0.9.33 更新 streamlit 组件

czsc/__init__.py

@@ -90,6 +90,7 @@
     show_sectional_ic,
     show_factor_returns,
     show_factor_layering,
+    show_symbol_factor_layering,
 )
 
 from czsc.utils.bi_info import (

czsc/utils/features.py

@@ -20,10 +20,7 @@ def normalize_feature(df, x_col, **kwargs):
         - q: float，缩尾比例, 默认 0.05
     """
     df = df.copy()
-    if df[x_col].isna().sum() > 0:
-        logger.warning(f"因子列 {x_col} 存在缺失值，已自动剔除，这有可能导致后续分析结果不准确")
-        df = df.dropna(subset=[x_col])
-
+    assert df[x_col].isna().sum() == 0, "因子有缺失值，缺失数量为：{}".format(df[x_col].isna().sum())
     q = kwargs.get("q", 0.05)           # 缩尾比例
     df[x_col] = df.groupby("dt")[x_col].transform(lambda x: scale(x.clip(lower=x.quantile(q), upper=x.quantile(1 - q))))
     return df
@@ -37,29 +34,52 @@ def normalize_ts_feature(df, x_col, n=10, **kwargs):
     :param n: 分层数量，默认为10
     :param kwargs:
 
+        - method: 分层方法，expanding 或 rolling，默认为 expanding
         - min_periods: expanding 时的最小样本数量，默认为300
 
     :return: df, 添加了 x_col_norm, x_col_qcut, x_col分层 列
     """
     assert df[x_col].nunique() > n, "因子值的取值数量必须大于分层数量"
+    assert df[x_col].isna().sum() == 0, "因子有缺失值，缺失数量为：{}".format(df[x_col].isna().sum())
+    method = kwargs.get("method", "expanding")
     min_periods = kwargs.get("min_periods", 300)
-    if df[x_col].isna().sum() > 0:
-        logger.warning(f"因子列 {x_col} 存在缺失值，请注意！建议先对因子缺失值进行填充")
 
     if f"{x_col}_norm" not in df.columns:
-        df[f"{x_col}_norm"] = df[x_col].expanding(min_periods=min_periods).apply(
-            lambda x: (x.iloc[-1] - x.mean()) / x.std(), raw=False)
+        if method == "expanding":
+            df[f"{x_col}_norm"] = df[x_col].expanding(min_periods=min_periods).apply(
+                lambda x: (x.iloc[-1] - x.mean()) / x.std(), raw=False)
+
+        elif method == "rolling":
+            df[f"{x_col}_norm"] = df[x_col].rolling(min_periods=min_periods, window=min_periods).apply(
+                lambda x: (x.iloc[-1] - x.mean()) / x.std(), raw=False)
+
+        else:
+            raise ValueError("method 必须为 expanding 或 rolling")
 
         # 用标准化后的值填充原始值中的缺失值
         na_x = df[df[f"{x_col}_norm"].isna()][x_col].values
         df.loc[df[f"{x_col}_norm"].isna(), f"{x_col}_norm"] = na_x - na_x.mean() / na_x.std()
 
     if f"{x_col}_qcut" not in df.columns:
-        df[f'{x_col}_qcut'] = df[x_col].expanding(min_periods=min_periods).apply(
-            lambda x: pd.qcut(x, q=n, labels=False, duplicates='drop', retbins=False).values[-1], raw=False)
+        if method == "expanding":
+            df[f'{x_col}_qcut'] = df[x_col].expanding(min_periods=min_periods).apply(
+                lambda x: pd.qcut(x, q=n, labels=False, duplicates='drop', retbins=False).values[-1], raw=False)
+
+        elif method == "rolling":
+            df[f'{x_col}_qcut'] = df[x_col].rolling(min_periods=min_periods, window=min_periods).apply(
+                lambda x: pd.qcut(x, q=n, labels=False, duplicates='drop', retbins=False).values[-1], raw=False)
 
