标准因子库因子分析模板¶

# 导入函数库
from jqdata import *
import numpy as np
import pandas as pd
import jqfactor
from jqlib import alpha191
from jqlib.alpha191 import *
from jqfactor import get_factor_values
from jqfactor import Factor
from jqfactor import analyze_factor
warnings.filterwarnings('ignore') 

#获取交易日期列表
#四个参数分别为开始日期，结束日期，交易周期（'day','month','quarter','halfyear'）,count：天数，与start二者取其一
def get_tradeday_list(start,end,frequency=None,count=None):
    if count != None:
        df = get_price('000001.XSHG',end_date=end,count=count)
    else:
        df = get_price('000001.XSHG',start_date=start,end_date=end)
    #如果频率为“day”或者没有设置，直接返回df.index
    if frequency == None or frequency =='day':
        return df.index
    else:
        #否则增加一列'year-month'，值为前7位
        df['year-month'] = [str(i)[0:7] for i in df.index]
        if frequency == 'month':
            return df.drop_duplicates('year-month').index#删除重复项，设置'year-month'为index
        elif frequency == 'quarter':#季度
            df['month'] = [str(i)[5:7] for i in df.index]
            df = df[(df['month']=='01') | (df['month']=='04') | (df['month']=='07') | (df['month']=='10') ]
            return df.drop_duplicates('year-month').index
        elif frequency =='halfyear':
            df['month'] = [str(i)[5:7] for i in df.index]
            df = df[(df['month']=='01') | (df['month']=='06')]
            return df.drop_duplicates('year-month').index 

# 设置起止时间
start='2016-07-01'
end='2016-08-01'
# 设置调仓周期
periods=(5,10,20)
# 设置分层数量
quantiles=5
#获取日期列表
date_list = get_tradeday_list(start=start,end=end,count=None)#获取回测日期间的所有交易日
date_list

#定义一个空的dataframe记录因子值
factor_df = pd.DataFrame()
#循环计算给定日期范围的因子值
mark = 1
for d in date_list:
    pool = get_index_stocks('000905.XSHG',date=d)
    #alpha191.alpha_005为因子库，标准因子,也可以用定义因子函数
    far=alpha191.alpha_005(pool, end_date=d)
    if mark == 1:
        factor_df = far
        mark = 0
    else:
        #逐日合并factor_df
        factor_df = pd.concat([far,factor_df],axis=1,sort=True)
#将columns更改为可以日期标签
factor_df.columns = date_list
factor_df.head()

#数据清洗、包括去极值、标准化、中性化等,并加入y值
from jqfactor import *
for date in date_list:
    #对数据进行处理、标准化、去极值、中性化
    #factor_df = winsorize_med(factor_df, scale=3, inclusive=True, inf2nan=True, axis=0) #中位数去极值处理
    se = standardlize(factor_df[date], inf2nan=True) #对每列做标准化处理
    se = neutralize(se, how=['liquidity'], date=date)#剔除原始因子值与流动性相关的部分
    factor_df[date] = se
#进行转置，调整为分析可用的格式
factor_df = factor_df.T
factor_df.head()

#使用获取的因子值进行单因子分析
far = analyze_factor(factor=factor_df, start_date=date_list[0], end_date=date_list[-1], weight_method='avg', industry='jq_l1', quantiles=quantiles, periods=periods,max_loss=0.3)

# 打印信息比率（IC）相关表
far.plot_information_table(group_adjust=False, method='rank')

# 画各分位数平均收益图
far.plot_quantile_returns_bar(by_group=False, demeaned=0, group_adjust=False)

# 打印换手率表
far.plot_turnover_table()

#调用因子分析方法，进行因子信息全览
far.create_full_tear_sheet(demeaned=False, group_adjust=False, by_group=False, turnover_periods=None, avgretplot=(5, 15), std_bar=False)

# 计算指定调仓周期的各分位数每日累积收益
df = far.calc_cumulative_return_by_quantile(period=5)

#进行数据展示
df.plot(figsize=(15,6))