^i2H UdZddlZddlmZddlmZddlmZmZddl m Z ddl m Z m Z mZmZmZmZmZmZmZmZmZmZmZmZmZmZmZddlZddlZddlZddlm Z!dd lm"Z#dd lm$Z%dd l&m'Z'dd lm(Z(d dl)m*Z*m+Z+d dl,m-Z-d dl.m/Z/m0Z0m1Z1d dl2m3Z3d dl*m4Z5d dl*m6Z7d dl*m8Z9d dl:m;Z;d dlZ>m?Z?m@Z@mAZAmBZBmCZCmDZDd dlEmFZFmGZGd dlHmIZImJZJmKZKmLZLmMZMmNZNmOZOmPZPmQZQmRZRmSZSmTZTd dlUmVZVd dlWmXZYddlEmZZZm[Z[ddl\m]Z]m^Z^m_Z_m`Z`ee!je%je%jfZdeeed<ee!je%jfZfeeed<ed e=ed!Zggd"Zhejd#Zjd$ekd%eeeeleeelekffd&eekd'e7fd(Zmd$ekd)eeld*eeelekfd&eekd'e7f d+ZnGd,d-e*jZod.ed/d'd/fd0ZpGd1d2Zqed3Zred4Zsd.ed/d5eeserfd6e d7eeld'erf d8ZtGd9d:eqZu dd.d/d$ekd;eeele fdZwd?eqd@eeeeqelfd'eelfdAZxd7eeld.d/d'dfdBZyd.d/dCeele fd;eeele fdDeele fd?eqdEekd@eeeeqelfdFee@dGeekdHeekezfdIee=dJeee3dKee?d` for simple tutorial. Also :doc:`/python/dask-examples/index` for some examples. There are two sets of APIs in this module, one is the functional API including ``train`` and ``predict`` methods. Another is stateful Scikit-Learner wrapper inherited from single-node Scikit-Learn interface. The implementation is heavily influenced by dask_xgboost: https://github.com/dask/dask-xgboost Optional dask configuration =========================== - **coll_cfg**: Specify the scheduler address along with communicator configurations. This can be used as a replacement of the existing global Dask configuration `xgboost.scheduler_address` (see below). See :ref:`tracker-ip` for more info. The `tracker_host_ip` should specify the IP address of the Dask scheduler node. .. versionadded:: 3.0.0 .. code-block:: python from xgboost import dask as dxgb from xgboost.collective import Config coll_cfg = Config( retry=1, timeout=20, tracker_host_ip="10.23.170.98", tracker_port=0 ) clf = dxgb.DaskXGBClassifier(coll_cfg=coll_cfg) # or dxgb.train(client, {}, Xy, num_boost_round=10, coll_cfg=coll_cfg) - **xgboost.scheduler_address**: Specify the scheduler address .. versionadded:: 1.6.0 .. deprecated:: 3.0.0 .. code-block:: python dask.config.set({"xgboost.scheduler_address": "192.0.0.100"}) # We can also specify the port. dask.config.set({"xgboost.scheduler_address": "192.0.0.100:12345"}) N) defaultdict)contextmanager)partialupdate_wrapper)Thread)Any AwaitableCallableDict GeneratorIterableListOptional ParamSpecSequenceSetTuple TypeAlias TypedDict TypeGuardTypeVarUnion)array)bag) dataframe)Delayed)Future) collectiveconfig) Categories) FeatureNames FeatureTypesIterationRange)TrainingCallback)Config)_Args)_ArgVals) _is_cudf_df)BoosterDMatrixMetric Objective XGBoostError_check_distributed_params_deprecate_positional_args_expect) _is_cudf_ser_is_cupy_alike) XGBClassifierXGBClassifierBaseXGBModel XGBRankerXGBRankerMixInXGBRegressorBase _can_use_qdm_check_rf_callback_cls_predict_proba_objective_decorator_wrap_evaluation_matricesxgboost_model_doc) RabitTracker)train)_get_dmatricesno_group_split)_DASK_2024_12_1_DASK_2025_3_0get_address_from_user