234 lines
7.2 KiB
Python
234 lines
7.2 KiB
Python
|
"""CYQ Performance (筹码分布) interface.
|
|||
|
|
|
|||
|
|
Fetch A-share stock chip distribution data (cost distribution and win rate) from Tushare.
|
|||
|
|
This interface retrieves daily chip average cost and win rate information.
|
|||
|
|
Data starts from 2018.
|
|||
|
|
"""
|
|||
|
|
|
|||
|
|
import pandas as pd
|
|||
|
|
from typing import Optional
|
|||
|
|
|
|||
|
|
from src.data.client import TushareClient
|
|||
|
|
from src.data.api_wrappers.base_sync import StockBasedSync
|
|||
|
|
|
|||
|
|
|
|||
|
|
def get_cyq_perf(
|
|||
|
|
ts_code: str,
|
|||
|
|
start_date: Optional[str] = None,
|
|||
|
|
end_date: Optional[str] = None,
|
|||
|
|
client: Optional[TushareClient] = None,
|
|||
|
|
) -> pd.DataFrame:
|
|||
|
|
"""Fetch chip distribution (CYQ) performance data from Tushare.
|
|||
|
|
|
|||
|
|
This interface retrieves daily chip average cost and win rate information
|
|||
|
|
for A-share stocks. Data starts from 2018.
|
|||
|
|
|
|||
|
|
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
|
|||
|
|
client: Optional TushareClient instance for shared rate limiting.
|
|||
|
|
If None, creates a new client. For concurrent sync operations,
|
|||
|
|
pass a shared client to ensure proper rate limiting.
|
|||
|
|
|
|||
|
|
Returns:
|
|||
|
|
pd.DataFrame with columns:
|
|||
|
|
- ts_code: Stock code
|
|||
|
|
- trade_date: Trade date (YYYYMMDD)
|
|||
|
|
- his_low: Historical lowest price
|
|||
|
|
- his_high: Historical highest price
|
|||
|
|
- cost_5pct: 5th percentile cost
|
|||
|
|
- cost_15pct: 15th percentile cost
|
|||
|
|
- cost_50pct: 50th percentile cost (median)
|
|||
|
|
- cost_85pct: 85th percentile cost
|
|||
|
|
- cost_95pct: 95th percentile cost
|
|||
|
|
- weight_avg: Weighted average cost
|
|||
|
|
- winner_rate: Win rate (percentage)
|
|||
|
|
|
|||
|
|
Example:
|
|||
|
|
>>> # Get chip distribution data for a stock
|
|||
|
|
>>> data = get_cyq_perf('000001.SZ', start_date='20240101', end_date='20240131')
|
|||
|
|
>>>
|
|||
|
|
>>> # Get data with shared client for rate limiting
|
|||
|
|
>>> from src.data.client import TushareClient
|
|||
|
|
>>> client = TushareClient()
|
|||
|
|
>>> data = get_cyq_perf('000001.SZ', start_date='20240101', end_date='20240131', client=client)
|
|||
|
|
"""
|
|||
|
|
client = client or TushareClient()
|
|||
|
|
|
|||
|
|
# Build parameters
|
|||
|
|
params = {"ts_code": ts_code}
|
|||
|
|
|
|||
|
|
if start_date:
|
|||
|
|
params["start_date"] = start_date
|
|||
|
|
if end_date:
|
|||
|
|
params["end_date"] = end_date
|
|||
|
|
|
|||
|
|
# Fetch data using cyq_perf API
|
|||
|
|
data = client.query("cyq_perf", **params)
|
|||
|
|
|
|||
|
|
# Rename date column if needed
|
|||
|
|
if "date" in data.columns:
|
|||
|
|
data = data.rename(columns={"date": "trade_date"})
|
|||
|
|
|
|||
|
|
return data
