research: add US alpha exploration scripts

research/run_interaction.py

@@ -0,0 +1,136 @@
+"""
+Evaluate interaction/ensemble strategies on 1/3/5/10y PIT windows with a
+proper 500-day warmup preload, so 252d-warmup strategies are active from the
+measurement start.
+"""
+
+from __future__ import annotations
+
+import os
+import warnings
+
+import pandas as pd
+
+import research.pit_backtest as pit
+from research.alpha_factors import AlphaFactorStrategy
+from research.interaction_alpha import (MultiplicativeFactorStrategy,
+                                          SubStrategyEnsemble, VotingFactorStrategy,
+                                          default_ensemble)
+from strategies.factor_combo import FactorComboStrategy
+from strategies.recovery_momentum import RecoveryMomentumStrategy
+
+warnings.filterwarnings("ignore", category=FutureWarning)
+warnings.filterwarnings("ignore", category=RuntimeWarning)
+
+DATA_DIR = "data"
+BENCHMARK = "SPY"
+
+
+def load():
+    raw = pit.load_pit_prices()
+    masked = pit.pit_universe(raw)
+    masked[BENCHMARK] = raw[BENCHMARK]
+    return masked
+
+
+def warmup_slice(df, years, warmup_days=500):
+    measurement_start = df.index[-1] - pd.DateOffset(years=years)
+    cutoff = max(df.index[0], measurement_start - pd.Timedelta(days=warmup_days * 1.5))
+    return df[df.index >= cutoff], measurement_start
+
+
+def measure(eq, start, name=""):
+    eq = eq[eq.index >= start]
+    eq = eq / eq.iloc[0] * 10_000
+    return pit.summarize(eq, name=name)
+
+
+def make_configs(mkt_ret):
+    pair = ["mom_12_1", "recovery_63"]
+    return {
+        "Mult(mom12×rec63) eq, tn=10":
+            lambda: MultiplicativeFactorStrategy(
+                factor_names=pair, top_n=10, rebal_freq=21, mkt_returns=mkt_ret),
+        "Mult(mom12×rec63) eq, tn=15":
+            lambda: MultiplicativeFactorStrategy(
+                factor_names=pair, top_n=15, rebal_freq=21, mkt_returns=mkt_ret),
+        "Mult(mom12×rec63) eq, rebal=10":
+            lambda: MultiplicativeFactorStrategy(
+                factor_names=pair, top_n=10, rebal_freq=10, mkt_returns=mkt_ret),
+        "Mult(mom12×rec63) sig^2, tn=15":
+            lambda: MultiplicativeFactorStrategy(
+                factor_names=pair, top_n=15, rebal_freq=21, mkt_returns=mkt_ret,
+                weighting="signal", signal_concentration=2.0),
+        "Mult(mom12×rec63) sig^4, tn=15":
+            lambda: MultiplicativeFactorStrategy(
+                factor_names=pair, top_n=15, rebal_freq=21, mkt_returns=mkt_ret,
+                weighting="signal", signal_concentration=4.0),
+        "Mult(mom12×rec63) disp-scale":
+            lambda: MultiplicativeFactorStrategy(
+                factor_names=pair, top_n=10, rebal_freq=21, mkt_returns=mkt_ret,
+                dispersion_scale=True),
+        "Mult(mom12×rec63) inv_vol":
+            lambda: MultiplicativeFactorStrategy(
+                factor_names=pair, top_n=10, rebal_freq=21, mkt_returns=mkt_ret,
+                weighting="inv_vol"),
+        "Ensemble3 (RM/upcap/mult)":
+            lambda: default_ensemble(mkt_ret),
+        "Recovery+Mom Top10":
+            lambda: RecoveryMomentumStrategy(top_n=10),
+        "fc_up_cap+mom_gap":
+            lambda: FactorComboStrategy("up_cap+mom_gap", rebal_freq=21, top_n=10),
+    }
+
+
+def main():
+    print("Loading PIT data…")
+    masked = load()
+    tickers = [c for c in masked.columns if c != BENCHMARK]
+    mkt_ret = masked[BENCHMARK].pct_change(fill_method=None)
+    print(f"  shape={masked.shape} range={masked.index[0].date()} → {masked.index[-1].date()}")
+
+    rows = []
+    for years in (10, 5, 3, 1):
+        sliced, start = warmup_slice(masked, years, warmup_days=500)
+        prices = sliced[tickers]
+        print(f"\n--- {years}y window "
+              f"(measure {start.date()} → {sliced.index[-1].date()}, "
+              f"warmup from {sliced.index[0].date()}) ---")
+        spy = sliced[BENCHMARK].dropna()
+        spy_eq = (spy / spy.iloc[0]) * 10_000
+        m = measure(spy_eq, start, "")
+        rows.append({"years": years, "strategy": "SPY buy-and-hold",
+                     **{k: v for k, v in m.items() if k != "name"}})
+        configs = make_configs(mkt_ret)
+        for name, factory in configs.items():
+            strat = factory()
+            eq = pit.backtest(strategy=strat, prices=prices,
+                               initial_capital=10_000, transaction_cost=0.001)
+            m = measure(eq, start, "")
+            rows.append({"years": years, "strategy": name,
+                         **{k: v for k, v in m.items() if k != "name"}})
+        tail = [r for r in rows if r["years"] == years]
+        tail.sort(key=lambda r: r["Sharpe"], reverse=True)
+        for r in tail:
+            print(f"  {r['strategy']:<34s} CAGR={r['CAGR']*100:>6.1f}%  "
+                  f"Sharpe={r['Sharpe']:>5.2f}  Sortino={r['Sortino']:>5.2f}  "
+                  f"MaxDD={r['MaxDD']*100:>6.1f}%  Calmar={r['Calmar']:>5.2f}")
+
+    df = pd.DataFrame(rows)
+    df.to_csv(os.path.join(DATA_DIR, "interaction_results.csv"), index=False)
+
+    print("\n=== Cross-window CAGR summary (sorted by 10y Sharpe) ===")
+    pv = df.pivot(index="strategy", columns="years", values="CAGR")
+    pv.columns = [f"CAGR_{y}y" for y in pv.columns]
+    sh10 = df[df["years"] == 10].set_index("strategy")["Sharpe"]
+    pv["Sharpe_10y"] = sh10
+    pv = pv.sort_values("Sharpe_10y", ascending=False)
+    print(pv.to_string(formatters={
+        "CAGR_10y": "{:.1%}".format, "CAGR_5y": "{:.1%}".format,
+        "CAGR_3y": "{:.1%}".format, "CAGR_1y": "{:.1%}".format,
+        "Sharpe_10y": "{:.2f}".format,
+    }))
+
+
+if __name__ == "__main__":
+    main()