from __future__ import annotations

import json
import math
from dataclasses import asdict, dataclass, field
from typing import Any

from crypto_spot_bot.config import Settings
from crypto_spot_bot.models import Candle


@dataclass(slots=True)
class TimeSeriesForecast:
    enabled: bool
    usable: bool
    model: str
    volatility_model: str
    expected_return_percent: float
    expected_price: float
    volatility_percent: float
    probability_up: float
    confidence_adjustment: float
    block_entry: bool
    validation_mae_percent: float
    baseline_mae_percent: float
    skill: float
    horizon: int
    reason: str
    candidates: list[dict[str, Any]] = field(default_factory=list)

    def as_dict(self) -> dict[str, Any]:
        return asdict(self)


class TimeSeriesForecaster:
    def __init__(self, settings: Settings):
        self.settings = settings
        self._lstm_artifact_mtime: float | None = None
        self._lstm_artifact: dict[str, Any] = {}

    def forecast(self, candles: list[Candle], symbol: str | None = None) -> TimeSeriesForecast:
        if not self.settings.time_series_forecast_enabled:
            return _empty_forecast(False, "прогноз временных рядов выключен")
        closes = [float(candle.close) for candle in candles if candle.close > 0]
        min_candles = max(30, self.settings.time_series_min_candles)
        if len(closes) < min_candles:
            return _empty_forecast(True, "недостаточно свечей для PyTorch прогноза")
        returns = _log_returns(closes)
        if len(returns) < 20:
            return _empty_forecast(True, "недостаточно доходностей для PyTorch прогноза")

        artifact = self._load_lstm_artifact()
        model = _torch_recurrent_model_name(symbol, artifact)
        if not model or not _can_use_torch_recurrent(returns, symbol, artifact):
            return _empty_forecast(True, "нет валидной PyTorch LSTM/GRU модели для пары")
        entry = _torch_recurrent_entry(symbol, artifact)
        prediction = _torch_recurrent_predict(returns, symbol, artifact)
        if entry is None or prediction is None:
            return _empty_forecast(True, "PyTorch LSTM/GRU модель не смогла построить прогноз")

        horizon = max(1, self.settings.time_series_forecast_horizon)
        expected_return = prediction * horizon
        expected_price = closes[-1] * math.exp(expected_return)
        model_mae = _torch_validation_mae(entry, returns)
        baseline_mae = max(_float_entry(entry, "baseline_mae_percent", model_mae * 100) / 100, model_mae)
        uncertainty_one_step = max(model_mae, _return_scale(returns) * 0.25, 1e-9)
        uncertainty = uncertainty_one_step * math.sqrt(horizon)
        volatility_percent = uncertainty * 100
        expected_return_percent = (math.exp(expected_return) - 1) * 100
        probability_up = _normal_cdf(expected_return / max(uncertainty, 1e-9))
        skill = _clamp(_float_entry(entry, "skill", 0.0), -1.0, 1.0)
        min_edge = max(0.0, self.settings.time_series_min_edge_percent)
        confidence_adjustment = _confidence_adjustment(
            expected_return_percent=expected_return_percent,
            probability_up=probability_up,
            skill=skill,
            min_edge=min_edge,
            max_adjustment=self.settings.time_series_max_adjustment,
        )
        block_entry = bool(expected_return_percent <= -min_edge and probability_up <= 0.45)
        reason = _reason(
            model=model,
            expected_return_percent=expected_return_percent,
            probability_up=probability_up,
            skill=skill,
            block_entry=block_entry,
        )
        return TimeSeriesForecast(
            enabled=True,
            usable=True,
            model=model,
            volatility_model="torch validation MAE",
            expected_return_percent=round(expected_return_percent, 4),
            expected_price=round(expected_price, 8),
            volatility_percent=round(volatility_percent, 4),
            probability_up=round(probability_up, 4),
            confidence_adjustment=round(confidence_adjustment, 4),
            block_entry=block_entry,
            validation_mae_percent=round(model_mae * 100, 4),
            baseline_mae_percent=round(baseline_mae * 100, 4),
            skill=round(skill, 4),
            horizon=horizon,
            reason=reason,
            candidates=[{"model": model, "mae_percent": round(model_mae * 100, 4)}],
        )

