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

analysis/report.py

@@ -1,6 +1,13 @@
 """Performance analysis and reporting for backtest results."""
+import os
 from typing import Any
 
+import matplotlib
+
+matplotlib.use("Agg")
+import matplotlib.pyplot as plt  # noqa: E402
+import pandas as pd  # noqa: E402
+
 
 def print_results(results: list, initial_cash: float = 1_000_000.0) -> dict[str, Any]:
     """Print and return key performance metrics from a backtrader run result."""
@@ -44,3 +51,109 @@ def print_results(results: list, initial_cash: float = 1_000_000.0) -> dict[str,
     print("=" * 50)
 
     return report
+
+
+def plot_accumulated_pnl(
+    results: list, output_path: str = "reports/pnl.png", initial_cash: float = 1_000_000.0
+) -> str:
+    """Plot accumulated portfolio value from a backtest run.
+
+    Reads the per-day TimeReturn analyzer attached by ``BacktestRunner`` and
+    compounds it into an equity curve.
+
+    Args:
+        results: The list returned by ``cerebro.run()``.
+        output_path: Destination PNG path.
+        initial_cash: Starting portfolio value for scaling the curve.
+
+    Returns:
+        The path the chart was written to.
+    """
+    os.makedirs(os.path.dirname(output_path) or ".", exist_ok=True)
+    series = pd.Series(dtype=float)
+    if results:
+        tr = results[0].analyzers.timereturn.get_analysis()
+        series = pd.Series(tr).sort_index()
+
+    fig, ax = plt.subplots(figsize=(10, 5))
+    if len(series):
+        equity = (1.0 + series).cumprod() * initial_cash
+        ax.plot(equity.index, equity.values, color="C0")
+    ax.set_title("Accumulated Portfolio Value")
+    ax.set_xlabel("Date")
+    ax.set_ylabel("Value")
+    ax.grid(True, alpha=0.3)
+    fig.autofmt_xdate()
+    fig.tight_layout()
+    fig.savefig(output_path, dpi=100)
+    plt.close(fig)
+    return output_path
+
+
+def plot_ic(signal_eval: dict, output_path: str = "reports/ic.png") -> str:
+    """Plot the per-period rank IC time series from a signal evaluation.
+
+    Args:
+        signal_eval: Dict returned by ``evaluate_cross_sectional`` (expects a
+            ``rank_ic_series`` pandas Series).
+        output_path: Destination PNG path.
+
+    Returns:
+        The path the chart was written to.
+    """
+    os.makedirs(os.path.dirname(output_path) or ".", exist_ok=True)
+    rank_ic = signal_eval.get("rank_ic_series", pd.Series(dtype=float))
+
+    fig, ax = plt.subplots(figsize=(10, 5))
+    if len(rank_ic):
+        ax.bar(rank_ic.index, rank_ic.values, width=1.0, color="C1", alpha=0.6, label="Rank IC")
+        ax.axhline(rank_ic.mean(), color="C3", linestyle="--", label=f"mean={rank_ic.mean():.3f}")
+        ax.legend()
+    ax.set_title("Cross-Sectional Rank IC")
+    ax.set_xlabel("Date")
+    ax.set_ylabel("Rank IC")
+    ax.grid(True, alpha=0.3)
+    fig.autofmt_xdate()
+    fig.tight_layout()
+    fig.savefig(output_path, dpi=100)
+    plt.close(fig)
+    return output_path
+
+
+def generate_report(
+    results: list,
+    signal_eval: dict,
+    output_dir: str = "reports/",
+    initial_cash: float = 1_000_000.0,
+) -> dict[str, str]:
+    """Generate the full report: PnL chart, IC chart, and a summary text file.
+
+    Args:
+        results: The list returned by ``cerebro.run()``.
+        signal_eval: Dict returned by ``evaluate_cross_sectional``.
+        output_dir: Directory to write artifacts into.
+        initial_cash: Starting portfolio value.
+
+    Returns:
+        Mapping of artifact name to file path.
+    """
+    os.makedirs(output_dir, exist_ok=True)
+    pnl_path = plot_accumulated_pnl(
+        results, os.path.join(output_dir, "pnl.png"), initial_cash
+    )
+    ic_path = plot_ic(signal_eval, os.path.join(output_dir, "ic.png"))
+
+    metrics = print_results(results, initial_cash)
+    summary_path = os.path.join(output_dir, "summary.txt")
+    with open(summary_path, "w") as f:
+        f.write("BACKTEST SUMMARY\n")
+        f.write("=" * 40 + "\n")
+        for k, v in metrics.items():
+            f.write(f"{k}: {v}\n")
+        f.write("\nSIGNAL IC\n")
+        f.write("=" * 40 + "\n")
+        for k in ("ic_mean", "ic_std", "ir", "rank_ic_mean", "rank_ic_std", "rank_ir", "hit_rate", "n_periods"):
+            if k in signal_eval:
+                f.write(f"{k}: {signal_eval[k]}\n")
+
+    return {"pnl": pnl_path, "ic": ic_path, "summary": summary_path}

