原创文章第447篇，专注“AI量化投资、个人成长与财富自由"。
本周星球代码计划——因子分析，因子挖掘：
1、（因子表达式优化）Alpha158以及world quant101部分因子实现。
2、基于lightgbm的因子筛选。
3、优秀因子的单因子分析。
4、deepalphagen和gplearn部分代码优化。
或者可以这么说，当前主流私募基金的做法就是因子挖掘。——手工挖，遗传算法，机器学习等。然后合成因子。
因为因子到策略，还有很多人工可以干预的环节。
完全所谓端到端，哪怕就是现在最强的GPT-5也做不到。当下大模型可以真正落地的场景，还是Agent生态，通过多环节的串联+工具来实现预期的目标。
投资也如此。
最多到端对端挖掘因子，然后把因子拿出来做策略。
因子表达式重构
两个包装器，一个按symbol来groupby，另一个按date来groupby
def calc_by_date(func):
@wraps(func)
def wrapper(*args, **kwargs):
other_args = []
se_args = []
se_names = []
for arg in args:
if type(arg) is not pd.Series:
other_args.append(arg)
else:
se_args.append(arg)
se_names.append(arg.name)
if len(se_args) == 1:
ret = se_args[0].groupby(level=0, group_keys=False).apply(lambda x: func(x, *other_args, **kwargs))
elif len(se_args) > 1:
count = len(se_args)
df = pd.concat(se_args, axis=1)
df.index = se_args[0].index
ret = df.groupby(level=0, group_keys=False).apply(
lambda sub_df: func(*[sub_df[name] for name in se_names], *other_args))
ret.index = df.index
return ret
return wrapper
def calc_by_symbol(func):
@wraps(func)
def wrapper(*args, **kwargs):
other_args = []
se_args = []
se_names = []
for arg in args:
if type(arg) is not pd.Series:
other_args.append(arg)
else:
se_args.append(arg)
se_names.append(arg.name)
if len(se_args) == 1:
ret = se_args[0].groupby(level=1, group_keys=False).apply(lambda x: func(x, *other_args, **kwargs))
elif len(se_args) > 1:
count = len(se_args)
df = pd.concat(se_args, axis=1)
df.index = se_args[0].index
ret = df.groupby(level=1, group_keys=False).apply(
lambda sub_df: func(*[sub_df[name] for name in se_names], *other_args))
ret.index = df.index
return ret
return wrapper
目前，需要使用截面排序rank，需要截面排序。
这样做的好处，就是所有的计算子函数都不需要变更了，加上这个包装器即可：
@calc_by_symbol
def ta_atr(high, low, close, period=14):
se = talib.ATR(high, low, close, period)
se = pd.Series(se)
se.index = high.index
return se
@calc_by_date
def rank(se: pd.Series):
ret = se.rank(pct=True)
return ret
这样csv_dataloader加载数据，因子计算速度也快了很多，最重要的是，我们解决了rank，ts_rank嵌套的问题。
Alpha158因子库
代码完全移植过来了，qlib的158因子，大家感兴趣可以把alpha360也迁移过来。
代码在如下位置：
from datafeed import AlphaBase
class Alpha158(AlphaBase):
def get_fields_names(self):
# ['CORD30', 'STD30', 'CORR5', 'RESI10', 'CORD60', 'STD5', 'LOW0',
# 'WVMA30', 'RESI5', 'ROC5', 'KSFT', 'STD20', 'RSV5', 'STD60', 'KLEN']
fields = []
names = []
# kbar
fields += [
"(close-open)/open",
"(high-low)/open",
"(close-open)/(high-low+1e-12)",
"(high-greater(open, close))/open",
"(high-greater(open, close))/(high-low+1e-12)",
"(less(open, close)-low)/open",
"(less(open, close)-low)/(high-low+1e-12)",
"(2*close-high-low)/open",
"(2*close-high-low)/(high-low+1e-12)",
]
names += [
"KMID",
"KLEN",
"KMID2",
"KUP",
"KUP2",
"KLOW",
"KLOW2",
"KSFT",
"KSFT2",
]
# =========== price ==========
feature = ["OPEN", "HIGH", "LOW", "CLOSE"]
windows = range(5)
for field in feature:
field = field.lower()
fields += ["shift(%s, %d)/close" % (field, d) if d != 0 else "%s/close" % field for d in windows]
names += [field.upper() + str(d) for d in windows]
# ================ volume ===========
fields += ["shift(volume, %d)/(volume+1e-12)" % d if d != 0 else "volume/(volume+1e-12)" for d in windows]
names += ["VOLUME" + str(d) for d in windows]
# ================= rolling ====================
windows = [5, 10, 20, 30, 60]
fields += ["shift(close, %d)/close" % d for d in windows]
names += ["ROC%d" % d for d in windows]
fields += ["mean(close, %d)/close" % d for d in windows]
names += ["MA%d" % d for d in windows]
fields += ["std(close, %d)/close" % d for d in windows]
names += ["STD%d" % d for d in windows]
#fields += ["slope(close, %d)/close" % d for d in windows]
#names += ["BETA%d" % d for d in windows]
