okx-codex-trader/scripts/search_eth_bb_squeeze_risk_10y.py

from __future__ import annotations

import argparse
import sys
from dataclasses import dataclass
from pathlib import Path

import pandas as pd

sys.path.insert(0, str(Path(__file__).resolve().parents[1]))

from okx_codex_trader.models import Candle
from okx_codex_trader.sampled_report import SegmentResult, mark_to_market, trade_equity


ETH_SYMBOL = "ETH-USDT-SWAP"
BTC_SYMBOL = "BTC-USDT-SWAP"
BAR = "15m"
YEARS = 10.0
LEVERAGE = 3
INITIAL_EQUITY = 10_000.0
DATA_DIR = Path("data/okx-candles")
OUTPUT_DIR = Path("reports/eth-exploration")
PRIMARY_COST = "maker_taker"
COSTS = (
    ("maker_maker", 0.0012),
    ("maker_taker", 0.0021),
    ("taker_taker", 0.0030),
)
HORIZONS = (
    ("3y", pd.DateOffset(years=3)),
    ("1y", pd.DateOffset(years=1)),
    ("6m", pd.DateOffset(months=6)),
    ("3m", pd.DateOffset(months=3)),
)


@dataclass(frozen=True)
class Variant:
    band_length: int
    bandwidth_lookback: int
    bandwidth_quantile: float
    stop_loss_pct: float
    take_profit_pct: float | None
    side_mode: str
    btc_filter: str
    eth_vol_cap: float | None
    dd_overlay: float | None
    cooldown_bars: int

    @property
    def name(self) -> str:
        tp = "none" if self.take_profit_pct is None else f"{self.take_profit_pct:g}"
        vol = "none" if self.eth_vol_cap is None else f"{self.eth_vol_cap:g}"
        dd = "none" if self.dd_overlay is None else f"{self.dd_overlay:g}"
        return (
            f"bb-squeeze-l{self.band_length}-bw{self.bandwidth_lookback}"
            f"-q{self.bandwidth_quantile:g}-sl{self.stop_loss_pct:g}-tp{tp}"
            f"-{self.side_mode}-{self.btc_filter}-vc{vol}-dd{dd}-cd{self.cooldown_bars}"
        )


def _format_ts(ts: int) -> str:
    return pd.to_datetime(ts, unit="ms", utc=True).strftime("%Y-%m-%d %H:%M")


def _load_candles(symbol: str, bar: str) -> list[Candle]:
    frame = pd.read_csv(DATA_DIR / symbol / f"{bar}.csv")
    return [
        Candle(
            symbol=symbol,
            ts=int(row.ts),
            open=float(row.open),
            high=float(row.high),
            low=float(row.low),
            close=float(row.close),
            volume=float(row.volume),
        )
        for row in frame.itertuples(index=False)
    ]


def _align_pair(left: list[Candle], right: list[Candle]) -> tuple[list[Candle], list[Candle]]:
    right_by_ts = {candle.ts: candle for candle in right}
    left_out: list[Candle] = []
    right_out: list[Candle] = []
    for candle in left:
        other = right_by_ts.get(candle.ts)
        if other is not None:
            left_out.append(candle)
            right_out.append(other)
    return left_out, right_out


def _close_position(
    *,
    trades: list[dict[str, object]],
    exits: list[dict[str, object]],
    position: dict[str, object],
    candle: Candle,
    exit_price: float,
) -> tuple[float, bool]:
    margin_used = float(position["margin_used"])
    exit_equity = trade_equity(
        side=str(position["side"]),
        margin_used=margin_used,
        entry_price=float(position["entry_price"]),
        exit_price=exit_price,
        leverage=LEVERAGE,
    )
    pnl = exit_equity - margin_used
    trades.append(
        {
            "side": "Long" if position["side"] == "long" else "Short",
            "entry_time": _format_ts(int(position["entry_time"])),
            "exit_time": _format_ts(candle.ts),
            "entry_price": round(float(position["entry_price"]), 4),
            "exit_price": round(exit_price, 4),
            "pnl": round(pnl, 4),
            "return_pct": round(pnl / margin_used * 100.0, 4),
            "cost_weight": 1.0,
        }
    )
    exits.append({"ts": candle.ts, "price": exit_price, "side": position["side"]})
    return exit_equity, pnl > 0.0


