def _filter(self, R):
# sh[col] = tools.sharpe(total_ret.div(total_weights, axis=0), alpha=0.000001)
# to_remove = set(sh.index[sh - full_sharpe > 0.00001])
SAMPLES = 50
np.random.seed(42)
sh = []
for _ in range(SAMPLES):
# get bootstrap sample
R_sample = R.sample(n=len(R), replace=True)
sh.append({
col: tools.sharpe(R_sample[col], alpha=0.00001)
for col in R_sample
})
sh = pd.DataFrame(sh)
sh_diff = sh.subtract(sh["full"], 0)
cdf = stats.norm.cdf(0.0,
loc=sh_diff.mean(),
scale=0.01 +
sh_diff.std() / np.sqrt(len(sh_diff)))
to_remove = sh_diff.columns[cdf < self.threshold]
to_remove = to_remove.drop("full", errors="ignore")
print(list(to_remove))
return to_remove
def _filter(self, R):
# sh[col] = tools.sharpe(total_ret.div(total_weights, axis=0), alpha=0.000001)
# to_remove = set(sh.index[sh - full_sharpe > 0.00001])
SAMPLES = 50
np.random.seed(42)
sh = []
for _ in range(SAMPLES):
# get bootstrap sample
R_sample = R.sample(n=len(R), replace=True)
sh.append({col: tools.sharpe(R_sample[col], alpha=0.00001) for col in R_sample})
sh = pd.DataFrame(sh)
sh_diff = sh.subtract(sh['full'], 0)
cdf = stats.norm.cdf(0., loc=sh_diff.mean(), scale=0.01 + sh_diff.std() / np.sqrt(len(sh_diff)))
to_remove = sh_diff.columns[cdf < self.threshold]
to_remove = to_remove.drop('full', errors='ignore')
print(list(to_remove))
return to_remove
def sharpe(self):
""" Compute annualized sharpe ratio from log returns. If data does
not contain datetime index, assume daily frequency with 252 trading days a year.
"""
return tools.sharpe(self.r_log, rf_rate=self.rf_rate, freq=self.freq())
def sharpe(self):
""" Compute annualized sharpe ratio from log returns. If data does
not contain datetime index, assume daily frequency with 252 trading days a year.
"""
return tools.sharpe(self.r_log, rf_rate=self.rf_rate, freq=self.freq())
