55b3574040
- THEME_SYMBOLS expanded: added banks, retail, telecom_it, property, healthcare, petrochem_materials, consumer_staples, utilities, nonbank_finance, exploration -> all 49 SET50 names now in a theme - THEME_LABELS_TH Thai labels; THEME_FREQUENCY per theme - symbol_breakdown now lists EVERY theme the symbol belongs to (label_th + surprise, or 'ยังไม่มีข้อมูล'), so theme_score is transparent per source - frontend: theme column maps all 49 symbols (mirrors backend); modal shows per-theme score detail - Fixed test for BANPU multi-theme; full suite 199 OK - Verified: 49/49 rows have theme chip; AOT modal shows ท่องเที่ยว 0.57σ + full calc
313 lines
12 KiB
Python
313 lines
12 KiB
Python
"""Multi-theme registry, symbol->theme exposure mapping, and combined scoring.
|
||
|
||
Aggregates the three Thai alternative-factor themes (tourism, auto_credit,
|
||
refining_energy) plus the Siamchart fundamental provider into a per-symbol
|
||
combined score, per the user's confirmed weighting:
|
||
|
||
combined = 0.6 * theme_score + 0.4 * siamchart_score
|
||
|
||
where `theme_score` is the mean of the enabled theme scores that cover a symbol
|
||
(so a symbol in several themes averages its theme scores), and `siamchart_score`
|
||
is a normalized fundamental score.
|
||
|
||
Frequency handling: theme scores carry an explicit `frequency` (daily/monthly/
|
||
quarterly/annual). Consumers must not mix different-frequency factors as if they
|
||
were the same timestamp — see `frequency` on each scored theme.
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import statistics
|
||
from dataclasses import dataclass
|
||
from typing import Optional
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Theme registry + symbol->theme exposure mapping
|
||
# ---------------------------------------------------------------------------
|
||
|
||
# Symbols known to belong to each theme. This is a *curated* partial mapping of
|
||
# the SET50 universe; symbols not listed here get no direct theme exposure for
|
||
# that theme (theme_score contribution = those themes' factor value applied via
|
||
# a generic market exposure fallback, see scoring).
|
||
#
|
||
# Expanded to cover the FULL SET50 universe (2026, 49 names): every symbol is
|
||
# assigned to at least one industry/theme so the board + per-symbol detail can
|
||
# always report a theme. Deterministic, curated by industry sector.
|
||
THEME_SYMBOLS: dict[str, set[str]] = {
|
||
"tourism": {
|
||
"AOT", "CENTEL", "MINT", "AWC", "CPN", "CRC", "BEM", "BTS", "ERW",
|
||
"DHOUSE", "MAJOR", "SNNP",
|
||
},
|
||
"auto_credit": {
|
||
"KKP", "TISCO", "TCAP", "THANI", "MTC", "SAWAD", "NSI", "AEONTS", "TK",
|
||
"THG", "GLAND", "ASI", "TGPRO",
|
||
},
|
||
"refining_energy": {
|
||
"PTT", "PTTGC", "TOP", "IRPC", "SPRC", "BCP", "ESSO", "BANPU", "GPSC",
|
||
},
|
||
"banks": {"BBL", "KBANK", "KTB", "SCB", "TTB"},
|
||
"retail": {"CPALL", "COM7", "GLOBAL", "HMPRO", "OSP", "OR", "CPN", "CRC"},
|
||
"telecom_it": {"ADVANC", "TRUE", "DELTA", "COM7"},
|
||
"property": {"LH", "AWC", "CPN", "CRC", "GLOBAL", "HMPRO"},
|
||
"healthcare": {"BDMS", "BH"},
|
||
"petrochem_materials": {"IVL", "SCC", "SCGP", "PTTGC", "BANPU"},
|
||
"consumer_staples": {"CPF", "TU", "OSP", "CBG"},
|
||
"utilities": {"BGRIM", "EGCO", "RATCH", "GPSC", "GULF", "BANPU", "EA"},
|
||
"nonbank_finance": {"JMT", "JMART", "KTC", "TIDLOR", "MTC", "SAWAD", "KTC", "AEONTS"},
