def computeInformationRatio(self, portfolio):
returns = self.preprocess.retrieve_return()
index = self.preprocess.retrieve_benchmark_change("snp500")
if self.alpha is None:
alpha = post.compute_alpha(
index, returns).loc[portfolio.keys()]["alpha"].values
self.alpha = alpha
else:
alpha = self.alpha
#print("alpha:", alpha)
weight = np.array(list(portfolio.values()))
#print("weight", weight)
portfolio_return = np.sum(np.multiply(alpha, weight))
#print("portfolio return", portfolio_return)
volatility = np.std(alpha)
#print("volatility", volatility)
if self.index is None:
index = self.preprocess.retrieve_benchmark_change(
self.benchmark) - 1
self.index = index
else:
index = self.index
#print("benchmark", index)
information_ratio = (portfolio_return - index) / volatility
return information_ratio
'steps': []
}
summaries = []
for i in range(steps):
print("summarizing step:", i)
start = i
end = -steps + 1 + i if (steps - i > 1) else duration
price_frame = daily_price.iloc[start: end]
start_date = dates[start]
end_index = duration - steps + i if end < 0 else duration - 1
end_date = dates[end_index]
return_frame = preprocess.retrieve_return(date1=start_date, date2=end_date)
index_change = preprocess.retrieve_benchmark_change(benchmark, date1=start_date, date2=end_date)
alpha = post.compute_alpha(index_change, return_frame)
index_series = preprocess.retrieve_benchmark(benchmark, dates=[start_date, end_date])
beta = post.compute_beta(index_series, price_frame)
alpha_beta = pd.concat([alpha, beta], axis=1, join='inner')
alpha_beta_sector = pd.concat([alpha_beta, symbolSector], axis=1, join='inner') # type: pd.DataFrame
summary = pd.concat([alpha_beta_sector, mktcap["size"]], axis=1, join='inner')
summary["symbol"] = "circle" # set default symbol
summary.loc[summary.index.isin(stars), "symbol"] = "star" # mark selected stocks as star
summaries.append(summary)
# process summaries for index alignment (showing the same data throughout animation)
valid_index = summaries[0].index.values
i = 1 # keep track of summaries index
for summary in summaries[1:]: