Python financial Monte Carlo simulation related parameter calculation

Python financial Monte Carlo simulation related parameter calculation and generation of pictures

import numpy as np
import numpy.random as npr
import pandas as pd
import matplotlib.pyplot as plt

# 导入外部数据
stock_price = pd.read_excel("D:\python代码\\first\daorutry.xlsx",sheet_name="Sheet1",header =0,index_col=0)
# print(stock_price)

# X为置信水平，I为蒙特卡洛模拟的次数，P0为固值（是后台设定还是老师设定待定）
# X = float(input("请输入置信水平："))
I = 10000
P0 = 1000


# 股票日收益
stock_return = np.log(stock_price/stock_price.shift(1))
# 删除缺失行
stock_return = stock_return.dropna()
# print(stock_return)

a = stock_return.loc[:,"收盘/最新价"]
# print(a)
# a_mean为平均收益率  b为保留小数点后四位的a_mean
a_mean =a.mean()*252
# 计算资产收益率的年化波动率
a_vol = a.std()*np.sqrt(252)
# 设定交易日的步长
dt = 1/252

# excel中投资组合中资产的个数
N_assets=len(stock_return.columns)

# 从标准正态分布中抽取随机数
epsilon = npr.standard_normal(size=I)

# 取excel表格中月末的股价并以数组格式
p=np.array(stock_price.iloc[-1])

# 生成放置下一个交易日资产价格初始数组
p_new = np.zeros(shape=(I,N_assets))
p_new[:,0] = p*np.exp((a_mean-0.5*a_vol**2)*dt + a_vol*epsilon*np.sqrt(dt))

S = P0*np.exp(np.cumsum((a_mean - 0.5*a_mean **2) *dt +a_mean *np.sqrt(dt) *np.random.standard_normal((50, I)),axis=0))

# 计算模拟下一个交易日投资组合盈亏额
s_delta=(np.dot(p_new/(p.T)-1,1))*P0

# 计算var的值
var = np.abs(np.percentile(a=s_delta,q=(1-0.95)*100))
print(var)

N = int(input("请输入持有天数:"))
var1 = np.sqrt(N)*float(var)
print(var1)

plt.hist(S,bins = 100)
plt.xlabel('price')
plt.ylabel('ferquency')
plt.show()

# 路径可视化 lw为所绘线的粗细
plt.plot(S,lw=1)
plt.xlabel('time step')
plt.ylabel('index level')
plt.show()

This article refers to other articles and then compiles it. If there are any errors, please correct me