quantcli 0.1.13__tar.gz → 0.1.15__tar.gz

{quantcli-0.1.13/quantcli.egg-info → quantcli-0.1.15}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: quantcli
-Version: 0.1.13
+Version: 0.1.15
 Summary: 面向AI的多因子量化选股策略挖掘工具，AI Agent 友好 CLI
 Author-email: QuantCLI Team <quantcli@example.com>
 Project-URL: repository, https://github.com/wumu2013/quantcli

{quantcli-0.1.13 → quantcli-0.1.15}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "quantcli"
-version = "0.1.13"
+version = "0.1.15"
 description = "面向AI的多因子量化选股策略挖掘工具，AI Agent 友好 CLI"
 readme = "README.md"
 requires-python = ">=3.9"

{quantcli-0.1.13 → quantcli-0.1.15}/quantcli/cli.py

@@ -174,7 +174,7 @@ def data_fetch(ctx, symbol, start, end, source, use_cache, output):
 
 @data.group("cache")
 @click.pass_context
-def data_cache():
+def data_cache(ctx):
     """缓存管理"""
     pass
 

{quantcli-0.1.13 → quantcli-0.1.15}/quantcli/core/data.py

@@ -21,10 +21,7 @@ from pathlib import Path
 import pandas as pd
 
 from ..datasources import create_datasource, DataSource, StockInfo
-from ..utils import (
-    get_logger, project_root, ensure_dir, format_size,
-    parse_date, today
-)
+from ..utils import get_logger, project_root, ensure_dir, format_size, parse_date, today
 
 logger = get_logger(__name__)
 
@@ -32,6 +29,7 @@ logger = get_logger(__name__)
 @dataclass
 class DataConfig:
     """数据管理配置"""
+
     source: str = "akshare"
     cache_dir: str = "./data"
     parallel: int = 4
@@ -54,6 +52,7 @@ class DataConfig:
 @dataclass
 class DataQualityReport:
     """数据质量报告"""
+
     total_rows: int
     null_count: Dict[str, int]
     outlier_count: Dict[str, int]
@@ -113,12 +112,7 @@ class DataManager:
     # =============================================================================
 
     def get_daily(
-        self,
-        symbol: str,
-        start_date,
-        end_date,
-        use_cache: bool = True,
-        **kwargs
+        self, symbol: str, start_date, end_date, use_cache: bool = True, **kwargs
     ) -> pd.DataFrame:
         """获取单只股票日线数据"""
         cache_file = self.cache_dir / "raw" / "stock_daily" / f"{symbol}.parquet"
@@ -151,7 +145,7 @@ class DataManager:
         start_date,
         end_date,
         use_cache: bool = True,
-        parallel: bool = False
+        parallel: bool = False,
     ) -> pd.DataFrame:
         """批量获取多只股票日线数据"""
         if not symbols:
@@ -161,6 +155,7 @@ class DataManager:
 
         if parallel and len(symbols) > 1:
             from concurrent.futures import ThreadPoolExecutor
+
             with ThreadPoolExecutor(max_workers=self.config.parallel) as executor:
                 futures = [
                     executor.submit(self.get_daily, s, start_date, end_date, use_cache)
@@ -192,10 +187,7 @@ class DataManager:
         return result
 
     def get_universe(
-        self,
-        universe: str = "all",
-        market: str = "all",
-        use_cache: bool = True
+        self, universe: str = "all", market: str = "all", use_cache: bool = True
     ) -> List[StockInfo]:
         """获取股票池"""
         cache_file = self.cache_dir / "cache" / f"stock_list_{market}.json"
@@ -221,9 +213,7 @@ class DataManager:
         return stocks
 
     def get_trading_calendar(
-        self,
-        exchange: str = "SSE",
-        use_cache: bool = True
+        self, exchange: str = "SSE", use_cache: bool = True
     ) -> List:
         """获取交易日历"""
         cache_file = self.cache_dir / "cache" / f"trading_calendar_{exchange}.json"
@@ -244,11 +234,7 @@ class DataManager:
         return trading_days
 