    def _load_lstm_artifact(self) -> dict[str, Any]:
        if not self.settings.time_series_lstm_enabled:
            return {}
        path = self.settings.time_series_lstm_model_path
        try:
            stat = path.stat()
        except OSError:
            self._lstm_artifact_mtime = None
            self._lstm_artifact = {}
            return {}
        if self._lstm_artifact_mtime == stat.st_mtime:
            return self._lstm_artifact
        try:
            data = json.loads(path.read_text(encoding="utf-8"))
        except (OSError, json.JSONDecodeError):
            data = {}
        self._lstm_artifact = data if isinstance(data, dict) else {}
        self._lstm_artifact_mtime = stat.st_mtime
        return self._lstm_artifact


def _empty_forecast(enabled: bool, reason: str) -> TimeSeriesForecast:
    return TimeSeriesForecast(
        enabled=enabled,
        usable=False,
        model="none",
        volatility_model="none",
        expected_return_percent=0.0,
        expected_price=0.0,
        volatility_percent=0.0,
        probability_up=0.5,
        confidence_adjustment=0.0,
        block_entry=False,
        validation_mae_percent=0.0,
        baseline_mae_percent=0.0,
        skill=0.0,
        horizon=0,
        reason=reason,
    )


def _log_returns(closes: list[float]) -> list[float]:
    return [math.log(closes[index] / closes[index - 1]) for index in range(1, len(closes))]


def _torch_recurrent_model_name(symbol: str | None, artifact: dict[str, Any]) -> str | None:
    entry = _torch_recurrent_entry(symbol, artifact)
    if not entry:
        return None
    architecture = str(entry.get("architecture", "")).strip().lower()
    if architecture in {"lstm", "gru"}:
        return f"torch_{architecture}"
    model = str(entry.get("model", "")).strip().lower()
    return model if model in {"torch_lstm", "torch_gru"} else None


def _torch_recurrent_entry(symbol: str | None, artifact: dict[str, Any]) -> dict[str, Any] | None:
    if artifact.get("type") != "pytorch_recurrent_forecaster":
        return None
    symbols = artifact.get("symbols")
    entry = symbols.get(symbol.upper()) if symbol and isinstance(symbols, dict) else None
    if not isinstance(entry, dict):
        default = artifact.get("default")
        entry = default if isinstance(default, dict) else None
    if not isinstance(entry, dict):
        return None
    if not isinstance(entry.get("state_dict"), dict):
        return None
    return entry


def _can_use_torch_recurrent(returns: list[float], symbol: str | None, artifact: dict[str, Any]) -> bool:
    entry = _torch_recurrent_entry(symbol, artifact)
    if not entry:
        return False
    lookback = int(_clamp(_float_entry(entry, "lookback", 0.0), 4.0, 512.0))
    hidden_size = int(_clamp(_float_entry(entry, "hidden_size", 0.0), 1.0, 512.0))
    num_layers = int(_clamp(_float_entry(entry, "num_layers", 1.0), 1.0, 8.0))
    return len(returns) >= lookback + 1 and hidden_size > 0 and num_layers > 0


def _torch_recurrent_predict(
    returns: list[float],
    symbol: str | None,
    artifact: dict[str, Any],
) -> float | None:
    entry = _torch_recurrent_entry(symbol, artifact)
    model_name = _torch_recurrent_model_name(symbol, artifact)
    if not entry or not model_name:
        return None
    lookback = int(_clamp(_float_entry(entry, "lookback", 0.0), 4.0, 512.0))
    hidden_size = int(_clamp(_float_entry(entry, "hidden_size", 0.0), 1.0, 512.0))
    num_layers = int(_clamp(_float_entry(entry, "num_layers", 1.0), 1.0, 8.0))
    mean = _float_entry(entry, "mean", 0.0)
    scale = max(_float_entry(entry, "scale", _return_scale(returns)), 1e-8)
    clip = _clamp(_float_entry(entry, "clip", 8.0), 1.0, 50.0)
    if len(returns) < lookback:
        return None

