Python: 组合管理与蒙特卡洛方法实现

尽管最优化的方法是理论上最优解，但我认为还是蒙特卡洛方法来看简单，也更真实一些。
另外，数据处理和清洗其实是这段代码花的时间最长的部分。尽管数据是从相应的网站copy下来的，但是数据还是有不少的奇异值，需要处理。如果你不亲身经历的话，就不会知道经历了什么。

需要说明的是，收益率和波动，需要严格的日期对齐，并不象随机数一样，简单，活不少。

# -*- coding: utf-8 -*-
"""
Created on Tue Oct 22 08:34:18 2019@author: songroom
"""#https://blog.csdn.net/weixin_42018258/article/details/80953809
#https://blog.csdn.net/itcastcpp/article/details/75807811
# Pyfolio
# https://www.jianshu.com/p/4cc811402477
# import pandas as pd  # https://blog.csdn.net/asialee_bird/article/details/89417750
#
import matplotlib.pyplot as plt
import pandas as pd
import os
import numpy as np
import time as t
import datetime as dt
from datetime import timedeltastocks = ["YUM","DIS","RIO","COST","FCN","PEP","TAL","GOOG","OKE","NKE","FB","CELG","BABA","ICE","BAX"]
stocks = ["YUM","DIS","RIO","COST","FCN","PEP","TAL","GOOG","OKE","NKE","FB","BABA","ICE","BAX"]
stocks = ["YUM","DIS","RIO","COST","FCN","PEP","TAL","GOOG","OKE","NKE","BABA","ICE","BAX"]
stocks = ["YUM","DIS","RIO","COST","FCN","PEP","TAL","GOOG","NKE","BABA","ICE","BAX"]
stocks = ["YUM","DIS","COST","FCN","PEP","TAL","NKE","ICE","BAX"]
path   = r"S:\data"
output_path = r"C:\Users\Administrator\Desktop\output"
nowtime = dt.datetime.now().strftime("%Y%m%d_%H%M%S")
port_best_weight ={
"YUM":  0.023756235171897618,"DIS" :0.03014070796771593,"COST": 0.08892953965680671,"FCN" :0.1876235028458973,"PEP": 0.07380931812203975,"TAL": 0.20264458091189966,"NKE": 0.2257260573355881,"ICE": 0.037347140266800055,"BAX": 0.13002291772135482}def best_portfolio():passdef read_sp500_source():path_stock = os.path.join(path,"sp500.csv")df = pd.read_csv(path_stock,sep=',',index_col= 0,encoding='utf-8')df.index = [dt.datetime.strptime(day,'%Y/%m/%d') for day in df.index]return df
def read_csv_stocks_source():data =[]for stock in stocks:path_stock = os.path.join(path,stock+".csv")print("stock=>",stock)df = pd.read_csv(path_stock,sep=',',index_col= 0,encoding='utf-8')df.index = [dt.datetime.strptime(day,'%Y/%m/%d') for day in df.index]data.append(df)return data#close    open    high    low volume  pct
def etl_index_data(sp500,common_start_dt):df = sp500.iloc[sp500.index >= common_start_dt,:]df = df.sort_index(ascending=True)return df.closedef etl_stock_data(data,common_start_dt):new_data =[]i =0for d in data:df = d.iloc[d.index >= common_start_dt,:]df2 = df.sort_index(ascending=True)new_data.append(df2)print("etl=>i:",i, "stock:",stocks[i],"len:",len(df2))i = i+1return new_datadef get_common_dates_array(data,sp500):length = len(data)dates ={}i = 1for d in data[1:length]:for date in sp500.index:if date not in d.index:breakelse:dates[stocks[i]] = datei = i+1return datesdef put_stocks_df_data_together(sort_data):data = pd.DataFrame()for df in sort_data:if len(data)==0:data = df.closeelse:data = pd.concat([data,df.close],axis=1)data.columns = stocksreturn datadef price2ret(stocks_close_price):stocks_returns_raw = stocks_close_price.pct_change()#dropna(how='all',axis=0)# row stocks_returns = stocks_returns_raw.iloc[1:,:]return stocks_returnsdef get_portfolio_random_weight(count):random_weights = np.random.random(count)portfolio_weights = np.array(random_weights/sum(random_weights))return portfolio_weightsdef get_portfolio_returns(stock_returns,portfolio_weights):weighted_returns = stock_returns.mul(portfolio_weights, axis=1)portfolio_returns = weighted_returns.sum(axis=1)return portfolio_returnsdef get_portfolio_cumprod_return(portfolio_returns):portfolio_cumprod_returns = (1+portfolio_returns).cumprod()-1return portfolio_cumprod_returnsdef get_porfolio_gain_return(portfolio_returns):portfolio_cumprod_returns = get_portfolio_cumprod_return(portfolio_returns)length = len(portfolio_cumprod_returns)gained_portfolio_return = portfolio_cumprod_returns[length-1]return (gained_portfolio_return/length)*252def get_std(portfolio_returns):portfolio_std = np.std(portfolio_returns)* np.sqrt(252)return portfolio_stddef get_max_drawdown_value(portfolio_returns):passdef get_sharpe_ratio(portfolio_returns,expect_market_annual_return):'''计算公式为：SharpeRatio=[ E(Rp)－Rf ] / σpE(Rp)：投资组合预期报酬率（平均回报率）:Rf： 无风险利率（通常用国债利率来代替）σp：投资组合的标准差'''gained_portfolio_return = get_porfolio_gain_return(portfolio_returns)portfolio_std     = get_std(portfolio_returns)sharpe_ratio      = (gained_portfolio_return-expect_market_annual_return) / portfolio_stdprint("gained_return: ",gained_portfolio_return," std: ",portfolio_std," sharp ratio: ",sharpe_ratio)return sharpe_ratiodef get_stock_beta_value(stock_returns,index_returns):'''beta = 个股与市场的相关性corr* 个股标准差std /指数的标准差 std'''codes = stock_returns.columnsstock_stds = stock_returns.std()*np.sqrt(252) # seriesindex_std = index_returns.std()*np.sqrt(252) # valuestocks_beta =[]for code in codes:corr = stock_returns[code].corr(index_returns)beta = corr*stock_stds[code]/index_stdstocks_beta.append(beta)print("code: ",code , "beta:",beta,"corr:",corr)return stocks_betadef get_portfolio_beta(stocks_beta,weights):beta =0for i in range(len(stocks_beta)):beta = beta + stocks_beta[i]*weights[i]return beta#def get_sp500_close_price():
#    sp500 = read_sp500_source()
#    sort_index_data = etl_index_data(sp500,common_start_dt)if __name__ == '__main__':# 数据准备t0 = t.time()count = len(stocks)print("including sp500, stock counts:",count)sp500 = read_sp500_source()stocks_data = read_csv_stocks_source()dates = get_common_dates_array(stocks_data,sp500)add_days = 1800common_start_dt = np.max(list(dates.values()))+timedelta(days =add_days)print("common_start_dt:",common_start_dt)sort_stock_data = etl_stock_data(stocks_data,common_start_dt)sort_index_data = etl_index_data(sp500,common_start_dt)stocks_close_price = put_stocks_df_data_together(sort_stock_data)stock_returns = price2ret(stocks_close_price)index_returns = (sort_index_data-sort_index_data.shift(1))/sort_index_data.shift(1)index_returns = index_returns.dropna()print("=>")print(len(index_returns))simu_counts = 100expect_market_annual_return = 0.02best_sharp_ratio = -10000best_weights =[]best_return = 0.0for i in range(simu_counts):portfolio_weights = get_portfolio_random_weight(count)portfolio_returns = get_portfolio_returns(stock_returns,portfolio_weights)sharp_ratio_value = get_sharpe_ratio(portfolio_returns,expect_market_annual_return)print("now simu : ",i,"sharpe ratio:",sharp_ratio_value)if sharp_ratio_value > best_sharp_ratio:best_sharp_ratio = sharp_ratio_valuebest_weights = portfolio_weightsprint("simu get better sharp ratio: ",sharp_ratio_value)t1 = t.time()print("simu process is over,cost time:",t1-t0,'s')j = 0for w in best_weights:print("stock:",stocks[j],"weights:",w)j =j+1best_simulation_returns =get_portfolio_returns(stock_returns,best_weights)print("start_dt:",common_start_dt,"end_dt:2019-10-21")print("return:",get_porfolio_gain_return(best_simulation_returns))print("best sharpe ratio:",best_sharp_ratio)# corrprint("stocks corr:")print(stock_returns.corr())# cov:print("stocks cov:")corr_df =stock_returns.corr()print(corr_df)#df.to_csv(file,index = False,encoding = 'utf_8_sig')corr_df.to_csv(output_path+"\\corr_matrix_"+nowtime+".csv",index = True,encoding = 'utf_8_sig')# stock stdprint("stocks std:")print(stock_returns.std()*np.sqrt(252))# stock beta and portfolio betastocks_beta = get_stock_beta_value(stock_returns,index_returns)portfolio_beta = get_portfolio_beta(stocks_beta,best_weights)print("portfolio beta: ",portfolio_beta)best_simulation_cumprod_return = get_portfolio_cumprod_return(best_simulation_returns)best_simulation_cumprod_return.plot()print("----------best portfolio-----------")best_portfolio_returns_used = get_portfolio_returns(stock_returns,list(port_best_weight.values()))best_portfolio_returns_used.to_frame().to_csv(output_path+"\\portfolio_return_"+nowtime+".csv")best_portfolio_cumprod_return_used = get_portfolio_cumprod_return(best_portfolio_returns_used)best_portfolio_cumprod_return_used.to_frame().to_csv(output_path+"\\cumprod_portfolio_return_"+nowtime+".csv")sp500_cumprod_return = get_portfolio_cumprod_return(index_returns)sp500_cumprod_return.to_frame().to_csv(output_path+"\\cumprod_sp500_return_"+nowtime+".csv")pd.DataFrame.from_dict(port_best_weight,orient='index').to_csv(output_path+"\\weights_"+nowtime+".csv")best_port_beta = get_portfolio_beta(stocks_beta,list(port_best_weight.values()))print("best_risk_portfolio_beta:", best_port_beta)best_sharp_ratio_value_used = get_sharpe_ratio(best_portfolio_returns_used,expect_market_annual_return)print("best portfolio sharp-ratio value:",best_sharp_ratio_value_used)

