Zhuang's Diary

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import pandas_datareader
import scipy.stats as stats
from mpl_toolkits import mplot3d
from matplotlib import cm

# 假设投资组合包含以下公司
tickers = ['GOOGL','FB','AAPL','NFLX','AMZN']
ticker_num = len(tickers)
price_data = []
for ticker in range(ticker_num):
    # 获取股票的历史数据
    prices = pandas_datareader.DataReader(tickers[ticker], start='2015-11-30', end = '2020-11-30', data_source='yahoo')   
    price_data.append(prices[['Adj Close']])
    df_stocks = pd.concat(price_data, axis=1)
    
# stock log returns计算“日对数回报率”
logreturns = np.log(df_stocks/df_stocks.shift(1))[1:]  
logreturns.columns = tickers 
logreturns.head() 

# 假设它们的对数回报率满足正态分布，下面代码计算并展示股票的回报率分布
# plot log return distribution for GOOGL
plt.style.use('ggplot')
mu, std = stats.norm.fit(logreturns['GOOGL'])
x = np.linspace(mu-5*std, mu+5*std, 500)
logreturns['GOOGL'].hist(bins=60, density=True, histtype="stepfilled", alpha=0.5)
x = np.linspace(mu - 3*std, mu+3*std, 500)
plt.plot(x, stats.norm.pdf(x, mu, std))
plt.title("Log return distribution for GOOGL")
plt.xlabel("Return")
plt.ylabel("Density")

# plot log return distribution
rows = 2
cols = 2
fig, axs = plt.subplots(rows, cols, figsize=(12,6))
ticker_n = 1
for i in range(rows):
    for j in range(cols):
        mu, std = stats.norm.fit(logreturns[tickers[ticker_n]])
        x = np.linspace(mu-5*std, mu+5*std, 500)
        axs[i,j].hist(logreturns[tickers[ticker_n]], bins=60, density=True, histtype="stepfilled", alpha=0.5)
        axs[i,j].plot(x, stats.norm.pdf(x, mu, std))
        axs[i,j].set_title("Log return distribution for "+tickers[ticker_n])
        axs[i,j].set_xlabel("Return")
        axs[i,j].set_ylabel("Density")
        ticker_n = ticker_n + 1
plt.tight_layout()

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import pandas_datareader
import seaborn as sns

# 假设投资组合包含以下公司
tickers = ['GOOGL','FB','AAPL','NFLX','AMZN']
ticker_num = len(tickers)
price_data = []
for ticker in range(ticker_num):   
    prices = pandas_datareader.DataReader(tickers[ticker], start='2015-11-30', end = '2020-11-30', data_source='yahoo')   
    price_data.append(prices[['Adj Close']])
    df_stocks = pd.concat(price_data, axis=1)
df_stocks.columns = tickers

# 然后计算股票的累积回报率
# cumulative returns
stock_return = []
for i in range(ticker_num):  
    return_tmp = np.log(df_stocks[[tickers[i]]]/df_stocks[[tickers[i]]].shift(1))[1:]  
    return_tmp = (return_tmp+1).cumprod()
    stock_return.append(return_tmp[[tickers[i]]])
    return_all = pd.concat(stock_return,axis=1)
return_all.head()

# 利用曲线更直观地展示所有股票的回报率
# plot cumulative returns of all stocks
plt.style.use('ggplot')
for i, col in enumerate(return_all.columns):
    return_all[col].plot()
plt.title('Cumulative returns')
plt.xlabel('Date')
plt.ylabel('Return')
plt.xticks(rotation=30)
plt.legend(return_all.columns)

# 设定投资组合中各个股票的比重，并且在持有期内保持不变。进而计算得到整个投资组合的预期回报和股价
# lastest return and price values
latest_return = return_all.iloc[-1,:]
latest_price = df_stocks.iloc[-1,:]
sigma = latest_return.std()
# weights for stocks in the portfolio
stock_weight = [0.2, 0.3, 0.1, 0.15, 0.25] 
# calculate expected return
expected_return = latest_return.dot(stock_weight)
print('The weighted expected portfolio return: %.2f' % expected_return)
# calculate weighted price
price = latest_price.dot(stock_weight)
print('The weighted price of the portfolio: %.0f' % price)

#假设该投资组合的回报率符合正态分布，以一天中的每一分钟作为步长，即分为1440个节点，利用蒙特卡洛模拟随机产生500个回报率数值。
# monte carlo simulation
MC_num = 500
confidence_level = 0.95
time_step = 1440
for i in range(MC_num):  
  daily_returns = np.random.normal(expected_return/time_step, sigma/np.sqrt(time_step), time_step)
  plt.plot(daily_returns)
plt.axhline(np.percentile(daily_returns,(1.0-confidence_level)*100), color='r', linestyle='dashed')
plt.axhline(np.percentile(daily_returns,confidence_level*100), color='g', linestyle='dashed')
plt.axhline(np.mean(daily_returns), color='b', linestyle='solid')
plt.xlabel('Time')
plt.ylabel('Return')
# 可视化，红线处为风险价值
# plot return distribution
sns.distplot(daily_returns, kde=True, color='lightblue')
plt.axvline(np.percentile(daily_returns,(1.0-confidence_level)*100), color='red', linestyle='dashed', linewidth=2)
plt.title("Return distribution")
plt.xlabel('Return')
plt.ylabel('Frequency')
plt.show()

# 假设初始投资金额为100万美元，得到VaR值为 33185
initial_investment  = 1000000
VaR = initial_investment*np.percentile(daily_returns,(1.0-confidence_level)*100)
print('The value at risk is %.0f' % VaR)

import pandas as pd

# Creating the series. Using the range() function, we create a series and set the index to shot.
my_series=pd.Series(range(1,20,5), index=[x for x in 'shot'])

# Printing the series
print(my_series)

# Using Series.ewm(). We calculate the exponential weight of elements in the series using the ewm() function and set the com and adjust parameters.
print(my_series.ewm(com=0.5, adjust=True).mean())

Series.ewm(self, com=None, span=None, halflife=None, alpha=None, min_periods=0, adjust=True, ignore_na=False, axis=0)

import numpy as np
import pandas_datareader
import matplotlib.pyplot as plt 
from arch import arch_model
# sp500 price
sp500 = pandas_datareader.data.DataReader(['sp500'], data_source='fred', start='12-28-2009', end='12-28-2020')
# daily log return
log_return_daily = np.log(sp500 / sp500.shift(1))
log_return_daily.dropna(inplace=True)
# ARCH(1) model
arch=arch_model(y=log_return_daily,mean='Constant',lags=0,vol='ARCH',p=1,o=0,q=0,dist='normal')
archmodel=arch.fit()
archmodel.summary()
archmodel.plot()

# GARCH(1,1) model
garch=arch_model(y=log_return_daily,mean='Constant',lags=0,vol='GARCH',p=1,o=0,q=1,dist='normal')
garchmodel=garch.fit()
garchmodel.summary()
garchmodel.plot()