feat: dump alpha values + daily PnL as parquet (pyarrow)

analysis/report.py

@@ -122,6 +122,51 @@ def plot_ic(signal_eval: dict, output_path: str = "reports/ic.png") -> str:
     return output_path
 
 
+def dump_signals(signals_df: pd.DataFrame, output_dir: str = "results/") -> str:
+    """Save the signal matrix (date x stock) as a parquet file.
+
+    Args:
+        signals_df: Date-indexed DataFrame of per-stock signal values.
+        output_dir: Directory to write the parquet file into.
+
+    Returns:
+        The path the parquet file was written to.
+    """
+    os.makedirs(output_dir, exist_ok=True)
+    path = os.path.join(output_dir, "signals.parquet")
+    signals_df.to_parquet(path)
+    return path
+
+
+def dump_daily_pnl(
+    results: list, output_dir: str = "results/", initial_cash: float = 1_000_000.0
+) -> str:
+    """Extract the daily portfolio value from a backtest run and save as parquet.
+
+    Compounds the per-day TimeReturn analyzer into an equity curve.
+
+    Args:
+        results: The list returned by ``cerebro.run()``.
+        output_dir: Directory to write the parquet file into.
+        initial_cash: Starting portfolio value for scaling the curve.
+
+    Returns:
+        The path the parquet file was written to.
+    """
+    os.makedirs(output_dir, exist_ok=True)
+    series = pd.Series(dtype=float)
+    if results:
+        tr = results[0].analyzers.timereturn.get_analysis()
+        series = pd.Series(tr).sort_index()
+
+    equity = (1.0 + series).cumprod() * initial_cash
+    pnl_df = pd.DataFrame({"date": equity.index, "value": equity.values})
+
+    path = os.path.join(output_dir, "daily_pnl.parquet")
+    pnl_df.to_parquet(path)
+    return path
+
+
 def generate_report(
     results: list,
     signal_eval: dict,