From c89701668527ab94a124ac5ceb7a8e1045da1d72 Mon Sep 17 00:00:00 2001
From: TheSiahxyz <164138827+TheSiahxyz@users.noreply.github.com>
Date: Wed, 1 Apr 2026 16:22:07 +0900
Subject: feat(backtester): add detailed metrics (Sharpe, Sortino, drawdown)

Add metrics.py with TradeRecord/DetailedMetrics dataclasses and
compute_detailed_metrics() that pairs BUY/SELL trades FIFO, computes
win/loss stats, profit factor, equity curve, max drawdown, Sharpe,
Sortino, Calmar ratios, and monthly returns.
---
 services/backtester/src/backtester/metrics.py | 215 ++++++++++++++++++++++++++
 services/backtester/tests/test_metrics.py     |  96 ++++++++++++
 2 files changed, 311 insertions(+)
 create mode 100644 services/backtester/src/backtester/metrics.py
 create mode 100644 services/backtester/tests/test_metrics.py

diff --git a/services/backtester/src/backtester/metrics.py b/services/backtester/src/backtester/metrics.py
new file mode 100644
index 0000000..15be0e6
--- /dev/null
+++ b/services/backtester/src/backtester/metrics.py
@@ -0,0 +1,215 @@
+"""Detailed backtest metrics: Sharpe, Sortino, drawdown, and more."""
+from __future__ import annotations
+
+import math
+from dataclasses import dataclass, field
+from datetime import datetime, timedelta
+from decimal import Decimal
+from typing import Any
+
+
+@dataclass
+class TradeRecord:
+    time: datetime
+    symbol: str
+    side: str  # "BUY" or "SELL"
+    price: Decimal
+    quantity: Decimal
+
+
+@dataclass
+class DetailedMetrics:
+    total_return: float
+    total_trades: int
+    winning_trades: int
+    losing_trades: int
+    win_rate: float
+    profit_factor: float
+    sharpe_ratio: float
+    sortino_ratio: float
+    calmar_ratio: float
+    max_drawdown: float
+    max_drawdown_duration: timedelta
+    monthly_returns: dict[str, float] = field(default_factory=dict)
+    avg_win: float = 0.0
+    avg_loss: float = 0.0
+    largest_win: float = 0.0
+    largest_loss: float = 0.0
+    avg_holding_period: timedelta = field(default_factory=timedelta)
+    trade_pairs: list[dict[str, Any]] = field(default_factory=list)
+
+
+def _pair_trades(trades: list[TradeRecord]) -> list[dict[str, Any]]:
+    """Pair BUY/SELL trades using FIFO matching."""
+    buys: list[TradeRecord] = []
+    pairs: list[dict[str, Any]] = []
+
+    for trade in trades:
+        if trade.side == "BUY":
+            buys.append(trade)
+        elif trade.side == "SELL" and buys:
+            buy = buys.pop(0)
+            pnl = float((trade.price - buy.price) * trade.quantity)
+            pairs.append(
+                {
+                    "entry_time": buy.time,
+                    "exit_time": trade.time,
+                    "symbol": trade.symbol,
+                    "entry_price": float(buy.price),
+                    "exit_price": float(trade.price),
+                    "quantity": float(trade.quantity),
+                    "pnl": pnl,
+                    "holding_period": trade.time - buy.time,
+                }
+            )
+    return pairs
+
+
+def compute_detailed_metrics(
+    trades: list[TradeRecord],
+    initial_balance: Decimal,
+    final_balance: Decimal,
+) -> DetailedMetrics:
+    """Compute detailed backtest metrics from a list of trade records."""
