pystra.distributions.normal.Normal

class Normal(name, mean, stdv, input_type=None, startpoint=None)

Bases: Distribution

Normal distribution

Attributes:

• name (str): Name of the random variable

• mean (float): Mean

• stdv (float): Standard deviation

• input_type (any): Change meaning of mean and stdv

• startpoint (float): Start point for seach

Note: while we could use SciPy norm distribution here, there is a substantial perfromance hit, so use local implementation.

Leave initialization to the base class

Methods

cdf	cumulative distribution function
getMean
getName
getStartPoint
getStdv
jacobian	Compute the Jacobian (e.g.
pdf	probability density function
plot	Plots the PDF of the distribution
ppf	inverse cumulative distribution function
sample	Override sample from base class due to bespoke implementation
setStartPoint
set_location	Updating the distribution location parameter.
set_scale	Updating the distribution scale parameter.
u_to_x	Transformation from u to x
x_to_u	Transformation from x to u

Attributes

std_normal

pdf(x)

probability density function

cdf(x)

cumulative distribution function

ppf(p)

inverse cumulative distribution function

sample(n=1000)

Override sample from base class due to bespoke implementation

u_to_x(u)

Transformation from u to x

x_to_u(x)

Transformation from x to u

jacobian(u, x)

Compute the Jacobian (e.g. Lemaire, eq. 4.9) For the Normal distribution, the more usual general function can be specialized as follows.

set_location(loc=0)

Updating the distribution location parameter. For Normal, there is no need to update other properties as a result of this change.

set_scale(scale=1)

Updating the distribution scale parameter. For Normal, there is no need to update other properties as a result of this change.

plot(ax=None, **kwargs)

Plots the PDF of the distribution