0.9.47 first commit

.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

@@ -154,12 +154,13 @@
     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/connectors/cooperation.py

@@ -82,6 +82,11 @@ def get_symbols(name, **kwargs):
         kline = dc.future_klines(trade_date="20231101")
         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！")
 
 

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/utils/st_components.py

@@ -762,6 +762,7 @@ def show_out_in_compare(df, ret_col, mid_dt, **kwargs):
     df = df[[ret_col]].copy().fillna(0)
     df.sort_index(inplace=True, ascending=True)
 
+    mid_dt = pd.to_datetime(mid_dt)
     dfi = df[df.index < mid_dt].copy()
     dfo = df[df.index >= mid_dt].copy()
 
@@ -807,7 +808,7 @@ def show_out_in_compare(df, ret_col, mid_dt, **kwargs):
             '新高占比': '{:.2%}',
         }
     )
-    st.dataframe(df_stats, use_container_width=True)
+    st.dataframe(df_stats, use_container_width=True, hide_index=True)
 
 
 def show_optuna_study(study: optuna.Study, **kwargs):

test/test_features.py

@@ -37,3 +37,37 @@ def test_rolling_tanh():
     result_df = rolling_tanh(df, 'col1', new_col='col1_tanh3', window=100, min_periods=50)
     assert 'col1_tanh3' in result_df.columns
     assert result_df['col1_tanh3'].between(-1, 1).all()
+
+
+def test_normalize_corr():
+    from czsc.features.utils import normalize_corr
+
+    np.random.seed(123)
+    # Create a fake DataFrame
+    df = pd.DataFrame({
+        'dt': pd.date_range(start='1/1/2021', periods=3000),
+        'symbol': ['AAPL'] * 3000,
+        'price': np.random.rand(3000),
+        'factor': np.random.rand(3000),
+    })
+
+    df['n1b'] = df['price'].shift(-1) / df['price'] - 1
+    raw_corr = df['n1b'].corr(df['factor'])
+
+    # Call the function with the fake DataFrame
+    result = normalize_corr(df, fcol='factor', copy=True, mode='rolling', window=600)
+    corr1 = result['n1b'].corr(result['factor'])
+    assert result.shape == df.shape and np.sign(corr1) == -np.sign(raw_corr)
+
+    # Call the function with the fake DataFrame
+    result = normalize_corr(df, fcol='factor', copy=True, mode='rolling', window=300)
+    corr1 = result['n1b'].corr(result['factor'])
+    assert result.shape == df.shape and np.sign(corr1) == np.sign(raw_corr)
+
+    result = normalize_corr(df, fcol='factor', copy=True, mode='rolling', window=2000)
+    corr1 = result['n1b'].corr(result['factor'])
+    assert result.shape == df.shape and np.sign(corr1) == -np.sign(raw_corr)
+
+    result = normalize_corr(df, fcol='factor', copy=True, mode='simple')
+    corr2 = result['n1b'].corr(result['factor'])
+    assert result.shape == df.shape and corr2 == -raw_corr