
    Ǆgi                     j    d dl mZ d dlZd dlmZ d dlmZ d dlmZ d dl	m
Z
 dgZd Z G d	 de      Zy)
    )NumberN)constraints)ExponentialFamily)broadcast_all)_sizeGammac                 ,    t        j                  |       S N)torch_standard_gamma)concentrations    a/home/mcse/projects/flask_80/flask-venv/lib/python3.12/site-packages/torch/distributions/gamma.pyr   r      s      //    c                        e Zd ZdZej
                  ej
                  dZej                  ZdZ	dZ
ed        Zed        Zed        Zd fd	Zd fd		Z ej$                         fd
edej(                  fdZd Zd Zed        Zd Zd Z xZS )r   aC  
    Creates a Gamma distribution parameterized by shape :attr:`concentration` and :attr:`rate`.

    Example::

        >>> # xdoctest: +IGNORE_WANT("non-deterministic")
        >>> m = Gamma(torch.tensor([1.0]), torch.tensor([1.0]))
        >>> m.sample()  # Gamma distributed with concentration=1 and rate=1
        tensor([ 0.1046])

    Args:
        concentration (float or Tensor): shape parameter of the distribution
            (often referred to as alpha)
        rate (float or Tensor): rate = 1 / scale of the distribution
            (often referred to as beta)
    r   rateTr   c                 4    | j                   | j                  z  S r
   r   selfs    r   meanz
Gamma.mean+   s    !!DII--r   c                 Z    | j                   dz
  | j                  z  j                  d      S )N   r   min)r   r   clampr   s    r   modez
Gamma.mode/   s*    ##a'4994;;;BBr   c                 R    | j                   | j                  j                  d      z  S )N   )r   r   powr   s    r   variancezGamma.variance3   s     !!DIIMM!$444r   c                     t        ||      \  | _        | _        t        |t              r%t        |t              rt        j                         }n| j                  j                         }t        | %  ||       y )Nvalidate_args)
r   r   r   
isinstancer   r   Sizesizesuper__init__)r   r   r   r#   batch_shape	__class__s        r   r(   zGamma.__init__7   s]    (5mT(J%DImV,D&1I**,K,,113KMBr   c                 *   | j                  t        |      }t        j                  |      }| j                  j                  |      |_        | j                  j                  |      |_        t        t        |#  |d       | j                  |_	        |S )NFr"   )
_get_checked_instancer   r   r%   r   expandr   r'   r(   _validate_args)r   r)   	_instancenewr*   s       r   r-   zGamma.expand?   sy    ((	:jj- ..55kB99##K0eS";e"D!00
r   sample_shapereturnc                 6   | j                  |      }t        | j                  j                  |            | j                  j                  |      z  }|j                         j                  t        j                  |j                        j                         |S )Nr   )_extended_shaper   r   r-   r   detachclamp_r   finfodtypetiny)r   r1   shapevalues       r   rsamplezGamma.rsampleH   s    $$\2 2 2 9 9% @ADIIDTDTE
 
 	EKK(-- 	 	
 r   c                    t        j                  || j                  j                  | j                  j                        }| j
                  r| j                  |       t        j                  | j                  | j                        t        j                  | j                  dz
  |      z   | j                  |z  z
  t        j                  | j                        z
  S )N)r8   devicer   )
r   	as_tensorr   r8   r>   r.   _validate_samplexlogyr   lgammar   r;   s     r   log_probzGamma.log_probR   s    TYY__TYYEUEUV!!%(KK**DII6kk$,,q0%89ii%  ll4--./	
r   c                     | j                   t        j                  | j                        z
  t        j                  | j                         z   d| j                   z
  t        j
                  | j                         z  z   S )Ng      ?)r   r   logr   rB   digammar   s    r   entropyzGamma.entropy]   sf    ii		"#ll4--./ T'''5==9K9K+LLM	
r   c                 :    | j                   dz
  | j                   fS Nr   r   r   s    r   _natural_paramszGamma._natural_paramse   s    ""Q&
33r   c                     t        j                  |dz         |dz   t        j                  |j                                z  z   S rJ   )r   rB   rF   
reciprocal)r   xys      r   _log_normalizerzGamma._log_normalizeri   s4    ||AE"a!euyy!,,./I%IIIr   c                     | j                   r| j                  |       t        j                  j	                  | j
                  | j                  |z        S r
   )r.   r@   r   specialgammaincr   r   rC   s     r   cdfz	Gamma.cdfl   s?    !!%(}}%%d&8&8$))e:KLLr   r
   )__name__
__module____qualname____doc__r   positivearg_constraintsnonnegativesupporthas_rsample_mean_carrier_measurepropertyr   r   r    r(   r-   r   r%   r   Tensorr<   rD   rH   rK   rP   rT   __classcell__)r*   s   @r   r   r      s    " %--$$O %%GK. . C C 5 5C -7EJJL E U\\ 	

 4 4JMr   )numbersr   r   torch.distributionsr   torch.distributions.exp_familyr   torch.distributions.utilsr   torch.typesr   __all__r   r    r   r   <module>ri      s6      + < 3  )0]M ]Mr   