backtest/config.py

@@ -11,3 +11,4 @@ class BacktestConfig:
     commission: float = 0.0003  # 0.03% for Chinese A-shares
     stamp_duty: float = 0.001   # 0.1% stamp duty on sells only (handled in strategy)
     adjust: str = "qfq"
+    sizer_percent: float = 0.95  # fraction of portfolio per trade

backtest/feed.py

@@ -10,3 +10,26 @@ def df_to_bt_feed(df: pd.DataFrame) -> bt.feeds.PandasData:
     df = df.set_index("date")
     df = df[["open", "high", "low", "close", "volume"]]
     return bt.feeds.PandasData(dataname=df)
+
+
+class SignalPandasData(bt.feeds.PandasData):
+    """PandasData feed carrying an extra ``signal`` line alongside OHLCV."""
+
+    lines = ("signal",)
+    params = (("signal", -1),)  # -1 -> match by column name
+
+
+def df_to_signal_feed(df: pd.DataFrame) -> "SignalPandasData":
+    """Convert an OHLCV+signal DataFrame to a SignalPandasData feed.
+
+    Args:
+        df: DataFrame with ``date``, OHLCV columns, and a ``signal`` column.
+
+    Returns:
+        A SignalPandasData feed (NaN signals are preserved for the strategy to skip).
+    """
+    df = df.copy()
+    df["date"] = pd.to_datetime(df["date"])
+    df = df.set_index("date")
+    df = df[["open", "high", "low", "close", "volume", "signal"]]
+    return SignalPandasData(dataname=df)

backtest/runner.py

@@ -4,7 +4,7 @@ import backtrader as bt
 from typing import Optional
 
 from backtest.config import BacktestConfig
-from backtest.feed import df_to_bt_feed
+from backtest.feed import df_to_bt_feed, df_to_signal_feed
 from data.downloader import download_daily
 
 logger = logging.getLogger(__name__)
@@ -30,33 +30,49 @@ class BacktestRunner:
         self.cerebro.adddata(feed, name=symbol)
         logger.info(f"Added {symbol}: {len(df)} bars")
 
+    def add_signal_data(self, df, name: str) -> None:
+        """Add a pre-built OHLCV+signal DataFrame as a SignalPandasData feed."""
+        feed = df_to_signal_feed(df)
+        self.cerebro.adddata(feed, name=name)
+        logger.info(f"Added signal feed {name}: {len(df)} bars")
+
     def add_strategy(self, strategy_cls, **kwargs) -> None:
         """Add a strategy class to cerebro."""
         self.cerebro.addstrategy(strategy_cls, **kwargs)
 
-    def setup(self, strategy_cls, strategy_kwargs: Optional[dict] = None) -> None:
-        """Full setup: load data for all symbols, configure cerebro, add strategy."""
-        # Load data for all symbols
-        for sym in self.config.symbols:
-            self.add_data(sym)
-
-        # Configure cerebro
+    def _configure(self) -> None:
+        """Configure broker, sizer, and analyzers (independent of data feeds)."""
         self.cerebro.broker.setcash(self.config.initial_cash)
         self.cerebro.broker.setcommission(commission=self.config.commission)
+        self.cerebro.addsizer(bt.sizers.PercentSizer, percents=self.config.sizer_percent * 100)
 
-        # Add analyzers
         self.cerebro.addanalyzer(bt.analyzers.SharpeRatio, _name="sharpe", riskfreerate=0.02)
         self.cerebro.addanalyzer(bt.analyzers.DrawDown, _name="drawdown")
         self.cerebro.addanalyzer(bt.analyzers.Returns, _name="returns")
         self.cerebro.addanalyzer(bt.analyzers.TradeAnalyzer, _name="trades")
+        self.cerebro.addanalyzer(
+            bt.analyzers.TimeReturn, _name="timereturn", timeframe=bt.TimeFrame.Days
+        )
 