+    if not trades:
+        return DetailedMetrics(
+            total_return=0.0,
+            total_trades=0,
+            winning_trades=0,
+            losing_trades=0,
+            win_rate=0.0,
+            profit_factor=0.0,
+            sharpe_ratio=0.0,
+            sortino_ratio=0.0,
+            calmar_ratio=0.0,
+            max_drawdown=0.0,
+            max_drawdown_duration=timedelta(0),
+        )
+
+    pairs = _pair_trades(trades)
+    total_return = float(final_balance - initial_balance) / float(initial_balance) if initial_balance else 0.0
+
+    if not pairs:
+        return DetailedMetrics(
+            total_return=total_return,
+            total_trades=len(trades),
+            winning_trades=0,
+            losing_trades=0,
+            win_rate=0.0,
+            profit_factor=0.0,
+            sharpe_ratio=0.0,
+            sortino_ratio=0.0,
+            calmar_ratio=0.0,
+            max_drawdown=0.0,
+            max_drawdown_duration=timedelta(0),
+        )
+
+    # Win/loss stats
+    wins = [p for p in pairs if p["pnl"] > 0]
+    losses = [p for p in pairs if p["pnl"] <= 0]
+    winning_trades = len(wins)
+    losing_trades = len(losses)
+    total_pairs = len(pairs)
+    win_rate = winning_trades / total_pairs * 100 if total_pairs else 0.0
+
+    gross_profit = sum(p["pnl"] for p in wins)
+    gross_loss = abs(sum(p["pnl"] for p in losses))
+    profit_factor = gross_profit / gross_loss if gross_loss > 0 else float("inf") if gross_profit > 0 else 0.0
+
+    avg_win = gross_profit / winning_trades if winning_trades else 0.0
+    avg_loss = gross_loss / losing_trades if losing_trades else 0.0
+    largest_win = max((p["pnl"] for p in wins), default=0.0)
+    largest_loss = min((p["pnl"] for p in losses), default=0.0)
+
+    # Holding periods
+    holding_periods = [p["holding_period"] for p in pairs]
+    avg_holding = sum(holding_periods, timedelta(0)) / len(holding_periods) if holding_periods else timedelta(0)
+
+    # Build equity curve from pairs
+    init_bal = float(initial_balance)
+    equity = [init_bal]
+    for p in pairs:
+        equity.append(equity[-1] + p["pnl"])
+
+    # Returns per pair
+    returns = []
+    for i in range(1, len(equity)):
+        if equity[i - 1] != 0:
+            returns.append((equity[i] - equity[i - 1]) / equity[i - 1])
+        else:
+            returns.append(0.0)
+
+    # Max drawdown
+    peak = equity[0]
+    max_dd = 0.0
+    max_dd_duration = timedelta(0)
+    dd_start_idx = 0
+    for i in range(1, len(equity)):
+        if equity[i] > peak:
+            peak = equity[i]
+            dd_start_idx = i
+        dd = (peak - equity[i]) / peak if peak > 0 else 0.0
+        if dd > max_dd:
+            max_dd = dd
+            # Duration: use pair exit times
+            if i <= len(pairs) and dd_start_idx < len(pairs):
+                start_time = pairs[dd_start_idx]["exit_time"] if dd_start_idx < len(pairs) else pairs[0]["entry_time"]
+                end_time = pairs[i - 1]["exit_time"]
+                max_dd_duration = end_time - start_time if end_time > start_time else timedelta(0)
+
+    # Sharpe ratio (annualized, assume 365 trading days)
+    if len(returns) > 1:
+        mean_r = sum(returns) / len(returns)
+        std_r = math.sqrt(sum((r - mean_r) ** 2 for r in returns) / (len(returns) - 1))
+        sharpe = (mean_r / std_r * math.sqrt(365)) if std_r > 0 else 0.0
+    elif len(returns) == 1:
+        sharpe = 0.0
+    else:
+        sharpe = 0.0
+
+    # Sortino ratio (annualized)
+    if len(returns) > 1:
+        mean_r = sum(returns) / len(returns)
+        downside = [min(r, 0.0) for r in returns]
+        downside_var = sum(d ** 2 for d in downside) / (len(downside) - 1)
+        downside_std = math.sqrt(downside_var)
+        sortino = (mean_r / downside_std * math.sqrt(365)) if downside_std > 0 else 0.0
+    else:
+        sortino = 0.0
+
+    # Calmar ratio = annualized return / max drawdown
+    # Estimate annualized return from total return and time span
+    if pairs and max_dd > 0:
+        time_span = (pairs[-1]["exit_time"] - pairs[0]["entry_time"]).total_seconds()
+        years = time_span / (365.25 * 86400) if time_span > 0 else 1.0
+        annualized_return = (1 + total_return) ** (1 / years) - 1 if years > 0 else total_return
+        calmar = annualized_return / max_dd
+    else:
+        calmar = 0.0
+
+    # Monthly returns grouped by exit_time month
+    monthly: dict[str, float] = {}
+    for p in pairs:
+        key = p["exit_time"].strftime("%Y-%m")
+        monthly[key] = monthly.get(key, 0.0) + p["pnl"]
+
+    return DetailedMetrics(
+        total_return=total_return,
+        total_trades=len(trades),
+        winning_trades=winning_trades,
+        losing_trades=losing_trades,
+        win_rate=win_rate,
+        profit_factor=profit_factor,
+        sharpe_ratio=sharpe,
+        sortino_ratio=sortino,
+        calmar_ratio=calmar,
+        max_drawdown=max_dd,
+        max_drawdown_duration=max_dd_duration,
+        monthly_returns=monthly,
+        avg_win=avg_win,
+        avg_loss=avg_loss,
+        largest_win=largest_win,
+        largest_loss=largest_loss,
+        avg_holding_period=avg_holding,
+        trade_pairs=[p for p in pairs],
+    )
diff --git a/services/backtester/tests/test_metrics.py b/services/backtester/tests/test_metrics.py
new file mode 100644
index 0000000..b222b8a
--- /dev/null
+++ b/services/backtester/tests/test_metrics.py
@@ -0,0 +1,96 @@
+"""Tests for detailed backtest metrics."""
