feat: signal abstraction layer + sizer + HS300 universe + PnL/IC reports

run_example.py

@@ -1,25 +1,89 @@
 #!/usr/bin/env python3
-"""End-to-end smoke test: download data -> backtest 5-day reversal -> print results."""
+"""End-to-end pipeline: HS300 universe -> reversal signal -> cross-sectional IC
+-> multi-stock backtest (AlphaStrategy + PercentSizer) -> reports.
+
+Note: this runs the first 30 HS300 constituents to keep runtime manageable.
+Downloading daily bars for the full ~300 names takes roughly 10 minutes.
+"""
 import logging
+
+import pandas as pd
+
+from analysis.report import generate_report
 from backtest.config import BacktestConfig
 from backtest.runner import BacktestRunner
-from strategies.reversal import FiveDayReversal
-from analysis.report import print_results
+from data.downloader import download_batch
+from data.universe import SYMBOLS
+from eval.metrics import evaluate_cross_sectional
+from portfolio.builder import ThresholdBuilder
+from signals.reversal import ReversalSignal
+from strategies.alpha_strategy import AlphaStrategy
 
 logging.basicConfig(level=logging.INFO, format="%(asctime)s [%(levelname)s] %(message)s")
+logger = logging.getLogger(__name__)
 
 
 def main():
+    symbols = SYMBOLS[:30]
+    start, end = "2023-01-01", "2024-12-31"
+    initial_cash = 1_000_000
+
+    # 1-2. Download daily data for the universe.
+    data = download_batch(symbols, start, end)
+    data = {s: df for s, df in data.items() if df is not None and not df.empty}
+    logger.info(f"Downloaded {len(data)}/{len(symbols)} symbols")
+
+    # 3. Compute the reversal signal per stock.
+    signal = ReversalSignal(lookback=5)
+    signal_series: dict[str, pd.Series] = {}
+    forward_returns: dict[str, pd.Series] = {}
+    for sym, df in data.items():
+        idx = pd.to_datetime(df["date"])
+        sig = signal.compute(df)
+        sig.index = idx
+        signal_series[sym] = sig
+        fwd = df["close"].pct_change().shift(-1)  # next-day return
+        fwd.index = idx
+        forward_returns[sym] = fwd
+
+    # 4. Cross-sectional IC evaluation.
+    signals_df = pd.DataFrame(signal_series)
+    returns_df = pd.DataFrame(forward_returns)
+    signal_eval = evaluate_cross_sectional(signals_df, returns_df)
+
+    # 5. Attach the signal column to each DataFrame and build feeds.
     config = BacktestConfig(
-        symbols=["sh600000", "sz000001", "sh600519"],  # 浦发银行, 平安银行, 贵州茅台
-        start_date="2023-01-01",
-        end_date="2024-12-31",
-        initial_cash=1_000_000,
+        symbols=list(data.keys()),
+        start_date=start,
+        end_date=end,
+        initial_cash=initial_cash,
+        sizer_percent=0.95,
+    )
+    runner = BacktestRunner(config)
+    builder = ThresholdBuilder(buy_threshold=0.02, sell_threshold=-0.02, size_pct=0.95)
+    for sym, df in data.items():
+        df = df.copy()
+        df["signal"] = signal.compute(df).values
+        runner.add_signal_data(df, name=sym)
+
+    # 6. Run the multi-stock backtest.
+    results = runner.run_prepared(AlphaStrategy, {"builder": builder})
+
+    # 7. Reports.
+    artifacts = generate_report(
+        results, signal_eval, output_dir="reports/", initial_cash=initial_cash
     )
 
-    runner = BacktestRunner(config)
-    results = runner.run(FiveDayReversal)
-    print_results(results, config.initial_cash)
+    # 8. Print summary.
+    print("\nSIGNAL IC")
+    print("=" * 50)
+    print(f"IC mean / std / IR:       {signal_eval['ic_mean']:.4f} / "
+          f"{signal_eval['ic_std']:.4f} / {signal_eval['ir']:.4f}")
+    print(f"Rank IC mean / std / IR:  {signal_eval['rank_ic_mean']:.4f} / "
+          f"{signal_eval['rank_ic_std']:.4f} / {signal_eval['rank_ir']:.4f}")
+    print(f"Hit rate:                 {signal_eval['hit_rate']:.2%}")
+    print(f"Periods:                  {signal_eval['n_periods']}")
+    print(f"\nReports written to: {artifacts}")
 
 
 if __name__ == "__main__":