-        # Add strategy
-        strategy_kwargs = strategy_kwargs or {}
-        self.cerebro.addstrategy(strategy_cls, **strategy_kwargs)
+    def setup(self, strategy_cls, strategy_kwargs: Optional[dict] = None) -> None:
+        """Full setup: load data for all symbols, configure cerebro, add strategy."""
+        for sym in self.config.symbols:
+            self.add_data(sym)
+        self._configure()
+        self.cerebro.addstrategy(strategy_cls, **(strategy_kwargs or {}))
 
     def run(self, strategy_cls, strategy_kwargs: Optional[dict] = None) -> list:
-        """Setup and run the backtest. Returns cerebro run results."""
+        """Setup (downloading all symbols) and run the backtest."""
         self.setup(strategy_cls, strategy_kwargs)
+        return self._execute()
+
+    def run_prepared(self, strategy_cls, strategy_kwargs: Optional[dict] = None) -> list:
+        """Run a backtest using feeds already added via ``add_signal_data``."""
+        self._configure()
+        self.cerebro.addstrategy(strategy_cls, **(strategy_kwargs or {}))
+        return self._execute()
+
+    def _execute(self) -> list:
         start_val = self.cerebro.broker.getvalue()
         logger.info(f"Starting portfolio value: {start_val:,.2f}")
         self._results = self.cerebro.run()

data/universe.py

@@ -0,0 +1,38 @@
+"""CSI 300 (HS300) universe helpers."""
+import logging
+
+import baostock as bs
+import pandas as pd
+
+logger = logging.getLogger(__name__)
+
+# First 30 HS300 constituents (large caps) in 'shXXXXXX' / 'szXXXXXX' format.
+# Hardcoded for fast, deterministic smoke tests. Use get_hs300_stocks() for the
+# live, full list — downloading daily bars for all ~300 takes roughly 10 minutes.
+SYMBOLS = [
+    "sh600000", "sh600009", "sh600010", "sh600028", "sh600030",
+    "sh600036", "sh600048", "sh600050", "sh600104", "sh600276",
+    "sh600309", "sh600519", "sh600585", "sh600887", "sh600900",
+    "sh601012", "sh601166", "sh601288", "sh601318", "sh601398",
+    "sh601628", "sh601668", "sh601857", "sh601888", "sh601988",
+    "sz000001", "sz000002", "sz000333", "sz000651", "sz000858",
+]
+
+
+def get_hs300_stocks() -> pd.DataFrame:
+    """Fetch the current CSI 300 constituents from baostock.
+
+    Returns:
+        DataFrame with columns ``code`` (e.g. ``sh600000``), ``name``, ``date``.
+    """
+    bs.login()
+    try:
+        rs = bs.query_hs300_stocks()
+        stocks = []
+        while rs.next():
+            stocks.append(rs.get_row_data())
+    finally:
+        bs.logout()
+    df = pd.DataFrame(stocks, columns=["code", "name", "date"])
+    df["code"] = df["code"].str.replace(".", "", regex=False)
+    return df

eval/__init__.py

@@ -0,0 +1,4 @@
+"""Signal evaluation metrics."""
+from eval.metrics import evaluate_cross_sectional
+
+__all__ = ["evaluate_cross_sectional"]