     def get_index_daily(
-        self,
-        symbol: str,
-        start_date,
-        end_date,
-        use_cache: bool = True
+        self, symbol: str, start_date, end_date, use_cache: bool = True
     ) -> pd.DataFrame:
         """获取指数日线数据"""
         cache_file = self.cache_dir / "raw" / "index_daily" / f"{symbol}.parquet"
@@ -268,7 +254,9 @@ class DataManager:
 
         return df
 
-    def _filter_universe(self, stocks: List[StockInfo], universe: str) -> List[StockInfo]:
+    def _filter_universe(
+        self, stocks: List[StockInfo], universe: str
+    ) -> List[StockInfo]:
         """根据股票池名称过滤股票"""
         return stocks
 
@@ -303,8 +291,10 @@ class DataManager:
             try:
                 existing = pd.read_parquet(cache_file)
                 df_copy = pd.concat([existing, df_copy]).drop_duplicates(
-                    subset=["date"] if "symbol" not in df_copy.columns else ["date", "symbol"],
-                    keep="last"
+                    subset=["date"]
+                    if "symbol" not in df_copy.columns
+                    else ["date", "symbol"],
+                    keep="last",
                 )
             except Exception:
                 pass
@@ -313,35 +303,62 @@ class DataManager:
 
         self._cache_metadata[cache_key] = {
             "last_updated": datetime.now().isoformat(),
-            "rows": len(df_copy)
+            "rows": len(df_copy),
         }
         self._save_metadata()
 
         logger.debug(f"Cached {len(df_copy)} rows to {cache_file}")
 
-    def clear_cache(self, older_than: Optional[int] = None, pattern: Optional[str] = None) -> int:
+    def clear_cache(
+        self, older_than: Optional[int] = None, pattern: Optional[str] = None
+    ) -> int:
         """清理缓存"""
         count = 0
-        raw_dir = self.cache_dir / "raw"
+
+        # 清理所有缓存子目录
+        cache_subdirs = ["raw", "prices", "stocklist", "calendar"]
 
         if older_than:
             from datetime import timedelta
+
             cutoff = today() - timedelta(days=older_than)
-            for cache_file in raw_dir.rglob("*.parquet"):
-                mtime = parse_date(cache_file.stat().st_mtime)
-                if mtime < cutoff:
-                    cache_file.unlink()
-                    count += 1
+            for subdir in cache_subdirs:
+                dir_path = self.cache_dir / subdir
+                if dir_path.exists():
+                    for cache_file in dir_path.rglob("*.parquet"):
+                        try:
+                            mtime = parse_date(cache_file.stat().st_mtime)
+                            if mtime < cutoff:
+                                cache_file.unlink()
+                                count += 1
+                        except OSError:
+                            continue
         elif pattern:
-            for cache_file in raw_dir.rglob(pattern):
-                if cache_file.is_file():
-                    cache_file.unlink()
-                    count += 1
+            for subdir in cache_subdirs:
+                dir_path = self.cache_dir / subdir
+                if dir_path.exists():
+                    for cache_file in dir_path.rglob(pattern):
+                        if cache_file.is_file():
+                            try:
+                                cache_file.unlink()
+                                count += 1
+                            except OSError:
+                                continue
         else:
-            for cache_file in raw_dir.rglob("*.parquet"):
-                cache_file.unlink()
-                count += 1
-            ensure_dir(self.cache_dir / "features")
+            # 清理所有缓存目录
+            for subdir in cache_subdirs:
+                dir_path = self.cache_dir / subdir
+                if dir_path.exists():
+                    for cache_file in dir_path.rglob("*.parquet"):
+                        try:
+                            cache_file.unlink()
+                            count += 1
+                        except OSError:
+                            continue
+
+            # 确保目录结构存在
+            for subdir in cache_subdirs:
+                ensure_dir(self.cache_dir / subdir)
 
         logger.info(f"Cleared {count} cache files")
         return count
@@ -354,7 +371,13 @@ class DataManager:
                 relative = str(path.relative_to(self.cache_dir))
                 sizes[relative] = format_size(path.stat().st_size)
 