    normalized = [_clamp((value - mean) / scale, -clip, clip) for value in returns[-lookback:]]
    try:
        hidden = _torch_recurrent_hidden(
            normalized,
            entry=entry,
            model_name=model_name,
            hidden_size=hidden_size,
            num_layers=num_layers,
        )
        if hidden is None:
            return None
        head_weight = _float_vector(entry.get("head_weight"))
        head_bias = _float_entry(entry, "head_bias", 0.0)
        if len(head_weight) != hidden_size:
            return None
        normalized_prediction = sum(weight * value for weight, value in zip(head_weight, hidden)) + head_bias
        if not math.isfinite(normalized_prediction):
            return None
        prediction = _clamp(normalized_prediction, -clip, clip) * scale + mean
    except (IndexError, KeyError, TypeError, ValueError, OverflowError):
        return None

    recent_abs = sorted(abs(value) for value in returns[-48:]) if len(returns) >= 8 else [0.01]
    cap = max(recent_abs[int(len(recent_abs) * 0.9)], 0.0002)
    return _clamp(prediction, -cap, cap)


def _torch_recurrent_hidden(
    normalized: list[float],
    *,
    entry: dict[str, Any],
    model_name: str,
    hidden_size: int,
    num_layers: int,
) -> list[float] | None:
    state = entry.get("state_dict")
    if not isinstance(state, dict):
        return None
    h_layers = [[0.0 for _ in range(hidden_size)] for _ in range(num_layers)]
    c_layers = [[0.0 for _ in range(hidden_size)] for _ in range(num_layers)]
    for value in normalized:
        layer_input = [value]
        for layer in range(num_layers):
            if model_name == "torch_lstm":
                next_hidden, next_cell = _torch_lstm_step(layer_input, h_layers[layer], c_layers[layer], state, layer)
                h_layers[layer] = next_hidden
                c_layers[layer] = next_cell
            elif model_name == "torch_gru":
                h_layers[layer] = _torch_gru_step(layer_input, h_layers[layer], state, layer)
            else:
                return None
            layer_input = h_layers[layer]
    return h_layers[-1]


def _torch_lstm_step(
    inputs: list[float],
    hidden: list[float],
    cell: list[float],
    state: dict[str, Any],
    layer: int,
) -> tuple[list[float], list[float]]:
    hidden_size = len(hidden)
    gates = _torch_gate_values(inputs, hidden, state, layer, gate_count=4)
    input_gate = [_sigmoid(value) for value in gates[0]]
    forget_gate = [_sigmoid(value) for value in gates[1]]
    cell_gate = [math.tanh(value) for value in gates[2]]
    output_gate = [_sigmoid(value) for value in gates[3]]
    next_cell = [
        forget_gate[index] * cell[index] + input_gate[index] * cell_gate[index]
        for index in range(hidden_size)
    ]
    next_hidden = [
        output_gate[index] * math.tanh(next_cell[index])
        for index in range(hidden_size)
    ]
    return next_hidden, next_cell


def _torch_gru_step(
    inputs: list[float],
    hidden: list[float],
    state: dict[str, Any],
    layer: int,
) -> list[float]:
    hidden_size = len(hidden)
    weight_ih = _float_matrix(state[f"weight_ih_l{layer}"])
    weight_hh = _float_matrix(state[f"weight_hh_l{layer}"])
    bias_ih = _float_vector(state[f"bias_ih_l{layer}"])
    bias_hh = _float_vector(state[f"bias_hh_l{layer}"])

    def gate_input(gate: int) -> list[float]:
        start = gate * hidden_size
        output = []
        for index in range(hidden_size):
            row = start + index
            output.append(_dot(weight_ih[row], inputs) + bias_ih[row])
        return output

    def gate_hidden(gate: int) -> list[float]:
        start = gate * hidden_size
        output = []
        for index in range(hidden_size):
            row = start + index
            output.append(_dot(weight_hh[row], hidden) + bias_hh[row])
        return output

    reset_input = gate_input(0)
    update_input = gate_input(1)
    new_input = gate_input(2)
    reset_hidden = gate_hidden(0)
    update_hidden = gate_hidden(1)
    new_hidden = gate_hidden(2)

