ГhSrSSKrSSKrSSKrSSKJrJr SSKJrJ r J r SSK J r J r JrJr S\S\4S jr"S S 5rg) zTracker for XGBoost collective.N)IntEnumunique)DictOptionalUnion)_LIB _check_call_deprecate_positional_args make_jcargsaddrreturnc<[R"US5SS$)z Get network family from address.Nr)socket getaddrinfo)r s bC:\Users\julio\OneDrive\Documentos\Trabajo\Ideas Frescas\venv\Lib\site-packages\xgboost/tracker.py get_familyr s   dD )! ,Q //c\rSrSrSr\"SS\55r\SSSS.S\ S \ \ S \ S \ S \ S S4 Sjjj5r SSjr SSjrSSjrSS \ \ S S4SjjrS \\ \\ \ 444SjrSrg) RabitTrackeraTracker for the collective used in XGBoost, acting as a coordinator between workers. Parameters ---------- n_workers: The total number of workers in the communication group. host_ip: The IP address of the tracker node. XGBoost can try to guess one by probing with sockets. But it's best to explicitly pass an address. port: The port this tracker should listen to. XGBoost can query an available port from the OS, this configuration is useful for restricted network environments. sortby: How to sort the workers for rank assignment. The default is host, but users can set the `DMLC_TASK_ID` via arguments of :py:meth:`~xgboost.collective.init` and obtain deterministic rank assignment through sorting by task name. Available options are: - host - task timeout : Timeout for constructing (bootstrap) and shutting down the communication group, doesn't apply to communication when the group is up and running. The timeout value should take the time of data loading and pre-processing into account, due to potential lazy execution. By default the Tracker doesn't have any timeout to avoid pre-mature aborting. The :py:meth:`.wait_for` method has a different timeout parameter that can stop the tracker even if the tracker is still being used. A value error is raised when timeout is reached. Examples -------- .. code-block:: python from xgboost.tracker import RabitTracker from xgboost import collective as coll tracker = RabitTracker(host_ip="127.0.0.1", n_workers=2) tracker.start() with coll.CommunicatorContext(**tracker.worker_args()): ret = coll.broadcast("msg", 0) assert str(ret) == "msg" c\rSrSrSrSrSrg)RabitTracker._SortByNrrN)__name__ __module__ __qualname____firstlineno__HOSTTASK__static_attributes__rrr_SortByrNs rr#rhost)sortbytimeout n_workershost_ipportr%r&rNc n[R"5nUS;a [S5eUb [U5 [ UUUSUS:XaUR R OUR R[U5S9n[[R"U[R"U555 X`l g)N)r$taskz-Expecting either 'host' or 'task' for sortby.rabitr$)r$r'r)dmlc_communicatorr%r&)ctypesc_void_p ValueErrorrr r#r r!intr r XGTrackerCreatebyrefhandle)selfr'r(r)r%r&r4argss r__init__RabitTracker.__init__Ss" ) )LM M   w %(.&(84<<$$dll>O>OL   D((v||F/CDE rc[US5(a.URnU?[[R"U55 gg)zInternal function for testing.r4N)hasattrr4r r XGTrackerFree)r5r4s rfreeRabitTracker.freens5 4 " "[[F **62 3 #rc$UR5 gN)r<r5s r__del__RabitTracker.__del__us  rch[[R"UR[ 555 g)zStart the tracker. Once started, the client still need to call the :py:meth:`wait_for` method in order to wait for it to finish (think of it as a thread). N)r r XGTrackerRunr4r r@s rstartRabitTracker.startxs D%%dkk;=ABrc f[[R"UR[ US955 g)zWait for the tracker to finish all the work and shutdown. When timeout is reached, a value error is raised. By default we don't have timeout since we don't know how long it takes for the model to finish training. )r&N)r r XGTrackerWaitForr4r )r5r&s rwait_forRabitTracker.wait_fors" D))$++{77STUrc [R"5n[[R"UR [R "U555 URce[R"UR5nU$)zGet arguments for workers.) r.c_char_pr r XGTrackerWorkerArgsr4r3valuejsonloads)r5c_envenvs r worker_argsRabitTracker.worker_argssW!D,,T[[&,,u:MNO{{&&&jj% r)r4)r)rNr?)rrrr__doc__rrr#r r1rstrr7r<rArErIrrrSr"rrrrrs:x '    #     44CV VVT#uS#X"67rr)rUr.rOrenumrrtypingrrrcorer r r r rVr1rrrrrrZs?% ((LL0S0S0 }}r