fields += ["max(high, %d)/close" % d for d in windows]
names += ["MAX%d" % d for d in windows]
fields += ["min(low, %d)/close" % d for d in windows]
names += ["MIN%d" % d for d in windows]
fields += ["quantile(close, %d, 0.8)/close" % d for d in windows]
names += ["QTLU%d" % d for d in windows]
fields += ["quantile(close, %d, 0.2)/close" % d for d in windows]
names += ["QTLD%d" % d for d in windows]
#fields += ["ts_rank(close, %d)" % d for d in windows]
#names += ["RANK%d" % d for d in windows]
fields += ["(close-min(low, %d))/(max(high, %d)-min(low, %d)+1e-12)" % (d, d, d) for d in windows]
names += ["RSV%d" % d for d in windows]
fields += ["idxmax(high, %d)/%d" % (d, d) for d in windows]
names += ["IMAX%d" % d for d in windows]
fields += ["idxmin(low, %d)/%d" % (d, d) for d in windows]
names += ["IMIN%d" % d for d in windows]
fields += ["(idxmax(high, %d)-idxmin(low, %d))/%d" % (d, d, d) for d in windows]
names += ["IMXD%d" % d for d in windows]
fields += ["corr(close, log(volume+1), %d)" % d for d in windows]
names += ["CORR%d" % d for d in windows]
fields += ["corr(close/shift(close,1), log(volume/shift(volume, 1)+1), %d)" % d for d in windows]
names += ["CORD%d" % d for d in windows]
fields += ["mean(close>shift(close, 1), %d)" % d for d in windows]
names += ["CNTP%d" % d for d in windows]
fields += ["mean(close<shift(close, 1), %d)" % d for d in windows]
names += ["CNTN%d" % d for d in windows]
fields += ["mean(close>shift(close, 1), %d)-mean(close<shift(close, 1), %d)" % (d, d) for d in windows]
names += ["CNTD%d" % d for d in windows]
fields += [
"sum(greater(close-shift(close, 1), 0), %d)/(sum(Abs(close-shift(close, 1)), %d)+1e-12)" % (d, d)
for d in windows
]
names += ["SUMP%d" % d for d in windows]
fields += [
"sum(greater(shift(close, 1)-close, 0), %d)/(sum(Abs(close-shift(close, 1)), %d)+1e-12)" % (d, d)
for d in windows
]
names += ["SUMN%d" % d for d in windows]
fields += [
"(sum(greater(close-shift(close, 1), 0), %d)-sum(greater(shift(close, 1)-close, 0), %d))"
"/(sum(Abs(close-shift(close, 1)), %d)+1e-12)" % (d, d, d)
for d in windows
]
names += ["SUMD%d" % d for d in windows]
fields += ["mean(volume, %d)/(volume+1e-12)" % d for d in windows]
names += ["VMA%d" % d for d in windows]
fields += ["std(volume, %d)/(volume+1e-12)" % d for d in windows]
names += ["VSTD%d" % d for d in windows]
fields += [
"std(Abs(close/shift(close, 1)-1)*volume, %d)/(mean(Abs(close/shift(close, 1)-1)*volume, %d)+1e-12)"
% (d, d)
for d in windows
]
names += ["WVMA%d" % d for d in windows]
fields += [
"sum(greater(volume-shift(volume, 1), 0), %d)/(sum(Abs(volume-shift(volume, 1)), %d)+1e-12)"
% (d, d)
for d in windows
]
names += ["VSUMP%d" % d for d in windows]
fields += [
"sum(greater(shift(volume, 1)-volume, 0), %d)/(sum(Abs(volume-shift(volume, 1)), %d)+1e-12)"
% (d, d)
for d in windows
]
names += ["VSUMN%d" % d for d in windows]
fields += [
"(sum(greater(volume-shift(volume, 1), 0), %d)-sum(greater(shift(volume, 1)-volume, 0), %d))"
"/(sum(Abs(volume-shift(volume, 1)), %d)+1e-12)" % (d, d, d)
for d in windows
]
names += ["VSUMD%d" % d for d in windows]
return fields, names
吾日三省吾身
“若无闲事在心头，便是人间好时节”。
这里的闲事，就是短期内，没有确定deadline要做的事情。
当然，本身很多事情，随着时间的推移，变得可有可无，或者就是随手的事情。
但在强迫症的眼里，既然要做，那就尽快做完，然后痛快地玩。
强迫症很难与杂事共处，尤其是带着不确定的事情。
要做就尽快做，不做就不做。
确实很多时候可以带来自律，给人专业，靠谱的感觉。
但过犹不及，对于家人，身边的朋友有时候也会造成困扰。
历史文章：
Quantlab3.3代码发布：全新引擎 | 静待花开：年化13.9%，回撤小于15% | lightGBM实现排序学习
创业板指布林带突破策略：年化12.8%，回撤20%+| Alphalens+streamlit单因子分析框架（代码+数据）
轮动策略模板重写，先来一个年化21%的策略（代码+数据）
去掉底层回测引擎，完全自研，增加超参数优化，因子自动挖掘，机器模型交易。
飞狐量化——AI驱动的量化。（持续给大家写代码的，交付最前沿AI量化技术和策略的星球）AI量化实验室——2024量化投资的星辰大海
关于我：CFA，北大光华金融硕士，十年量化投资实战。 / CTO，全栈技术，AI大模型 。——应该是金融圈最懂技术的男人。