def run_variant(eth: list[Candle], btc: list[Candle], variant: Variant) -> SegmentResult:
    eth_close = pd.Series([candle.close for candle in eth], dtype=float)
    btc_close = pd.Series([candle.close for candle in btc], dtype=float)
    middle_series = eth_close.rolling(variant.band_length).mean()
    stdev_series = eth_close.rolling(variant.band_length).std(ddof=0)
    upper = (middle_series + 2.0 * stdev_series).tolist()
    lower = (middle_series - 2.0 * stdev_series).tolist()
    middle = middle_series.tolist()
    bandwidth = ((pd.Series(upper) - pd.Series(lower)) / middle_series).tolist()
    threshold = pd.Series(bandwidth, dtype=float).rolling(variant.bandwidth_lookback).quantile(variant.bandwidth_quantile).tolist()
    btc_sma = btc_close.rolling(480).mean().tolist()
    btc_momentum = (btc_close / btc_close.shift(96) - 1.0).tolist()
    eth_realized_vol = eth_close.pct_change().rolling(96).std(ddof=0).tolist()
    warmup_bars = max(variant.band_length, variant.bandwidth_lookback, 480, 96)

    equity = INITIAL_EQUITY
    ending_equity = equity
    peak_equity = equity
    max_drawdown = 0.0
    wins = 0
    trades: list[dict[str, object]] = []
    entries: list[dict[str, object]] = []
    exits: list[dict[str, object]] = []
    equity_curve: list[dict[str, float | int]] = []
    position: dict[str, object] | None = None
    pending_entry_side: str | None = None
    pending_exit = False
    cooldown_until = -1

    for index in range(warmup_bars, len(eth)):
        candle = eth[index]
        if pending_exit and position is not None:
            equity, won = _close_position(trades=trades, exits=exits, position=position, candle=candle, exit_price=candle.open)
            wins += int(won)
            position = None
            pending_exit = False
            cooldown_until = index + variant.cooldown_bars
        if pending_entry_side is not None and position is None and equity > 0.0:
            position = {
                "side": pending_entry_side,
                "entry_time": candle.ts,
                "entry_price": candle.open,
                "margin_used": equity,
                "stop_price": candle.open * (1.0 - variant.stop_loss_pct if pending_entry_side == "long" else 1.0 + variant.stop_loss_pct),
                "take_price": None
                if variant.take_profit_pct is None
                else candle.open * (1.0 + variant.take_profit_pct if pending_entry_side == "long" else 1.0 - variant.take_profit_pct),
            }
            entries.append({"ts": candle.ts, "price": candle.open, "side": pending_entry_side})
            pending_entry_side = None

        current_equity = equity
        if position is not None:
            side = str(position["side"])
            stop_hit = (side == "long" and candle.low <= float(position["stop_price"])) or (
                side == "short" and candle.high >= float(position["stop_price"])
            )
            take_price = position["take_price"]
            take_hit = take_price is not None and (
                (side == "long" and candle.high >= float(take_price)) or (side == "short" and candle.low <= float(take_price))
            )
            if stop_hit or take_hit:
                exit_price = float(position["stop_price"] if stop_hit else take_price)
                equity, won = _close_position(trades=trades, exits=exits, position=position, candle=candle, exit_price=exit_price)
                wins += int(won)
                current_equity = equity
                position = None
                cooldown_until = index + variant.cooldown_bars
        if position is not None:
            current_equity = mark_to_market(
                side=str(position["side"]),
                margin_used=float(position["margin_used"]),
                entry_price=float(position["entry_price"]),
                mark_price=candle.close,
                leverage=LEVERAGE,
            )
        peak_equity = max(peak_equity, current_equity)
        max_drawdown = max(max_drawdown, (peak_equity - current_equity) / peak_equity)
        equity_curve.append({"ts": candle.ts, "equity": current_equity, "close": candle.close})
        ending_equity = current_equity
        if index == len(eth) - 1 or equity <= 0.0:
            continue