    reset_gate = [_sigmoid(reset_input[index] + reset_hidden[index]) for index in range(hidden_size)]
    update_gate = [_sigmoid(update_input[index] + update_hidden[index]) for index in range(hidden_size)]
    candidate = [
        math.tanh(new_input[index] + reset_gate[index] * new_hidden[index])
        for index in range(hidden_size)
    ]
    return [
        (1 - update_gate[index]) * candidate[index] + update_gate[index] * hidden[index]
        for index in range(hidden_size)
    ]


def _torch_gate_values(
    inputs: list[float],
    hidden: list[float],
    state: dict[str, Any],
    layer: int,
    gate_count: int,
) -> list[list[float]]:
    hidden_size = len(hidden)
    weight_ih = _float_matrix(state[f"weight_ih_l{layer}"])
    weight_hh = _float_matrix(state[f"weight_hh_l{layer}"])
    bias_ih = _float_vector(state[f"bias_ih_l{layer}"])
    bias_hh = _float_vector(state[f"bias_hh_l{layer}"])
    gates: list[list[float]] = []
    for gate in range(gate_count):
        values = []
        start = gate * hidden_size
        for index in range(hidden_size):
            row = start + index
            values.append(_dot(weight_ih[row], inputs) + _dot(weight_hh[row], hidden) + bias_ih[row] + bias_hh[row])
        gates.append(values)
    return gates


def _torch_validation_mae(entry: dict[str, Any], returns: list[float]) -> float:
    mae_percent = _float_entry(entry, "validation_mae_percent", 0.0)
    if mae_percent > 0:
        return mae_percent / 100
    return _return_scale(returns)


def _float_entry(data: dict[str, Any], key: str, default: float) -> float:
    value = data.get(key)
    if isinstance(value, (int, float)):
        return float(value)
    if isinstance(value, str):
        try:
            return float(value)
        except ValueError:
            return default
    return default


def _float_vector(data: Any) -> list[float]:
    if not isinstance(data, list):
        return []
    return [float(value) for value in data]


def _float_matrix(data: Any) -> list[list[float]]:
    if not isinstance(data, list):
        return []
    return [_float_vector(row) for row in data]


def _dot(left: list[float], right: list[float]) -> float:
    return sum(left[index] * right[index] for index in range(min(len(left), len(right))))


def _return_scale(returns: list[float]) -> float:
    recent = returns[-120:] if len(returns) > 120 else returns
    values = sorted(abs(value) for value in recent if math.isfinite(value))
    if not values:
        return 0.0005
    median = values[len(values) // 2]
    mean = sum(values) / len(values)
    return max(max(median, mean * 0.5), 1e-5)


def _sigmoid(value: float) -> float:
    if value >= 40:
        return 1.0
    if value <= -40:
        return 0.0
    return 1 / (1 + math.exp(-value))


def _confidence_adjustment(
    *,
    expected_return_percent: float,
    probability_up: float,
    skill: float,
    min_edge: float,
    max_adjustment: float,
) -> float:
    edge = abs(expected_return_percent) - min_edge
    if edge <= 0:
        return 0.0
    direction = 1.0 if expected_return_percent > 0 and probability_up >= 0.55 else -1.0
    if direction < 0 and probability_up > 0.45:
        return 0.0
    strength = _clamp(edge / max(min_edge, 0.05), 0.0, 1.0)
    probability_strength = _clamp(abs(probability_up - 0.5) / 0.25, 0.0, 1.0)
    skill_strength = _clamp((skill + 0.03) / 0.18, 0.25, 1.0)
    return direction * _clamp(max_adjustment, 0.0, 0.18) * strength * probability_strength * skill_strength


def _reason(
    *,
    model: str,
    expected_return_percent: float,
    probability_up: float,
    skill: float,
    block_entry: bool,
) -> str:
    if block_entry:
        return f"модель {model}: ожидаемое движение вниз {expected_return_percent:.3f}%, P(рост)={probability_up:.2f}"
    return f"модель {model}: прогноз {expected_return_percent:.3f}%, P(рост)={probability_up:.2f}, skill={skill:.3f}"


def _normal_cdf(value: float) -> float:
    return 0.5 * (1 + math.erf(value / math.sqrt(2)))


def _clamp(value: float, low: float, high: float) -> float:
    return max(low, min(high, value))