
    cf+                         d Z ddlZddlZddlZddlZddlZddlZddlmZ ddl	Z	ddl
mZ ddlmZ  ej        d          ZdZdZd	Z G d
 d          Zd Zedk    r e             dS dS )aN  Dispatcher process which orchestrates distributed Latent Dirichlet Allocation
(LDA, :class:`~gensim.models.ldamodel.LdaModel`) computations.
Run this script only once, on any node in your cluster.

Notes
-----
The dispatcher expects to find worker scripts already running. Make sure you run as many workers as you like on
your machines **before** launching the dispatcher.


How to use distributed :class:`~gensim.models.ldamodel.LdaModel`
----------------------------------------------------------------

#. Install needed dependencies (Pyro4) ::

    pip install gensim[distributed]

#. Setup serialization (on each machine) ::

    export PYRO_SERIALIZERS_ACCEPTED=pickle
    export PYRO_SERIALIZER=pickle

#. Run nameserver ::

    python -m Pyro4.naming -n 0.0.0.0 &

#. Run workers (on each machine) ::

    python -m gensim.models.lda_worker &

#. Run dispatcher ::

    python -m gensim.models.lda_dispatcher &

#. Run :class:`~gensim.models.ldamodel.LdaModel` in distributed mode :

.. sourcecode:: pycon

    >>> from gensim.test.utils import common_corpus, common_dictionary
    >>> from gensim.models import LdaModel
    >>>
    >>> model = LdaModel(common_corpus, id2word=common_dictionary, distributed=True)


Command line arguments
----------------------

.. program-output:: python -m gensim.models.lda_dispatcher --help
   :ellipsis: 0, -7

    N)Queue)utils)LDA_WORKER_PREFIXzgensim.models.lda_dispatcher
   i3zgensim.lda_dispatcherc                   j   e Zd ZdZedfdZej        d             Zej        d             Z	ej        d             Z
ej        d             Zej        d             Zej        d	             Zej        ej         ej        d
          d                                     Zd Zej        d             ZdS )
DispatcherzDispatcher object that communicates and coordinates individual workers.

    Warnings
    --------
    There should never be more than one dispatcher running at any one time.

    Nc                 8    || _         d| _        ||ni | _        dS )a  Partly initializes the dispatcher.

        A full initialization (including initialization of the workers) requires a call to
        :meth:`~gensim.models.lda_dispatcher.Dispatcher.initialize`

        Parameters
        ----------
        maxsize : int, optional
                Maximum number of jobs to be kept pre-fetched in the queue.
        ns_conf : dict of (str, object)
            Sets up the name server configuration for the pyro daemon server of dispatcher.
            This also helps to keep track of your objects in your network by using logical object names
            instead of exact object name(or id) and its location.

        N)maxsizecallbackns_conf)selfr
   r   s      <lib/python3.11/site-packages/gensim/models/lda_dispatcher.py__init__zDispatcher.__init__c   s&      ")=ww2    c                 Z   t          | j                  | _        t          j                    | _        d| _        d| _        i | _        t          j
        d	i | j        5 }t          j        |                    t                    t                             | _        |                    t"                                                    D ]\  }}	 t          j        |          }t'          | j                  }t(                              d||            |j        |fd| j        i| || j        |<   j# t          j        j        $ r3 t(                              d|           |                    |           Y w xY w	 ddd           n# 1 swxY w Y   | j        st7          d          dS )
a  Fully initialize the dispatcher and all its workers.

        Parameters
        ----------
        **model_params
            Keyword parameters used to initialize individual workers, see :class:`~gensim.models.ldamodel.LdaModel`.

        Raises
        ------
        RuntimeError
            When no workers are found (the :mod:`gensim.models.lda_worker` script must be ran beforehand).