-        sizes["_total"] = format_size(sum(path.stat().st_size for path in self.cache_dir.rglob("*.parquet") if path.is_file()))
+        sizes["_total"] = format_size(
+            sum(
+                path.stat().st_size
+                for path in self.cache_dir.rglob("*.parquet")
+                if path.is_file()
+            )
+        )
         return sizes
 
     # =============================================================================
@@ -369,7 +392,7 @@ class DataManager:
         filter_st: Optional[bool] = None,
         filter_suspended: Optional[bool] = None,
         filter_new: Optional[int] = None,
-        inplace: bool = False
+        inplace: bool = False,
     ) -> pd.DataFrame:
         """数据清洗"""
         if not inplace:
@@ -381,7 +404,7 @@ class DataManager:
             outlier_count={},
             st_filtered=0,
             suspended_filtered=0,
-            new_stock_filtered=0
+            new_stock_filtered=0,
         )
 
         # 空值填充
@@ -404,14 +427,20 @@ class DataManager:
             report.st_filtered = original_len - len(df)
 
         # 过滤停牌
-        filter_suspended_flag = filter_suspended if filter_suspended is not None else self.config.filter_suspended
+        filter_suspended_flag = (
+            filter_suspended
+            if filter_suspended is not None
+            else self.config.filter_suspended
+        )
         if filter_suspended_flag:
             original_len = len(df)
             df = self._filter_suspended(df)
             report.suspended_filtered = original_len - len(df)
 
         # 过滤新股
-        filter_new_days = filter_new if filter_new is not None else self.config.filter_new
+        filter_new_days = (
+            filter_new if filter_new is not None else self.config.filter_new
+        )
         if filter_new_days and filter_new_days > 0:
             original_len = len(df)
             df = self._filter_new_stocks(df, filter_new_days)
@@ -506,7 +535,10 @@ class DataManager:
             return {
                 **status,
                 "cache": self.get_cache_size(),
-                "config": {"source": self.config.source, "cache_dir": str(self.cache_dir)}
+                "config": {
+                    "source": self.config.source,
+                    "cache_dir": str(self.cache_dir),
+                },
             }
         except Exception as e:
             return {"status": "error", "error": str(e)}

{quantcli-0.1.13 → quantcli-0.1.15}/quantcli/datasources/akshare.py

@@ -35,6 +35,7 @@ class AkshareDataSource(DataSource):
 
         try:
             import akshare as ak
+
             self._ak = ak
         except ImportError:
             raise ImportError("akshare not installed. Run: pip install akshare")
@@ -56,11 +57,7 @@ class AkshareDataSource(DataSource):
         symbol = symbol.replace(".SH", "").replace(".SZ", "")
         return f"sh{symbol}" if symbol.startswith(("6", "5", "9")) else f"sz{symbol}"
 
-    def _market_filter(
-        self,
-        df: pd.DataFrame,
-        market: str
-    ) -> pd.DataFrame:
+    def _market_filter(self, df: pd.DataFrame, market: str) -> pd.DataFrame:
         """过滤股票市场"""
         if market == "all":
             return df
@@ -73,16 +70,12 @@ class AkshareDataSource(DataSource):
     # ==================== 核心接口 ====================
 
     def get_daily(
-        self,
-        symbol: str,
-        start_date,
-        end_date,
-        fields: Optional[List[str]] = None
+        self, symbol: str, start_date, end_date, fields: Optional[List[str]] = None
     ) -> pd.DataFrame:
         """获取A股日线数据（腾讯接口）"""
         start_str = format_date(start_date, "%Y-%m-%d")
         end_str = format_date(end_date, "%Y-%m-%d")
-        cache_key = f"{symbol}_{start_str}_{end_str}"
+        cache_key = f"akshare_{symbol}_{start_str}_{end_str}"
 
