Files

160 lines
6.2 KiB
Python

"""Build the dated SET100 universe from public SET constituent publications.
The symbol snapshots below are transcribed from the official SET PDFs listed in
data/universes/README.md. The 2025 H1 events are dated from SET's index notices.
"""
from __future__ import annotations
import csv
from collections import defaultdict
from dataclasses import dataclass
from datetime import date, timedelta
from pathlib import Path
HERE = Path(__file__).resolve().parent
def symbols(value: str) -> set[str]:
return set(value.split())
SET100_H2_2024 = symbols("""
AAV ADVANC AEONTS AMATA AOT AP AWC BA BAM BANPU BBL BCH BCP BCPG BDMS BEM
BGRIM BH BJC BLA BSRC BTG BTS CBG CENTEL CHG CK CKP COM7 CPALL CPF CPN CRC
DELTA DOHOME EA EGCO ERW GLOBAL GPSC GULF GUNKUL HANA HMPRO ICHI INTUCH IRPC
ITC IVL JAS JMART JMT KBANK KCE KKP KTB KTC LH M MBK MEGA MINT MTC OR OSP
PLANB PRM PTT PTTEP PTTGC QH RATCH RBF RCL SAPPE SAWAD SCB SCC SCGP SIRI
SISB SJWD SKY SPALI SPRC STA STGT TASCO TCAP TIDLOR TIPH TISCO TLI TOA TOP
TRUE TTB TU VGI WHA
""")
# SET's H2 2024 PDF lists the nine inclusions and nine exclusions. Reversing
# those dated changes reconstructs the January-June 2024 review snapshot.
H2_2024_INCLUSIONS = symbols("BA BJC CKP JAS MBK PRM QH SKY TIPH")
H2_2024_EXCLUSIONS = symbols("AURA BYD FORTH MOSHI NEX ORI SNNP THG TKN")
SET100_H1_2024 = (SET100_H2_2024 - H2_2024_INCLUSIONS) | H2_2024_EXCLUSIONS
SET100_H1_2025 = symbols("""
AAV ADVANC AEONTS AMATA AOT AP AWC BA BAM BANPU BBL BCH BCP BCPG BDMS BEM
BGRIM BH BJC BLA BSRC BTG BTS CBG CCET CENTEL CHG CK CKP COCOCO COM7 CPALL
CPF CPN CRC DELTA DOHOME EA EGCO ERW GLOBAL GPSC GULF GUNKUL HANA HMPRO ICHI
INTUCH IRPC ITC IVL JAS JMART JMT JTS KBANK KCE KKP KTB KTC LH M MEGA MINT
MTC OR OSP PLANB PR9 PRM PTT PTTEP PTTGC QH RATCH RCL SAPPE SAWAD SCB SCC
SCGP SIRI SISB SJWD SKY SPALI SPRC STA STGT TASCO TCAP TIDLOR TISCO TLI TOP
TRUE TTB TU VGI WHA
""")
SET100_H2_2025 = symbols("""
AAV ADVANC AEONTS AMATA AOT AP AURA AWC BA BAM BANPU BBL BCH BCP BCPG BDMS
BEM BGRIM BH BJC BLA BTG BTS CBG CCET CENTEL CHG CK COM7 CPALL CPF CPN CRC
DELTA DOHOME EA EGCO ERW GLOBAL GPSC GULF GUNKUL HANA HMPRO ICHI IRPC ITC
IVL JAS JMART JMT JTS KBANK KCE KKP KTB KTC LH M MBK MEGA MINT MOSHI MTC OR
OSP PLANB PR9 PRM PTT PTTEP PTTGC QH RATCH RCL SAWAD SCB SCC SCGP SIRI SISB
SJWD SPALI SPRC STA STGT TASCO TCAP TFG TIDLOR TISCO TLI TOA TOP TRUE TTB TU
VGI WHA WHAUP
""")
@dataclass
class Snapshot:
start: date
end: date
members: set[str]
sectors: dict[str, str]
def change(members: set[str], *, add: str = "", remove: str = "") -> set[str]:
updated = set(members)
for symbol in symbols(remove):
if symbol not in updated:
raise ValueError(f"cannot remove missing SET100 member: {symbol}")
updated.remove(symbol)
for symbol in symbols(add):
if symbol in updated:
raise ValueError(f"cannot add existing SET100 member: {symbol}")
updated.add(symbol)
if len(updated) != 100:
raise ValueError(f"dated SET100 snapshot has {len(updated)} members")
return updated
def snapshots() -> list[Snapshot]:
current = set(SET100_H1_2025)
result = [
Snapshot(date(2024, 1, 2), date(2024, 6, 30), SET100_H1_2024, {}),
Snapshot(date(2024, 7, 1), date(2024, 12, 31), SET100_H2_2024, {}),
Snapshot(date(2025, 1, 1), date(2025, 2, 26), current, {}),
]
