# Import modules for API calls import requests import io import pandas as pd import requests import json from datetime import datetime import matplotlib.pyplot as plt # Import module for plotting import seaborn as sns ## JHU Vaccination Rates (Taken From: https://github.com/owid/covid-19-data/tree/master/public/data) url = 'https://raw.githubusercontent.com/owid/covid-19-data/master/public/data/owid-covid-data.csv' download = requests.get(url).content covid = pd.read_csv(io.StringIO(download.decode('utf-8')), parse_dates=['date'])

namelist = ['China','Singapore','United Arab Emirates', 'Japan'] selected_case = covid[covid['location'].isin(namelist)] sns.scatterplot('date', 'new_cases', data=selected_case, hue='location') plt.title('China against a selection of countries')

# Separate plot for comparison to United States and United Kingdom since these values dwarf the # values for China and other countries. namelist2 = ['China','United States','United Kingdom'] selected_case = covid[covid['location'].isin(namelist2)] sns.scatterplot('date', 'new_cases', data=selected_case, hue='location') plt.title('China against the United States and United Kingdom')

tmp = covid[covid['location']=="China"] tmp=tmp.set_index('date') China_data = tmp[['total_cases','new_cases','total_deaths','new_deaths','total_tests','new_tests','positive_rate','tests_per_case','total_vaccinations','new_vaccinations']]

China_data['total_vaccinations'].plot()

China_data.tail()

# new_vaccinations, people_fully_vaccinated, tests_per_case China_data[['tests_per_case', 'new_cases']].plot() China_data[['new_vaccinations', 'new_cases']].plot()

import numpy as np import matplotlib.pyplot as plt import pandas as pd import datetime as dt import yfinance as yf # find the symbol (i.e., google the instrument + 'yahoo finance') to any data series you are interested at # e.g., market/sector index ETF for your chosen country and various asset classes (e.g., Comex Gold's symbol is 'GC=F') # e.g., SPY (https://finance.yahoo.com/quote/SPY/) symbols_list = ['000001.SS', '510710.SS', '510500.SS','510300.SS','002049.SZ','600196.SS','002594.SZ','300750.SZ' ] start = dt.datetime(2020,4,1) end = dt.datetime(2021,9,17) data = yf.download(symbols_list, start=start, end=end)

# filter column adjusted close df = data['Adj Close'] df.columns = ['SSE','SSE50','CSI500',"CSI300","Unigroup","Fosun","BYD",'Amperex'] df = df.ffill() df0 = df.copy()

df = df.loc[:,'SSE50':'Amperex'] df.head()

df.info()

!pip install PyPortfolioOpt==1.2.1

from pypfopt.efficient_frontier import EfficientFrontier from pypfopt import risk_models from pypfopt import expected_returns from pypfopt import cla from pypfopt.plotting import Plotting from pypfopt.discrete_allocation import DiscreteAllocation, get_latest_prices from matplotlib.ticker import FuncFormatter import seaborn as sns

# Check NaN values in the data #nullin_df = pd.DataFrame(df,columns=symbols_list) #print(nullin_df.isnull().sum()) # Calculate portfolio mean return mu = expected_returns.mean_historical_return(df) print(mu) # Calculate portfolio return variance sigma = risk_models.sample_cov(df) print(sigma)

# Note max sharpe ratio is the tangency portfolio # weight bounds in negative allows shorting of stocks ef = EfficientFrontier(mu, sigma, weight_bounds=(-1,1)) # if don't short, put(0,1) # optional constraints possible, read pypfopt documentation. # Where for the last year, the range of the chinese government bond was from 2.21-2.7% # ,so an average of 2.45% was taken. sharpe_portfolio=ef.max_sharpe(risk_free_rate=0.0245) sharpe_portfolio_wt=ef.clean_weights() print(sharpe_portfolio_wt) Plotting.plot_weights(sharpe_portfolio_wt)

latest_prices = get_latest_prices(df) # Allocate Portfolio Value in $ as required to show number of shares/stocks to buy, # also bounds for shorting will affect allocation # Maximum Sharpe Portfolio Allocation $1000000 da = DiscreteAllocation(sharpe_portfolio_wt, latest_prices, total_portfolio_value=1000000) allocation, leftover = da.greedy_portfolio() print(allocation) print("Leftover Fund value for the maximum Sharpe portfolio is ${:.2f}".format(leftover))

max_sharpe_cla = cla.CLA(mu, sigma) max_sharpe_cla.max_sharpe() Plotting.plot_efficient_frontier(max_sharpe_cla, show_assets="True")

sharpe_portfolio_wt_list = list(sharpe_portfolio_wt.values()) ret_data = df.pct_change()[1:] # need keep first observation to aviod NaN in ret weighted_returns = (sharpe_portfolio_wt_list * ret_data) portfolio_ret = pd.DataFrame(weighted_returns.sum(axis=1)) ret_data = ret_data.merge(portfolio_ret, on="Date", how="left") ret_data = ret_data.rename(columns={0: "portfolio_ret"}) ret_data['SSE'] = df0["SSE"].pct_change()[1:] ret_data.head()

ret_data['portfolio_ret'].hist(bins = 50,density = True, histtype = 'step', color = 'red') plt.ylabel('Return') plt.title('Daily Return for Max-Sharpe Portfolio')

# note: unlike drawing from the population, bootstrapping draws random sample (with replacement) from the actual data def bootstrap_replicate_1d(data, func): # bootstrap from actual data # draw random sample from actual data with replacement # sample size is the number of observations of the actual data bs_sample = np.random.choice(data, len(data)) # return the mean of a draw return func(bs_sample) # draw bootstrap replicates def draw_bs_reps(data, func, size=1): # initialize a numpy array of the dimension size bs_replicates = np.empty(size) # call function bootstrap_replicate_1d for i in range(size): bs_replicates[i] = bootstrap_replicate_1d(data,func) # return a numpy array of the means of draws return bs_replicates # bootstrap from actual samples # note that this is not sample randomly drawn from a theoretical population data = ret_data.copy() bs_replicates = draw_bs_reps(data['portfolio_ret'], np.mean, size=10000)

# pasted code for confidence interval, need changing conf_int = np.percentile(bs_replicates,[2.5, 97.5]) print('95% bootstrapped confidence interval for portfolio is', conf_int) # Theoretical confidence intervals conf_int_actual_upper = data['portfolio_ret'].mean() + data['portfolio_ret'].std()/np.sqrt(data['portfolio_ret'].count())*1.96 conf_int_actual_lower = data['portfolio_ret'].mean() - data['portfolio_ret'].std()/np.sqrt(data['portfolio_ret'].count())*1.96 conf_int_actual = [conf_int_actual_lower, conf_int_actual_upper] print('-'*120) print('95% theoretical confidence interval for portfolio is=', conf_int_actual,)

ret_data['cumulative_portfolio_ret'] = (ret_data['portfolio_ret'] + 1).cumprod() ret_data['cumulative_SSE_ret'] = (ret_data['SSE'] + 1).cumprod() ret_data.tail()

sns.scatterplot('Date', 'cumulative_portfolio_ret', data=ret_data) sns.scatterplot('Date', 'cumulative_SSE_ret', data=ret_data) plt.title('Cumulative portfolio ret against time')

#May use add objective to ensure minimum zero weighting to individual stocks min_vol_portfolio=ef.min_volatility() min_vol_portfolio_wt=ef.clean_weights() print(min_vol_portfolio_wt) Plotting.plot_weights(min_vol_portfolio_wt)

# Allocate Portfolio Value in $ as required to show number of shares/stocks to buy, # also bounds for shorting will affect allocation # Maximum Sharpe Portfolio Allocation $1000000 da = DiscreteAllocation(min_vol_portfolio_wt, latest_prices, total_portfolio_value=1000000) allocation, leftover = da.greedy_portfolio() print(allocation) print("Leftover Fund value for the maximum Sharpe portfolio is ${:.2f}".format(leftover))

min_vol_cla = cla.CLA(mu, sigma) min_vol_cla.min_volatility() Plotting.plot_efficient_frontier(min_vol_cla, show_assets="True")

min_vol_portfolio_wt_list = list(min_vol_portfolio_wt.values()) ret_data = df.pct_change()[1:] # need keep first observation to aviod NaN in ret weighted_returns = (min_vol_portfolio_wt_list * ret_data) portfolio_ret = pd.DataFrame(weighted_returns.sum(axis=1)) ret_data = ret_data.merge(portfolio_ret, on="Date", how="left") ret_data = ret_data.rename(columns={0: "portfolio_ret"}) ret_data['SSE'] = df0["SSE"].pct_change()[1:] ret_data.head()

ret_data['cumulative_portfolio_ret'] = (ret_data['portfolio_ret'] + 1).cumprod() ret_data['cumulative_SSE_ret'] = (ret_data['SSE'] + 1).cumprod() ret_data.tail()

ret_data['portfolio_ret'].hist(bins = 50,density = True, histtype = 'step', color = 'red') plt.ylabel('Return') plt.title('Daily Return for Min-Vol Portfolio')

# pasted code for confidence interval, need changing conf_int = np.percentile(bs_replicates,[2.5, 97.5]) print('95% bootstrapped confidence interval for portfolio is', conf_int) # Theoretical confidence intervals conf_int_actual_upper = data['portfolio_ret'].mean() + data['portfolio_ret'].std()/np.sqrt(data['portfolio_ret'].count())*1.96 conf_int_actual_lower = data['portfolio_ret'].mean() - data['portfolio_ret'].std()/np.sqrt(data['portfolio_ret'].count())*1.96 conf_int_actual = [conf_int_actual_lower, conf_int_actual_upper] print('-'*120) print('95% theoretical confidence interval for portfolio is=', conf_int_actual,)

sns.scatterplot('Date', 'cumulative_portfolio_ret', data=ret_data) sns.scatterplot('Date', 'cumulative_SSE_ret', data=ret_data) plt.title('Cumulative portfolio ret against time')

df = df.stack() df.head()

df = df.reset_index() df = df.rename(columns={"level_1": "ticker", 0: "price"}) df.head()

df = df.set_index('Date') df['ret'] = df.groupby('ticker').pct_change()

df = df.dropna() df.head()

sns.scatterplot('Date', 'price', data=df, hue='ticker') plt.title('Price against date')