python量化动量效应、pe_ttm、pb估值和美林时钟

将下面三个策略结合判断，
动量策略
估值策略
改进美林时钟

三个策略都判断股票上涨做多股票，        则股：债=0.5:0.5
三个中有两个策略判断涨做多股票信号 ，则股：债=0.4:0.6
三个中有一个策略判断涨做多股票信号 ，则股：债=0.3:0.7
否则，股：债=0.1:0.9

# coding=utf-8
import math
import tushare as ts
import pandas as pd
import matplotlib
import matplotlib.pyplot as plt
import numpy as np
import talib
import pandas as pd
from datetime import datetime, date
import pymysql
import threading
from queue import Queue
import warnings
warnings.filterwarnings("ignore")
import seaborn as sns  
sns.set(style="darkgrid", palette="muted", color_codes=True) 
from scipy import stats,integrate
%matplotlib inline 
sns.set(color_codes=True)

matplotlib.rcParams['axes.unicode_minus']=False
plt.rcParams['font.sans-serif']=['SimHei']
ts.set_token('  ')
pro = ts.pro_api()

#移动均值策略部分
def mean_fun():
    code1,code2,test_start,test_end,t1,t2,t3,t4,t5,n=["000300.SH","000012.SH","20050101","20550101",50,70,90,110,130,1]
    def dataread():
        df_stock=pro.index_daily(ts_code=code1,  start_date=test_start, end_date=test_end, fields='close,trade_date')
        df_bond=df=pro.index_daily(ts_code=code2,start_date=test_start, end_date=test_end , fields='trade_date,close')
        return df_stock,df_bond
    df_stock,df_bond=dataread() 
        #计算均值，时间为t1  t2  t3  t4
    def mean(t):
        df_stock.index=pd.to_datetime(df_stock.trade_date)
        return df_stock.close.sort_index().rolling(window=t).mean()
    def ret_base():
        df_stock.index=pd.to_datetime(df_stock.trade_date)
        df_bond.index =pd.to_datetime(df_bond.trade_date)
        ret_stock=(df_stock.close-df_stock.close.shift(-1))/df_stock.close.shift(-1)
        ret_bond= (df_bond.close- df_bond.close.shift(-1))/df_bond.close.shift(-1)
        return ret_stock,ret_bond.sort_index()

    def ret_same_time(x):
        return x[x.index>=mean(max(t1,t2,t3,t4,t5)).dropna().index[0] ]
    ret_stock=ret_same_time(ret_base()[0]).sort_index()#ret_base()[0][ret_base()[0].index>=mean(max(t1,t2,t3,t4,t5)).dropna().index[0] ]
    ret_bond= ret_same_time(ret_base()[1] )#ret_base()[1][ret_base()[1].index>=mean(max(t1,t2,t3,t4,t5)).dropna().index[0] ]
    DF=ret_same_time(df_stock.close).sort_index()
    return ret_same_time(mean(t1)),ret_same_time(mean(t2)),ret_same_time(mean(t3)),ret_same_time(mean(t4)),ret_same_time(mean(t5)),DF
mean1,mean2,mean3,mean4,mean5,DFF=mean_fun()

#估值pe_ttm部分
def fun():
    start,end,code1,code2,t,T,start1,end1=["20140101","20550101","000300.SH","000012.SH",10,1400,"20080901","20550101"]
    #读取数据
    def dataread():
        df_base=pro.index_dailybasic(ts_code=code1,start_date=start1,end_date=end1, fields='trade_date,pe_ttm,pb')
        df_stock=pro.index_daily(ts_code=code1,  start_date=start, end_date=end, fields='close,trade_date')
        df_bond=df=pro.index_daily(ts_code=code2,start_date=start, end_date=end , fields='trade_date,close')
        return df_base,df_stock,df_bond
    df,df_stock,df_bond=dataread()   
    class prepare:
    #计算单日收益率
        def ret_base(self):
            df_stock.index=pd.to_datetime(df_stock.trade_date)
            ret_stock=(df_stock.close-df_stock.close.shift(-1))/df_stock.close.shift(-1)
            df_bond.index=pd.to_datetime( df_bond.trade_date  )
            ret_bond=(df_bond.close-df_bond.close.shift(-1))/df_bond.close.shift(-1)
            return ret_stock,ret_bond
    #计算pe均值，标准差及滚动均值
        def data_fun(self,freq,df):
            df.index=pd.to_datetime(df.trade_date )
            df=df.sort_index()
            df_std=df.sort_index().rolling(window=T).std()[df.index>=start]#[df.index<=end]
            df_std=df_std[df_std.index<=end]
            df_pe_std=df_std.pe_ttm
            df_pb_std=df_std.pb
            df_mean=df.sort_index().rolling(window=T).mean()[df.index>=start]#[df.index<=end]
            df_mean=df_mean[df_mean.index<=end]
            df_pe_mean=df_mean.pe_ttm
            df_pb_mean=df_mean.pb
            df_roll=df.sort_index().rolling(window=t).mean()[df.index>=start]#[df.index<=end]
            df_roll=df_roll[df_roll.index<=end]
            df_pb_roll_mean=df_roll.pb
            df_pe_ttm_roll_mean=df_roll.pe_ttm
            return df_pe_mean,df_pb_mean,df_pe_std,df_pb_std,df_pe_ttm_roll_mean,df_pb_roll_mean
    mean1,mean2,std1,std2,mean_roll1,mean_roll2=prepare().data_fun(t,df)
    return mean1,mean2,std1,std2,mean_roll1,mean_roll2
mean_pe,mean_pb,std1,std2,mean_roll1,mean_roll2=fun()