|
||
"exploration": {"PTTEP", "PTT"},
|
||
}
|
||
|
||
# Theme frequency (data cadence of the underlying factor). Used to keep
|
||
# multi-frequency factors from being mixed as same-timestamp.
|
||
THEME_FREQUENCY: dict[str, str] = {
|
||
"tourism": "monthly",
|
||
"auto_credit": "monthly",
|
||
"refining_energy": "quarterly",
|
||
"banks": "quarterly",
|
||
"retail": "monthly",
|
||
"telecom_it": "quarterly",
|
||
"property": "quarterly",
|
||
"healthcare": "quarterly",
|
||
"petrochem_materials": "quarterly",
|
||
"consumer_staples": "quarterly",
|
||
"utilities": "quarterly",
|
||
"nonbank_finance": "quarterly",
|
||
"exploration": "quarterly",
|
||
}
|
||
|
||
# Thai labels for every theme (used in the board theme column + per-symbol view)
|
||
THEME_LABELS_TH: dict[str, str] = {
|
||
"tourism": "ท่องเที่ยว",
|
||
"auto_credit": "รถยนต์/สินเชื่อ",
|
||
"refining_energy": "พลังงาน/โรงกลั่น",
|
||
"banks": "ธนาคาร",
|
||
"retail": "ค้าปลีก",
|
||
"telecom_it": "สื่อสาร/ไอที",
|
||
"property": "อสังหาริมทรัพย์",
|
||
"healthcare": "โรงพยาบาล",
|
||
"petrochem_materials": "ปิโตรเคมี/วัสดุ",
|
||
"consumer_staples": "อาหาร/อุปโภค",
|
||
"utilities": "สาธารณูปโภค",
|
||
"nonbank_finance": "การเงินนอกธนาคาร",
|
||
"exploration": "สำรวจ/ผลิตพลังงาน",
|
||
}
|
||
|
||
|
||
@dataclass
|
||
class Theme:
|
||
id: str
|
||
label_en: str
|
||
label_th: str
|
||
frequency: str
|
||
source: str
|
||
enabled: bool = True
|
||
|
||
|
||
def list_themes() -> list[Theme]:
|
||
return [
|
||
Theme("tourism", "Tourism Pulse", "การท่องเที่ยว", "monthly", "BOT tourism", enabled=True),
|
||
Theme("auto_credit", "Auto Credit Cycle", "สินเชื่อรถยนต์", "monthly", "TradingEconomics car sales", enabled=True),
|
||
Theme("refining_energy", "Refining / Energy", "โรงกลั่น/พลังงาน", "quarterly", "Thai Oil (TOP) financials", enabled=True),
|
||
]
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Scoring helpers
|
||
# ---------------------------------------------------------------------------
|
||
def _zscore(values: list) -> dict:
|
||
"""Normalize a list of floats to z-scores, clamped to [-3, 3]."""
|
||
n = len(values)
|
||
if n == 0:
|
||
return {}
|
||
mean = sum(values) / n
|
||
var = sum((v - mean) ** 2 for v in values) / n
|
||
std = var ** 0.5 or 1.0
|
||
out = {}
|
||
for i, v in enumerate(values):
|
||
z = (v - mean) / std
|
||
out[i] = max(-3.0, min(3.0, z))
|
||
return out
|
||
|
||
|
||
def _map_index(symbols: list[str]) -> dict[str, int]:
|
||
return {s: i for i, s in enumerate(symbols)}
|
||
|
||
|
||
def build_theme_scores(theme_id: str, signals: list[dict]) -> dict[str, float]:
|
||
"""Score every symbol in a theme's signal list.
|
||
|
||
`signals` is the tourism-style list of per-symbol signal dicts with
|
||
`score` (higher = more bullish) and `symbol`.