         # 1. 尝试缓存
         if self.config.use_cache:
@@ -95,7 +88,7 @@ class AkshareDataSource(DataSource):
         df = self._ak.stock_zh_a_hist_tx(
             symbol=tx_symbol,
             start_date=format_date(start_date, "%Y%m%d"),
-            end_date=format_date(end_date, "%Y%m%d")
+            end_date=format_date(end_date, "%Y%m%d"),
         )
 
         if df.empty:
@@ -109,16 +102,11 @@ class AkshareDataSource(DataSource):
 
         return self._filter_fields(df, fields) if fields else df
 
-    def get_index_daily(
-        self,
-        symbol: str,
-        start_date,
-        end_date
-    ) -> pd.DataFrame:
+    def get_index_daily(self, symbol: str, start_date, end_date) -> pd.DataFrame:
         """获取指数日线数据（腾讯接口）"""
         start_str = format_date(start_date, "%Y-%m-%d")
         end_str = format_date(end_date, "%Y-%m-%d")
-        cache_key = f"idx_{symbol}_{start_str}_{end_str}"
+        cache_key = f"akshare_idx_{symbol}_{start_str}_{end_str}"
 
         if self.config.use_cache:
             cached = self._price_cache.get(cache_key)
@@ -143,7 +131,7 @@ class AkshareDataSource(DataSource):
         symbol: str,
         start_date: Optional[date] = None,
         end_date: Optional[date] = None,
-        period: str = "5"
+        period: str = "5",
     ) -> pd.DataFrame:
         """获取分钟级数据
 
@@ -172,37 +160,43 @@ class AkshareDataSource(DataSource):
                 period=period,
                 start_date=start_date.strftime("%Y%m%d"),
                 end_date=end_date.strftime("%Y%m%d"),
-                adjust="qfq"
+                adjust="qfq",
             )
 
             if df.empty:
-                return pd.DataFrame(columns=['date', 'open', 'high', 'low', 'close', 'volume'])
+                return pd.DataFrame(
+                    columns=["date", "open", "high", "low", "close", "volume"]
+                )
 
             # 标准化列名
-            df = df.rename(columns={
-                "时间": "date",
-                "开盘": "open",
-                "最高": "high",
-                "最低": "low",
-                "收盘": "close",
-                "成交量": "volume",
-                "成交额": "amount"
-            })
+            df = df.rename(
+                columns={
+                    "时间": "date",
+                    "开盘": "open",
+                    "最高": "high",
+                    "最低": "low",
+                    "收盘": "close",
+                    "成交量": "volume",
+                    "成交额": "amount",
+                }
+            )
 
             # 转换日期格式
             df["date"] = pd.to_datetime(df["date"])
 
             # 确保数值列是数值类型
-            numeric_cols = ['open', 'high', 'low', 'close', 'volume', 'amount']
+            numeric_cols = ["open", "high", "low", "close", "volume", "amount"]
             for col in numeric_cols:
                 if col in df.columns:
-                    df[col] = pd.to_numeric(df[col], errors='coerce')
+                    df[col] = pd.to_numeric(df[col], errors="coerce")
 
             return df
 
         except Exception as e:
             logger.warning(f"Failed to get intraday data for {symbol}: {e}")
-            return pd.DataFrame(columns=['date', 'open', 'high', 'low', 'close', 'volume'])
+            return pd.DataFrame(
+                columns=["date", "open", "high", "low", "close", "volume"]
+            )
 
     def get_stock_list(self, market: str = "all") -> pd.DataFrame:
         """获取A股股票列表
@@ -217,7 +211,7 @@ class AkshareDataSource(DataSource):
 
         df = self._ak.stock_info_a_code_name()
         if df.empty:
-            return pd.DataFrame(columns=['symbol', 'name', 'exchange', 'market'])
+            return pd.DataFrame(columns=["symbol", "name", "exchange", "market"])
 