#美林时钟部分
class read_data:
    def fetchData(self, query, q, name, db, host='192.168.0.153', user='jcyj',password='jcyjQwer'):
        'get data from mysql database'
        conn = pymysql.connect(host, user, password, database=db, charset='utf8', cursorclass=pymysql.cursors.DictCursor)
        cursor = conn.cursor()
        res = cursor.execute(query)
        fetch = cursor.fetchall()
        data = pd.DataFrame(fetch)
        q.put((name, data))
    def multithread(self, dataList, db):
        threads = []
        q = Queue()
        for key, value in dataList.items():
            t = threading.Thread(target=self.fetchData, args=(value, q, key, db))  # initiate a thread
            t.start()  # activate a thread
            threads.append(t)  # collect threads list
        for thread in threads:
            thread.join()
        result = []
        for _ in range(len(threads)):
            result.append(q.get())

        result = {i[0]: i[1] for i in result}
        return result
    def readhgyz(self, db='py_daziguan_2_1'):
        baseQuery = "select report_date , shibor_1w "\
                    " from py_hgyz_pbc_shanghai_shibor_statistics_month  where DATE(report_date) > '2005-12-01'  "
        data = self.multithread({'base': baseQuery},db)
        return data
    def readetl1(self, db='py_etl'):
        baseQuery = "select trading_date , bond_1y "\
                    " from py_etl_risk_free_rate_daily_2_1 where DATE(trading_date) > '2006-04-30'"
        data = self.multithread({'base2': baseQuery},db)
        return data
BO1=read_data()
BO1=BO1.readetl1()["base2"]
BO1.set_index('trading_date',inplace=True)
BO1.index = pd.to_datetime(BO1.index)
BO1.bond_1y
R_B=BO1.bond_1y

############################读取数据类###################################
class readData:
    def read_index_daily(self,code,star,end):#指数数据
        dsb = pro.index_daily(ts_code=code, start_date=star, end_date=end,fields='ts_code,trade_date,close,change')#默认读取三个数据
        return dsb
    def read_daily(self,code,star,end):
        dsc1 = pro.daily(ts_code=code, start_date=star, end_date=end,fields='ts_code,trade_date,close,change')
        return dsc1
    def read_CPI(self,star,end):#时间格式start_cpi='201609'
        dc=pro.cn_ppi(start_m=star, end_m=end,fields='month,ppi_yoy')
        return dc
    def read_GDP(self,star,end):#时间格式star='2016Q4'
        df1 = pro.cn_gdp(start_q=star, end_q=end,fields='quarter,gdp_yoy')
        return df1
    def read_bond(self,code,star,end):
        df=pro.cb_daily(ts_code=code,start_date=star,end_date=end)
        return df
    def readshibor(self,star,end):
        return pro.shibor(start_date=star, end_date=end)
#####################################################################    

