"""核心衛星（60% 0050＋40% 四因子複合）：跑到最新資料的版本（/strategies/30k-stock-selection 的數字來源）。

條件與 /blog/30k-stock-selection 附的 strategy.py 的核心衛星配置相同，只是不截斷結束日：
- 核心：60% 資金放 0050
- 衛星：40% 資金放四因子複合。股票池是近 60 日日均成交額全市場前 50%，
  ROE、120 日動能、120 日低波動（2 倍權重）、營收年增四個百分位加權平均，取前 25 檔、分數三次方加權
- 每月換股（月初延後 14 天）並把比重拉回 60／40，sim() 預設手續費 0.1425% 與證交稅 0.3%

統計口徑：日夏普 = 日報酬平均 / 標準差 × √252，不扣無風險利率；
0050 含息 = etl:adj_close 還原價買進持有，與策略同一段期間。
執行後會在目前目錄輸出 data.csv（淨值曲線）與 metrics.json（統計）。

    pip install finlab
    python strategy.py

finlab 需要資料時會自動引導登入，不需要在程式裡填 token。
"""

import json

import pandas as pd

import finlab
from finlab import data
from finlab.backtest import sim

STRATEGY_NAME = "核心衛星配置（四因子複合衛星）"
START = "2018-01-01"
CORE_WEIGHT = 0.6
LOOKBACK = 120  # 動能與波動回看交易日
TOP_N = 25


def build_report():
    close = data.get("price:收盤價")
    volume = data.get("price:成交股數")
    roe = data.get("fundamental_features:ROE稅後").index_str_to_date().reindex(close.index, method="ffill")
    rev = data.get("monthly_revenue:去年同月增減(%)").reindex(close.index, method="ffill")

    amount = (close * volume).rolling(60).mean()
    liquid = amount.rank(axis=1, pct=True) > 0.5
    quality = roe.rank(axis=1, pct=True)
    momentum = (close / close.shift(LOOKBACK) - 1).rank(axis=1, pct=True)
    lowvol = (-close.pct_change(fill_method=None).rolling(LOOKBACK).std()).rank(axis=1, pct=True)
    revenue = rev.rank(axis=1, pct=True)

    score = ((quality + momentum + 2 * lowvol + revenue) / 5).where(liquid)
    selected = score.rank(axis=1, ascending=False) <= TOP_N
    satellite = (score ** 3).where(selected)
    satellite = satellite.div(satellite.sum(axis=1), axis=0).fillna(0)

    # 衛星佔 40%，再把 0050 補到 60%
    weight = satellite * (1 - CORE_WEIGHT)
    weight["0050"] = weight.get("0050", 0) + CORE_WEIGHT
    return sim(weight[weight.index >= START], resample="M", resample_offset="14D",
               upload=False, name=STRATEGY_NAME)


def curve_stats(curve: pd.Series) -> dict:
    curve = curve / curve.iloc[0]
    daily = curve.pct_change().dropna()
    years = (curve.index[-1] - curve.index[0]).days / 365.25
    return {
        "cagr": curve.iloc[-1] ** (1 / years) - 1,
        "daily_sharpe": daily.mean() / daily.std() * 252 ** 0.5,
        "max_drawdown": (curve / curve.cummax() - 1).min(),
        "total_return": curve.iloc[-1] - 1,
    }


def main() -> None:
    finlab.login()
    bench_all = data.get("etl:adj_close")["0050"].dropna()
    report = build_report()

    # 從第一次有部位的那天起算，0050 含息用同一段期間
    creturn = report.creturn.dropna()
    first_move = (creturn != creturn.iloc[0]).argmax()
    creturn = creturn.iloc[max(first_move - 1, 0):]
    bench = bench_all.loc[creturn.index[0]:creturn.index[-1]]

    strategy_stats = curve_stats(creturn)
    bench_stats = curve_stats(bench)
    holdings = (report.position.fillna(0) != 0).sum(axis=1)
    strategy_stats["avg_holdings"] = holdings[holdings > 0].mean()

    start, end = creturn.index[0].date(), creturn.index[-1].date()
    print(f"期間 {start} 至 {end}")
    for label, s in [("策略", strategy_stats), ("0050 含息", bench_stats)]:
        print(f"{label}：年化 {s['cagr']:.2%}，日夏普 {s['daily_sharpe']:.2f}，最大回撤 {s['max_drawdown']:.2%}")

    curves = pd.DataFrame({STRATEGY_NAME: creturn / creturn.iloc[0], "0050含息": bench / bench.iloc[0]})
    curves.index.name = "date"
    curves.round(6).to_csv("data.csv")
    metrics = {
        "window": f"{start}/{end}",
        "star": STRATEGY_NAME,
        "variants": {STRATEGY_NAME: {k: round(float(v), 6) for k, v in strategy_stats.items()}},
        "benchmark_0050": {k: round(float(v), 6) for k, v in bench_stats.items()},
        "run_date": str(pd.Timestamp.today().date()),
        "finlab_version": finlab.__version__,
        "generated_by": "static/blog/30k-stock-selection/validation/strategy.py",
    }
    with open("metrics.json", "w", encoding="utf-8") as f:
        json.dump(metrics, f, ensure_ascii=False, indent=2)


if __name__ == "__main__":
    main()