|
||
"""
|
||
out: dict[str, float] = {}
|
||
for sig in signals:
|
||
sym = sig.get("symbol")
|
||
score = sig.get("score")
|
||
if sym and score is not None:
|
||
out[sym] = float(score)
|
||
# z-normalize across scored symbols so theme scores are comparable.
|
||
syms = list(out.keys())
|
||
values = [out[s] for s in syms]
|
||
z = _zscore(values)
|
||
return {s: z.get(i, 0.0) for i, s in enumerate(syms)}
|
||
|
||
|
||
def build_siamchart_score(factors: dict) -> dict[str, float]:
|
||
"""Derive a normalized fundamental score from the Siamchart factor view.
|
||
|
||
Uses EPS growth YoY and dividend yield as the "value+quality" signals.
|
||
Positive EPS growth and higher yield both push the score up.
|
||
"""
|
||
out: dict[str, float] = {}
|
||
for f in factors.get("factors", []):
|
||
sym = f.get("symbol")
|
||
if not sym:
|
||
continue
|
||
g = f.get("eps_growth_yoy")
|
||
d = f.get("dividend_yield") or 0.0
|
||
g = float(g) if g is not None else 0.0
|
||
# combine growth and yield; yield adds a floor so dividend names get weight
|
||
out[sym] = g + d * 2.0
|
||
syms = list(out.keys())
|
||
z = _zscore([out[s] for s in syms])
|
||
return {s: z.get(i, 0.0) for i, s in enumerate(syms)}
|
||
|
||
|
||
def combine_score(theme_scores: list[dict[str, float]], siamchart_score: dict[str, float],
|
||
weight_theme: float = 0.6, weight_siamchart: float = 0.4) -> dict[str, dict]:
|
||
"""Combine per-symbol theme (averaged) and siamchart scores into final.
|
||
|
||
Returns {symbol: {'theme_score', 'siamchart_score', 'combined', 'themes':[...]}}.
|
||
"""
|
||
all_syms: dict[str, list[float]] = {}
|
||
theme_membership: dict[str, list[str]] = {}
|
||
|
||
for ts in theme_scores:
|
||
for sym, val in ts.items():
|
||
all_syms.setdefault(sym, []).append(val)
|
||
theme_membership.setdefault(sym, []).append(sym)
|
||
|
||
merged: dict[str, dict] = {}
|
||
# every symbol that has a siamchart score OR a theme score
|
||
universe = set(all_syms) | set(siamchart_score)
|
||
for sym in universe:
|
||
tl = all_syms.get(sym, [])
|
||
tavg = (sum(tl) / len(tl)) if tl else 0.0
|
||
sc = siamchart_score.get(sym, 0.0)
|
||
combined = weight_theme * tavg + weight_siamchart * sc
|
||
merged[sym] = {
|
||
"theme_score": tavg,
|
||
"siamchart_score": sc,
|
||
"combined": combined,
|
||
"themes": theme_membership.get(sym, []),
|
||
}
|
||
return merged
|
||
|
||
|
||
def symbol_breakdown(
|
||
symbol: str,
|
||
*,
|
||
factor_view: dict,
|
||
theme_surprises: dict[str, float],
|
||
latest_price: Optional[float] = None,
|
||
price_date: str = "",
|
||
weight_theme: float = 0.6,
|
||
weight_siamchart: float = 0.4,
|
||
) -> dict:
|
||
"""Transparent per-symbol scoring breakdown.
|
||
|
||
Shows exactly how `combined` was derived:
|
||
theme_score = mean of the theme surprise scores covering this symbol
|
||
siamchart_score = z-scored (EPS growth + dividend_yield*2)
|
||
combined = weight_theme*theme_score + weight_siamchart*siamchart_score
|
||
|
||
Returns a dict suitable for the /api/v1/symbols/<symbol> view. Deterministic
|
||
and reuses the same formula as `combine_score` so the board and the detail
|
||
always agree.