get_n_threads_DaskCollection_DataT TrainReturnTboosterhistory) CommunicatorContext DaskDMatrixDaskQuantileDMatrixDaskXGBRegressorDaskXGBClassifier DaskXGBRankerDaskXGBRFRegressorDaskXGBRFClassifierrApredictinplace_predictz[xgboost.dask] n_workersaddrstimeoutreturnc ji} t|dtr%|dd}|dd}t|||d|dn|}n,|d}t|ts|Jt||d|dn|}|j t |j }d|_|j |j|j|S#t$rc} t|dkrtjd t|dt|dt| t||dd|}Yd} ~ |Sd} ~ wwxYw) NrrBtask)rYhost_ipportsortbyr[)rYr_rar[)targetTrzCFailed to bind address '%s', trying to use '%s' instead. Error: %s) isinstancetupler@strstartrwait_fordaemonupdate worker_argsr.lenLOGGERwarning_try_start_tracker) rYrZr[envr_r` rabit_trackeraddrthreades V/var/www/html/hubwallet-dev/venv/lib/python3.12/site-packages/xgboost/dask/__init__.pyrnrnsD C%@ eAh &AhqkG8A;D(#$_' M8DdC(DL 88(#$_' M }556   =,,./ J  @ u:>  R aM aM F  !E!"Iw? J @sCC D2AD--D2addr_from_daskaddr_from_userc$t|||g|}|S)z8Start Rabit tracker, recurse to try different addresses.)rn)rYrurvr[ros rt_start_trackerrxs Y(H' RC Jc,eZdZdZdeddffd ZxZS)rOzNA context controlling collective communicator initialization and finalization.argsr\Nc t|di|tj}d|jd|j |j d<y)Nz[xgboost.dask-z]: DMLC_TASK_ID)super__init__ distributed get_workernameaddressr{)selfr{worker __class__s rtrzCommunicatorContext.__init__sG  4 '') '5V[[MFNNCS$T .!ry)__name__ __module__ __qualname____doc__ CollArgsValsr __classcell__rs@rtrOrOs"XU|UUUryrOclientdistributed.Clientc&t|ttjtdfsDt t ttjtdgt||tj}|S|}|S)z#Simple wrapper around testing None.N)rctyper get_client TypeErrorr1)rrets rt _get_clientrs{ ftK$:$:$<=tDzJ K T+0023T$Z@$v, O  '-n+ "C J;AC Jryc#neZdZdZe dddddddddddddd deddedeed eed eed eed e d ee dee deedeedeedeedeede ddf dZ de dfdZdddddddddddedeedeed eedeedeedeedeeddfdZdedeeeffdZdefdZy) rPaqDMatrix holding on references to Dask DataFrame or Dask Array. Constructing a `DaskDMatrix` forces all lazy computation to be carried out. Wait for the input data explicitly if you want to see actual computation of constructing `DaskDMatrix`. See doc for :py:obj:`xgboost.DMatrix` constructor for other parameters. DaskDMatrix accepts only dask collection. .. note:: `DaskDMatrix` does not repartition or move data between workers. It's the caller's responsibility to balance the data. .. note:: For aligning partitions with ranking query groups, use the :py:class:`DaskXGBRanker` and its ``allow_group_split`` option. .. versionadded:: 1.0.0 Parameters ---------- client : Specify the dask client used for training. Use default client returned from dask if it's set to None. NF) weight base_marginmissingsilent feature_names feature_typesgroupqidlabel_lower_boundlabel_upper_boundfeature_weightsenable_categoricalrrdatalabelrrrrrrrrrrrrr\c t|}||_| |_t| tr t d||nt j|_||_ | | td| tdt|jdk7rtd|jt|tjt j"fst3D!