        values = (middle[index], upper[index], lower[index], bandwidth[index], threshold[index])
        if any(value != value for value in values):
            continue
        if position is not None:
            if (position["side"] == "long" and candle.close < float(middle[index])) or (
                position["side"] == "short" and candle.close > float(middle[index])
            ):
                pending_exit = True
            continue
        if index < cooldown_until:
            continue
        if variant.eth_vol_cap is not None and float(eth_realized_vol[index]) > variant.eth_vol_cap:
            continue
        if variant.dd_overlay is not None and (peak_equity - current_equity) / peak_equity > variant.dd_overlay:
            continue
        if variant.btc_filter == "btc-up" and not (btc_close.iloc[index] > float(btc_sma[index])):
            continue
        if variant.btc_filter == "btc-up-momo" and not (btc_close.iloc[index] > float(btc_sma[index]) and float(btc_momentum[index]) > 0.0):
            continue

        if bandwidth[index] <= threshold[index]:
            if candle.close > float(upper[index]):
                pending_entry_side = "long"
            elif variant.side_mode == "both" and candle.close < float(lower[index]):
                pending_entry_side = "short"

    trade_count = len(trades)
    return SegmentResult(
        trade_count=trade_count,
        total_return=(ending_equity - INITIAL_EQUITY) / INITIAL_EQUITY,
        win_rate=wins / trade_count if trade_count else 0.0,
        max_drawdown=max_drawdown,
        trades=trades,
        open_position=position,
        candles=eth[warmup_bars:],
        equity_curve=equity_curve,
        entries=entries,
        exits=exits,
    )


def cost_equity_frame(result: SegmentResult, cost: float) -> pd.DataFrame:
    rows = [{"ts": pd.to_datetime(result.equity_curve[0]["ts"], unit="ms", utc=True), "equity": INITIAL_EQUITY}]
    equity = INITIAL_EQUITY
    for trade in result.trades:
        equity *= 1.0 + float(trade["return_pct"]) / 100.0 - cost * float(trade.get("cost_weight", 1.0))
        rows.append({"ts": pd.to_datetime(str(trade["exit_time"]), utc=True), "equity": equity})
    return pd.DataFrame(rows)


def max_drawdown(values: list[float]) -> float:
    peak = values[0]
    dd = 0.0
    for value in values:
        peak = max(peak, value)
        dd = max(dd, (peak - value) / peak if peak else 0.0)
    return dd


def equity_metrics(frame: pd.DataFrame, first_ts: int, last_ts: int) -> dict[str, float]:
    years = (last_ts - first_ts) / 86_400_000 / 365
    total_return = float(frame["equity"].iloc[-1] / frame["equity"].iloc[0] - 1.0)
    annualized = (1.0 + total_return) ** (1.0 / years) - 1.0 if total_return > -1.0 and years > 0.0 else 0.0
    dd = max_drawdown([float(value) for value in frame["equity"]])
    return {
        "net_total_return": total_return,
        "net_annualized_return": annualized,
        "net_max_drawdown": dd,
        "net_calmar": annualized / dd if dd else 0.0,
    }