|
||
"""
|
||
# the themes this symbol belongs to (from the curated exposure map)
|
||
member_themes = [tid for tid, syms in THEME_SYMBOLS.items() if symbol in syms]
|
||
theme_lines = []
|
||
theme_values = []
|
||
for tid in member_themes:
|
||
s = theme_surprises.get(tid)
|
||
if s is not None:
|
||
theme_values.append(float(s))
|
||
theme_lines.append({
|
||
"theme": tid,
|
||
"label_th": THEME_LABELS_TH.get(tid, tid),
|
||
"surprise": round(float(s), 3),
|
||
})
|
||
else:
|
||
theme_lines.append({
|
||
"theme": tid,
|
||
"label_th": THEME_LABELS_TH.get(tid, tid),
|
||
"surprise": None,
|
||
})
|
||
theme_score = (sum(theme_values) / len(theme_values)) if theme_values else 0.0
|
||
|
||
# find the factor row for this symbol
|
||
fac = next((f for f in factor_view.get("factors", []) if f.get("symbol") == symbol), {})
|
||
g = fac.get("eps_growth_yoy")
|
||
d = fac.get("dividend_yield") or 0.0
|
||
g = float(g) if g is not None else 0.0
|
||
raw_siamchart = g + d * 2.0
|
||
|
||
# z-score against the full universe (same as build_siamchart_score); capture
|
||
# the population stats so the view can show HOW -2.8 became -0.588.
|
||
siamchart_map = build_siamchart_score(factor_view)
|
||
siamchart_score = siamchart_map.get(symbol, 0.0)
|
||
# recompute the population of raw scores to expose mean / stdev
|
||
raw_values = []
|
||
for f in factor_view.get("factors", []):
|
||
if not f.get("symbol"):
|
||
continue
|
||
gg = f.get("eps_growth_yoy")
|
||
dd = f.get("dividend_yield") or 0.0
|
||
gg = float(gg) if gg is not None else 0.0
|
||
raw_values.append(gg + dd * 2.0)
|
||
pop_mean = statistics.mean(raw_values) if raw_values else 0.0
|
||
pop_stdev = statistics.pstdev(raw_values) if raw_values else 0.0
|
||
|
||
combined = round(weight_theme * theme_score + weight_siamchart * siamchart_score, 3)
|
||
|
||
return {
|
||
"symbol": symbol,
|
||
"company_name": fac.get("company_name", ""),
|
||
"themes": member_themes,
|
||
"theme_contributions": theme_lines,
|
||
"theme_score": round(theme_score, 3),
|
||
"siamchart_score": round(siamchart_score, 3),
|
||
"siamchart_components": {
|
||
"eps_growth_yoy": fac.get("eps_growth_yoy"),
|
||
"dividend_yield": fac.get("dividend_yield"),
|
||
"raw_growth_plus_yield_2x": round(raw_siamchart, 3),
|
||
},
|
||
"siamchart_z_note": {
|
||
"formula": "z = (raw_i - mean) / stdev",
|
||
"raw_i": round(raw_siamchart, 3),
|
||
"population_mean": round(pop_mean, 3),
|
||
"population_stdev": round(pop_stdev, 3),
|
||
"universe_size": len(raw_values),
|
||
},
|
||
"combined_calc": [
|
||
{"label": "คะแนนธีม", "value": round(theme_score, 3), "weight": weight_theme,
|
||
"note": "ค่าเฉลี่ยของ theme surprise ที่หุ้นนี้อยู่ใน", "term": f"{theme_score:.3f} × {weight_theme}"},
|
||
{"label": "คะแนนพื้นฐาน", "value": round(siamchart_score, 3), "weight": weight_siamchart,
|
||
"note": f"z-score ของ ((EPS growth {g:+.1f}%) + ปันผล {d:.1f}%×2) เมื่อเทียบทั้ง universe",
|
||
"term": f"{siamchart_score:.3f} × {weight_siamchart}"},
|
||
],
|
||
"combined_score": combined,
|
||
"combined_formula": f"({theme_score:.3f} × {weight_theme}) + ({siamchart_score:.3f} × {weight_siamchart}) = {combined}",
|
||
"weights": {"theme": weight_theme, "siamchart": weight_siamchart},
|
||
"fundamentals": {
|
||
"pe": fac.get("pe"),
|
||
"eps": fac.get("eps"),
|
||
"pbv": fac.get("pbv"),
|
||
"roe": fac.get("roe"),
|
||
"dps": fac.get("dps"),
|
||
"is_dividend": fac.get("is_dividend"),
|
||
},
|
||
"price": {"latest": latest_price, "date": price_date},
|
||
}
|