Package csb :: Package statistics :: Module maxent :: Class MaxentModel

Class MaxentModel

         object --+        
                  |        
pdf.AbstractDensity --+    
                      |    
        pdf.BaseDensity --+
                          |
                         MaxentModel

Fourier expansion of a biangular log-probability density

Nested Classes
Inherited from `pdf.AbstractDensity`: `__metaclass__`

Instance Methods

__init__(self, n, beta=1.0)
x.__init__(...) initializes x; see help(type(x)) for signature

source code

calculate_statistics(self, data)
Calculate the sufficient statistics for the data.

source code

energy(self, x, y=None)
Return the energy at positions (x,y).

source code

entropy(self, n=500)
Calculate the entropy of the model.

source code

get(self)
Return current expansion coefficients.

source code

load(self, aa, f_name)
Load set of expansion coefficients from isd+.

source code

load_old(self, aa, f_name)
Load set of expansion coefficients from isd.

source code

array

log_prob(self, x, y)
Return the energy at positions (x,y).

source code

log_z(self, n=500, integration='simpson')
Calculate the log partion function. source code

normalize(self, normalize_full=True)
Remove parameter, which do not have any influence on the model and compute the partition function.

source code

prob(self, x, y)
Return the probability of the configurations x cross y.

source code

sample_weights(self)
Create a random set of expansion coefficients.

source code

set(self, coef)
Set the fourier expansion coefficients and calculations the new partation function.

source code

z(self)
Calculate the partion function .

source code

Inherited from pdf.AbstractDensity: __call__, __getitem__, __setitem__, __str__, estimate, evaluate, get_params, random, set_params

Inherited from object: __delattr__, __format__, __getattribute__, __hash__, __new__, __reduce__, __reduce_ex__, __repr__, __setattr__, __sizeof__, __subclasshook__

Class Variables
	__abstractmethods__ = `frozenset([])`

Properties
float	beta Inverse temperature
int	n Order of the fourier expansion
Inherited from `pdf.AbstractDensity`: `estimator`, `parameters` Inherited from `object`: `__class__`

Method Details

init(self, n, beta=1.0)
(Constructor)

source code

x.__init__(...) initializes x; see help(type(x)) for signature

Parameters:

n (int) - order of the fourier expansion
beta (float) - inverse temperature

Overrides: object.__init__

energy(self, x, y=None)

source code

Return the energy at positions (x,y).

Parameters:

x (array-like) - x-coordinates for evaluation
y (array-like) - y-coordinates for evaluation

entropy(self, n=500)

source code

Calculate the entropy of the model.

Parameters:

n (integer) - number of integration points for numerical integration

load(self, aa, f_name)

source code

Load set of expansion coefficients from isd+.

Parameters:

aa - Amino acid type
f_name - File containing ramachandran definition

load_old(self, aa, f_name)

source code

Load set of expansion coefficients from isd.

Parameters:

aa - Amino acid type
f_name - File containing ramachandran definition

log_prob(self, x, y)

source code

Return the energy at positions (x,y).

Parameters:

x (array-like) - x-coordinates for evaluation
y (array-like) - y-coordinates for evaluation

Returns: array

Overrides: pdf.AbstractDensity.log_prob

normalize(self, normalize_full=True)

source code

Remove parameter, which do not have any influence on the model and compute the partition function.

Parameters:

normalize_full (boolean) - compute partition function

set(self, coef)

source code

Set the fourier expansion coefficients and calculations the new partation function.

Parameters:

coef (array like, with shape (4,n,n)) - expansion coefficents

Property Details

beta

Inverse temperature

Get Method:: unreachable.beta(self) - Inverse temperature
Type:: float

n

Order of the fourier expansion

Get Method:: unreachable.n(self) - Order of the fourier expansion
Type:: int

Class MaxentModel

__init__(self, n, beta=1.0) (Constructor)

energy(self, x, y=None)

entropy(self, n=500)

load(self, aa, f_name)

load_old(self, aa, f_name)

log_prob(self, x, y)

normalize(self, normalize_full=True)

set(self, coef)

beta

n

init(self, n, beta=1.0)
(Constructor)