def horizon_rows(frame: pd.DataFrame, last_ts: int) -> list[dict[str, object]]:
    rows: list[dict[str, object]] = []
    end_time = pd.to_datetime(last_ts, unit="ms", utc=True)
    for label, offset in HORIZONS:
        cutoff = end_time - offset
        before = frame[frame["ts"] <= cutoff]
        if len(before):
            start_equity = float(before["equity"].iloc[-1])
            start_time = cutoff
            after = frame[frame["ts"] > cutoff]
            horizon_frame = pd.concat([pd.DataFrame([{"ts": cutoff, "equity": start_equity}]), after[["ts", "equity"]]], ignore_index=True)
        else:
            horizon_frame = frame[["ts", "equity"]].copy()
            start_time = pd.Timestamp(horizon_frame["ts"].iloc[0])
        rows.append(
            {
                "horizon": label,
                "horizon_start": start_time.strftime("%Y-%m-%d %H:%M"),
                "horizon_end": end_time.strftime("%Y-%m-%d %H:%M"),
                **equity_metrics(horizon_frame, int(start_time.timestamp() * 1000), last_ts),
            }
        )
    return rows


def worst_month(frame: pd.DataFrame) -> tuple[str, float]:
    monthly = frame.set_index("ts")["equity"].resample("ME").last().ffill().pct_change().dropna()
    if not len(monthly):
        return "", 0.0
    idx = monthly.idxmin()
    return idx.strftime("%Y-%m"), float(monthly.loc[idx])


def build_variants() -> list[Variant]:
    bases = (
        (96, 480, 0.15),
        (96, 960, 0.25),
        (48, 960, 0.25),
        (48, 480, 0.15),
    )
    variants: list[Variant] = []
    for length, bandwidth_lookback, quantile in bases:
        for side_mode in ("long", "both"):
            for btc_filter in ("none", "btc-up", "btc-up-momo"):
                for eth_vol_cap in (None, 0.006):
                    for dd_overlay in (None, 0.25):
                        for stop_loss_pct, take_profit_pct in (
                            (0.006, 0.012),
                            (0.008, 0.018),
                            (0.010, None),
                        ):
                            variants.append(
                                Variant(
                                    band_length=length,
                                    bandwidth_lookback=bandwidth_lookback,
                                    bandwidth_quantile=quantile,
                                    stop_loss_pct=stop_loss_pct,
                                    take_profit_pct=take_profit_pct,
                                    side_mode=side_mode,
                                    btc_filter=btc_filter,
                                    eth_vol_cap=eth_vol_cap,
                                    dd_overlay=dd_overlay,
                                    cooldown_bars=24,
                                )
                            )
    return variants


def format_cell(value: object) -> str:
    if isinstance(value, float):
        return f"{value:.6g}"
    return str(value).replace("|", "\\|")


def markdown_table(frame: pd.DataFrame) -> str:
    columns = list(frame.columns)
    rows = [columns, ["---" for _ in columns]]
    for record in frame.to_dict("records"):
        rows.append([record[column] for column in columns])
    return "\n".join("| " + " | ".join(format_cell(value) for value in row) + " |" for row in rows)


def write_report(
    *,
    summary: pd.DataFrame,
    horizon: pd.DataFrame,
    output_files: list[Path],
    command: str,
    first_ts: int,
    last_ts: int,
    requested_years: float,
) -> str:
    primary = summary[summary["cost"] == PRIMARY_COST]
    top_calmar = primary.head(10)
    top_worst_month = primary.sort_values(
        ["worst_month_return", "net_calmar", "net_annualized_return"],
        ascending=[False, False, False],
    ).head(10)
    acceptable = primary[(primary["net_max_drawdown"] <= 0.45) & (primary["worst_month_return"] >= -0.25) & (primary["net_calmar"] > 1.0)]
    best = primary.iloc[0] if len(primary) else None
    horizon_top = (
        horizon[horizon["cost"] == PRIMARY_COST]
        .sort_values(["horizon", "net_calmar", "net_annualized_return"], ascending=[True, False, False])
        .groupby("horizon", observed=True)
        .head(3)
    )
    verdict = (
        "Yes: at least one variant met MDD <= 45%, worst month >= -25%, and Calmar > 1.0."
        if len(acceptable)
        else "No: this run did not find a BB squeeze variant with acceptable drawdown under MDD <= 45% and worst month >= -25%."
    )
    lines = [
        "# ETH BB squeeze breakout risk 10y exploration",
        "",
        f"Run command: `{command}`",
        f"Requested years: {requested_years:g}",
        f"Actual continuous local history: `{_format_ts(first_ts)}` to `{_format_ts(last_ts)}`.",
        "",
        "Output files:",
        *[f"- `{path}`" for path in output_files],
        "",
        "Cost model: maker_taker is the primary ranking cost; maker_maker and taker_taker are included for sensitivity.",
        "Objective: reduce drawdown, not maximize total return.",
        "",
        "Top 10 by Calmar:",
        markdown_table(
            top_calmar[
                [
                    "name",
                    "trades",
                    "net_total_return",
                    "net_annualized_return",
                    "net_max_drawdown",
                    "net_calmar",
                    "worst_month",
                    "worst_month_return",
                ]
            ]
        ),
        "",
        "Top 10 by worst month:",
        markdown_table(
            top_worst_month[
                [
                    "name",
                    "trades",
                    "net_total_return",
                    "net_annualized_return",
                    "net_max_drawdown",
                    "net_calmar",
                    "worst_month",
                    "worst_month_return",
                ]
            ]
        ),
        "",
        "Recent horizon leaders:",
        markdown_table(
            horizon_top[
                [
                    "horizon",
                    "name",
                    "trades",
                    "net_total_return",
                    "net_annualized_return",
                    "net_max_drawdown",
                    "net_calmar",
                ]
            ]
        ),
        "",
        "Verdict:",
        f"- {verdict}",
    ]
    if best is not None:
        lines.append(
            f"- Best Calmar variant is `{best['name']}`: Calmar {format_cell(best['net_calmar'])}, MDD {format_cell(best['net_max_drawdown'])}, worst month {best['worst_month']} {format_cell(best['worst_month_return'])}, trades {best['trades']}."
        )
    if len(acceptable):
        lines.extend(
            [
                "",
                "Acceptable drawdown candidates:",
                markdown_table(
                    acceptable.head(10)[
                        [
                            "name",
                            "trades",
                            "net_annualized_return",
                            "net_max_drawdown",
                            "net_calmar",
                            "worst_month_return",
                        ]
                    ]
                ),
            ]
        )
    return "\n".join(lines) + "\n"


def main() -> int:
    parser = argparse.ArgumentParser()
    parser.add_argument("--bar", default=BAR)
    parser.add_argument("--years", type=float, default=YEARS)
    parser.add_argument("--output-dir", type=Path, default=OUTPUT_DIR)
    args = parser.parse_args()

    eth = _load_candles(ETH_SYMBOL, args.bar)
    btc = _load_candles(BTC_SYMBOL, args.bar)
    eth, btc = _align_pair(eth, btc)
    requested_bars = int(args.years * 365 * 24 * 60 / 15)
    eth = eth[-requested_bars:]
    btc = btc[-requested_bars:]