eval/metrics.py

@@ -0,0 +1,90 @@
+"""Information-coefficient metrics for alpha signals."""
+from typing import Any
+
+import pandas as pd
+
+
+def _summarize(ic: pd.Series, rank_ic: pd.Series) -> dict[str, Any]:
+    """Aggregate per-period IC series into summary statistics."""
+    ic = ic.dropna()
+    rank_ic = rank_ic.dropna()
+
+    ic_mean = float(ic.mean()) if len(ic) else float("nan")
+    ic_std = float(ic.std()) if len(ic) else float("nan")
+    rank_ic_mean = float(rank_ic.mean()) if len(rank_ic) else float("nan")
+    rank_ic_std = float(rank_ic.std()) if len(rank_ic) else float("nan")
+
+    return {
+        "ic_mean": ic_mean,
+        "ic_std": ic_std,
+        "ir": ic_mean / ic_std if ic_std else float("nan"),
+        "rank_ic_mean": rank_ic_mean,
+        "rank_ic_std": rank_ic_std,
+        "rank_ir": rank_ic_mean / rank_ic_std if rank_ic_std else float("nan"),
+        "hit_rate": float((rank_ic > 0).mean()) if len(rank_ic) else float("nan"),
+        "n_periods": int(len(rank_ic)),
+        "ic_series": ic,
+        "rank_ic_series": rank_ic,
+    }
+
+
+def _cross_sectional(signals_df: pd.DataFrame, returns_df: pd.DataFrame) -> dict[str, Any]:
+    """Per-date IC across stocks (requires >= 2 stocks)."""
+    dates = signals_df.index
+    ic_vals, rank_ic_vals, idx = [], [], []
+    for dt in dates:
+        s = signals_df.loc[dt]
+        r = returns_df.loc[dt]
+        mask = s.notna() & r.notna()
+        if mask.sum() < 2:
+            continue
+        sv, rv = s[mask], r[mask]
+        # A degenerate (constant) vector makes correlation undefined.
+        if sv.nunique() < 2 or rv.nunique() < 2:
+            continue
+        ic_vals.append(sv.corr(rv))
+        rank_ic_vals.append(sv.corr(rv, method="spearman"))
+        idx.append(dt)
+    ic = pd.Series(ic_vals, index=idx, dtype=float)
+    rank_ic = pd.Series(rank_ic_vals, index=idx, dtype=float)
+    return _summarize(ic, rank_ic)
+
+
+def _rolling_single(
+    signals_df: pd.DataFrame, returns_df: pd.DataFrame, window: int = 20
+) -> dict[str, Any]:
+    """Rolling time-series IC for the single-stock case.
+
+    With one stock there is no cross-section, so we measure how well the signal
+    tracks forward returns over a trailing window instead.
+    """
+    col = signals_df.columns[0]
+    s = signals_df[col]
+    r = returns_df[col]
+    ic = s.rolling(window).corr(r)
+    rank_ic = s.rank().rolling(window).corr(r.rank())
+    return _summarize(ic, rank_ic)
+
+
+def evaluate_cross_sectional(
+    signals_df: pd.DataFrame, returns_df: pd.DataFrame
+) -> dict[str, Any]:
+    """Evaluate a signal's predictive power against forward returns.
+
+    Args:
+        signals_df: DataFrame indexed by date, one column per stock, signal values.
+        returns_df: DataFrame indexed by date, one column per stock, forward returns.
+
+    Returns:
+        Dict with ``ic_mean``, ``ic_std``, ``ir``, ``rank_ic_mean``,
+        ``rank_ic_std``, ``rank_ir``, ``hit_rate``, ``n_periods`` and the
+        per-period ``ic_series`` / ``rank_ic_series`` (for plotting).
+    """
+    cols = signals_df.columns.intersection(returns_df.columns)
+    idx = signals_df.index.intersection(returns_df.index)
+    signals_df = signals_df.loc[idx, cols]
+    returns_df = returns_df.loc[idx, cols]
+
+    if len(cols) >= 2:
+        return _cross_sectional(signals_df, returns_df)
+    return _rolling_single(signals_df, returns_df)

portfolio/__init__.py

@@ -0,0 +1,4 @@
+"""Translate signal values into position actions."""
+from portfolio.builder import PositionAction, ThresholdBuilder
+
+__all__ = ["PositionAction", "ThresholdBuilder"]

portfolio/builder.py

@@ -0,0 +1,40 @@
+"""Map signal values to discrete position actions."""
+from dataclasses import dataclass
+
+
+@dataclass
+class PositionAction:
+    """A target action for a single stock on a single bar."""
+
+    action: str  # "buy", "sell", or "hold"
+    size_pct: float = 0.0  # target portfolio fraction for buys
+
+
+class ThresholdBuilder:
+    """Open on strong positive signal, close on strong negative signal."""
+
+    def __init__(
+        self,
+        buy_threshold: float = 0.02,
+        sell_threshold: float = -0.02,
+        size_pct: float = 0.95,
+    ):
+        self.buy_threshold = buy_threshold
+        self.sell_threshold = sell_threshold
+        self.size_pct = size_pct
+
+    def build(self, signal_value: float, in_position: bool) -> PositionAction:
+        """Decide what to do given the current signal and position state.
+
+        Args:
+            signal_value: Latest signal value for the stock.
+            in_position: Whether the portfolio currently holds the stock.
+
+        Returns:
+            The action to take ("buy", "sell", or "hold").
+        """
+        if not in_position and signal_value >= self.buy_threshold:
+            return PositionAction("buy", self.size_pct)
+        if in_position and signal_value <= self.sell_threshold:
+            return PositionAction("sell", 0.0)
+        return PositionAction("hold", 0.0)

