liaozhaorun/ProStock
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(data): 移除 api_daily 模块并更新文档

Browse Source 
- 删除 src/data/api_wrappers/api_daily.py (240行)
- 更新 6 个文档文件，将 daily 表引用替换为 pro_bar
- 同步 README.md 中的因子框架和训练模块示例

BREAKING CHANGE: api_daily 模块已移除，请使用 api_pro_bar 替代
This commit is contained in:
liaozhaorun
2026-03-14 01:48:56 +08:00
parent 181994f063
commit a22bc2d282
7 changed files with 161 additions and 342 deletions
Download Patch File Download Diff File Expand all files Collapse all files

240
src/data/api_wrappers/api_daily.py
View File

@@ -1,240 +0,0 @@
"""Simplified daily market data interface.
A single function to fetch A股日线行情 data from Tushare.
Supports all output fields including tor (换手率) and vr (量比).
This module provides both single-stock fetching (get_daily) and
batch synchronization (DailySync class) for daily market data.
"""
import pandas as pd
from typing import Optional, List, Literal, Dict
from src.data.client import TushareClient
from src.data.api_wrappers.base_sync import StockBasedSync
def get_daily(
ts_code: str,
start_date: Optional[str] = None,
end_date: Optional[str] = None,
trade_date: Optional[str] = None,
adj: Literal[None, "qfq", "hfq"] = None,
factors: Optional[List[Literal["tor", "vr"]]] = None,
adjfactor: bool = False,
) -> pd.DataFrame:
"""Fetch daily market data for A-share stocks.
This is a simplified interface that combines rate limiting, API calls,
and error handling into a single function.
Args:
ts_code: Stock code (e.g., '000001.SZ', '600000.SH')
start_date: Start date in YYYYMMDD format
end_date: End date in YYYYMMDD format
trade_date: Specific trade date in YYYYMMDD format
adj: Adjustment type - None, 'qfq' (forward), 'hfq' (backward)
factors: List of factors to include - 'tor' (turnover rate), 'vr' (volume ratio)
adjfactor: Whether to include adjustment factor
Returns:
pd.DataFrame with daily market data containing:
- Base fields: ts_code, trade_date, open, high, low, close, pre_close,
change, pct_chg, vol, amount
- Factor fields (if requested): tor, vr
- Adjustment factor (if adjfactor=True): adjfactor
Example:
>>> data = get_daily('000001.SZ', start_date='20240101', end_date='20240131')
>>> data = get_daily('600000.SH', factors=['tor', 'vr'])
"""
# Initialize client
client = TushareClient()
# Build parameters
params = {"ts_code": ts_code}
if start_date:
params["start_date"] = start_date
if end_date:
params["end_date"] = end_date
if trade_date:
params["trade_date"] = trade_date
if adj:
params["adj"] = adj
if factors:
# Tushare expects factors as comma-separated string, not list
if isinstance(factors, list):
factors_str = ",".join(factors)
else:
factors_str = factors
params["factors"] = factors_str
if adjfactor:
params["adjfactor"] = "True"
# Fetch data using pro_bar (supports factors like tor, vr)
data = client.query("pro_bar", **params)
return data
class DailySync(StockBasedSync):
"""日线数据批量同步管理器，支持全量/增量同步。
继承自 StockBasedSync，使用多线程按股票并发获取数据。
Example:
>>> sync = DailySync()
>>> results = sync.sync_all() # 增量同步
>>> results = sync.sync_all(force_full=True) # 全量同步
>>> preview = sync.preview_sync() # 预览
"""
table_name = "daily"
# 表结构定义
TABLE_SCHEMA = {
"ts_code": "VARCHAR(16) NOT NULL",
"trade_date": "DATE NOT NULL",
"open": "DOUBLE",
"high": "DOUBLE",
"low": "DOUBLE",
"close": "DOUBLE",
"pre_close": "DOUBLE",
"change": "DOUBLE",
"pct_chg": "DOUBLE",
"vol": "DOUBLE",
"amount": "DOUBLE",
"turnover_rate": "DOUBLE",
"volume_ratio": "DOUBLE",
}
# 索引定义
TABLE_INDEXES = [
("idx_daily_date_code", ["trade_date", "ts_code"]),
]
# 主键定义
PRIMARY_KEY = ("ts_code", "trade_date")
def fetch_single_stock(
self,
ts_code: str,
start_date: str,
end_date: str,
) -> pd.DataFrame:
"""获取单只股票的日线数据。
Args:
ts_code: 股票代码
start_date: 起始日期（YYYYMMDD）
end_date: 结束日期（YYYYMMDD）
Returns:
包含日线数据的 DataFrame
"""
# 使用共享客户端进行跨线程速率限制
data = self.client.query(
"pro_bar",
ts_code=ts_code,
start_date=start_date,
end_date=end_date,
factors="tor,vr",
)
return data
def sync_daily(
force_full: bool = False,
start_date: Optional[str] = None,
end_date: Optional[str] = None,
max_workers: Optional[int] = None,
dry_run: bool = False,
) -> Dict[str, pd.DataFrame]:
"""同步所有股票的日线数据。
这是日线数据同步的主要入口点。
Args:
force_full: 若为 True，强制从 20180101 完整重载
start_date: 手动指定起始日期（YYYYMMDD）
end_date: 手动指定结束日期（默认为今天）
max_workers: 工作线程数（默认: 10）
dry_run: 若为 True，仅预览将要同步的内容，不写入数据
Returns:
映射 ts_code 到 DataFrame 的字典
Example:
>>> # 首次同步（从 20180101 全量加载）
>>> result = sync_daily()
>>>
>>> # 后续同步（增量 - 仅新数据）
>>> result = sync_daily()
>>>
>>> # 强制完整重载
>>> result = sync_daily(force_full=True)
>>>
>>> # 手动指定日期范围
>>> result = sync_daily(start_date='20240101', end_date='20240131')
>>>
>>> # 自定义线程数
>>> result = sync_daily(max_workers=20)
>>>
>>> # Dry run（仅预览）
>>> result = sync_daily(dry_run=True)
"""
sync_manager = DailySync(max_workers=max_workers)
return sync_manager.sync_all(
force_full=force_full,
start_date=start_date,
end_date=end_date,
dry_run=dry_run,
)
def preview_daily_sync(
force_full: bool = False,
start_date: Optional[str] = None,
end_date: Optional[str] = None,
sample_size: int = 3,
) -> dict:
"""预览日线同步数据量和样本（不实际同步）。
这是推荐的方式，可在实际同步前检查将要同步的内容。
Args:
force_full: 若为 True，预览全量同步（从 20180101）
start_date: 手动指定起始日期（覆盖自动检测）
end_date: 手动指定结束日期（默认为今天）
sample_size: 预览用样本股票数量（默认: 3）
Returns:
包含预览信息的字典：
{
'sync_needed': bool,
'stock_count': int,
'start_date': str,
'end_date': str,
'estimated_records': int,
'sample_data': pd.DataFrame,
'mode': str, # 'full', 'incremental', 'partial', 或 'none'
}
Example:
>>> # 预览将要同步的内容
>>> preview = preview_daily_sync()
>>>
>>> # 预览全量同步
>>> preview = preview_daily_sync(force_full=True)
>>>
>>> # 预览更多样本
>>> preview = preview_daily_sync(sample_size=5)
"""
sync_manager = DailySync()
return sync_manager.preview_sync(
force_full=force_full,
start_date=start_date,
end_date=end_date,
sample_size=sample_size,
)