    summary_rows: list[dict[str, object]] = []
    horizon_output_rows: list[dict[str, object]] = []
    variants = build_variants()
    for index, variant in enumerate(variants, start=1):
        result = run_variant(eth, btc, variant)
        if not result.equity_curve:
            print(f"skip {index}/{len(variants)} {variant.name}")
            continue
        for cost_name, cost in COSTS:
            frame = cost_equity_frame(result, cost)
            metrics = equity_metrics(frame, eth[0].ts, eth[-1].ts)
            month, month_return = worst_month(frame)
            row = {
                "family": "bb_squeeze_breakout_risk",
                "cost": cost_name,
                "symbol": ETH_SYMBOL,
                "signal_symbol": BTC_SYMBOL if variant.btc_filter != "none" else "",
                "bar": args.bar,
                "name": variant.name,
                "band_length": variant.band_length,
                "bandwidth_lookback": variant.bandwidth_lookback,
                "bandwidth_quantile": variant.bandwidth_quantile,
                "stop_loss_pct": variant.stop_loss_pct,
                "take_profit_pct": variant.take_profit_pct,
                "side_mode": variant.side_mode,
                "btc_filter": variant.btc_filter,
                "eth_vol_cap": variant.eth_vol_cap,
                "dd_overlay": variant.dd_overlay,
                "cooldown_bars": variant.cooldown_bars,
                "first_candle": _format_ts(eth[0].ts),
                "last_candle": _format_ts(eth[-1].ts),
                "years": (eth[-1].ts - eth[0].ts) / 86_400_000 / 365,
                "trades": result.trade_count,
                "gross_total_return": result.total_return,
                "gross_max_drawdown_mark_to_market": result.max_drawdown,
                "worst_month": month,
                "worst_month_return": month_return,
                **metrics,
            }
            summary_rows.append(row)
            for horizon_row in horizon_rows(frame, eth[-1].ts):
                horizon_output_rows.append(
                    {
                        "family": "bb_squeeze_breakout_risk",
                        "cost": cost_name,
                        "symbol": ETH_SYMBOL,
                        "signal_symbol": BTC_SYMBOL if variant.btc_filter != "none" else "",
                        "bar": args.bar,
                        "name": variant.name,
                        "trades": result.trade_count,
                        **horizon_row,
                    }
                )
        print(f"done {index}/{len(variants)} {variant.name}")

    summary = pd.DataFrame(summary_rows).sort_values(
        ["cost", "net_calmar", "worst_month_return", "net_annualized_return"],
        ascending=[True, False, False, False],
    )
    primary = summary[summary["cost"] == PRIMARY_COST]
    summary = pd.concat([primary, summary[summary["cost"] != PRIMARY_COST]], ignore_index=True)
    horizon = pd.DataFrame(horizon_output_rows)
    horizon["horizon"] = pd.Categorical(horizon["horizon"], categories=[label for label, _ in HORIZONS], ordered=True)
    horizon = horizon.sort_values(["cost", "horizon", "net_calmar", "net_annualized_return"], ascending=[True, True, False, False])

    args.output_dir.mkdir(parents=True, exist_ok=True)
    prefix = "eth-bb-squeeze-risk-10y"
    summary_path = args.output_dir / f"{prefix}-summary.csv"
    horizon_path = args.output_dir / f"{prefix}-horizon.csv"
    top_calmar_path = args.output_dir / f"{prefix}-top10-calmar.csv"
    top_worst_month_path = args.output_dir / f"{prefix}-top10-worst-month.csv"
    report_path = args.output_dir / f"{prefix}-report.md"
    output_files = [summary_path, horizon_path, top_calmar_path, top_worst_month_path, report_path]

    summary.to_csv(summary_path, index=False)
    horizon.to_csv(horizon_path, index=False)
    primary.head(10).to_csv(top_calmar_path, index=False)
    primary.sort_values(["worst_month_return", "net_calmar", "net_annualized_return"], ascending=[False, False, False]).head(10).to_csv(
        top_worst_month_path,
        index=False,
    )
    command = f"rtk .venv/bin/python {Path(__file__).as_posix()} --bar {args.bar} --years {args.years}"
    report_path.write_text(
        write_report(
            summary=summary,
            horizon=horizon,
            output_files=output_files,
            command=command,
            first_ts=eth[0].ts,
            last_ts=eth[-1].ts,
            requested_years=args.years,
        ),
        encoding="utf-8",
    )
    print(primary.head(10).to_string(index=False))
    return 0


if __name__ == "__main__":
    raise SystemExit(main())