|
ExponentialPrior = class ExponentialPrior(Prior) |
| |
ExponentialPrior(scale=1.0, prior=None)
Exponential prior distribution.
Pr( x ) = exp( -x / scale )
By default scale = 1.
The domain is [0,+Inf].
In computational practice the domain is limited to about [0,36] scale units
domain2unit: u = 1 - exp( - d / scale )
unit2domain: d = -log( 1 - u ) * scale
Optionally one can set a zero fraction as the fraction of u where the unit2Domain
method returns a 0.
Examples
--------
>>> pr = ExponentialPrior() # scale=1.0
>>> pr = ExponentialPrior( scale=5.0 ) # scale=5
Attributes
----------
scale : float
scale of the exponential
zeroFraction : float
fraction of unit that map to zero in domain and vice versa.
Hidden Attributes
-----------------
_shift : float
shift of the exponential part to make room for zeros.
_uval : float
random number within [0,zeroFraction].
Attributes from Prior
--------------------=
lowLimit, highLimit, deltaP, _lowDomain, _highDomain
lowLimit and highLimit cannot be used in this implementation.
Author: Do Kester.
|
| |
- Method resolution order:
- ExponentialPrior
- Prior
- builtins.object
Constructor:
- ExponentialPrior( scale=1.0, prior=None )
- Constructor.
Parameters:
scale : float
of the exponential
prior : ExponentialPrior
prior to copy (with new scale if applicable)
Methods defined here:
- copy()
- Copy the prior
- domain2Unit( dval )
- Return a value in [0,1] given a value within the valid domain of
a parameter for a Exponential distribution.
Parameters
----------
dval : float
value within the domain of a parameter
- isBound()
- Return true if the integral over the prior is bound.
- logResult( x )
- Return a the log of the result of the distribution function to p.
Parameters
----------
x : float
value within the domain of a parameter
- partialLog( p )
- Return partial derivative of log( Prior ) wrt parameter.
Parameters
----------
p : float
the value
- result( x )
- Return a the result of the distribution function at x.
Parameters
----------
x : float
value within the domain of a parameter
- unit2Domain( uval )
- Return a value within the valid domain of the parameter given a value
between [0,1] for a Exponential distribution.
Parameters
----------
uval : float
value within [0,1]
Methods inherited from Prior:
|
|