import seaborn as sns import numpy as np # linear algebra import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv) # Input data files are available in the read-only "../input/" directory # For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory import os for dirname, _, filenames in os.walk('/kaggle/input'): for filename in filenames: print(os.path.join(dirname, filename)) # You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All" # You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session

# Import modules for API calls import requests import io import pandas as pd import requests import json from datetime import datetime # 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']) covid.tail()

sns.scatterplot('date', 'new_cases', data=covid, hue='continent')

!pip install yfinance --upgrade --no-cache-dir

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 = [ 'SPY', 'ETH-USD', 'ADA-USD', 'BTC-USD','USDT-USD', 'ICLN','TAN','PBW', 'FMAT', 'LIT', 'QCLN', 'SKYY','BUG','SOXX', 'IYW','VGT','VHT','IHI','XLV','VBR','VBK'] start = dt.datetime(2017,11,1) #chosen date - 1M after ADA listing end = dt.datetime(2021,7,15) data = yf.download(symbols_list, start=start, end=end)

# filter column adjusted close df = data['Adj Close'] df = df.ffill() df.head()

!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 # Thus, we put (0,1) as no shorting is allowed in this scenario ef1 = EfficientFrontier(mu, sigma, weight_bounds=(0,1)) # optional constraints possible, read pypfopt documentation. sharpe_portfolio1=ef1.max_sharpe(risk_free_rate=0.008) sharpe_portfolio1_wt=ef1.clean_weights() print(sharpe_portfolio1_wt) Plotting.plot_weights(sharpe_portfolio1_wt) print(sharpe_portfolio1) # weight bounds in negative allows shorting of stocks without boundaries, i.e. possible 100% long and 100% short # Thus, we put (-1,1) as shorting is allowed in this scenario ef2 = EfficientFrontier(mu, sigma, weight_bounds=(-1,1)) # optional constraints possible, read pypfopt documentation. sharpe_portfolio2=ef2.max_sharpe(risk_free_rate=0.008) sharpe_portfolio2_wt=ef2.clean_weights() print(sharpe_portfolio2_wt) Plotting.plot_weights(sharpe_portfolio2_wt) print(sharpe_portfolio2) ef3 = EfficientFrontier(mu, sigma, weight_bounds=(-0.3,1.3)) #130long-30short capital neutral strategy # optional constraints possible, read pypfopt documentation. sharpe_portfolio3=ef3.max_sharpe(risk_free_rate=0.008) sharpe_portfolio3_wt=ef3.clean_weights() print(sharpe_portfolio3_wt) Plotting.plot_weights(sharpe_portfolio3_wt) print(sharpe_portfolio3)

ef1.portfolio_performance(verbose=True)

ef2.portfolio_performance(verbose=True)

ef3.portfolio_performance(verbose=True)

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_portfolio3_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_portfolio3_wt_list = list(sharpe_portfolio3_wt.values()) ret_data = df.pct_change()[1:] weighted_returns = (sharpe_portfolio3_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.head()

ret_data['cumulative_portfolio_ret'] = (ret_data['portfolio_ret'] + 1).cumprod() ret_data['cumulative_spy_ret'] = (ret_data['SPY'] + 1).cumprod() ret_data.tail()

sns.scatterplot('Date', 'cumulative_portfolio_ret', data=ret_data,label="portfolio ret") sns.scatterplot('Date', 'cumulative_spy_ret', data=ret_data,label="spy_ret")

#May use add objective to ensure minimum zero weighting to individual stocks min_vol_portfolio=ef3.min_volatility() min_vol_portfolio_wt=ef3.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")

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()

sns.scatterplot('Date', 'price', data=df, hue='ticker')

!pip install autoviz !pip install xlrd==2.0.1 !pip install wordcloud==1.8.1