V0.9.47 更新一批代码 (waditu#191)

* 0.9.47 first commit

* 0.9.47 新增 clear cache 方法

* 0.9.47 update

* 0.9.47 update

* 0.9.47 fix minites split

* 0.9.47 update

* 0.9.47 coo 优化缓存逻辑

* 0.9.47 update

* 0.9.47 update

* 0.9.47 新增一个信号函数

* 0.9.47 合并XL贡献的信号函数

* 0.9.47 update

* 0.9.47 update

* 09.47 最大回撤分析组件，新增分位数分析

* 0.9.47 update

* 0.9.47 update tqsdk

.github/workflows/pythonpackage.yml

@@ -5,7 +5,7 @@ name: Python package
 
 on:
   push:
-    branches: [ master, V0.9.46 ]
+    branches: [ master, V0.9.47 ]
   pull_request:
     branches: [ master ]
 

czsc/__init__.py

@@ -88,6 +88,7 @@
     home_path,
     DiskCache,
     disk_cache,
+    clear_cache,
     get_dir_size,
     empty_cache_path,
     print_df_sample,
@@ -154,12 +155,13 @@
     rolling_slope,
     rolling_tanh,
     feature_adjust,
+    normalize_corr,
 )
 
-__version__ = "0.9.46"
+__version__ = "0.9.47"
 __author__ = "zengbin93"
 __email__ = "[email protected]"
-__date__ = "20240318"
+__date__ = "20240328"
 
 
 def welcome():

czsc/cmd.py

@@ -17,8 +17,7 @@ def czsc():
 
 
 @czsc.command()
-def aphorism():
+def a():
     """随机输出一条缠中说禅良言警句"""
     from czsc.aphorism import print_one
-
     print_one()

czsc/connectors/cooperation.py

@@ -56,46 +56,52 @@ def get_symbols(name, **kwargs):
     :return:
     """
     if name == "股票":
-        df = dc.stock_basic(nobj=1, status=1)
+        df = dc.stock_basic(nobj=1, status=1, ttl=3600 * 6)
         symbols = [f"{row['code']}#STOCK" for _, row in df.iterrows()]
         return symbols
 
     if name == "ETF":
-        df = dc.etf_basic(v=2, fields='code,name')
-        dfk = dc.pro_bar(trade_date="2023-11-17", asset="e", v=2)
+        df = dc.etf_basic(v=2, fields='code,name', ttl=3600 * 6)
+        dfk = dc.pro_bar(trade_date="2024-04-02", asset="e", v=2)
         df = df[df['code'].isin(dfk['code'])].reset_index(drop=True)
         symbols = [f"{row['code']}#ETF" for _, row in df.iterrows()]
         return symbols
 
     if name == "A股指数":
         # 指数 https://s0cqcxuy3p.feishu.cn/wiki/KuSAweAAhicvsGk9VPTc1ZWKnAd
-        df = dc.index_basic(v=2, market='SSE,SZSE')
+        df = dc.index_basic(v=2, market='SSE,SZSE', ttl=3600 * 6)
         symbols = [f"{row['code']}#INDEX" for _, row in df.iterrows()]
         return symbols
 
     if name == "南华指数":
-        df = dc.index_basic(v=2, market='NH')
+        df = dc.index_basic(v=2, market='NH', ttl=3600 * 6)
         symbols = [row['code'] for _, row in df.iterrows()]
         return symbols
 
     if name == "期货主力":
-        kline = dc.future_klines(trade_date="20231101")
+        kline = dc.future_klines(trade_date="20240402", ttl=3600 * 6)
         return kline['code'].unique().tolist()
 
+    if name.upper() == "ALL":
+        symbols = get_symbols("股票") + get_symbols("ETF")
+        symbols += get_symbols("A股指数") + get_symbols("南华指数") + get_symbols("期货主力")
+        return symbols
+
     raise ValueError(f"{name} 分组无法识别，获取标的列表失败！")
 
 
 def get_min_future_klines(code, sdt, edt, freq='1m'):
     """分段获取期货1分钟K线后合并"""
     # dates = pd.date_range(start=sdt, end=edt, freq='1M')
-    dates = pd.date_range(start=sdt, end=edt, freq='30D')
+    dates = pd.date_range(start=sdt, end=edt, freq='120D')
 
     dates = [d.strftime('%Y%m%d') for d in dates] + [sdt, edt]
     dates = sorted(list(set(dates)))
 
