def generate_random_portfolios(stocks: List[str],
period: str = "3mo",
n_portfolios: int = 300):
"""[summary]
Parameters
----------
stocks : List[str]
[description]
period : str, optional
[description], by default "3mo"
n_portfolios : int, optional
[description], by default 300
"""
stock_prices = yahoo_finance_model.process_stocks(stocks, period)
mu = expected_returns.mean_historical_return(stock_prices)
S = risk_models.sample_cov(stock_prices)
ef = EfficientFrontier(mu, S)
# Generate random portfolios
n_samples = n_portfolios
w = np.random.dirichlet(np.ones(len(mu)), n_samples)
rets = w.dot(mu)
stds = np.sqrt(np.diag(w @ S @ w.T))
return ef, rets, stds
def get_maxquadutil_portfolio(
stocks: List[str],
period: str = "3mo",
risk_aversion: float = 1.0,
market_neutral: bool = False,
) -> Tuple[Dict, EfficientFrontier]:
"""Get portfolio maximizing quadratic utility at a given risk aversion
Parameters
----------
stocks : List[str]
List of portfolio stocks
period : str, optional
Period to get stock data, by default "3mo"
risk_aversion : float, optional
Risk aversion level, by default 1.0
market_neutral : bool, optional
Whether portfolio is market neutral, by default False
Returns
-------
Dict
Dictionary of portfolio weights
EfficientFrontier
EfficientFrontier object
"""
stock_prices = yahoo_finance_model.process_stocks(stocks, period)
ef = prepare_efficient_frontier(stock_prices)
return ef.max_quadratic_utility(risk_aversion, market_neutral), ef
def get_efficient_return_portfolio(
stocks: List[str],
period: str = "3mo",
target_return: float = 0.1,
market_neutral: bool = False,
) -> Tuple[Dict, EfficientFrontier]:
"""Get portfolio that minimizes volatility at given return
Parameters
----------
stocks : List[str]
List of portfolio stocks
period : str, optional
Period to get stock data, by default "3mo"
target_return : float, optional
Target return level, by default 0.1
market_neutral : bool, optional
Whether portfolio is market neutral, by default False
Returns
-------
Dict
Dictionary of weights
EfficientFrontier
Efficient Frontier object
"""
stock_prices = yahoo_finance_model.process_stocks(stocks, period)
ef = prepare_efficient_frontier(stock_prices)
return ef.efficient_return(target_return, market_neutral), ef
def get_minvol_portfolio(
stocks: List[str],
period: str = "3mo") -> Tuple[Dict, EfficientFrontier]:
"""Generate weights for minimum volatility portfolio
Parameters
----------
stocks : List[str]
List of portfolio tickers
period : str, optional
Period to get stock data, by default "3mo"
Returns
-------
Dict
Dictionary of tickers and weights
EfficientFrontier
EfficientFrontier object
"""
stock_prices = yahoo_finance_model.process_stocks(stocks, period)
ef = prepare_efficient_frontier(stock_prices)
return dict(ef.min_volatility()), ef
def get_maxsharpe_portfolio(stocks: List[str], period: str,
rfrate: float) -> Tuple[Dict, EfficientFrontier]:
"""Generate weights for max sharpe portfolio
Parameters
----------
stocks : List[str]
List of portfolio tickers
period : str, optional
Period to get stock data, by default "3mo"
rfrate : float, optional
Risk free rate, by default 0.02
Returns
-------
Dict
Dictionary of tickers and weights
EfficientFrontier
EfficientFrontier object
"""
stock_prices = yahoo_finance_model.process_stocks(stocks, period)
ef = prepare_efficient_frontier(stock_prices)
return dict(ef.max_sharpe(rfrate)), ef
