"""SEA08 — US-session momentum on 1h bars.

HYPOTHESIS: On 1h: go long during 13-21 UTC when the prior (Asian+London) session
was positive; otherwise flat. Idea: captures US risk-on drift when prior price
action was constructive.

CAUSALITY CHECK:
- "Prior session" = we look at the cumulative return of bars from the prior day's
  Asian+London window (00-12 UTC) that CLOSED before bar[i].
- We compute the prior-session return as the log return from close[previous_day_00:00 UTC]
  to close[current_day_12:00 UTC], decided at bar[i] open (i.e., at close[i-1]).
- Actually, we'll compute it simpler: the bar that ENDS at 12:00 UTC (the last
  Asian/London bar), and compare vs the bar that started the day (00:00 UTC).
- For each hourly bar[i], at close[i-1] (= open of bar[i]), we know:
    * current UTC hour of bar[i]
    * the close at 12:00 UTC of today (if past 12:00)
    * the open at 00:00 UTC of today
- Implementation: for each bar ending at time t (with UTC hour h):
    * If h in [13,21]: session is active
    * prior_session_return = (close at 12:00 of the current day / close at 00:00 of current day) - 1
    * We read close[i-1] with hour h (0-indexed, bar closes at h:00 UTC = bar represents h-1:00 to h:00)
    * Position at bar i = long (1.0) if h in [14..22] (bars DURING 13-21 UTC) AND prior session positive

Wait - let me be precise about 1h bar labeling:
  - A bar timestamped at "13:00 UTC" represents the candle from 12:00 to 13:00 UTC.
  - "close[13:00]" = price at end of 13:00 bar = price at 13:00 UTC.

For US session: we want to be long FROM 13:00 UTC TO 21:00 UTC.
  - We want to hold during bars whose close times are 14:00, 15:00, ..., 21:00 UTC
    (i.e., the bar from 13:00-14:00, ..., 20:00-21:00).

CAUSAL DECISION AT close[i]:
  - For each bar[i], we compute target[i] (what position to hold during bar i+1).
  - Bar i+1 closes at hour h+1.
  - We want to be long during bar i+1 if h+1 in {14,15,...,21}.
  - So target[i] = 1 if h in {13,...,20} AND prior_session_ret > 0.
  - prior_session_ret: from close at midnight (00:00 UTC) to close at noon (12:00 UTC) of the same day.
  - At close[i] with h in [13..20], we already know close[12:00] of today (it's in the past).

GRID: 3 variants tested to find best config:
  1. Pure time filter (no prior session condition)
  2. Prior session > 0 (baseline hypothesis)
  3. Prior session + vol-target scaling

We keep TF = 1h only (the hypothesis is inherently intraday on 1h bars).
Total backtests: 1 tf × 3 variants × 2 assets = 6. Within budget.
"""

import sys
sys.path.insert(0, "/opt/docker/PythagorasGoal/scripts/research/alt")
import altlib as al
import numpy as np
import pandas as pd


def _build_session_features(df: pd.DataFrame):
    """
    For each 1h bar at index i:
    - dt[i] = the UTC datetime when this bar closes (label of bar)
    - hour[i] = UTC hour of bar close
    - prior_session_ret[i] = return from close at 00:00 UTC to close at 12:00 UTC
      of the same day as bar[i], computed CAUSALLY (only available if bar[i] closes after 12:00 UTC).
    Returns (hour_arr, prior_session_ret_arr).
    """
    dt = pd.to_datetime(df["datetime"], utc=True)
    close = df["close"].values.astype(float)
    n = len(df)

    hour_arr = dt.dt.hour.values  # UTC hour of bar close

    # Build a lookup: for each (date, hour_target) -> close price
    # We need close at 00:00 UTC and close at 12:00 UTC for each date.
    #
    # The bar timestamped/labeled at 00:00 UTC closes at midnight = end of prior day.
    # So "open of day" price = close of the 23:00 bar (previous day) or close of 00:00 bar.
    #
    # Let's use simpler: close at 12:00 UTC bar (hour==12) as end of prior session.
    # Anchor = close at 00:00 UTC bar (hour==0) as start of day.
    # prior_session_ret = close[12:00] / close[00:00] - 1, for the same calendar date.
    #
    # To be causal at bar[i] with hour[i] >= 13: we need close[12:00] of same day,
    # which was available since 12:00 UTC (in the past).

