify(a, panels[a], vwides[a], metas[a], funds[a], perp)
+        pdf = A.get(a, "1h")
+        perps[a] = pd.Series(
+            pdf["close"].astype(float).values,
+            index=pd.DatetimeIndex(pd.to_datetime(pdf["datetime"], utc=True))).sort_index()
+        perps[a] = perps[a][~perps[a].index.duplicated()]
+        certs[a] = certify(a, panels[a], vwides[a], metas[a], funds[a], perps[a])
         x = certs[a]["xchk"]
         if x.get("status") == "ok" and len(x["table"]):
             t = x["table"]
@@ -628,7 +649,7 @@ def main() -> None:
     print("\n[3] Q1 — LA CURVA E' PREVEDIBILE?")
     curves = {}
     for a in ASSETS:
-        cv = curve_frame(a, panels[a], metas[a], funds[a], roll_dte=7)
+        cv = curve_frame(a, panels[a], metas[a], funds[a], roll_dte=7, perp=perps[a])
         curves[a] = cv
         describe_curve(a, cv)
 
@@ -665,7 +686,7 @@ def main() -> None:
           f" le conto lo stesso, al rialzo)")
 
     ctxs = {a: asset_ctx(panels[a]) for a in ASSETS}
-    cvcache = {(a, rl): curve_frame(a, panels[a], metas[a], funds[a], rl)
+    cvcache = {(a, rl): curve_frame(a, panels[a], metas[a], funds[a], rl, perp=perps[a])
                for a in ASSETS for rl in ROLLS}
     pidx = {(a, rl): pair_idx(cvcache[(a, rl)], ctxs[a]) for a in ASSETS for rl in ROLLS}