# 27 Feb 2025: MOSHI replaced BSRC.
current = change(current, add="MOSHI", remove="BSRC")
result.append(Snapshot(date(2025, 2, 27), date(2025, 3, 20), current, {}))
# GULF's symbol changed to GULFI when the suspension began on 21 Mar 2025.
current = change(current, add="GULFI", remove="GULF")
result.append(Snapshot(date(2025, 3, 21), date(2025, 4, 1), current, {}))
# 2 Apr 2025: the merger delisted GULFI and INTUCH; new GULF and reserve
# stock ROJNA entered SET100.
current = change(current, add="GULF ROJNA", remove="GULFI INTUCH")
result.append(Snapshot(date(2025, 4, 2), date(2025, 4, 15), current, {}))
# 16 Apr 2025: SNNP replaced JTS after JTS defaulted on bond payments.
current = change(current, add="SNNP", remove="JTS")
result.append(Snapshot(date(2025, 4, 16), date(2025, 6, 30), current, {}))
result.extend([
Snapshot(date(2025, 7, 1), date(2025, 12, 31), SET100_H2_2025, {}),
])
# Preserve SET's H1 2026 sector labels only for their effective dates.
h1_2026 = HERE / "set100_2026_h1.csv"
sectors: dict[str, str] = {}
members: set[str] = set()
with h1_2026.open(encoding="utf-8-sig", newline="") as source:
for row in csv.DictReader(source):
symbol = row["symbol"].strip().upper()
members.add(symbol)
sectors[symbol] = row.get("sector", "").strip()
result.append(Snapshot(date(2026, 1, 1), date(2026, 6, 30), members, sectors))
return result
def build() -> Path:
by_symbol: dict[str, list[dict[str, str]]] = defaultdict(list)
for snapshot in snapshots():
if len(snapshot.members) != 100:
raise ValueError(
f"{snapshot.start} snapshot has {len(snapshot.members)} members, expected 100"
)
for symbol in sorted(snapshot.members):
sector = snapshot.sectors.get(symbol, "")
rows = by_symbol[symbol]
if (rows and rows[-1]["sector"] == sector
and date.fromisoformat(rows[-1]["end_date"]) + timedelta(days=1)
== snapshot.start):
rows[-1]["end_date"] = snapshot.end.isoformat()
else:
rows.append({
"symbol": symbol,
"start_date": snapshot.start.isoformat(),
"end_date": snapshot.end.isoformat(),
"sector": sector,
})
output = HERE / "set100_pit_2024_2026_h1.csv"
with output.open("w", encoding="utf-8", newline="") as destination:
writer = csv.DictWriter(
destination, fieldnames=["symbol", "start_date", "end_date", "sector"]
)
writer.writeheader()
for symbol in sorted(by_symbol):
writer.writerows(by_symbol[symbol])
return output
if __name__ == "__main__":
print(build())