start_time='20000430'#发布GDP需要时间，我们延迟1个月，即第一季度的GDP4月份才发布。
end_time="20550731"
star_GDP='2005Q1'#延后一年，因为我们找的是差分   
end_GDP='2055Q1'#不是以3 4季度结尾
star_CPI='200501'
end_CPI='205503'
df1=readData()#读取
dc=readData()
dsc1=readData()
dsp=readData()
dsb=readData()
df1=df1.read_GDP(star_GDP,end_GDP)
dc=dc.read_CPI(star_CPI,end_CPI)
dsc1=dsc1.read_index_daily('000300.SH',start_time,end_time)  
dsb=dsb.read_index_daily('000012.SH',start_time,end_time)
dsp=dsp.read_index_daily('NHCI.NH',start_time,end_time)         
##########################GDP信号处理################################
def GDP_fun(df1):
    df1.set_index('quarter',inplace=True)#设置日期索引
    df2=(df1.shift(4)-df1).shift(-4)
    df2=df2.dropna()
    G=pd.Series(0,index=df2.gdp_yoy.index)
    for i in range(len(df2.gdp_yoy)):
        if df2.gdp_yoy[i]>0:
            G[i]=1
        elif df2.gdp_yoy[i]<0:
            G[i]=0
        else:
            G[i]=G[i-1]
    return G
G=GDP_fun(df1)
####################################################################
###########################CPI信号函数##############################
def CPI_fun(dc):
    dc=dc.sort_index()
    dc.set_index('month',inplace=True)
    dc2=(dc.shift(12)-dc.shift()).shift(-12).dropna()
    C=pd.Series(0,index=G.index)
    for j in range( 3*math.floor( len(dc2.ppi_yoy)/3)):
        if (3+j)%3==0:
            for i in range(int(j/3),int((3+j)/3)):
                if   dc2.ppi_yoy[j]+dc2.ppi_yoy[j+1]+dc2.ppi_yoy[j+2] >0:
                    C[i]=1
                elif dc2.ppi_yoy[j]+dc2.ppi_yoy[j+1]+dc2.ppi_yoy[j+2]<0:
                    C[i]=0
                else:
                    C[i]=C[i-1] 
        else:
            pass 
    return C
C=CPI_fun(dc)
########################################################################
##############################利率处理##################################
DF=read_data()
DF2=DF.readhgyz()
DF=DF2['base']

def LV_fun(dc):
    dc=dc.sort_index()
    dc.set_index('report_date',inplace=True)
    dc2=(dc.shift(12)-dc.shift()).shift(-12).dropna()
    C=pd.Series(0,index=G.index)
    for j in range(   3*math.floor( len(dc2.shibor_1w)/3)):
        if (3+j)%3==0:
            for i in range(int(j/3),int((3+j)/3)):
                
                if dc2.shibor_1w[j]+dc2.shibor_1w[j+1]+dc2.shibor_1w[j+2]  >0:
                    C[i]=1
                elif dc2.shibor_1w[j]+dc2.shibor_1w[j+1]+dc2.shibor_1w[j+2]<0:
                    C[i]=0
                else:
                    C[i]=C[i-1] 
        else:
            pass 
    return C
LV=LV_fun(DF)
#########################################################################
#将季度时间转化成对应的可读的年月日时间。
def time_fun(i):
    if C.index[i][5:6]=='1':
        time=C.index[i][0:4]+"0505"
        for j in range(2,10):
            if len(R_B[R_B.index==time])==0:
                time=C.index[i][0:4]+"050"+str(j)
            else:
                break
    if C.index[i][5:6]=='2':
        time=C.index[i][0:4]+"0801"
        if len(R_B[R_B.index==time])==0:
            time=C.index[i][0:4]+"0802"
            if len(R_B[R_B.index==time])==0:
                time=C.index[i][0:4]+"0803"
    if C.index[i][5:6]=='3':
        time=C.index[i][0:4]+"1101"
        if len(R_B[R_B.index==time])==0:
            time=C.index[i][0:4]+"1102"
            if len(R_B[R_B.index==time])==0:
                time=C.index[i][0:4]+"1103"
    if C.index[i][5:6]=='4':
        time=C.index[i-1][0:4]+"0201"
        for j in range(2,10):
            if len(R_B[R_B.index==time])==0:
                time=C.index[i-1][0:4]+"020"+str(j)
            else:
                break
        for j in range(10,29):
            if len(R_B[R_B.index==time])==0:
                time=C.index[i-1][0:4]+"02"+str(j)
            else:
                break
    return time
############################计算收益率+索引函数##########################
class ZC_fun:
    def ret_function(self,ds):
        #standard_base=pro.index_daily( ts_code='000300.SH', start_date='20081031', end_date="20200430")
        standard_base=ds.sort_index()
        standard_base.index=pd.to_datetime(standard_base.trade_date,format='%Y-%m-%d')#设置日期索引
        close_base= standard_base.close
        standard_ret=standard_base.change/standard_base.close.shift(-1)
        ret=standard_ret.sort_index(axis=0,ascending=True)
        ret=ret.dropna()
        return ret#,close_base/close_base[start_time_jz].values#=str(RETT.index[0])[:4]+str(RETT.index[0])[5:7]+str(RETT.index[0])[8:10]###############
#有点问题，上面一行
    def bsc_fun(self,ds):
        dsc=ds.drop(['ts_code'],axis=1)
        dsc=dsc.sort_index()
        dsc.index=pd.to_datetime(dsc.trade_date,format='%Y-%m-%d')#设置日期索引
        dsc=dsc.drop(['trade_date'],axis=1)
        return dsc
#########################################################################    