|
|||
|
|
|
|||
|
|
|
|||
|
|
class CyqPerfSync(StockBasedSync):
|
|||
|
|
"""筹码分布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 = CyqPerfSync()
|
|||
|
|
>>> 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 = "cyq_perf"
|
|||
|
|
|
|||
|
|
# 表结构定义
|
|||
|
|
TABLE_SCHEMA = {
|
|||
|
|
"ts_code": "VARCHAR(16) NOT NULL",
|
|||
|
|
"trade_date": "DATE NOT NULL",
|
|||
|
|
"his_low": "DOUBLE",
|
|||
|
|
"his_high": "DOUBLE",
|
|||
|
|
"cost_5pct": "DOUBLE",
|
|||
|
|
"cost_15pct": "DOUBLE",
|
|||
|
|
"cost_50pct": "DOUBLE",
|
|||
|
|
"cost_85pct": "DOUBLE",
|
|||
|
|
"cost_95pct": "DOUBLE",
|
|||
|
|
"weight_avg": "DOUBLE",
|
|||
|
|
"winner_rate": "DOUBLE",
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
# 索引定义
|
|||
|
|
TABLE_INDEXES = [
|
|||
|
|
("idx_cyq_perf_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:
|
|||
|
|
"""获取单只股票的筹码分布数据。
|
|||
|
|
|
|||
|
|
Args:
|
|||
|
|
ts_code: 股票代码
|
|||
|
|
start_date: 起始日期（YYYYMMDD）
|
|||
|
|
end_date: 结束日期（YYYYMMDD）
|
|||
|
|
|
|||
|
|
Returns:
|
|||
|
|
包含筹码分布数据的 DataFrame
|
|||
|
|
"""
|
|||
|
|
# 使用 get_cyq_perf 获取数据（传递共享 client）
|
|||
|
|
data = get_cyq_perf(
|
|||
|
|
ts_code=ts_code,
|
|||
|
|
start_date=start_date,
|
|||
|
|
end_date=end_date,
|
|||
|
|
client=self.client, # 传递共享客户端以确保限流
|
|||
|
|
)
|
|||
|
|
return data
|
|||
|
|
|
|||
|
|
|
|||
|
|
def sync_cyq_perf(
|
|||
|
|
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]:
|
|||
|
|
"""同步所有股票的筹码分布数据。
|
|||
|
|
|
|||
|
|
这是筹码分布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_cyq_perf()
|
|||
|
|
>>>
|
|||
|
|
>>> # 后续同步（增量 - 仅新数据）
|
|||
|
|
>>> result = sync_cyq_perf()
|
|||
|
|
>>>
|
|||
|
|
>>> # 强制完整重载
|
|||
|
|
>>> result = sync_cyq_perf(force_full=True)
|
|||
|
|
>>>
|
|||
|
|
>>> # 手动指定日期范围
|
|||
|
|
>>> result = sync_cyq_perf(start_date='20240101', end_date='20240131')
|
|||
|
|
>>>
|
|||
|
|
>>> # 自定义线程数
|
|||
|
|
>>> result = sync_cyq_perf(max_workers=20)
|
|||
|
|
>>>
|
|||
|
|
>>> # Dry run（仅预览）
|
|||
|
|
>>> result = sync_cyq_perf(dry_run=True)
|
|||
|
|
"""
|
|||
|
|
sync_manager = CyqPerfSync(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_cyq_perf_sync(
|
|||
|
|
force_full: bool = False,
|
|||
|
|
start_date: Optional[str] = None,
|
|||
|
|
end_date: Optional[str] = None,
|
|||
|
|
sample_size: int = 3,
|
|||
|
|
) -> dict:
|
|||
|
|
"""预览筹码分布数据同步数据量和样本（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_cyq_perf_sync()
|
|||
|
|
>>>
|
|||
|
|
>>> # 预览全量同步
|
|||
|
|
>>> preview = preview_cyq_perf_sync(force_full=True)
|
|||
|
|
>>>
|
|||
|
|
>>> # 预览更多样本
|
|||
|
|
>>> preview = preview_cyq_perf_sync(sample_size=5)
|
|||
|
|
"""
|
|||
|
|
sync_manager = CyqPerfSync()
|
|||
|
|
return sync_manager.preview_sync(
|
|||
|
|
force_full=force_full,
|
|||
|
|
start_date=start_date,
|
|||
|
|
end_date=end_date,
|
|||
|
|
sample_size=sample_size,
|
|||
|
|
)
|