"""Synthetic market data with known statistics.

A geometric random walk is used rather than a recorded price series because
the coverage test needs a distribution whose true quantiles are known in
closed form. Real prices would make that test a measurement of the market
rather than of the arithmetic.
"""

from __future__ import annotations

import numpy as np
import pandas as pd


def synth(n: int = 600, tf: str = "1h", seed: int = 7, s0: float = 50000.0,
          sigma: float = 0.01, mu: float = 0.0) -> pd.DataFrame:
    rng = np.random.default_rng(seed)
    r = rng.normal(mu, sigma, n)
    close = s0 * np.exp(np.cumsum(r))
    openp = np.concatenate([[s0], close[:-1]])
    hi = np.maximum(openp, close) * (1 + np.abs(rng.normal(0, sigma / 3, n)))
    lo = np.minimum(openp, close) * (1 - np.abs(rng.normal(0, sigma / 3, n)))
    vol = np.abs(rng.normal(1000, 200, n)) + 1.0
    step = pd.Timedelta("1h") if tf == "1h" else pd.Timedelta("1d")
    ts = pd.date_range("2025-01-01", periods=n, freq=step, tz="UTC")
    return pd.DataFrame({"ts": ts, "open": openp, "high": hi, "low": lo,
                         "close": close, "volume": vol})


def future_ts(context: pd.DataFrame, horizon: int) -> pd.DatetimeIndex:
    ts = pd.to_datetime(context["ts"], utc=True)
    step = ts.diff().dropna().mode().iloc[0]
    return pd.DatetimeIndex([ts.iloc[-1] + step * (i + 1) for i in range(horizon)])