Initial commit: cc-cursor 全链路量化研究平台

7 Sprints 全部完成: Sprint 0: 基础设施 (DataManager + MariaDB) Sprint 1: 因子引擎 (34因子/12分类) Sprint 2: VectorBT 回测 (5策略+截面) Sprint 3: Optuna 优化 (+Walk-Forward) Sprint 4: ML 模型 (LightGBM+CatBoost) Sprint 5: Qwen 情绪因子 (三源新闻+日期对齐) Sprint 6: Agent 系统 (4Agent+日报.md/.html) 生产加固 (15项): Tushare双源fallback, SSH自动恢复, pool_pre_ping, save_daily先删后插, load_dotenv绝对路径, 日报5d/20d修复, RiskAgent改上证指数, 昨日对比+数据截止, mac_report utf8mb4, CLAUDE-*.md 9条已知Bug, demo全参数化, djapi数据源归一化, indexDatas API修正 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-07 15:59:05 +08:00
commit 271a9343a5
293 changed files with 59598 additions and 0 deletions
@@ -0,0 +1,181 @@
+"""
+⚠️ 已废弃 — 2026-06-05
+
+AkShare 股息率数据获取功能已归一化到 data_source.py。
+如需 AkShare 日线数据，请使用：
+
+    from .data_source import get_daily
+    df = get_daily(ts_code, start, end, source='akshare')
+
+本文件保留仅用于向后兼容，所有公开函数委托给统一数据源。
+"""
+
+import pandas as pd
+import numpy as np
+from datetime import datetime, timedelta
+
+from .data_source import get_daily
+
+from .stock_utils import tscodeCheck, date_format_correction
+from .smoothBrush import smooth_dataframe_brush
+
+GAP_DAYS = 360  # TTM 计算窗口
+
+
+def _parse_tscode(tscode: str) -> tuple:
+    """将 tscode（如 000001.SZ）转为 akshare 格式的 symbol 和 market"""
+    code = tscode.split('.')[0]
+    suffix = tscode.split('.')[1].lower()
+    market_map = {'sz': 'sz', 'sh': 'sh', 'bj': 'bj'}
+    return code, market_map.get(suffix, suffix)
+
+
+def _fetch_daily_price(symbol: str, start_date: str, end_date: str) -> pd.DataFrame:
+    """通过 akshare 获取前复权日线行情"""
+    df = ak.stock_zh_a_hist(
+        symbol=symbol,
+        period='daily',
+        start_date=start_date,
+        end_date=end_date,
+        adjust='qfq'
+    )
+    if df.empty:
+        return pd.DataFrame()
+
+    df = df.rename(columns={
+        '日期': 'trade_date',
+        '开盘': 'open',
+        '收盘': 'close',
+        '最高': 'high',
+        '最低': 'low',
+        '成交量': 'vol',
+        '成交额': 'amount',
+        '换手率': 'turnover_rate',
+    })
+    df['trade_date'] = df['trade_date'].astype(str).str.replace('-', '')
+    return df
+
+
+def _fetch_dividends(symbol: str, market: str) -> pd.DataFrame:
+    """通过 akshare 获取历史分红记录"""
+    try:
+        df = ak.stock_dividend_cninfo(stock=symbol, symbol=market + symbol)
+    except Exception:
+        return pd.DataFrame()
+
+    if df.empty:
+        return pd.DataFrame()
+
+    # 列名映射（akshare 返回中文列名）
+    col_map = {
+        '除权除息日': 'ex_date',
+        '每股派息': 'cash_div_tax',
+    }
+    df = df.rename(columns={k: v for k, v in col_map.items() if k in df.columns})
+
+    if 'ex_date' not in df.columns or 'cash_div_tax' not in df.columns:
+        return pd.DataFrame()
+
+    df['ex_date'] = df['ex_date'].astype(str).str.replace('-', '').str[:8]
+    df['cash_div_tax'] = pd.to_numeric(df['cash_div_tax'], errors='coerce').fillna(0)
+    return df[['ex_date', 'cash_div_tax']]
+
+
+def get_akshare_dividend_yield(tscode: str, start_date: str = None, end_date: str = None) -> pd.DataFrame:
+    """
+    通过 akshare 获取股价和分红数据，计算股息率。
+
+    Args:
+        tscode: 股票代码，如 '000001.SZ'
+        start_date: 起始日期 yyyyMMdd
+        end_date: 结束日期 yyyyMMdd
+
+    Returns:
+        DataFrame: ts_code, trade_date, close, cash_div_tax, cash_div_year, div_yield
+    """
+    tscode = tscodeCheck(tscode)
+    today = datetime.now().strftime('%Y%m%d')
+
+    if start_date:
+        start_date = date_format_correction(start_date)
+    else:
+        start_date = '20200101'
+    if end_date:
+        end_date = date_format_correction(end_date)
+    else:
+        end_date = today
+
+    if end_date > today:
+        end_date = today
+
+    symbol, market = _parse_tscode(tscode)
+
+    # 1. 获取日线行情（运算时起始日期往前推 GAP_DAYS）
+    calc_start = datetime.strptime(start_date, '%Y%m%d') - timedelta(days=GAP_DAYS)
+    calc_start_str = calc_start.strftime('%Y%m%d')
+
+    df_price = _fetch_daily_price(symbol, calc_start_str, end_date)
+    if df_price.empty:
+        return pd.DataFrame()
+    df_price = df_price.sort_values('trade_date').reset_index(drop=True)
+
+    # 2. 获取分红数据
+    df_div = _fetch_dividends(symbol, market)
+
+    # 3. 计算 TTM 分红序列
+    if df_div.empty:
+        df_price['cash_div_tax'] = 0.0
+        df_price['cash_div_year'] = 0.0
+    else:
+        # 将分红按 ex_date 合并到交易日历
+        df_div['ex_date'] = pd.to_datetime(df_div['ex_date'], format='%Y%m%d')
+        df_price['trade_date_dt'] = pd.to_datetime(df_price['trade_date'], format='%Y%m%d')
+
+        # 按日期合并
+        div_dict = df_div.set_index('ex_date')['cash_div_tax'].to_dict()
+
+        def calc_ttm_div(trade_dt):
+            window_start = trade_dt - timedelta(days=GAP_DAYS)
+            total = 0.0
+            for ex_dt, cash in div_dict.items():
+                if window_start < ex_dt <= trade_dt:
+                    total += cash
+            return total
+
+        cash_div_tax_list = []
+        cash_div_year_list = []
+
+        for _, row in df_price.iterrows():
+            td = row['trade_date_dt']
+            cash = div_dict.get(td, 0.0)
+            cash_div_tax_list.append(cash)
+            cash_div_year_list.append(calc_ttm_div(td))
+
+        df_price['cash_div_tax'] = cash_div_tax_list
+        df_price['cash_div_year'] = cash_div_year_list
+        df_price = df_price.drop(columns=['trade_date_dt'])
+
+    # 4. 毛刺平滑
+    df_price = smooth_dataframe_brush(
+        df_price,
+        target_columns=['cash_div_year'],
+        window_size=31,
+        threshold_factor=0.5,
+        max_brush_length=15
+    )
+
+    # 5. 截取请求的时间范围
+    df_result = df_price[
+        (df_price['trade_date'] >= start_date) & (df_price['trade_date'] <= end_date)
+    ].copy()
+
+    # 6. 计算股息率
+    df_result['div_yield'] = 0.0
+    mask = (df_result['close'] > 0) & (df_result['cash_div_year'] > 0)
+    df_result.loc[mask, 'div_yield'] = (
+        (df_result.loc[mask, 'cash_div_year'] / df_result.loc[mask, 'close']) * 100
+    ).round(4)
+
+    df_result['ts_code'] = tscode
+    final_cols = ['ts_code', 'trade_date', 'close', 'cash_div_tax', 'cash_div_year', 'div_yield']
+    return df_result[final_cols].reset_index(drop=True)