def pdf(self, x, *args, **kwds):
"""
Probability density function at x of the given RV.
Parameters
----------
x : array-like
quantiles
arg1, arg2, arg3,... : array-like
The shape parameter(s) for the distribution (see docstring of the
instance object for more information)
loc : array-like, optional
location parameter (default=0)
scale : array-like, optional
scale parameter (default=1)
Returns
-------
pdf : array-like
Probability density function evaluated at x
"""
(loc, scale) = map(kwds.get, ['loc', 'scale'])
(args, loc, scale) = self._fix_loc_scale(args, loc, scale)
(x, loc, scale, shape) = map(arr, (x, loc, scale, args[0]))
x = (x - loc) * 1.0 / scale
scale = np.abs(scale)
#
isgamma = (shape > 0) & (scale != 0)
isnorm = (shape == 0) & (scale > 0)
ispe3 = (isgamma | isnorm)
indom = (x > self.a) & (x < self.b)
valid = ispe3 & indom
#
output = np.zeros(np.shape(valid), 'd')
np.putmask(output, (1 - ispe3) * np.array(indom, bool), self.badvalue)
(x, shape, scale) = argsreduce(valid, *((x, shape, scale,)))
np.place(output, (valid & isgamma), self._pdf(x, shape) / scale)
np.place(output, (valid & isnorm), dist._norm_pdf(x) / scale)
if output.ndim == 0:
return output[()]
return output
def norm_pdf(x):
return np.where(np.isinf(x), 0, _norm_pdf(x))
def _sf(self, x):
y = (x - self._mu) / self._sigma
return (distributions._norm_sf(y) -
self._herm_cdf(y) * distributions._norm_pdf(y))
def _pdf(self, x):
y = (x - self._mu) / self._sigma
return self._herm_pdf(y) * distributions._norm_pdf(y) / self._sigma