         # 转换格式：akshare 可能返回中文列名
         df = df.rename(columns={"代码": "symbol", "名称": "name"})
@@ -258,9 +252,7 @@ class AkshareDataSource(DataSource):
     # ==================== 辅助方法 ====================
 
     def _filter_fields(
-        self,
-        df: pd.DataFrame,
-        fields: Optional[List[str]]
+        self, df: pd.DataFrame, fields: Optional[List[str]]
     ) -> pd.DataFrame:
         """过滤字段"""
         if not fields:
@@ -272,21 +264,14 @@ class AkshareDataSource(DataSource):
         """健康检查"""
         try:
             self._ak.tool_trade_date_hist_sina()
-            return {
-                "status": "ok",
-                "source": self.name,
-                "cache": self.config.use_cache
-            }
+            return {"status": "ok", "source": self.name, "cache": self.config.use_cache}
         except Exception as e:
             return {"status": "error", "source": self.name, "error": str(e)}
 
     # ==================== 不支持的接口 ====================
 
     def get_fundamental(
-        self,
-        symbols: List[str],
-        date,
-        indicators: Optional[List[str]] = None
+        self, symbols: List[str], date, indicators: Optional[List[str]] = None
     ) -> pd.DataFrame:
         """基本面数据请使用 baostock 数据源"""
         raise NotImplementedError(
@@ -295,19 +280,9 @@ class AkshareDataSource(DataSource):
         )
 
     def get_fina_indicator(
-        self,
-        symbols: List[str],
-        report_type: str = "latest"
+        self, symbols: List[str], report_type: str = "latest"
     ) -> pd.DataFrame:
-        raise NotImplementedError(
-            "Use baostock datasource for financial indicators"
-        )
+        raise NotImplementedError("Use baostock datasource for financial indicators")
 
-    def get_valuation(
-        self,
-        symbols: List[str],
-        date
-    ) -> pd.DataFrame:
-        raise NotImplementedError(
-            "Use baostock datasource for valuation data"
-        )
+    def get_valuation(self, symbols: List[str], date) -> pd.DataFrame:
+        raise NotImplementedError("Use baostock datasource for valuation data")

{quantcli-0.1.13 → quantcli-0.1.15}/quantcli/datasources/baostock.py

@@ -39,12 +39,11 @@ class BaostockDataSource(DataSource):
         """
         try:
             import baostock as bs
+
             self._bs = bs
             self._login()
         except ImportError:
-            raise ImportError(
-                "baostock not installed. Run: pip install baostock"
-            )
+            raise ImportError("baostock not installed. Run: pip install baostock")
 
         # 缓存
         self._cache = FundamentalsCache(enabled=use_cache)
@@ -52,7 +51,7 @@ class BaostockDataSource(DataSource):
     def __del__(self):
         """登出"""
         try:
-            if hasattr(self, '_bs'):
+            if hasattr(self, "_bs"):
                 self._bs.logout()
         except Exception:
             pass
@@ -60,7 +59,7 @@ class BaostockDataSource(DataSource):
     def _login(self):
         """登录"""
         lg = self._bs.login()
-        if lg.error_code != '0':
+        if lg.error_code != "0":
             raise RuntimeError(f"Baostock 登录失败: {lg.error_msg}")
 
     def _to_bs_symbol(self, symbol: str) -> str:
@@ -72,9 +71,14 @@ class BaostockDataSource(DataSource):
         - "sh.600519" -> "sh.600519"
         - "SZ000001" -> "sz.000001"
         """
-        #转 统一大写，移除前缀
+        # 转 统一大写，移除前缀
         symbol = symbol.upper()
-        symbol = symbol.replace(".SH", "").replace(".SZ", "").replace("SH", "").replace("SZ", "")
+        symbol = (
+            symbol.replace(".SH", "")
+            .replace(".SZ", "")
+            .replace("SH", "")
+            .replace("SZ", "")
+        )
 
         # 判断交易所
         if symbol.startswith(("6", "5", "9")):
@@ -88,11 +92,7 @@ class BaostockDataSource(DataSource):
         return str(d)
 
     def get_daily(
-        self,
-        symbol: str,
-        start_date,
-        end_date,
-        fields: Optional[List[str]] = None
+        self, symbol: str, start_date, end_date, fields: Optional[List[str]] = None
     ) -> pd.DataFrame:
         """获取日线数据"""
         bs_symbol = self._to_bs_symbol(symbol)
@@ -122,10 +122,10 @@ class BaostockDataSource(DataSource):
                 ",".join(selected),
                 start_date=start_str,
                 end_date=end_str,
-                frequency="d"
+                frequency="d",
             )
 
