v3.6.2

pure_ocean_breeze/__init__.py

@@ -2,8 +2,8 @@
 一个量化多因子研究的框架，包含数据、回测、因子加工等方面的功能
 """
 
-__updated__ = "2022-12-14 01:02:39"
-__version__ = "3.6.1"
+__updated__ = "2022-12-15 20:52:25"
+__version__ = "3.6.2"
 __author__ = "chenzongwei"
 __author_email__ = "[email protected]"
 __url__ = "https://github.com/chen-001/pure_ocean_breeze"

pure_ocean_breeze/data/read_data.py

@@ -1,4 +1,4 @@
-__updated__ = "2022-12-13 00:59:02"
+__updated__ = "2022-12-16 00:48:25"
 
 import os
 import numpy as np
@@ -32,6 +32,7 @@ def read_daily(
     ret: bool = 0,
     ret_inday: bool = 0,
     ret_night: bool = 0,
+    vol_daily: bool = 0,
     vol: bool = 0,
     vol_inday: bool = 0,
     vol_night: bool = 0,
@@ -79,6 +80,8 @@ def read_daily(
         为1则表示读取日内收益率, by default 0
     ret_night : bool, optional
         为1则表示读取隔夜波动率, by default 0
+    vol_daily : bool, optional
+        为1则表示读取使用分钟收盘价的标准差计算的波动率, by default 0
     vol : bool, optional
         为1则选择读取滚动20日日间波动率, by default 0
     vol_inday : bool, optional
@@ -159,6 +162,8 @@ def read_daily(
                 / read_daily(close=1, start=start).shift(1)
                 - 1
             )
+        elif vol_daily:
+            df = pd.read_parquet(homeplace.factor_data_file + "草木皆兵/草木皆兵_初级.parquet")
         elif vol:
             df = read_daily(ret=1, start=start)
             df = df.rolling(20, min_periods=10).std()
@@ -202,7 +207,7 @@ def read_daily(
         else:
             raise IOError("阁下总得读点什么吧？🤒")
     df = df[df.index >= pd.Timestamp(str(start))]
-    return df
+    return df.dropna(how='all')
 
 
 def read_market(
@@ -378,7 +383,7 @@ def read_index_single(code: str) -> pd.Series:
     -------
     pd.Series
         日行情数据
-    """    
+    """
     try:
         chc = ClickHouseClient("minute_data")
         hs300 = (

pure_ocean_breeze/labor/process.py

@@ -1,4 +1,4 @@
-__updated__ = "2022-12-14 00:27:19"
+__updated__ = "2022-12-16 00:45:28"
 
 import warnings
 
@@ -1231,8 +1231,18 @@ def show_corrs_with_old(
             daily = 1
         else:
             daily = 0
+    nums = os.listdir(homeplace.final_factor_file)
+    nums = sorted(
+        set(
+            [
+                int(i.split("多因子")[1].split("_月")[0])
+                for i in nums
+                if i.endswith(".parquet")
+            ]
+        )
+    )
     olds = []
-    for i in range(1, 100):
+    for i in nums:
         try:
             if daily:
                 old = database_read_final_factors(order=i)[0]
@@ -1243,13 +1253,9 @@ def show_corrs_with_old(
             break
     if df is not None:
         olds = [df] + olds
-        corrs = show_corrs(
-            olds, ["new"] + [f"old{i}" for i in range(1, len(olds))], method=method
-        )
+        corrs = show_corrs(olds, ["new"] + [f"old{i}" for i in nums], method=method)
     else:
-        corrs = show_corrs(
-            olds, [f"old{i}" for i in range(1, len(olds))], method=method
-        )
+        corrs = show_corrs(olds, [f"old{i}" for i in nums], method=method)
     return corrs
 
 

更新日志/version3.md

@@ -1,5 +1,9 @@
 ## 更新日志🗓 — v3
 
+* v3.6.2 — 2022.12.18
+> 1. 给read_daily函数增加了vol_daily参数，用于读取使用分钟收益率的标准差计算的每日波动率
+> 1. 使read_daily读出的数据不再包含全为空值的行
+> 1. 修复了因子标号跳跃导致的show_corrs_with_old函数显示不全的bug
 * v3.6.1 — 2022.12.14
 > 1. 修复了drop_duplicates_index的bug
 > 1. 给pure_moonnight增加了without_breakpoint参数，用于控制iplot画图忽略空格