Haozhe Wu
d3c76819c3
Fix live option guards, grounding operand evidence, source-bound benchmarks, trade artifacts, attribution, drawdowns, valuation tolerances, and SEC point-in-time factor inputs. Add Brazil research data and market support, 13 fundamental and valuation factors, channel progress forwarding, and opt-in ZimaOS templates. Update seven README News sections with three visible dates. Validation: 17,635 backend tests passed; 1,084 final targeted tests and 103 frontend tests passed. Frontend build, package build, documentation checks, and CI gates passed.
91 lines
3.4 KiB
Python
91 lines
3.4 KiB
Python
"""B3 COTAHIST loader: official daily bars for every B3 instrument.
|
|
|
|
Reads the local SQLite store filled by ``python -m src.br_data sync`` (see
|
|
:mod:`src.br_data.cotahist`); it never touches the network, so it is the
|
|
offline fallback of the ``br_equity`` chain after Yahoo/yfinance.
|
|
|
|
Symbol convention: ``PETR4.SA`` -> COTAHIST ``CODNEG`` ``PETR4``. Round-lot
|
|
rows (TPMERC 010) are served; ``PETR4F.SA`` reads the odd-lot market (020).
|
|
Prices are as traded (caliber ``raw``): no dividend/split adjustment.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
from typing import Dict, List, Optional
|
|
|
|
import pandas as pd
|
|
|
|
from backtest.loaders.base import normalize_declared_quote_currency, validate_date_range
|
|
from backtest.loaders.registry import register
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
_OUTPUT_COLUMNS = ["open", "high", "low", "close", "volume"]
|
|
_CASH_MARKET = 10
|
|
_ODD_LOT_MARKET = 20
|
|
|
|
|
|
def map_symbol(code: str) -> tuple[str, int]:
|
|
"""``PETR4.SA`` -> (``PETR4``, 10); ``PETR4F.SA`` -> (``PETR4F``, 20)."""
|
|
ticker = code.strip().upper()
|
|
if ticker.endswith(".SA"):
|
|
ticker = ticker[:-3]
|
|
market = _ODD_LOT_MARKET if ticker.endswith("F") and ticker[-2:-1].isdigit() else _CASH_MARKET
|
|
return ticker, market
|
|
|
|
|
|
@register
|
|
class DataLoader:
|
|
"""Offline B3 daily bars from the official COTAHIST files."""
|
|
|
|
name = "b3_cotahist"
|
|
markets = {"br_equity"}
|
|
# QUATOT is the number of securities traded.
|
|
volume_units = {"br_equity": "shares"}
|
|
requires_auth = False
|
|
|
|
def is_available(self) -> bool:
|
|
"""Available once a sync has created the store."""
|
|
from src.br_data.store import db_path
|
|
|
|
return db_path().exists()
|
|
|
|
def fetch(
|
|
self,
|
|
codes: List[str],
|
|
start_date: str,
|
|
end_date: str,
|
|
*,
|
|
interval: str = "1D",
|
|
fields: Optional[List[str]] = None,
|
|
) -> Dict[str, pd.DataFrame]:
|
|
"""Return ``{code: OHLCV frame}`` for codes present in the store."""
|
|
validate_date_range(start_date, end_date)
|
|
if str(interval).strip().lower() not in {"1d", "d", "day", "daily"}:
|
|
logger.warning("b3_cotahist serves daily bars only; rejecting interval=%r", interval)
|
|
return {}
|
|
from src.br_data.store import connect
|
|
|
|
result: Dict[str, pd.DataFrame] = {}
|
|
try:
|
|
with connect() as conn:
|
|
for code in codes:
|
|
ticker, market = map_symbol(code)
|
|
rows = conn.execute(
|
|
"SELECT trade_date, open, high, low, close, volume FROM b3_quotes "
|
|
"WHERE ticker = ? AND market_type = ? AND trade_date BETWEEN ? AND ? "
|
|
"ORDER BY trade_date",
|
|
(ticker, market, start_date[:10], end_date[:10]),
|
|
).fetchall()
|
|
if not rows:
|
|
continue
|
|
frame = pd.DataFrame([tuple(r) for r in rows], columns=["trade_date", *_OUTPUT_COLUMNS])
|
|
frame["trade_date"] = pd.to_datetime(frame["trade_date"])
|
|
frame = frame.set_index("trade_date").astype(float)
|
|
# The importer admits only explicit R$ records, excluding older currencies.
|
|
result[code] = normalize_declared_quote_currency(frame, code, "BRL")
|
|
except FileNotFoundError as exc:
|
|
logger.warning("b3_cotahist: %s", exc)
|
|
return result
|