reports/summary.txt

@@ -0,0 +1,21 @@
+BACKTEST SUMMARY
+========================================
+sharpe: -5.633716896325243
+max_drawdown: 48.659457956769764
+max_drawdown_len: 451
+total_return: -0.48968077055625825
+avg_return: -0.0010117371292484674
+total_trades: 33
+won_trades: 20
+lost_trades: 12
+
+SIGNAL IC
+========================================
+ic_mean: -0.006912277738865651
+ic_std: 0.3332983458971776
+ir: -0.020739010030965125
+rank_ic_mean: -0.006980297831283274
+rank_ic_std: 0.32283972442680237
+rank_ir: -0.02162155801513181
+hit_rate: 0.4811715481171548
+n_periods: 478

requirements.txt

@@ -2,4 +2,5 @@ backtrader>=1.9.76.123
 akshare>=1.14.0
 baostock>=0.8.8
 pandas>=2.0.0
+matplotlib>=3.7.0
 pytest>=7.0.0

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__":

signals/__init__.py

@@ -0,0 +1,5 @@
+"""Alpha signal abstractions."""
+from signals.base import AlphaSignal
+from signals.reversal import ReversalSignal
+
+__all__ = ["AlphaSignal", "ReversalSignal"]

signals/base.py

@@ -0,0 +1,28 @@
+"""Base class for cross-sectional alpha signals."""
+from abc import ABC, abstractmethod
+
+import pandas as pd
+
+
+class AlphaSignal(ABC):
+    """A signal that maps a single stock's OHLCV history to a per-bar score.
+
+    Higher scores indicate a stronger expected forward return. Implementations
+    operate on one stock at a time; cross-sectional ranking happens downstream.
+    """
+
+    @abstractmethod
+    def compute(self, df: pd.DataFrame) -> pd.Series:
+        """Compute the signal for one stock.
+
+        Args:
+            df: OHLCV DataFrame with at least a ``close`` column, ordered by date.
+
+        Returns:
+            Signal series aligned to ``df`` (NaN where undefined).
+        """
+
+    @property
+    @abstractmethod
+    def name(self) -> str:
+        """Human-readable signal identifier."""

signals/reversal.py

@@ -0,0 +1,22 @@
+"""Short-horizon reversal signal."""
+import pandas as pd
+
+from signals.base import AlphaSignal
+
+
+class ReversalSignal(AlphaSignal):
+    """Negative trailing return: oversold stocks score high.
+
+    The signal is ``-close.pct_change(lookback)``, so a stock that fell over the
+    lookback window gets a positive (bullish) score.
+    """
+
+    def __init__(self, lookback: int = 5):
+        self.lookback = lookback
+
+    def compute(self, df: pd.DataFrame) -> pd.Series:
+        return -df["close"].pct_change(self.lookback)
+
+    @property
+    def name(self) -> str:
+        return f"reversal_{self.lookback}d"

strategies/alpha_strategy.py

@@ -0,0 +1,26 @@
+"""Signal-driven multi-stock strategy."""
+import backtrader as bt
+import pandas as pd
+
+
+class AlphaStrategy(bt.Strategy):
+    """Trade each feed based on its precomputed ``signal`` line.
+
+    The strategy delegates the buy/sell/hold decision to a portfolio builder
+    (e.g. ``ThresholdBuilder``) and sizes entries with ``order_target_percent``.
+    """
+
+    def __init__(self, builder):
+        self.builder = builder
+
+    def next(self):
+        for data in self.datas:
+            sig = data.signal[0]
+            if pd.isna(sig):
+                continue
+            in_position = bool(self.getposition(data).size)
+            action = self.builder.build(float(sig), in_position)
+            if action.action == "buy":
+                self.order_target_percent(data=data, target=action.size_pct)
+            elif action.action == "sell":
+                self.close(data=data)