-            if rs.error_code != '0':
+            if rs.error_code != "0":
                 raise RuntimeError(f"查询失败: {rs.error_msg}")
 
             data_list = []
@@ -155,7 +155,7 @@ class BaostockDataSource(DataSource):
         try:
             rs = self._bs.query_all_stock()
 
-            if rs.error_code != '0':
+            if rs.error_code != "0":
                 raise RuntimeError(f"查询失败: {rs.error_msg}")
 
             data_list = []
@@ -188,12 +188,14 @@ class BaostockDataSource(DataSource):
                 # 提取纯代码
                 symbol = code.replace("sh.", "").replace("sz.", "")
 
-                stocks.append(StockInfo(
-                    symbol=symbol,
-                    name=name,
-                    exchange=exchange,
-                    market=market_type,
-                ))
+                stocks.append(
+                    StockInfo(
+                        symbol=symbol,
+                        name=name,
+                        exchange=exchange,
+                        market=market_type,
+                    )
+                )
 
             return stocks
 
@@ -204,15 +206,12 @@ class BaostockDataSource(DataSource):
         """获取交易日历"""
         # Baostock 没有直接的交易日历，可以从日线数据推断
         # 这里暂时返回空列表，由其他数据源提供
-        logger.warning("Baostock 不提供交易日历，请使用 akshare 的 tool_trade_date_hist_sina")
+        logger.warning(
+            "Baostock 不提供交易日历，请使用 akshare 的 tool_trade_date_hist_sina"
+        )
         return []
 
-    def get_index_daily(
-        self,
-        symbol: str,
-        start_date,
-        end_date
-    ) -> pd.DataFrame:
+    def get_index_daily(self, symbol: str, start_date, end_date) -> pd.DataFrame:
         """获取指数数据"""
         # Baostock 主要支持股票数据，指数数据有限
         raise NotImplementedError(
@@ -228,9 +227,9 @@ class BaostockDataSource(DataSource):
                 "date,close",
                 start_date="2024-01-01",
                 end_date="2024-01-01",
-                frequency="d"
+                frequency="d",
             )
-            if rs.error_code == '0':
+            if rs.error_code == "0":
                 return {"status": "ok", "source": self.name}
             else:
                 return {"status": "error", "source": self.name, "error": rs.error_msg}
@@ -238,9 +237,7 @@ class BaostockDataSource(DataSource):
             return {"status": "error", "source": self.name, "error": str(e)}
 
     def get_fina_indicator(
-        self,
-        symbols: List[str],
-        report_type: str = "latest"
+        self, symbols: List[str], report_type: str = "latest"
     ) -> pd.DataFrame:
         """获取杜邦分析数据"""
         results = []
@@ -254,18 +251,22 @@ class BaostockDataSource(DataSource):
                     for quarter in [1, 2, 3, 4]:
                         rs = self._bs.query_dupont_data(bs_symbol, year, quarter)
 
-                        if rs.error_code != '0':
+                        if rs.error_code != "0":
                             continue
 
                         while rs.next():
                             row = rs.get_row_data()
-                            results.append({
-                                "symbol": symbol,
-                                "year": year,
-                                "quarter": quarter,
-                                "roe": float(row[3]) if row[3] else None,
-                                "netprofitmargin": float(row[7]) if row[7] else None,
-                            })
+                            results.append(
+                                {
+                                    "symbol": symbol,
+                                    "year": year,
+                                    "quarter": quarter,
+                                    "roe": float(row[3]) if row[3] else None,
+                                    "netprofitmargin": float(row[7])
+                                    if row[7]
+                                    else None,
+                                }
+                            )
 
             except Exception as e:
                 logger.warning(f"获取 {symbol} 杜邦数据失败: {e}")
@@ -278,10 +279,7 @@ class BaostockDataSource(DataSource):
         return df
 
     def get_dupont_analysis(
-        self,
-        symbols: List[str],
-        start_year: int = 2022,
-        end_year: int = 2024
+        self, symbols: List[str], start_year: int = 2022, end_year: int = 2024
     ) -> pd.DataFrame:
         """批量获取杜邦分析数据（带缓存）
 
@@ -297,7 +295,7 @@ class BaostockDataSource(DataSource):
 
         for symbol in symbols:
             # 尝试从缓存读取
-            cache_key = f"dupont_{symbol}_{start_year}_{end_year}"
+            cache_key = f"baostock_dupont_{symbol}_{start_year}_{end_year}"
             cached = self._cache.get(cache_key) if self._cache.enabled else None
 
             if cached is not None:
@@ -314,24 +312,36 @@ class BaostockDataSource(DataSource):
                     try:
                         rs = self._bs.query_dupont_data(bs_symbol, year, quarter)
 
-                        if rs.error_code != '0':
+                        if rs.error_code != "0":
                             continue
 
                         while rs.next():
                             row = rs.get_row_data()
-                            symbol_data.append({
-                                "symbol": symbol,
-                                "pub_date": row[1],
-                                "stat_date": row[2],
-                                "roe": float(row[3]) if row[3] else None,
-                                "asset_equity_ratio": float(row[4]) if row[4] else None,
-                                "asset_turnover": float(row[5]) if row[5] else None,
-                                "net_profit_margin": float(row[6]) if row[6] else None,
-                                "gross_profit_margin": float(row[7]) if row[7] else None,
-                                "tax_burden": float(row[8]) if row[8] else None,
-                                "interest_burden": float(row[9]) if row[9] else None,
-                                "ebit_to_nprofit": float(row[10]) if row[10] else None,
-                            })
+                            symbol_data.append(
+                                {
+                                    "symbol": symbol,
+                                    "pub_date": row[1],
+                                    "stat_date": row[2],
+                                    "roe": float(row[3]) if row[3] else None,
+                                    "asset_equity_ratio": float(row[4])
+                                    if row[4]
+                                    else None,
+                                    "asset_turnover": float(row[5]) if row[5] else None,
+                                    "net_profit_margin": float(row[6])
+                                    if row[6]
+                                    else None,
+                                    "gross_profit_margin": float(row[7])
+                                    if row[7]
+                                    else None,
+                                    "tax_burden": float(row[8]) if row[8] else None,
+                                    "interest_burden": float(row[9])
+                                    if row[9]
+                                    else None,
+                                    "ebit_to_nprofit": float(row[10])
+                                    if row[10]
+                                    else None,
+                                }
+                            )
 
                     except Exception as e:
                         logger.warning(f"获取 {symbol} {year}Q{quarter} 数据失败: {e}")
@@ -349,17 +359,14 @@ class BaostockDataSource(DataSource):
         return pd.concat(all_data, ignore_index=True)
 
     def get_profit_data(
-        self,
-        symbols: List[str],
-        start_year: int = 2022,
-        end_year: int = 2024
+        self, symbols: List[str], start_year: int = 2022, end_year: int = 2024
     ) -> pd.DataFrame:
         """批量获取利润表数据（带缓存）"""
         all_data = []
 
         for symbol in symbols:
             # 尝试从缓存读取
-            cache_key = f"profit_{symbol}_{start_year}_{end_year}"
+            cache_key = f"baostock_profit_{symbol}_{start_year}_{end_year}"
             cached = self._cache.get(cache_key) if self._cache.enabled else None
 
             if cached is not None:
@@ -376,20 +383,22 @@ class BaostockDataSource(DataSource):
                     try:
                         rs = self._bs.query_profit_data(bs_symbol, year, quarter)
 
-                        if rs.error_code != '0':
+                        if rs.error_code != "0":
                             continue
 