&[[  #+//!   ry)NNrPc6|jjSN)r __await__rs rtrzDaskDMatrix.__await__fszz##%%ry)rrrrrrrrc  !Kdttdtdttdtdtf ddtdttffd !d t tdt ttf!fd } !|| |} | |} | |} | |}| |}| | }d i d t ttd tddf fd }|| d|| d|| d||d||d||dg}t tD]5}i} jD] \}}||||<|j|7tttj|}j|}tj |d{|D]"}|j"dk(rJ|j"i|_t'|D]\}}||j$|j(< |Dcic]}|j(|}}j*j-|Dcgc]}|j(c}d{}t/t}|jD].\}}|t1t3|j||0||_| d|_|Sj|j9d{|_|S7Ecc}wcc}w77w)z Obtain references to local data.left left_nameright right_namer\c Hd|d|dt|dt|d }|S)NzPartitions between z and z are not consistent: z != z/. Please try to repartition/rechunk your data.rk)rrrrmsgs rt inconsistentz1DaskDMatrix._map_local_data..inconsistentxsA&i[j\B"4ykc%j\:?@  Jrydcj|}t|jdrIt|jjdkDr'|jjddkDr t dj |S)zBreaking data into partitions.rrBzData should be partitioned by row. To avoid this specify the number of columns for your dask Array explicitly. e.g. chunks=(partition_size, -1]))persisthasattr partitionsrkrr futures_of)rrs rt to_futuresz/DaskDMatrix._map_local_data..to_futuressrq!A g. **+a/LL&&q)A- 4 $$Q' 'rymetac| |}|Syrr~)r meta_partsrs rt flatten_metaz1DaskDMatrix._map_local_data..flatten_metas+5d+; !!ryrm_partsrNcd|-tt|k(sJd||||<yy)NXr)rrX_partsrpartss rt append_metaz0DaskDMatrix._map_local_data..append_metasF"7|s7|3\S'463&d #ryrrrrrrfinished)keys)rrrerIrrrangerkitemsappendrmapdaskdelayedcomputerwaitstatuspartition_order enumeratekey schedulerwho_hasrnextiterrrresult)"rrrrrrrrrrry_partsw_parts margin_parts qid_partsll_partslu_partsr packed_partsi part_dictrvalue delayed_parts fut_partspartkey_to_partitionrrworkersrrrrs" ` @@@@rtrzDaskDMatrix._map_local_datais s) (+ 48I KN    (/ (d6l (  x8 Xd6l=S  T"u%w'#K0  %  12 12*0'): &$v,!7 &s &t & GW%GX&L-0Iu%H12H12 13 s7|$ +A+-I#kkm * U!&q # *    *  +(,C l,K'L #).."? y))) :D;;*, 9dkk 9, : " + /GAt-.D  * /8AAtDHHdNAA4:4D4D4L4L'01t$((15M5 / /:$.? #MMO JLC tDM* + 2 23CC3H I J%  "#'D  *0)H)O)O)Q#QD  9 *B1/ $RsVF!K>(K-)K>A K> K0K>:K5 K>K:BK>!K<" K>0 K><K> worker_addrc |j|j|j|j|j|j j |d|jdS)z\Create a dictionary of objects that can be pickled for function arguments. N)rrrrrrr)rrrrrrgetr)rrs rt_create_fn_argszDaskDMatrix._create_fn_argssV "//!//#33||"&"9"9__((d;++  ryc|jS)zxGet the number of columns (features) in the DMatrix. Returns ------- number of columns )rrs rtnum_colzDaskDMatrix.num_cols||ryr)rrrrr0rrJrIfloatboolr"r#rr rrrer rrrrr~ryrtrPrP s6 ,0 = -115#'0404+/)-7;7;59#(#= -.= = ( = ) = o.= %= =  -=  -= (= o &= $O4= $O4= "/2!= "!#= $ %=  = ~&9%>?&,0-115)-597;7;x%x x ( x /* xo.xo &x"/2x$O4x$O4x xt  3  4S>  ryrP_MapRetT_Pfuncrefsrc Kt|}g}|D]}g}|D]D}t|tr!