tests/test_eval.py

@@ -0,0 +1,53 @@
+"""Tests for cross-sectional IC evaluation."""
+import numpy as np
+import pandas as pd
+
+from eval.metrics import evaluate_cross_sectional
+
+
+def test_cross_sectional_keys_present():
+    dates = pd.date_range("2024-01-01", periods=10)
+    cols = ["a", "b", "c"]
+    rng = np.random.default_rng(0)
+    signals = pd.DataFrame(rng.standard_normal((10, 3)), index=dates, columns=cols)
+    returns = pd.DataFrame(rng.standard_normal((10, 3)), index=dates, columns=cols)
+    res = evaluate_cross_sectional(signals, returns)
+    for key in (
+        "ic_mean", "ic_std", "ir", "rank_ic_mean", "rank_ic_std",
+        "rank_ir", "hit_rate", "n_periods",
+    ):
+        assert key in res
+
+
+def test_perfect_signal_has_positive_rank_ic():
+    # When the signal equals next-period returns, rank IC should be ~1 each day.
+    dates = pd.date_range("2024-01-01", periods=8)
+    cols = ["a", "b", "c"]
+    rng = np.random.default_rng(42)
+    returns = pd.DataFrame(rng.standard_normal((8, 3)), index=dates, columns=cols)
+    signals = returns.copy()  # perfect foresight
+    res = evaluate_cross_sectional(signals, returns)
+    assert res["rank_ic_mean"] > 0.99
+    assert res["hit_rate"] == 1.0
+    assert res["n_periods"] == 8
+
+
+def test_inverted_signal_has_negative_rank_ic():
+    dates = pd.date_range("2024-01-01", periods=6)
+    cols = ["a", "b", "c"]
+    rng = np.random.default_rng(7)
+    returns = pd.DataFrame(rng.standard_normal((6, 3)), index=dates, columns=cols)
+    signals = -returns  # perfectly wrong
+    res = evaluate_cross_sectional(signals, returns)
+    assert res["rank_ic_mean"] < -0.99
+
+
+def test_single_stock_falls_back_to_rolling():
+    dates = pd.date_range("2024-01-01", periods=40)
+    rng = np.random.default_rng(1)
+    signals = pd.DataFrame({"a": rng.standard_normal(40)}, index=dates)
+    returns = pd.DataFrame({"a": rng.standard_normal(40)}, index=dates)
+    res = evaluate_cross_sectional(signals, returns)
+    # Rolling fallback still yields the standard metric keys.
+    assert "rank_ic_mean" in res
+    assert res["n_periods"] > 0

tests/test_signals.py

@@ -0,0 +1,38 @@
+"""Tests for alpha signal computation."""
+import pandas as pd
+
+from signals.reversal import ReversalSignal
+
+
+def _make_df(closes):
+    return pd.DataFrame({"close": closes})
+
+
+def test_reversal_name():
+    assert ReversalSignal(lookback=5).name == "reversal_5d"
+    assert ReversalSignal(lookback=10).name == "reversal_10d"
+
+
+def test_reversal_is_negative_trailing_return():
+    # Monotonically rising prices -> negative (bearish) reversal signal.
+    df = _make_df([10.0, 11.0, 12.0, 13.0, 14.0, 15.0])
+    sig = ReversalSignal(lookback=5).compute(df)
+    # First 5 values are NaN (insufficient lookback).
+    assert sig.iloc[:5].isna().all()
+    # 15/10 - 1 = 0.5 return -> signal = -0.5
+    assert abs(sig.iloc[5] - (-0.5)) < 1e-9
+
+
+def test_reversal_oversold_is_positive():
+    # Falling prices -> positive (bullish) reversal signal.
+    df = _make_df([20.0, 18.0, 16.0, 14.0, 12.0, 10.0])
+    sig = ReversalSignal(lookback=5).compute(df)
+    assert sig.iloc[5] > 0
+    # 10/20 - 1 = -0.5 -> signal = +0.5
+    assert abs(sig.iloc[5] - 0.5) < 1e-9
+
+
+def test_reversal_output_length_matches_input():
+    df = _make_df([1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0])
+    sig = ReversalSignal(lookback=3).compute(df)
+    assert len(sig) == len(df)