claude_dev
1ed7b72aca
根因: daily_dir mixed-adjust(hfq bulk+akshare raw tail)致3-30 -94%假跌。 方案(Linus三问简化单raw, 除权留分期项#3): - datareader read_parquet_daily/15min 加 dir_key 参数 - data_source iter_bars/fetch_day: adjust=raw→raw_dir(缺配置报错防混源), qfq→daily_dir - engine PaperEngine 默认 adjust=raw - config 加 raw_dir; scripts/raw_redownload.py 新浪源adjust='' 直连+单线程限速 - 验证: 浦发606行close 6.5/14.6 mean10.08 0跳变, 撮合成交价9.71-10.25真实 - 测试9/9+trader全量108/108通过
74 lines
2.8 KiB
Python
74 lines
2.8 KiB
Python
import pandas as pd
|
|
from unittest.mock import patch, MagicMock
|
|
from vnpy.trader.constant import Exchange, Interval
|
|
from vnpy.trader.setting import SETTINGS
|
|
from sanguo_data.config import DataConfig
|
|
from sanguo_data.datareader import read_parquet_daily, guess_exchange, read_db_daily
|
|
|
|
def test_read_parquet_daily_returns_bardata(tmp_path):
|
|
year_dir = tmp_path / "2026"
|
|
year_dir.mkdir()
|
|
df = pd.DataFrame({
|
|
"date": ["2026-01-05", "2026-01-06"],
|
|
"open": [10.0, 11.0], "high": [10.5, 11.5],
|
|
"low": [9.8, 10.8], "close": [10.2, 11.2],
|
|
"volume": [10000, 12000],
|
|
})
|
|
df.to_parquet(year_dir / "600000.parquet")
|
|
|
|
cfg = DataConfig(
|
|
data_paths={"daily_dir": str(tmp_path)},
|
|
data_sources={}, validation={}, performance={},
|
|
)
|
|
bars = read_parquet_daily("600000", "2026-01-01", "2026-12-31", cfg)
|
|
assert len(bars) == 2
|
|
assert bars[0].symbol == "600000"
|
|
assert bars[0].open_price == 10.0
|
|
|
|
|
|
def test_read_parquet_daily_dir_key_raw(tmp_path):
|
|
"""dir_key='raw_dir'：切换到 raw 目录读真实价（task #79 双源）。"""
|
|
raw_year = tmp_path / "2026"
|
|
raw_year.mkdir()
|
|
df = pd.DataFrame({
|
|
"date": ["2026-03-30"],
|
|
"open": [9.97], "high": [10.05], "low": [9.95],
|
|
"close": [10.01], "volume": [800000],
|
|
})
|
|
df.to_parquet(raw_year / "sh600000_daily.parquet") # 真实文件名：sh 前缀 + _daily
|
|
cfg = DataConfig(
|
|
data_paths={"raw_dir": str(tmp_path)},
|
|
data_sources={}, validation={}, performance={},
|
|
)
|
|
bars = read_parquet_daily("600000", "2026-01-01", "2026-12-31", cfg, dir_key="raw_dir")
|
|
assert len(bars) == 1
|
|
assert bars[0].close_price == 10.01
|
|
|
|
|
|
def test_guess_exchange_sh():
|
|
assert guess_exchange("600000").value == "SSE"
|
|
|
|
|
|
def test_guess_exchange_sz():
|
|
assert guess_exchange("000001").value == "SZSE"
|
|
|
|
|
|
def test_read_db_daily_configures_vnpy_settings():
|
|
"""Test that read_db_daily configures vnpy SETTINGS with correct database path."""
|
|
cfg = DataConfig(
|
|
data_paths={"vnpy_db": "/volume1/stock/sanguo_vnpy/data/quant_trading.db"},
|
|
data_sources={}, validation={}, performance={},
|
|
)
|
|
|
|
# Mock get_database to avoid actual database connection
|
|
mock_db = MagicMock()
|
|
mock_db.load_bar_data.return_value = [] # Return empty list to avoid data processing
|
|
|
|
with patch('sanguo_data.datareader.get_database', return_value=mock_db):
|
|
# Call read_db_daily
|
|
read_db_daily("600000", "2024-01-01", "2024-12-31", cfg)
|
|
|
|
# Assert that SETTINGS was configured correctly
|
|
assert SETTINGS["database.name"] == "sqlite", f"Expected database.name to be 'sqlite', got {SETTINGS.get('database.name')}"
|
|
assert SETTINGS["database.database"] == cfg.data_paths["vnpy_db"], f"Expected database.database to be {cfg.data_paths['vnpy_db']}, got {SETTINGS.get('database.database')}"
|