Python: 组合管理与蒙特卡洛方法实现相关推荐

python学习之利用蒙特卡洛方法计算PI值
使用环境为python IDLE3.5. #利用蒙特卡洛方法计算PI值 from random import random from math import sqrt from time import ...
Cap21_项目组合管理
21 项目组合管理 21.1 项目组合管理概述 21.1.1 项目组合项目组合是将项目.项目集,以及其他方面的工作内容组合起来进行有效管理,以保证满足组织的战略性的业务目标. 21.1.2 项目组合 ...
用蒙特卡洛方法计算派－python和R语言
用蒙特卡洛方法算pi-基于python和R语言最近follow了MOOC上一门python课,开始学Python.同时,买来了概率论与数理统计,准备自学一下统计.(因为被鄙视过不是统计专业却想搞数据 ...
CentOS 6.4安装pip，CentOS安装python包管理安装工具pip的方法
之前有的朋友问我,CentOS版本怎么安装python的pip,我之前给出的Ubuntu下apt-get的方法 ubuntu 需要先安装下pip吧, apt-get install python-pi ...
3 随机数与蒙特卡洛方法及Python实现
0 建议学时 4学时 1 引入 1.1 随机数与采样客观世界的某些行为,结果具有随机性: 掷骰子.投硬币: 等待公交车的时间: 种子发芽的比例: 1.2 随机数函数 1.2.1 random模块 P ...
怎样用python计算π的值_IV.python初探日记：python实现蒙特卡洛方法计算π值
早上中级微观经济学课上复习泰勒展开和麦克劳林展开,顺带讲到了用蒙特卡洛方法实现计算π值,于是下午着手用python尝试着实现了一下,并用matplotlib输出了一部分数据. 完整的代码在文末,本文适 ...
蒙特卡洛python求解派_用蒙特卡洛方法计算派－python和R语言
标签: 用蒙特卡洛方法算pi-基于python和R语言最近follow了MOOC上一门python课,开始学Python.同时,买来了概率论与数理统计,准备自学一下统计.(因为被鄙视过不是统计专业却 ...
python 组合数字和字符_python无限生成不重复(字母,数字,字符)组合的方法
python无限生成不重复(字母,数字,字符)组合的方法使用python自带的itertools模块调用其product函数传入我们想组合生成的字符数据便会源源不断的生成组合而且不会重复 r ...
Python开发多媒体管理软件实现方法
软件开发环境 python 3.7.3 pycharm Community 2020 PYQT5 教师端控制界面下拉列表显示全部已经连接的客户端ip地址对选中的设备进行查看设备信息,重启电脑,关闭 ...
python 统计组合用什么库_Python数据分析之双色球统计两个红和蓝球哪组合比例高的方法...
本文实例讲述了Python数据分析之双色球统计两个红和蓝球哪组合比例高的方法.分享给大家供大家参考,具体如下: 统计两个红球和蓝球,哪个组合最多,显示前19组数据 #!/usr/bin/python ...

Python: 组合管理与蒙特卡洛方法实现

Python: 组合管理与蒙特卡洛方法实现相关推荐

最新文章

热门文章