o
    h                     @   sj   d dl mZ d dl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gZG dd deZdS )	    )NumberN)constraints)Distribution)broadcast_alllazy_propertylogits_to_probsprobs_to_logits) binary_cross_entropy_with_logits	Geometricc                       s   e Zd ZdZejejdZejZ	d fdd	Z
d fdd	Zedd	 Zed
d Zedd Zedd Zedd Ze fddZdd Zdd Z  ZS )r
   a  
    Creates a Geometric distribution parameterized by :attr:`probs`,
    where :attr:`probs` is the probability of success of Bernoulli trials.
    It represents the probability that in :math:`k + 1` Bernoulli trials, the
    first :math:`k` trials failed, before seeing a success.

    Samples are non-negative integers [0, :math:`\inf`).

    Example::

        >>> # xdoctest: +IGNORE_WANT("non-deterinistic")
        >>> 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logitsNc           	   	      s   |d u |d u krt d|d urt|\| _nt|\| _|d ur#|n|}t|tr/t }n| }t	 j
||d | jrk|d urm| j}|dk}| so|j|  }t dt|j dt|j dt|  d| d S d S d S )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/var/www/html/ai/venv/lib/python3.10/site-packages/torch/distributions/geometric.pyr   (   s<   

zGeometric.__init__c                    sf   |  t|}t|}d| jv r| j||_d| jv r#| j||_tt|j	|dd | j
|_
|S )Nr   r   Fr   )_get_checked_instancer
   r   r   __dict__r   expandr   r   r   r   )r   r    	_instancenewr$   r&   r'   r*   D   s   


zGeometric.expandc                 C   s   d| j  d S Ng      ?r   r   r&   r&   r'   meanO      zGeometric.meanc                 C   s   t | jS N)r   
zeros_liker   r/   r&   r&   r'   modeS   s   zGeometric.modec                 C   s   d| j  d | j  S r-   r.   r/   r&   r&   r'   varianceW   s   zGeometric.variancec                 C      t | jddS NT)	is_binary)r   r   r/   r&   r&   r'   r   [   r1   zGeometric.logitsc                 C   r6   r7   )r   r   r/   r&   r&   r'   r   _   r1   zGeometric.probsc                 C   s   |  |}t| jjj}t 6 tj r*tj	|| jj| jj
d}|j|d}n
| j||d}| | j    W  d    S 1 sJw   Y  d S )N)dtypedevice)min   )_extended_shaper   finfor   r9   tinyno_grad_C_get_tracing_staterandr:   clampr,   uniform_loglog1pfloor)r   sample_shaper   r?   ur&   r&   r'   samplec   s   


$zGeometric.samplec                 C   sZ   | j r| | t|| j\}}|jtjd}d||dk|dk@ < ||   | j  S )N)memory_formatr   r<   )	r   _validate_sampler   r   cloner   contiguous_formatrG   rF   )r   r!   r   r&   r&   r'   log_probo   s   
zGeometric.log_probc                 C   s   t | j| jdd| j S )Nnone)	reduction)r	   r   r   r/   r&   r&   r'   entropyw   s   zGeometric.entropy)NNNr2   )r   
__module____qualname____doc__r   unit_intervalrealarg_constraintsnonnegative_integersupportr   r*   propertyr0   r4   r5   r   r   r   r   r   rK   rP   rS   __classcell__r&   r&   r$   r'   r
      s&    




)numbersr   r   torch.distributionsr    torch.distributions.distributionr   torch.distributions.utilsr   r   r   r   torch.nn.functionalr	   __all__r
   r&   r&   r&   r'   <module>   s    