        )r
   r   )prefixzregistering worker #%i at %s
dispatcherz:unresponsive worker at %s,deleting it from the name serverNzEno workers found; run some lda_worker scripts on your machines first! )r   r
   jobs	threadingLocklock_update	_jobsdone_jobsreceivedworkersr   getNSr   Pyro4ProxylistLDA_DISPATCHER_PREFIXr   r   itemslenloggerinfo
initializeerrors	PyroErrorwarningremoveRuntimeError)r   model_paramsnsnameuriworkerworkerids          r   r%   zDispatcher.initializew   s    $,///	$>++[((4<(( 	$B!K7L(M(MNc(deeDMWW,=W>>DDFF 
$ 
$	c	$"[--F"4<00HKK >#NNN%F%hYY4=YLYYY-3DL**|- $ $ $NN#_adeeeIIdOOOOO$
$	$ 	$ 	$ 	$ 	$ 	$ 	$ 	$ 	$ 	$ 	$ 	$ 	$ 	$ 	$ | 	hfggg	h 	hs9   A0F
A#D32F
3AE:7F
9E::F

FFc                 H    d | j                                         D             S )zReturn pyro URIs of all registered workers.

        Returns
        -------
        list of URIs
            The pyro URIs for each worker.

        c                     g | ]	}|j         
S r   )_pyroUri).0r/   s     r   
<listcomp>z)Dispatcher.getworkers.<locals>.<listcomp>   s    DDDFDDDr   )r   valuesr   s    r   
getworkerszDispatcher.getworkers   s'     EDdl.A.A.C.CDDDDr   c                     t                               d|           | j                            dd          }t                               d|| j                                                   |S )a  Atomically pop a job from the queue.

        Parameters
        ----------
        worker_id : int
            The worker that requested the job.

        Returns
        -------
        iterable of list of (int, float)
            The corpus in BoW format.

        zworker #%i requesting a new jobT   blocktimeoutz"worker #%i got a new job (%i left))r#   r$   r   getqsize)r   	worker_idjobs      r   getjobzDispatcher.getjob   sX     	5yAAAimm$m228)TY__EVEVWWW
r   c                     | xj         dz  c_         | j                            |dt                     t                              d| j                                                   dS )zAtomically add a job to the queue.

        Parameters
        ----------
        job : iterable of list of (int, float)
            The corpus in BoW format.

        r:   Tr;   z%added a new job (len(queue)=%i items)N)r   r   putHUGE_TIMEOUTr#   r$   r?   )r   rA   s     r   putjobzDispatcher.putjob   sY     	a	c|<<<;TY__=N=NOOOOOr   c                 "   t                               d           t                               d| j        | j                   d}d}| j        | j        k     rt          j        d           |dz  }||k    rPd}| j                                        D ]4\  }}t                               d|           |	                                 5| j        | j        k     t                               dt          | j                             t          | j                                                  }|d                                         }|dd	         D ])}|                    |                                           *t                               d
           |S )zMerge states from across all workers and return the result.

        Returns
        -------
        :class:`~gensim.models.ldamodel.LdaState`
            Merged resultant state

        z*end of input, assigning all remaining jobsz jobs done: %s, jobs received: %sr   r   g      ?r:   z checking aliveness for worker %szmerging states from %i workersNzsending out merged state)r#   r$   debugr   r   timesleepr   r!   pingr"   r   r6   getstatemerge)r   icountr0   r/   r   results          r   rL   zDispatcher.getstate   so    	@AAA7I[\\\nt11 	"JsOOOFA5y "(,(:(:(<(< " "$HfKK BHMMMKKMMMM nt11 	" 	4c$,6G6GHHHt|**,,--$$&&abbk 	, 	,FLL**++++.///r   c                     | j                                         D ]I\  }}t                              d|           |                    |           |                                 Jd| _        d| _        dS )zReinitialize all workers for a new EM iteration.

        Parameters
        ----------
        state : :class:`~gensim.models.ldamodel.LdaState`
            State of :class:`~gensim.models.lda.LdaModel`.

        zresetting worker %sr   N)r   r!   r#   r$   reset
requestjobr   r   )r   stater0   r/   s       r   rR   zDispatcher.reset   sw     !% 2 2 4 4 	  	 HfKK-x888LLr   r   c                     | xj         dz  c_         t                              d|| j                    | j        |                                          dS )a  A worker has finished its job. Log this event and then asynchronously transfer control back to the worker.

