
    Vh                     |    d dl Z d dl mZ d dlmZ d dlmZ d dlmZmZm	Z	m
Z
 d dlmZ d dlmZ dgZ G d	 de      Zy)
    N)Tensor)constraints)Distribution)broadcast_alllazy_propertylogits_to_probsprobs_to_logits) binary_cross_entropy_with_logits)_Number	Geometricc                       e Zd ZdZej
                  ej                  dZej                  Z	d fd	Z
d fd	Zedefd       Zedefd       Zedefd       Zedefd	       Zedefd
       Z ej*                         fdZd Zd Z xZS )r   a  
    Creates a Geometric distribution parameterized by :attr:`probs`,
    where :attr:`probs` is the probability of success of Bernoulli trials.

    .. math::

        P(X=k) = (1-p)^{k} p, k = 0, 1, ...

    .. note::
        :func:`torch.distributions.geometric.Geometric` :math:`(k+1)`-th trial is the first success
        hence draws samples in :math:`\{0, 1, \ldots\}`, whereas
        :func:`torch.Tensor.geometric_` `k`-th trial is the first success hence draws samples in :math:`\{1, 2, \ldots\}`.

    Example::

        >>> # xdoctest: +IGNORE_WANT("non-deterministic")
        >>> m = Geometric(torch.tensor([0.3]))
        >>> m.sample()  # underlying Bernoulli has 30% chance 1; 70% chance 0
        tensor([ 2.])

    Args:
        probs (Number, Tensor): the probability of sampling `1`. Must be in range (0, 1]
        logits (Number, Tensor): the log-odds of sampling `1`.
    )probslogitsc           
      "   |d u |d u k(  rt        d      |t        |      \  | _        nt        |      \  | _        ||n|}t	        |t
              rt        j                         }n|j                         }t        	| )  ||       | j                  r{|x| j                  }|dkD  }|j                         sV|j                  |    }t        dt        |      j                   dt!        |j"                         dt%        |        d|       y y y )Nz;Either `probs` or `logits` must be specified, but not both.validate_argsr   zExpected parameter probs (z
 of shape z) of distribution z* to be positive but found invalid values:
)
ValueErrorr   r   r   
isinstancer   torchSizesizesuper__init___validate_argsalldatatype__name__tupleshaperepr)
selfr   r   r   probs_or_logitsbatch_shapevaluevalidinvalid_value	__class__s
            M/home/dcms/DCMS/lib/python3.12/site-packages/torch/distributions/geometric.pyr   zGeometric.__init__0   s    TMv~.M  )%0MTZ*62NT[#(#4%&ow/**,K)..0KMB5#4JJEAIE99; %

E6 2 U,,-Zekk8J7K L''+Dzl 3AANQ  	 $5    c                 b   | j                  t        |      }t        j                  |      }d| j                  v r | j
                  j                  |      |_        d| j                  v r | j                  j                  |      |_        t        t        |'  |d       | j                  |_
        |S )Nr   r   Fr   )_get_checked_instancer   r   r   __dict__r   expandr   r   r   r   )r"   r$   	_instancenewr(   s       r)   r.   zGeometric.expandL   s    ((I>jj-dmm#

))+6CIt}}$++K8CJi&{%&H!00
r*   returnc                 &    d| j                   z  dz
  S Ng      ?r   r"   s    r)   meanzGeometric.meanW   s    TZZ#%%r*   c                 @    t        j                  | j                        S N)r   
zeros_liker   r5   s    r)   modezGeometric.mode[   s    

++r*   c                 @    d| j                   z  dz
  | j                   z  S r3   r4   r5   s    r)   variancezGeometric.variance_   s    djj 3&$**44r*   c                 0    t        | j                  d      S NT)	is_binary)r	   r   r5   s    r)   r   zGeometric.logitsc   s    tzzT::r*   c                 0    t        | j                  d      S r>   )r   r   r5   s    r)   r   zGeometric.probsg   s    t{{d;;r*   c                    | j                  |      }t        j                  | j                  j                        j
                  }t        j                         5  t        j                  j                         rSt        j                  || j                  j                  | j                  j                        }|j                  |      }n+| j                  j                  |      j                  |d      }|j                         | j                   j                         z  j!                         cd d d        S # 1 sw Y   y xY w)N)dtypedevice)min   )_extended_shaper   finfor   rB   tinyno_grad_C_get_tracing_staterandrC   clampr0   uniform_loglog1pfloor)r"   sample_shaper    rH   us        r)   samplezGeometric.samplek   s    $$\2{{4::++,11]]_ 	=xx**,JJuDJJ,<,<TZZEVEVWGGG%JJNN5)224;EEG

{1133::<	= 	= 	=s   CD99Ec                 (   | j                   r| j                  |       t        || j                        \  }}|j	                  t
        j                        }d||dk(  |dk(  z  <   || j                         z  | j                  j                         z   S )N)memory_formatr   rE   )	r   _validate_sampler   r   cloner   contiguous_formatrP   rO   )r"   r%   r   s      r)   log_probzGeometric.log_probw   s~    !!%($UDJJ7u%*A*AB-.uzeqj)*~~''$**..*:::r*   c                 `    t        | j                  | j                  d      | j                  z  S )Nnone)	reduction)r
   r   r   r5   s    r)   entropyzGeometric.entropy   s(    ,T[[$**PVWjj	
r*   )NNNr8   )r   
__module____qualname____doc__r   unit_intervalrealarg_constraintsnonnegative_integersupportr   r.   propertyr   r6   r:   r<   r   r   r   r   r   rT   rZ   r^   __classcell__)r(   s   @r)   r   r      s    2 !, 9 9[EUEUVO--G8	 &f & & ,f , , 5& 5 5 ; ; ; <v < < #-%**, 
=;
r*   )r   r   torch.distributionsr    torch.distributions.distributionr   torch.distributions.utilsr   r   r   r	   torch.nn.functionalr
   torch.typesr   __all__r    r*   r)   <module>rp      s;      + 9  A  -p
 p
r*   