def alpha(self, factor_returns, risk_free=0.):
"""Annualized alpha.
Args:
factor_returns (array_like): Benchmark return to compare returns against. Will broadcast.
risk_free (float or array_like): Constant risk-free return throughout the period."""
factor_returns = reshape_fns.broadcast_to(
reshape_fns.to_2d(factor_returns, raw=True),
reshape_fns.to_2d(self._obj, raw=True))
risk_free = np.broadcast_to(risk_free, (len(self.columns),))
return self.wrap_reduced(nb.alpha_nb(self.to_2d_array(), factor_returns, self.ann_factor, risk_free))
def alpha(self, benchmark_rets, risk_free=0., wrap_kwargs=None):
"""Annualized alpha.
Args:
benchmark_rets (array_like): Benchmark return to compare returns against. Will broadcast.
risk_free (float or array_like): Constant risk-free return throughout the period."""
benchmark_rets = reshape_fns.broadcast_to(
reshape_fns.to_2d(benchmark_rets, raw=True),
reshape_fns.to_2d(self._obj, raw=True))
wrap_kwargs = merge_dicts(dict(name_or_index='alpha'), wrap_kwargs)
return self.wrapper.wrap_reduced(nb.alpha_nb(
self.to_2d_array(), benchmark_rets, self.ann_factor, risk_free
), **wrap_kwargs)
def alpha(self,
benchmark_rets: tp.ArrayLike,
risk_free: float = 0.,
wrap_kwargs: tp.KwargsLike = None) -> tp.MaybeSeries:
"""Annualized alpha.
Args:
benchmark_rets (array_like): Benchmark return to compare returns against. Will broadcast.
risk_free (float): Constant risk-free return throughout the period."""
benchmark_rets = broadcast_to(to_2d(benchmark_rets, raw=True),
to_2d(self._obj, raw=True))
result = nb.alpha_nb(self.to_2d_array(), benchmark_rets,
self.ann_factor, risk_free)
wrap_kwargs = merge_dicts(dict(name_or_index='alpha'), wrap_kwargs)
return self.wrapper.wrap_reduced(result, **wrap_kwargs)