     rows = []
     for sdt_, edt_ in tqdm(zip(dates[:-1], dates[1:]), total=len(dates) - 1):
-        df = dc.future_klines(code=code, sdt=sdt_, edt=edt_, freq=freq)
+        ttl = 60 if pd.to_datetime(edt_).date() == datetime.now().date() else -1
+        df = dc.future_klines(code=code, sdt=sdt_, edt=edt_, freq=freq, ttl=ttl)
         if df.empty:
             continue
         logger.info(f"{code}获取K线范围：{df['dt'].min()} - {df['dt'].max()}")
@@ -104,8 +110,19 @@ def get_min_future_klines(code, sdt, edt, freq='1m'):
     df = pd.concat(rows, ignore_index=True)
     df.rename(columns={'code': 'symbol'}, inplace=True)
     df['dt'] = pd.to_datetime(df['dt'])
-
     df = df.drop_duplicates(subset=['dt', 'symbol'], keep='last')
+
+    if code in ['SFIC9001', 'SFIF9001', 'SFIH9001']:
+        # 股指：仅保留 09:31 - 11:30, 13:01 - 15:00
+        dt1 = datetime.strptime("09:31:00", "%H:%M:%S")
+        dt2 = datetime.strptime("11:30:00", "%H:%M:%S")
+        c1 = (df['dt'].dt.time >= dt1.time()) & (df['dt'].dt.time <= dt2.time())
+
+        dt3 = datetime.strptime("13:01:00", "%H:%M:%S")
+        dt4 = datetime.strptime("15:00:00", "%H:%M:%S")
+        c2 = (df['dt'].dt.time >= dt3.time()) & (df['dt'].dt.time <= dt4.time())
+
+        df = df[c1 | c2].copy().reset_index(drop=True)
     return df
 
 
@@ -119,10 +136,14 @@ def get_raw_bars(symbol, freq, sdt, edt, fq='前复权', **kwargs):
     :param edt: 结束时间
     :param fq: 除权类型，可选值：'前复权', '后复权', '不复权'
     :param kwargs:
-    :return:
+    :return: RawBar 对象列表 or DataFrame
+
+    >>> from czsc.connectors import cooperation as coo
+    >>> df = coo.get_raw_bars(symbol="000001.SH#INDEX", freq="日线", sdt="2001-01-01", edt="2021-12-31", fq='后复权', raw_bars=False)
     """
     freq = czsc.Freq(freq)
     raw_bars = kwargs.get('raw_bars', True)
+    ttl = kwargs.get('ttl', -1)
 
     if "SH" in symbol or "SZ" in symbol:
         fq_map = {"前复权": "qfq", "后复权": "hfq", "不复权": None}
@@ -131,14 +152,17 @@ def get_raw_bars(symbol, freq, sdt, edt, fq='前复权', **kwargs):
         code, asset = symbol.split("#")
 
         if freq.value.endswith('分钟'):
-            df = dc.pro_bar(code=code, sdt=sdt, edt=edt, freq='min', adj=adj, asset=asset[0].lower(), v=2)
+            df = dc.pro_bar(code=code, sdt=sdt, edt=edt, freq='min', adj=adj, asset=asset[0].lower(), v=2, ttl=ttl)
             df = df[~df['dt'].str.endswith("09:30:00")].reset_index(drop=True)
-        else:
-            df = dc.pro_bar(code=code, sdt=sdt, edt=edt, freq='day', adj=adj, asset=asset[0].lower(), v=2)
+            df.rename(columns={'code': 'symbol'}, inplace=True)
+            df['dt'] = pd.to_datetime(df['dt'])
+            return czsc.resample_bars(df, target_freq=freq, raw_bars=raw_bars, base_freq='1分钟')
 
-        df.rename(columns={'code': 'symbol'}, inplace=True)
-        df['dt'] = pd.to_datetime(df['dt'])
-        return czsc.resample_bars(df, target_freq=freq, raw_bars=raw_bars)
+        else:
+            df = dc.pro_bar(code=code, sdt=sdt, edt=edt, freq='day', adj=adj, asset=asset[0].lower(), v=2, ttl=ttl)
+            df.rename(columns={'code': 'symbol'}, inplace=True)
+            df['dt'] = pd.to_datetime(df['dt'])
+            return czsc.resample_bars(df, target_freq=freq, raw_bars=raw_bars)
 