+from datetime import datetime, timedelta, timezone
+from decimal import Decimal
+
+import pytest
+
+from backtester.metrics import TradeRecord, compute_detailed_metrics
+
+
+def _make_trade(side: str, price: str, minutes_offset: int = 0) -> TradeRecord:
+    return TradeRecord(
+        time=datetime(2025, 1, 1, tzinfo=timezone.utc) + timedelta(minutes=minutes_offset),
+        symbol="BTCUSDT",
+        side=side,
+        price=Decimal(price),
+        quantity=Decimal("1"),
+    )
+
+
+def test_compute_metrics_basic():
+    """Two round-trip trades: 1 win, 1 loss. Verify counts and win_rate."""
+    trades = [
+        _make_trade("BUY", "100", 0),
+        _make_trade("SELL", "120", 10),   # win: +20
+        _make_trade("BUY", "130", 20),
+        _make_trade("SELL", "110", 30),   # loss: -20
+    ]
+    metrics = compute_detailed_metrics(trades, Decimal("10000"), Decimal("10000"))
+
+    assert metrics.total_trades == 4
+    assert metrics.winning_trades == 1
+    assert metrics.losing_trades == 1
+    assert metrics.win_rate == pytest.approx(50.0)
+
+
+def test_compute_metrics_profit_factor():
+    """Verify profit_factor = gross_profit / gross_loss."""
+    trades = [
+        _make_trade("BUY", "100", 0),
+        _make_trade("SELL", "150", 10),   # win: +50
+        _make_trade("BUY", "150", 20),
+        _make_trade("SELL", "130", 30),   # loss: -20
+    ]
+    metrics = compute_detailed_metrics(trades, Decimal("10000"), Decimal("10030"))
+
+    # gross_profit=50, gross_loss=20 → profit_factor=2.5
+    assert metrics.profit_factor == pytest.approx(2.5)
+
+
+def test_compute_metrics_max_drawdown():
+    """Max drawdown should be > 0 when there is a losing trade after a peak."""
+    trades = [
+        _make_trade("BUY", "100", 0),
+        _make_trade("SELL", "150", 10),   # win: equity goes up
+        _make_trade("BUY", "150", 20),
+        _make_trade("SELL", "120", 30),   # loss: equity drops
+    ]
+    metrics = compute_detailed_metrics(trades, Decimal("10000"), Decimal("10020"))
+
+    assert metrics.max_drawdown > 0
+
+
+def test_compute_metrics_sharpe_ratio():
+    """Sharpe ratio should be a finite number with multiple trades."""
+    trades = [
+        _make_trade("BUY", "100", 0),
+        _make_trade("SELL", "110", 60),
+        _make_trade("BUY", "105", 120),
+        _make_trade("SELL", "115", 180),
+        _make_trade("BUY", "110", 240),
+        _make_trade("SELL", "108", 300),
+    ]
+    metrics = compute_detailed_metrics(trades, Decimal("10000"), Decimal("10018"))
+
+    assert math.isfinite(metrics.sharpe_ratio)
+    assert math.isfinite(metrics.sortino_ratio)
+
+
+def test_compute_metrics_empty_trades():
+    """Empty trades should return all zeros."""
+    metrics = compute_detailed_metrics([], Decimal("10000"), Decimal("10000"))
+
+    assert metrics.total_return == 0.0
+    assert metrics.total_trades == 0
+    assert metrics.winning_trades == 0
+    assert metrics.losing_trades == 0
+    assert metrics.win_rate == 0.0
+    assert metrics.profit_factor == 0.0
+    assert metrics.sharpe_ratio == 0.0
+    assert metrics.sortino_ratio == 0.0
+    assert metrics.calmar_ratio == 0.0
+    assert metrics.max_drawdown == 0.0
+    assert metrics.monthly_returns == {}
+
+
+import math
-- 
cgit v1.2.3