gc=ZC_fun()
R_c=gc.ret_function(dsc1)#股票的利
gb=ZC_fun()
R_b=gb.ret_function(dsb)#债券的利
gp=ZC_fun()
R_p=gp.ret_function(dsp)#商品的利
R_B=pd.DataFrame(R_B,dtype=np.float).bond_1y/100#无风险利率   ###########

############################对应季度的收益####################################
def RET_sig(sig_c,i):#输入ret，输出i对应的时间段收益#####截取收益段
    if G.index[i][5:6] =='1':
        a=G.index[i][0:4]+'0505'
        b=G.index[i][0:4]+'0731'
        at1=pd.to_datetime(a,format='%Y-%m-%d')
        bt1=pd.to_datetime(b,format='%Y-%m-%d')
        sig_c=sig_c[ sig_c.index<=bt1]  
        sig_c=sig_c[ sig_c.index>=at1]
    elif G.index[i][5:6] =='2':
        a=G.index[i][0:4]+'0801'
        b=G.index[i][0:4]+'1031'
        at1=pd.to_datetime(a,format='%Y-%m-%d')
        bt1=pd.to_datetime(b,format='%Y-%m-%d')
        sig_c=sig_c[ sig_c.index<=bt1]  
        sig_c=sig_c[ sig_c.index>=at1]
    elif G.index[i][5:6] =='3':
        a= G.index[i][0:4]+'1101'
        a1=G.index[i][0:4]+'1231'
        at1=pd.to_datetime(a,format='%Y-%m-%d')
        bt1=pd.to_datetime(a1,format='%Y-%m-%d')
        sig_c1=sig_c
        sig_c1=sig_c1[ sig_c1.index<=bt1]  
        sig_c1=sig_c1[ sig_c1.index>=at1]
        sig_c1=sig_c1
        b= G.index[i-2][0:4]+'0101'
        b1=G.index[i-2][0:4]+'0131'
        at11=pd.to_datetime(b,format='%Y-%m-%d')
        bt11=pd.to_datetime(b1,format='%Y-%m-%d')
        sig_c=sig_c[ sig_c.index<=bt11]  
        sig_c=sig_c[ sig_c.index>=at11]
        sig_c=sig_c1.append(sig_c)
    else:
        a=G.index[i-1][0:4]+'0201'
        b=G.index[i-1][0:4]+'0430'
        at1=pd.to_datetime(a,format='%Y-%m-%d')
        bt1=pd.to_datetime(b,format='%Y-%m-%d')
        sig_c=sig_c[ sig_c.index<=bt1]  
        sig_c=sig_c[ sig_c.index>=at1]
    return sig_c
###########################################################################
###########################################################################
#由三个部分构建不同策略
#动量策略的信号，sig=1  判断高配股票（判断条件换成bool值形式）
def SIG1(i):
    n=1
    if DFF[DFF.index== time_fun(i)].values>n*mean1[mean1.index== time_fun(i)].values \
           and DFF[DFF.index== time_fun(i)].values>n*mean2[mean2.index== time_fun(i)].values \
           and DFF[DFF.index== time_fun(i)].values>n*mean3[mean3.index== time_fun(i)].values \
           and DFF[DFF.index== time_fun(i)].values>n*mean4[mean4.index== time_fun(i)].values \
           and DFF[DFF.index== time_fun(i)].values>n*mean5[mean5.index== time_fun(i)].values :
        sig=1
    else:
        sig=0
    return sig
#基本面—估值（pe_ttm）策略信号， sig=1高配股票
def SIG2(i):
    if mean_roll1[mean_roll1.index== time_fun(i)].values<mean_pe[mean_pe.index== \
       time_fun(i)].values-0.5*std1[std1.index== time_fun(i)].values or \
       mean_roll2[mean_roll2.index== time_fun(i)].values<mean_pb[mean_pb.index== \
       time_fun(i)].values-0.5*std2[std2.index== time_fun(i)].values:
        sig=1
    else:
        sig=0
    return sig   
#美林时钟高配股票信号
def SIG3(i):
    if C[i]==0 and LV[i]==0:
        sig=1
    else:
        sig=0
    return sig  

