feat: add PIT OHLCV runner and fetch support

research/us_alpha_pipeline.py

@@ -1,6 +1,8 @@
 import numpy as np
 import pandas as pd
 
+import data_manager
+import universe_history as uh
 from research.event_factors import breakout_after_compression_score
 from research.regime_filters import build_regime_filter
 from research.us_alpha_report import summarize_equity_window
@@ -16,6 +18,7 @@ LIQUIDITY_WINDOW = 60
 TREND_WINDOW = 126
 RECOVERY_WINDOW = 63
 HIGH_PROX_WINDOW = 126
+ETF_TICKERS = ["SPY", "QQQ", "IWM", "MDY", "XLK", "XLF", "XLI", "XLV"]
 
 
 def _price_rank_blend_score(close: pd.DataFrame) -> pd.DataFrame:
@@ -51,10 +54,36 @@ def _build_equal_weight_portfolio(
 def _equity_curve(close: pd.DataFrame, weights: pd.DataFrame) -> pd.Series:
     """Convert daily weights into a simple close-to-close equity curve."""
     returns = close.pct_change(fill_method=None).fillna(0.0)
-    portfolio_returns = (returns * weights.shift(1).fillna(0.0)).sum(axis=1)
+    portfolio_returns = (returns * weights).sum(axis=1)
     return (1.0 + portfolio_returns).cumprod()
 
 
+def _read_panel_csv(path: str) -> pd.DataFrame:
+    return pd.read_csv(path, index_col=0, parse_dates=True).sort_index()
+
+
+def load_saved_pit_market_data(data_dir: str = "data", prefix: str = "us_pit") -> dict[str, pd.DataFrame]:
+    """Load saved PIT OHLCV panels from disk."""
+    panels = {}
+    for field in ("close", "high", "low", "volume"):
+        panels[field] = _read_panel_csv(f"{data_dir}/{prefix}_{field}.csv")
+    return panels
+
+
+def load_saved_etf_close(data_dir: str = "data", market: str = "us_etf") -> pd.DataFrame:
+    """Load saved ETF closes or populate them on demand."""
+    path = f"{data_dir}/{market}.csv"
+    try:
+        return _read_panel_csv(path)
+    except FileNotFoundError:
+        original_data_dir = data_manager.DATA_DIR
+        try:
+            data_manager.DATA_DIR = data_dir
+            return data_manager.update_market_data(market, ETF_TICKERS, ["close"])["close"]
+        finally:
+            data_manager.DATA_DIR = original_data_dir
+
+
 def run_alpha_pipeline(
     market_data,
     etf_close,
@@ -93,3 +122,35 @@ def run_alpha_pipeline(
             summary_rows.append(summarize_equity_window(equity, strategy_name, window_years))
 
     return pd.DataFrame(summary_rows)
+
+
+def run_saved_pit_alpha_pipeline(
+    data_dir: str = "data",
+    windows=(1, 2, 3, 5, 10),
+    top_n: int = 10,
+) -> pd.DataFrame:
+    """Load saved PIT OHLCV inputs and run the strict alpha pipeline."""
+    market_data = load_saved_pit_market_data(data_dir=data_dir)
+    etf_close = load_saved_etf_close(data_dir=data_dir)
+    intervals = uh.load_sp500_history()
+    pit_membership = uh.membership_mask(
+        market_data["close"].index,
+        intervals=intervals,
+        tickers=list(market_data["close"].columns),
+    )
+    return run_alpha_pipeline(
+        market_data=market_data,
+        etf_close=etf_close,
+        pit_membership=pit_membership,
+        windows=windows,
+        top_n=top_n,
+    )
+
+
+def main() -> None:
+    summary = run_saved_pit_alpha_pipeline()
+    print(summary.to_string(index=False))
+
+
+if __name__ == "__main__":
+    main()