    # Build date -> index of 00:00 and 12:00 bars
    dates = dt.dt.date.values

    # For each bar, find the closest prior-session data
    prior_ret = np.full(n, np.nan)

    # Create a series indexed by datetime for easy lookup
    close_series = pd.Series(close, index=dt)

    # Group by date to find the 00:00 and 12:00 anchors per day
    date_anchors = {}  # date -> (close_00, close_12)

    for i in range(n):
        d = dates[i]
        h = hour_arr[i]
        if d not in date_anchors:
            date_anchors[d] = [np.nan, np.nan]  # [close_00, close_12]
        if h == 0:
            date_anchors[d][0] = close[i]
        elif h == 12:
            date_anchors[d][1] = close[i]

    # Now fill prior_ret for each bar
    for i in range(n):
        d = dates[i]
        h = hour_arr[i]
        # Only compute if bar is in US session window and after 12:00 UTC
        if h >= 13 and d in date_anchors:
            c00, c12 = date_anchors[d]
            if np.isfinite(c00) and np.isfinite(c12) and c00 > 0:
                prior_ret[i] = c12 / c00 - 1.0

    return hour_arr, prior_ret


def target_time_only(df: pd.DataFrame) -> np.ndarray:
    """
    Variant 1: Pure US-session time filter (13-21 UTC), no prior-session condition.
    Long during US session hours, flat otherwise.
    target[i] = 1.0 if bar[i+1] is in US session, else 0.0
    = 1.0 if hour[i] in {13,...,20} (so bar i+1 closes at 14..21 UTC).
    """
    hour_arr, _ = _build_session_features(df)
    # target[i] = position held during bar i+1
    # bar i+1 closes at hour (hour_arr[i] + 1) % 24 approximately,
    # but let's use: hold long if hour[i] in 13..20 so we're long during 13:00->21:00 window
    target = np.where((hour_arr >= 13) & (hour_arr <= 20), 1.0, 0.0)
    return target


def target_prior_session_momentum(df: pd.DataFrame) -> np.ndarray:
    """
    Variant 2: Long during US session (13-21 UTC) ONLY IF prior session (00-12 UTC) was positive.
    """
    hour_arr, prior_ret = _build_session_features(df)

    # Propagate prior_ret within the US session of the same day
    # For bars in 13-21 UTC, prior_ret should already be set.
    # For continuity: once we set prior_ret at h=13, keep it for h=14..20 of same day.
    # Actually our loop sets it for all h>=13 of each day already.

    us_session = (hour_arr >= 13) & (hour_arr <= 20)
    prior_positive = np.isfinite(prior_ret) & (prior_ret > 0)

    target = np.where(us_session & prior_positive, 1.0, 0.0)
    return target


def target_prior_session_vol_targeted(df: pd.DataFrame) -> np.ndarray:
    """
    Variant 3: Like Variant 2 but with vol-targeting (20% annualized vol, cap 2x).
    """
    direction = target_prior_session_momentum(df)
    return al.vol_target(direction, df, target_vol=0.20, vol_win_days=30, leverage_cap=2.0)


if __name__ == "__main__":
    print("SEA08 — US-session momentum on 1h bars")
    print("Testing 3 variants on 1h TF...")
    print()

    # Variant 1: pure time filter
    rep1 = al.study_weights("SEA08-v1-time-only", target_time_only, tfs=("1h",))
    print(al.fmt(rep1))
    print()

    # Variant 2: prior session momentum condition
    rep2 = al.study_weights("SEA08-v2-prior-session", target_prior_session_momentum, tfs=("1h",))
    print(al.fmt(rep2))
    print()

    # Variant 3: vol-targeted version
    rep3 = al.study_weights("SEA08-v3-vol-target", target_prior_session_vol_targeted, tfs=("1h",))
    print(al.fmt(rep3))
    print()

    # Pick the best config by holdout Sharpe
    reps = [rep1, rep2, rep3]
    best = max(reps, key=lambda r: r["verdict"].get("best_holdout_sharpe", -9))

    print("=== BEST CONFIG ===")
    print(al.fmt(best))
    print()
    print("JSON:", al.as_json(best))