+        else:
+            raise ValueError("method 必须为 expanding 或 rolling")
+
+        # 用分位数后的值填充原始值中的缺失值
         na_x = df[df[f"{x_col}_qcut"].isna()][x_col].values
         df.loc[df[f"{x_col}_qcut"].isna(), f"{x_col}_qcut"] = pd.qcut(na_x, q=n, labels=False, duplicates='drop', retbins=False)
+
+        if df[f'{x_col}_qcut'].isna().sum() > 0:
+            logger.warning(f"因子 {x_col} 分层存在 {df[f'{x_col}_qcut'].isna().sum()} 个缺失值，已使用前值填充")
+            df[f'{x_col}_qcut'] = df[f'{x_col}_qcut'].ffill()
+
         df[f'{x_col}分层'] = df[f'{x_col}_qcut'].apply(lambda x: f'第{str(int(x+1)).zfill(2)}层')
 
     return df

czsc/utils/st_components.py

@@ -41,8 +41,16 @@ def _stats(df_, type_='持有日'):
 
         df = df.cumsum()
         fig = px.line(df, y=df.columns.to_list(), title="日收益累计曲线")
+        fig.update_xaxes(title='')
+
+        # 添加每年的开始第一个日期的竖线
+        for year in range(df.index.year.min(), df.index.year.max() + 1):
+            first_date = df[df.index.year == year].index.min()
+            fig.add_vline(x=first_date, line_dash='dash', line_color='red')
+
         for col in kwargs.get("legend_only_cols", []):
             fig.update_traces(visible="legendonly", selector=dict(name=col))
+
         st.plotly_chart(fig, use_container_width=True)
 
 
@@ -183,14 +191,16 @@ def show_symbol_factor_layering(df, x_col, y_col='n1b', **kwargs):
     if df[y_col].max() > 100:       # 如果收益率单位为BP, 转换为万分之一
         df[y_col] = df[y_col] / 10000
 
-    if df[x_col].nunique() > n:
-        czsc.normalize_ts_feature(df, x_col)
-    else:
-        # 如果因子值的取值数量小于分层数量，直接使用因子独立值排序作为分层
-        x_rank = sorted(df[x_col].unique())
-        x_rank = {x_rank[i]: f'第{str(i+1).zfill(2)}层' for i in range(len(x_rank))}
-        st.success(f"因子值分层对应关系：{x_rank}")
-        df[f'{x_col}分层'] = df[x_col].apply(lambda x: x_rank[x])
+    if f'{x_col}分层' not in df.columns:
+        # 如果因子分层列不存在，先计算因子分层
+        if df[x_col].nunique() > n:
+            czsc.normlize_ts_feature(df, x_col, n=n)
+        else:
+            # 如果因子值的取值数量小于分层数量，直接使用因子独立值排序作为分层
+            x_rank = sorted(df[x_col].unique())
+            x_rank = {x_rank[i]: f'第{str(i+1).zfill(2)}层' for i in range(len(x_rank))}
+            st.success(f"因子值分层对应关系：{x_rank}")
+            df[f'{x_col}分层'] = df[x_col].apply(lambda x: x_rank[x])
 
     for i in range(n):
         df[f'第{str(i+1).zfill(2)}层'] = np.where(df[f'{x_col}分层'] == f'第{str(i+1).zfill(2)}层', df[y_col], 0)
@@ -209,7 +219,7 @@ def show_symbol_factor_layering(df, x_col, y_col='n1b', **kwargs):
         long = col1.multiselect("多头组合", layering_cols, default=["第02层"], key="symbol_factor_long")
         short = col2.multiselect("空头组合", layering_cols, default=["第01层"], key="symbol_factor_short")
         dfr = mrr.copy()
-        dfr['多头'] = dfr[long].mean(axis=1)
-        dfr['空头'] = -dfr[short].mean(axis=1)
-        dfr['多空'] = (dfr['多头'] + dfr['空头']) / 2
+        dfr['多头'] = dfr[long].sum(axis=1)
+        dfr['空头'] = -dfr[short].sum(axis=1)
+        dfr['多空'] = dfr['多头'] + dfr['空头']
         show_daily_return(dfr[['多头', '空头', '多空']])