set50-system/backend/app/factors.py

"""Declarative FACTORS registry — the single source of truth for every factor.

Each factor is a plain-data unit describing:
  - where the data comes from (source + fetch module + which key holds the value)
  - its data frequency (for frequency alignment, never naive mixing)
  - its SIGN (+1 = higher value is bullish for a theme, -1 = bearish)
  - a default weight (themes override per-theme)

ADDING A NEW DATA SOURCE/FACTOR = append one entry here + (optionally) a theme
factor line. It requires NO change to any scoring function. This is what makes the
analysis engine data-driven and auditable.
"""

from __future__ import annotations

import math
import statistics
from typing import Any, Callable, Optional

# fetch key -> module that exposes a fetch_<...>() callable returning .to_dict()
_FETCH_MODULE: dict[str, str] = {
    "tourism": "bot_tourism",
    "auto_credit": "auto_credit",
    "auto_npl": "auto_npl",
    "bank_npl": "bank_npl",
    "energy_thai": "energy_thai",
    "macro_thai": "macro_thai",
}

# Factor -> value key. Sign: +1 higher-is-bullish, -1 lower-is-bullish.
# weight: default global weight; themes may override.
FACTORS: dict[str, dict[str, Any]] = {
    # ---- real Thai collectors ----
    "tourism_arrivals_ytd": {
        "name_th": "นักท่องเที่ยวสะสมปี",
        "source": "BOT",
        "frequency": "monthly",
        "fetch": "macro_thai",
        "value_key": "tourists_ytd_mn",
        "sign": 1,
        "weight": 1.0,
        "center": 20.0, "span": 15.0,  # cumulative arrivals in millions, ~20mn neutral
    },
    "auto_sales_yoy": {
        "name_th": "ยอดขายรถยนต์ (YoY)",
        "source": "TradingEconomics",
        "frequency": "monthly",
        "fetch": "auto_credit",
        "value_key": "new_car_sales_yoy",
        "sign": 1,
        "weight": 1.0,
        "center": 5.0, "span": 10.0,  # YoY %, ~5% long-run growth
    },
    "auto_production": {
        "name_th": "การผลิตรถยนต์",
        "source": "TradingEconomics",
        "frequency": "monthly",
        "fetch": "auto_credit",
        "value_key": "vehicle_production",
        "sign": 1,
        "weight": 0.4,
        "center": 0.0, "span": 200000.0,  # units/month (~117K), scale captured as level
    },
    "auto_exports": {
        "name_th": "ส่งออกรถยนต์",
        "source": "TradingEconomics",
        "frequency": "monthly",
        "fetch": "auto_credit",
        "value_key": "auto_exports",
        "sign": 1,
        "weight": 0.3,
        "center": 0.0, "span": 200000.0,  # units (~82K), scale captured as level
    },
    "auto_npl": {
        "name_th": "NPL รถยนต์",
        "source": "BOT",
        "frequency": "quarterly",
        "fetch": "auto_npl",
        "value_key": "pct_of_npls",
        "sign": -1,
        "weight": 1.0,
        "center": 3.0, "span": 5.0,  # NPL as % of loans, ~3% neutral
    },
    "bank_npl": {
        "name_th": "NPL ภาคการเงิน",
        "source": "BOT",
        "frequency": "quarterly",
        "fetch": "bank_npl",
        "value_key": "pct_of_npls",
        "sign": -1,
        "weight": 1.0,
        "center": 0.5, "span": 3.0,  # financial-sector NPL share (~0.5-5%)
    },
    "energy_net_margin": {
        "name_th": "กำไรสุทธิโรงกลั่น",
        "source": "TOP",
        "frequency": "quarterly",
        "fetch": "energy_thai",
        "value_key": "net_margin_quarter",
        "sign": 1,
        "weight": 1.0,
        "center": 5.0, "span": 10.0,  # net margin % (derived from quarterly)
    },
    # ---- macro backdrop (proxy for expanded SET50 themes) ----
    "macro_consumption": {
        "name_th": "การบริโภคภาคเอกชน (YoY)",
        "source": "BOT",
        "frequency": "monthly",
        "fetch": "macro_thai",
        "value_key": "private_consumption_yoy",
        "sign": 1,
        "weight": 1.0,
        "center": 3.0, "span": 10.0,  # YoY %, ~3% trend
    },
    "macro_investment": {
        "name_th": "การลงทุนภาคเอกชน (YoY)",
        "source": "BOT",
        "frequency": "monthly",
        "fetch": "macro_thai",
        "value_key": "private_investment_yoy",
        "sign": 1,
        "weight": 1.0,
        "center": 5.0, "span": 10.0,  # YoY %, ~5% trend
    },
    "macro_mfg": {
        "name_th": "ผลผลิตภาคอุตสาหกรรม (MPI)",
        "source": "BOT",
        "frequency": "monthly",
        "fetch": "macro_thai",
        "value_key": "manufacturing_yoy",
        "sign": 1,
        "weight": 1.0,
        "center": 0.0, "span": 10.0,  # YoY %, ~0 neutral
    },
    "macro_inflation": {
        "name_th": "เงินเฟ้อ",
        "source": "BOT",
        "frequency": "monthly",
        "fetch": "macro_thai",
        "value_key": "headline_inflation_yoy",
        "sign": -1,
        "weight": 0.5,
        "center": 2.0, "span": 10.0,  # ~2% target; higher is worse (sign -1)
    },
}


class FactorError(ValueError):
    pass


def factor_value(fact: dict, fetched: Optional[dict]) -> Optional[float]:
    """Pull the numeric value out of a fetched collector dict for a factor."""
    key = fact.get("value_key")
    if fetched is None:
        return None
    if fact.get("fetch") == "energy_thai":
        # derive a single metric from the quarterly dict
        q = fetched.get("quarterly") or {}
        if isinstance(q, dict):
            row = next((v for v in q.values() if isinstance(v, dict)), {})
            np_ = row.get("net_profit")
            rev = row.get("sales")
            if np_ is not None and rev:
                try:
                    margin = float(np_) / float(rev) * 100.0  # net margin %
                except (TypeError, ValueError, ZeroDivisionError):
                    return None
                return margin if math.isfinite(margin) else None
        return None
    if key is None:
        return None
    val = fetched.get(key)
    try:
        out = float(val) if val is not None else None
    except (TypeError, ValueError):
        return None
    if out is None or not math.isfinite(out):
        return None
    return out


def normalize(value: Optional[float], sign: int = 1,
              center: float = 0.0, span: float = 10.0) -> Optional[float]:
    """Deterministic bounded normalization: sign-aware, clamped to [-1, +1].

    value == center -> 0. positive beyond center (for sign=+1) -> positive.
    Non-finite values (NaN/inf) are rejected rather than propagated.
    """
    if value is None:
        return None
    try:
        value = float(value)
    except (TypeError, ValueError):
        return None
    if not math.isfinite(value):
        return None
    if span <= 0:
        span = 1.0
    num = (value - center) / span * float(sign)
    return round(min(max(num, -1.0), 1.0), 4)


def z_score(value: float, population: list[float]) -> float:
    """Population z-score with tiny-stdev guard (deterministic)."""
    if not population:
        return 0.0
    mean = statistics.fmean(population)
    stdev = statistics.pstdev(population)
    if stdev < 1e-9:
        return 0.0
    return round((float(value) - mean) / stdev * 10.0, 4)  # scale to decile-ish