#################################策略判断条件##################################
def quanzhong_fun(R_c,R_p,R_b,R_B):
    RETT=None#初始化
    n=1
    for i in range(len(G)):
        if SIG1(i)+SIG2(i)+SIG3(i)==3:#三个策略信号约束
            RETT=( 0.5*RET_sig(R_c,i)+0*RET_sig(R_p,i) +0.5*RET_sig(R_b,i)+0*RET_sig(R_B,i)  ).append(RETT)
        elif SIG1(i)+SIG2(i)+SIG3(i)==2:#三个策略信号约束
            RETT=( 0.4*RET_sig(R_c,i)+0*RET_sig(R_p,i) +0.6*RET_sig(R_b,i)+0*RET_sig(R_B,i)  ).append(RETT)
        elif SIG1(i)+SIG2(i)+SIG3(i)==1:#三个策略信号约束
            RETT=( 0.3*RET_sig(R_c,i)+0*RET_sig(R_p,i) +0.7*RET_sig(R_b,i)+0*RET_sig(R_B,i)  ).append(RETT)
        else:
            RETT=( 0.1*RET_sig(R_c,i)+0*RET_sig(R_p,i)+0.9*RET_sig(R_b,i) +0*RET_sig(R_B,i)  ).append(RETT)           
    return RETT

RETT=quanzhong_fun(R_c,R_p,R_b,R_B)
RETT=RETT.sort_index(axis=0)
cum=np.cumprod(1+RETT)
cum=cum.dropna()

############################指数基准图#########################################
start_time_jz=str(RETT.index[0])[:4]+str(RETT.index[0])[5:7]+str(RETT.index[0])[8:10]
end_time_jz=str(RETT.index[-1])[:4]+str(RETT.index[-1])[5:7]+str(RETT.index[-1])[8:10]
def bj_standard(code,lab='000300.SH',col='k'):#针对沪深股票，直接画出比较基准（收益情况）
    standard_base = pro.index_daily( ts_code=code, start_date=start_time_jz, end_date=end_time_jz)
    standard_base=standard_base.sort_index()
    standard_base.index=pd.to_datetime(standard_base.trade_date,format='%Y-%m-%d')#设置日期索引
    close_base= standard_base.close
    standard_ret=standard_base.change/standard_base.close.shift(-1)
    standard_sig=pd.Series(0,index=close_base.index) 
    standard_trade=standard_sig.shift(1).dropna()/100#shift(1)整体下移一行
    standard_SmaRet=standard_ret*standard_trade.dropna()
    standard_cum=np.cumprod(1+standard_ret[standard_SmaRet.index[0:]])-1
    plt.plot(close_base/close_base[-1],label=lab,color=col)
    return close_base/close_base[-1] #standard_cum
###########################################################################   

def performance(port_ret):
    first_date = port_ret.index[0]
    final_date = port_ret.index[-1]
    time_interval = (final_date - first_date).days * 250 / 365
    # calculate portfolio's indicator
    nv = (1 + port_ret).cumprod()
    arith_mean = port_ret.mean() * 250
    geom_mean = (1 + port_ret).prod() ** (250 / time_interval) - 1
    sd = port_ret.std() * np.sqrt(250)
    mdd = ((nv.cummax() - nv) / nv.cummax()).max()
    sharpe = (geom_mean - 0) / sd
    calmar = geom_mean / mdd
    result = pd.DataFrame({'算术平均收益': [arith_mean], '几何平均收益': [geom_mean], '波动率': [sd],
                           '最大回撤率': [mdd], '夏普比率': [sharpe], '卡尔曼比率': [calmar]})
    print(result)
    return result

if __name__=="__main__":
    bj_standard('000300.SH')#比较基准函数（图）
    bj_standard('000012.SH',lab='上证国债',col='b')
    #bj_standard('NHCI.NH',lab='南华商品指数',col='y')
    performance(RETT)
    plt.plot(cum,label="组合策略",color='r',linestyle='-')
    plt.title("组合策略净值走势对比图")
    plt.legend()