     if symbol.endswith("9001"):
         # https://s0cqcxuy3p.feishu.cn/wiki/WLGQwJLWQiWPCZkPV7Xc3L1engg
@@ -148,19 +172,23 @@ def get_raw_bars(symbol, freq, sdt, edt, fq='前复权', **kwargs):
         freq_rd = '1m' if freq.value.endswith('分钟') else '1d'
         if freq.value.endswith('分钟'):
             df = get_min_future_klines(code=symbol, sdt=sdt, edt=edt, freq='1m')
+            df['amount'] = df['vol'] * df['close']
+            df = df[['symbol', 'dt', 'open', 'close', 'high', 'low', 'vol', 'amount']].copy().reset_index(drop=True)
+            df['dt'] = pd.to_datetime(df['dt'])
+            return czsc.resample_bars(df, target_freq=freq, raw_bars=raw_bars, base_freq='1分钟')
+
         else:
-            df = dc.future_klines(code=symbol, sdt=sdt, edt=edt, freq=freq_rd)
+            df = dc.future_klines(code=symbol, sdt=sdt, edt=edt, freq=freq_rd, ttl=ttl)
             df.rename(columns={'code': 'symbol'}, inplace=True)
-
-        df['amount'] = df['vol'] * df['close']
-        df = df[['symbol', 'dt', 'open', 'close', 'high', 'low', 'vol', 'amount']].copy().reset_index(drop=True)
-        df['dt'] = pd.to_datetime(df['dt'])
-        return czsc.resample_bars(df, target_freq=freq, raw_bars=raw_bars)
+            df['amount'] = df['vol'] * df['close']
+            df = df[['symbol', 'dt', 'open', 'close', 'high', 'low', 'vol', 'amount']].copy().reset_index(drop=True)
+            df['dt'] = pd.to_datetime(df['dt'])
+            return czsc.resample_bars(df, target_freq=freq, raw_bars=raw_bars)
 
     if symbol.endswith(".NH"):
         if freq != Freq.D:
             raise ValueError("南华指数只支持日线数据")
-        df = dc.nh_daily(code=symbol, sdt=sdt, edt=edt)
+        df = dc.nh_daily(code=symbol, sdt=sdt, edt=edt, ttl=ttl)
 
     raise ValueError(f"symbol {symbol} 无法识别，获取数据失败！")
 

czsc/connectors/tq_connector.py

@@ -183,26 +183,6 @@ def format_kline(df, freq=Freq.F1):
 }
 
 
-def is_trade_time(trade_time: Optional[str] = None):
-    """判断当前是否是交易时间"""
-    if trade_time is None:
-        trade_time = datetime.now().strftime("%H:%M:%S")
-
-    if trade_time >= "09:00:00" and trade_time <= "11:30:00":
-        return True
-
-    if trade_time >= "13:00:00" and trade_time <= "15:00:00":
-        return True
-
-    if trade_time >= "21:00:00" and trade_time <= "23:59:59":
-        return True
-
-    if trade_time >= "00:00:00" and trade_time <= "02:30:00":
-        return True
-
-    return False
-
-
 def get_daily_backup(api: TqApi, **kwargs):
     """获取每日账户中需要备份的信息
 
@@ -238,6 +218,18 @@ def get_daily_backup(api: TqApi, **kwargs):
     return backup
 
 
+def is_trade_time(quote):
+    """判断当前是否是交易时间"""
+    trade_time = pd.Timestamp.now().strftime("%H:%M:%S")
+    times = quote["trading_time"]['day'] + quote["trading_time"]['night']
+
+    for sdt, edt in times:
+        if trade_time >= sdt and trade_time <= edt:
+            logger.info(f"当前时间：{trade_time}，交易时间：{sdt} - {edt}")
+            return True
+    return False
+
+
 def adjust_portfolio(api: TqApi, portfolio, account=None, **kwargs):
     """调整账户组合
 
@@ -255,11 +247,21 @@ def adjust_portfolio(api: TqApi, portfolio, account=None, **kwargs):
 
     :param kwargs: dict, 其他参数
     """
+    timeout = kwargs.get("timeout", 600)
+    start_time = datetime.now()
+
     symbol_infos = {}
     for symbol, conf in portfolio.items():
         quote = api.get_quote(symbol)
+        if not is_trade_time(quote):
+            logger.warning(f"{symbol} 当前时间不是交易时间，跳过调仓")
+            continue
+
+        lots = conf.get("target_volume", None)
+        if lots is None:
+            logger.warning(f"{symbol} 目标手数为 None，跳过调仓")
+            continue
 
-        lots = conf.get("target_volume", 0)
         price = conf.get("price", "PASSIVE")
         offset_priority = conf.get("offset_priority", "今昨,开")
 
@@ -281,16 +283,17 @@ def adjust_portfolio(api: TqApi, portfolio, account=None, **kwargs):
 
             logger.info(f"调整仓位：{quote.datetime} - {contract}; 目标持仓：{lots}手; 当前持仓：{target_pos._pos.pos}手")
 