                         while rs.next():
                             row = rs.get_row_data()
-                            symbol_data.append({
-                                "symbol": symbol,
-                                "pub_date": row[1],
-                                "net_profits": float(row[2]) if row[2] else None,
-                                "net_profits_yr": float(row[3]) if row[3] else None,
-                                "dt_net_profits": float(row[4]) if row[4] else None,
-                                "total_revenue": float(row[5]) if row[5] else None,
-                                "revenue_yr": float(row[6]) if row[6] else None,
-                            })
+                            symbol_data.append(
+                                {
+                                    "symbol": symbol,
+                                    "pub_date": row[1],
+                                    "net_profits": float(row[2]) if row[2] else None,
+                                    "net_profits_yr": float(row[3]) if row[3] else None,
+                                    "dt_net_profits": float(row[4]) if row[4] else None,
+                                    "total_revenue": float(row[5]) if row[5] else None,
+                                    "revenue_yr": float(row[6]) if row[6] else None,
+                                }
+                            )
 
                     except Exception as e:
                         continue
@@ -405,17 +414,14 @@ class BaostockDataSource(DataSource):
         return pd.concat(all_data, ignore_index=True)
 
     def get_growth_data(
-        self,
-        symbols: List[str],
-        start_year: int = 2022,
-        end_year: int = 2024
+        self, symbols: List[str], start_year: int = 2022, end_year: int = 2024
     ) -> pd.DataFrame:
         """批量获取成长能力数据（带缓存）"""
         all_data = []
 
         for symbol in symbols:
             # 尝试从缓存读取
-            cache_key = f"growth_{symbol}_{start_year}_{end_year}"
+            cache_key = f"baostock_growth_{symbol}_{start_year}_{end_year}"
             cached = self._cache.get(cache_key) if self._cache.enabled else None
 
             if cached is not None:
@@ -432,18 +438,24 @@ class BaostockDataSource(DataSource):
                     try:
                         rs = self._bs.query_growth_data(bs_symbol, year, quarter)
 
-                        if rs.error_code != '0':
+                        if rs.error_code != "0":
                             continue
 
                         while rs.next():
                             row = rs.get_row_data()
-                            symbol_data.append({
-                                "symbol": symbol,
-                                "pub_date": row[1],
-                                "net_profits_growth": float(row[2]) if row[2] else None,
-                                "revenue_growth": float(row[3]) if row[3] else None,
-                                "total_assets_growth": float(row[4]) if row[4] else None,
-                            })
+                            symbol_data.append(
+                                {
+                                    "symbol": symbol,
+                                    "pub_date": row[1],
+                                    "net_profits_growth": float(row[2])
+                                    if row[2]
+                                    else None,
+                                    "revenue_growth": float(row[3]) if row[3] else None,
+                                    "total_assets_growth": float(row[4])
+                                    if row[4]
+                                    else None,
+                                }
+                            )
 
                     except Exception as e:
                         continue
@@ -458,11 +470,7 @@ class BaostockDataSource(DataSource):
 
         return pd.concat(all_data, ignore_index=True)
 
-    def get_valuation(
-        self,
-        symbols: List[str],
-        date
-    ) -> pd.DataFrame:
+    def get_valuation(self, symbols: List[str], date) -> pd.DataFrame:
         """获取估值数据（从日线数据计算）"""
         # Baostock 没有直接的估值数据接口
         # 可以从日线数据中提取最新收盘价
@@ -471,10 +479,7 @@ class BaostockDataSource(DataSource):
         )
 
     def get_fundamental(
-        self,
-        symbols: List[str],
-        date,
-        indicators: Optional[List[str]] = None
+        self, symbols: List[str], date, indicators: Optional[List[str]] = None
     ) -> pd.DataFrame:
         """获取合并基本面数据"""
         # 批量下载杜邦分析数据

{quantcli-0.1.13 → quantcli-0.1.15/quantcli.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: quantcli
-Version: 0.1.13
+Version: 0.1.15
 Summary: 面向AI的多因子量化选股策略挖掘工具，AI Agent 友好 CLI
 Author-email: QuantCLI Team <quantcli@example.com>
 Project-URL: repository, https://github.com/wumu2013/quantcli