"""投信買超＋營收創新高：跑到最新資料的版本（/strategies/institutional-investors-comparison 的數字來源）。

條件與 /blog/institutional-investors-comparison 的「投信＋營收」策略相同，只是不截斷結束日：
- 投信近 10 日累計買超大於 5,000 股
- 月營收近 3 個月平均創 12 個月新高，且月營收年增大於 15%
- 近 20 日平均成交量大於 300 張
- 依投信 10 日累計買超股數取前 12 檔等權、單檔上限 12%，2015 年起每月換股，
  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 = "投信買超＋營收創新高"
START = "2015"
TRUST_DAYS = 10  # 投信買超累計天數
TOP_N = 12       # 持股檔數


def build_report():
    trust = data.get("institutional_investors_trading_summary:投信買賣超股數")
    rev = data.get("monthly_revenue:當月營收")
    rev_yoy = data.get("monthly_revenue:去年同月增減(%)")
    volume = data.get("price:成交股數")

    trust_sum = trust.rolling(TRUST_DAYS).sum()
    rev_ma3 = rev.average(3)
    cond = (
        (trust_sum > 5000)
        & (rev_ma3 == rev_ma3.rolling(12).max())
        & (rev_yoy > 15)
        & (volume.average(20) > 300 * 1000)
    )
    position = trust_sum[cond].is_largest(TOP_N)
    position = position.reindex(rev.index_str_to_date().index, method="ffill")  # 在月營收公布日取樣
    return sim(position.loc[START:], resample="M", position_limit=0.12, 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/institutional-investors-comparison/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()