-            if target_pos._pos.pos == lots:
+            if target_pos._pos.pos == lots or target_pos.is_finished():
                 completed.append(True)
-                logger.info(f"调仓完成：{quote.datetime} - {contract}; {lots}手")
+                logger.info(f"调仓完成：{quote.datetime} - {contract}; 目标持仓：{lots}手; 当前持仓：{target_pos._pos.pos}手")
             else:
                 completed.append(False)
 
         if all(completed):
             break
 
-    if kwargs.get("close_api", True):
-        api.close()
+        if (datetime.now() - start_time).seconds > timeout:
+            logger.error(f"调仓超时，已运行 {timeout} 秒")
+            break
 
     return api

czsc/features/utils.py

@@ -256,6 +256,52 @@ def __lr_slope(x):
     return df
 
 
+def normalize_corr(df: pd.DataFrame, fcol, ycol=None, **kwargs):
+    """标准化因子与收益相关性为正数
+
+    方法说明：对因子进行滚动相关系数计算，因子乘以滚动相关系数的符号
+
+    **注意：**
+
+    1. simple 模式下，计算过程有一定的未来信息泄露，在回测中使用时需要注意
+    2. rolling 模式下，计算过程依赖 window 参数，有可能调整后相关性为负数
+
+    :param df: pd.DataFrame, 必须包含 dt、symbol、price 列，以及因子列
+    :param fcol: str 因子列名
+    :param kwargs: dict
+
+        - window: int, 滚动窗口大小
+        - min_periods: int, 最小计算周期
+        - mode: str, 计算方法, rolling 表示使用滚动调整相关系数，simple 表示使用镜像反转相关系数
+        - copy: bool, 是否复制 df
+
+    :return: pd.DataFrame
+    """
+    window = kwargs.get("window", 1000)
+    min_periods = kwargs.get("min_periods", 5)
+    mode = kwargs.get("mode", "rolling")
+    if kwargs.get("copy", False):
+        df = df.copy()
+
+    df = df.sort_values(['symbol', 'dt'], ascending=True).reset_index(drop=True)
+    for symbol, dfg in df.groupby("symbol"):
+        dfg['ycol'] = dfg['price'].pct_change().shift(-1)
+
+        if mode.lower() == "rolling":
+            dfg['corr_sign'] = np.sign(dfg[fcol].rolling(window=window, min_periods=min_periods).corr(dfg['ycol']))
+            dfg[fcol] = (dfg['corr_sign'].shift(3) * dfg[fcol]).fillna(0)
+
+        elif mode.lower() == "simple":
+            corr_sign = np.sign(dfg[fcol].corr(dfg['ycol']))
+            dfg[fcol] = corr_sign * dfg[fcol]
+
+        else:
+            raise ValueError(f"Unknown mode: {mode}")
+
+        df.loc[df['symbol'] == symbol, fcol] = dfg[fcol]
+    return df
+
+
 def feature_adjust_V230101(df: pd.DataFrame, fcol, **kwargs):
     """特征调整函数：对特征进行调整，使其符合持仓权重的定义
 
@@ -312,6 +358,7 @@ def feature_adjust(df: pd.DataFrame, fcol, method, **kwargs):
     :param fcol: str, 因子列名
     :param method: str, 调整方法
 
+        - KEEP: 直接使用原始因子值作为权重
         - V230101: 对因子进行滚动相关系数计算，然后对因子值用 maxabs_scale 进行归一化，最后乘以滚动相关系数的符号
         - V240323: 对因子进行滚动相关系数计算，然后对因子值用 scale + tanh 进行归一化，最后乘以滚动相关系数的符号
 
@@ -322,6 +369,10 @@ def feature_adjust(df: pd.DataFrame, fcol, method, **kwargs):
 
     :return: pd.DataFrame, 新增 weight 列
     """
+    if method == "KEEP":
+        df["weight"] = df[fcol]
+        return df
+
     if method == "V230101":
         return feature_adjust_V230101(df, fcol, **kwargs)
     elif method == "V240323":

czsc/signals/__init__.py

@@ -5,12 +5,6 @@
 create_dt: 2021/11/21 17:48
 describe: 信号函数
 """
-# ======================================================================================================================
-# 以下是 0.9.1 开始的新标准下实现的信号函数，规范定义：
-# 1. 前缀3个字符区分信号类别
-# 2. 后缀 V221107 之类的标识同一个信号函数的不同版本
-# ======================================================================================================================
-
 from czsc.signals.cxt import (
     cxt_fx_power_V221107,
     cxt_first_buy_V221126,
@@ -208,6 +202,7 @@
     tas_macd_bc_V230804,
     tas_macd_bc_ubi_V230804,
     tas_slope_V231019,
+    tas_macd_bc_V240307,
 )
 
 from czsc.signals.pos import (
@@ -263,3 +258,11 @@
     zdy_dif_V230528,
     pressure_support_V240222,
 )
+
+
+from czsc.signals.xls import (
+    xl_bar_position_V240328,
+    xl_bar_trend_V240329,
+    xl_bar_trend_V240330,
+    xl_bar_trend_V240331,
+)