import yfinance as yf
import numpy as np
import torch
import timesfm
import matplotlib
matplotlib.use("Agg")
import matplotlib.pyplot as plt
from datetime import datetime, timedelta

# 1. 获取 AAPL 数据（到今天为止）
print("下载 AAPL 股票数据...", flush=True)
end = datetime.now()
start = end - timedelta(days=365)
df = yf.download("AAPL", start=start.strftime("%Y-%m-%d"), end=end.strftime("%Y-%m-%d"), progress=False)
close = df["Close"].values.flatten().astype(np.float32)
dates = df.index

# 2. 分割：6/15 之前为训练集，6/16 之后为实际值
split_date = "2026-06-15"
split_idx = None
for i, d in enumerate(dates):
    if str(d.date()) <= split_date:
        split_idx = i
# split_idx 是 <= 6/15 的最后一个索引
train_data = close[: split_idx + 1]
train_dates = dates[: split_idx + 1]
actual_data = close[split_idx + 1 :]
actual_dates = dates[split_idx + 1 :]

HORIZON = len(actual_data)
print(f"训练数据: {len(train_data)} 天（截至 {train_dates[-1].date()}）", flush=True)
print(f"实际数据: {HORIZON} 天（{actual_dates[0].date()} ~ {actual_dates[-1].date()}）", flush=True)
print(f"分割日收盘价: {train_data[-1]:.2f}", flush=True)

# 3. 加载模型
print()
print("加载 TimesFM 模型...", flush=True)
torch.set_float32_matmul_precision("high")
model = timesfm.TimesFM_2p5_200M_torch.from_pretrained(
    "google/timesfm-2.5-200m-pytorch", torch_compile=False
)
print("模型加载完成", flush=True)

# 4. 编译并预测
model.compile(
    timesfm.ForecastConfig(
        max_context=512,
        max_horizon=128,
        normalize_inputs=True,
        use_continuous_quantile_head=True,
        force_flip_invariance=False,
        infer_is_positive=True,
        fix_quantile_crossing=True,
    )
)
print(f"预测未来 {HORIZON} 个交易日...", flush=True)
pf, qf = model.forecast(horizon=HORIZON, inputs=[train_data])
print("预测完成！", flush=True)

# 5. 计算误差指标
actual = actual_data
pred = pf[0][:HORIZON]
mae = np.mean(np.abs(actual - pred))
rmse = np.sqrt(np.mean((actual - pred) ** 2))
mape = np.mean(np.abs((actual - pred) / actual)) * 100

# 方向准确率
actual_dir = np.diff(actual)
pred_dir = np.diff(pred)
dir_acc = np.mean(actual_dir * pred_dir > 0) * 100

# 置信区间覆盖率
in_80 = np.mean((actual >= qf[0, :HORIZON, 1]) & (actual <= qf[0, :HORIZON, 9])) * 100
in_40 = np.mean((actual >= qf[0, :HORIZON, 3]) & (actual <= qf[0, :HORIZON, 7])) * 100

print()
print("=== 回测结果：6/16 ~ 6/30 预测 vs 实际 ===", flush=True)
print()
print("  日期          实际价    预测价    误差    误差%", flush=True)
for i in range(HORIZON):
    err = pred[i] - actual[i]
    err_pct = err / actual[i] * 100
    print(
        f"  {actual_dates[i].date()}  {actual[i]:7.2f}  {pred[i]:7.2f}  {err:+7.2f}  {err_pct:+6.2f}%",
        flush=True,
    )

print()
print("=== 误差指标 ===", flush=True)
print(f"  MAE  (平均绝对误差):     ${mae:.2f}", flush=True)
print(f"  RMSE (均方根误差):       ${rmse:.2f}", flush=True)
print(f"  MAPE (平均绝对百分比误差): {mape:.2f}%", flush=True)
print(f"  方向准确率:               {dir_acc:.1f}%", flush=True)
print(f"  80%置信区间覆盖率:        {in_80:.1f}%", flush=True)
print(f"  40%置信区间覆盖率:        {in_40:.1f}%", flush=True)

# 6. 画图
fig, ax = plt.subplots(figsize=(14, 6))
show_n = min(60, len(train_data))
ax.plot(range(show_n), train_data[-show_n:], label="Historical Close", color="steelblue", linewidth=1.5)
x_actual = range(show_n, show_n + HORIZON)
ax.plot(x_actual, actual, label="Actual", color="forestgreen", linewidth=2, marker="o", markersize=3)
ax.plot(x_actual, pred, label="Forecast", color="tomato", linewidth=2, linestyle="--")
ax.fill_between(x_actual, qf[0, :HORIZON, 1], qf[0, :HORIZON, 9], alpha=0.15, color="tomato", label="80% CI")
ax.fill_between(x_actual, qf[0, :HORIZON, 3], qf[0, :HORIZON, 7], alpha=0.3, color="tomato", label="40% CI")
ax.axvline(x=show_n - 1, color="gray", linestyle="--", alpha=0.5, label="Forecast Start")
ax.set_title(f"AAPL Backtest: Forecast vs Actual (MAPE={mape:.2f}%, Dir.Acc={dir_acc:.0f}%)", fontsize=14)
ax.set_xlabel("Trading Days")
ax.set_ylabel("Price (USD)")
ax.legend(loc="upper left")
plt.tight_layout()
plt.savefig("aapl_backtest.png", dpi=150)
print()
print("Chart saved: aapl_backtest.png", flush=True)
print("Done!", flush=True)