        Callback used by workers to notify when their job is done.

        The job done event is logged and then control is asynchronously transfered back to the worker
        (who can then request another job). In this way, control flow basically oscillates between
        :meth:`gensim.models.lda_dispatcher.Dispatcher.jobdone` and :meth:`gensim.models.lda_worker.Worker.requestjob`.

        Parameters
        ----------
        workerid : int
            The ID of the worker that finished the job (used for logging).

        r:   zworker #%s finished job #%iN)r   r#   r$   r   rS   )r   r0   s     r   jobdonezDispatcher.jobdone   sL    $ 	!18T^LLLX))+++++r   c                     | j         S )zWrap :attr:`~gensim.models.lda_dispatcher.Dispatcher._jobsdone` needed for remote access through proxies.

        Returns
        -------
        int
            Number of jobs already completed.

        )r   r7   s    r   jobsdonezDispatcher.jobsdone  s     ~r   c                     | j                                         D ]4\  }}t                              d|           |                                 5t                              d           t          j        d           dS )z9Terminate all registered workers and then the dispatcher.zterminating worker %szterminating dispatcherr   N)r   r!   r#   r$   exitos_exit)r   r0   r/   s      r   rZ   zDispatcher.exit  sn     !% 2 2 4 4 	 	HfKK/:::KKMMMM,---
r   )__name__
__module____qualname____doc__MAX_JOBS_QUEUEr   r   exposer%   r8   rB   rF   rL   rR   onewayr   synchronousrV   rX   rZ   r   r   r   r   r   Z   s^          .t > > > >( \#h #h \#hJ \	E 	E \	E \  \& \P P \P \  \> \  \  \
\U}%%, , &% \ \,&	 	 	 \  \  r   r   c            	         t          j        t          d d         t           j                  } |                     ddt
          t                     |                     ddd            |                     d	d
d t
                     |                     ddddd           |                     ddd            |                     dddddt          j        t          j	                   | 
                                }t          j        d|j                   t                              dd                    t           j                             |j        |j        |j        |j        d}t-          j        t0          t3          |j        |          |           t                              d d                    t           j                             d S )!Niy)descriptionformatter_classz	--maxsizez^How many jobs (=chunks of N documents) to keep 'pre-fetched' in a queue (default: %(default)s))helptypedefaultz--hostz*Nameserver hostname (default: %(default)s))rh   rj   z--portz&Nameserver port (default: %(default)s))rh   rj   ri   z--no-broadcastz(Disable broadcast (default: %(default)s)store_constTF)rh   actionrj   constz--hmacz*Nameserver hmac key (default: %(default)s)z-vz	--verbosezVerbose flagloglevel)rh   rl   destrm   rj   z)%(asctime)s : %(levelname)s : %(message)s)formatlevelz
running %s )	broadcasthostporthmac_key)r
   r   )r   zfinished running %s)argparseArgumentParserr`   RawTextHelpFormatteradd_argumentintra   loggingINFOWARNING
parse_argsbasicConfigrn   r#   r$   joinsysargvno_broadcastrt   ru   hmacr   pyro_daemonr    r   r
   )parserargsr   s      r   mainr   '  s   $$QYQnoooF
m.    
 'S]abbb
'OY]dghhh
(/Y,d%  I I I
'S]abbb
k:W\7?    
 DJRVR_````
KKchhsx00111 &		I	 G 
+ZV]-^-^-^hopppp
KK%sxx'9'9:::::r   __main__)r`   rw   r[   r   r|   r   rI   queuer   r   gensimr   gensim.models.lda_workerr   	getLoggerr#   ra   rE   r    r   r   r]   r   r   r   <module>r      s  2 2h  				 



                    6 6 6 6 6 6 
	9	:	: 
 "/ J J J J J J J JZ; ; ;@ z DFFFFF r   