|j|j |4|j|Fdt dt jdt jdttffd }|jtt|||g|d|gdd} |j| d tttdttfd } t!j"|} | j%| | d {} |j'| j)d {} | S7-7w) z.Map a function onto partitions of each worker._addressr{kwargsr\ctj}|j|k7rtd|jd|d|i|gS)NzInvalid worker address: z , expecting zz. This is likely caused by one of the workers died and Dask re-scheduled a different one. Resilience is not yet supported.)rrrr)rr{rrrs rtfnz!map_worker_partitions..fns^ ++-F~~) .v~~.>l8*UUU $)&)* *ryFT)purerallow_other_workersresultsc|D]}||cSyrr~)r vs rt first_validz*map_worker_partitions..first_valid:s  A} ryN)rrcrPrrrerr{rrrsubmitrrr rdb from_delayed reductionrr) rrrrfuturesrqr{refr futrrrs ` rtmap_worker_partitionsrsO FG- !C#{+ C//56 C  ! + +RWW + +d8n +:fmm 72t,b 1  F $   s[-^Xhx&89hx>P //' "C k;7 7C>>#&--/ /F M 8 /s$D&E)E*&EEEEc)(eZdZdZe ddddddddddddddddddeddedeed eed eed eed e d ee dee e e e fdeedeedeedeedeedeedeede deeddf&fdZdedeee fffd ZxZS)rQzmA dask version of :py:class:`QuantileDMatrix`. See :py:class:`DaskDMatrix` for parameter documents. NF)rrrrrrmax_binrrrrrrrmax_quantile_batchesrrrrrrrrrrrrrrrrrrrr\ct||||||| | ||||||| || |_||_d|_| t | |_yd|_y)N)rrrrrrrrrrrrrrrT)rrrrrid_ref)rrrrrrrrrrrrrrrrrrrrs rtrzDaskQuantileDMatrix.__init__Msr. #//+''1  " $8!.1o2c7 4 ryrct||}|j|d<|j|d<|j|j|d<|S)Nrrr)rrrrr)rrr{rs rtrz#DaskQuantileDMatrix._create_fn_argszsLw&{3,,Y'+'@'@ #$ 99 ))DK ryr)rrrrr0rrJrIrrr"rrrrrPrrer rrrs@rtrQrQGs  ,0 *H -115#'049=!%%)+/)-7;7;59#(.2)*H-.*H*H( *H ) *Ho.*H%*H*H -*H c49n 56*H#*Hk "*H(*Ho &*H $O4!*H"$O4#*H$"/2%*H&!'*H('sm)*H* +*H *HX34S>ryrQdconfigcoll_cfgcK| tn|}d}d}t||\}}|||f}nd} tjj |j j }|jd}|jt||||jd{}|j|}|J|S#t$rd}YOwxYw7,w)zBGet rabit context arguments from data distribution in DaskDMatrix.Nrz/:) CollConfigrGrcommget_address_hostrrstrip Exceptionrun_on_schedulerrxtracker_timeoutget_comm_config) rrYr r!r_r` user_addr sched_addrros rt_get_rabit_argsr-s (/z|XH!GD)'8.do_trains6'') oo' !+v6 yIFG35 i34 -9 - v/D/D/U}/U &  "%# IB#" /*"5zQeD+&;)## G  8 ::<1 "(+C  C G    s$&C3<=C'9C3'C0 ,C33C<r)r8r?r-rkr/r rerrrdictrrKr MultiLockrr)rr@r rAr2rBr3rCrDrErFrGrHr!rrKr]rn evals_datarMrNrs ` ` `````` rt _train_asyncrbs"%VU3G "7F 333%G gIf%44U38_,-44I 4 s) 4  44 , 44l$$Wf5  (-.1!.J.(-.1!.J.'12!12H2JJH,     vJ    h#     /}4z..2  sFE'FE*BFE-F F( E/4F< E5FE;!.FFF F!F"F*F-F/FFF F FFT)r3rCrDrFrErGrHr!ct|}|jtftjt dt S)aTrain XGBoost model. .. versionadded:: 1.0.0 .. note:: Other parameters are the same as :py:func:`xgboost.train` except for `evals_result`, which is returned as part of function return value instead of argument. Parameters ---------- client : Specify the dask client used for training. Use default client returned from dask if it's set to None. coll_cfg : Configuration for the communicator used during training. See :py:class:`~xgboost.collective.Config`. Returns ------- results: dict A dictionary containing trained booster and evaluation history. `history` field is the same as `eval_result` from `xgboost.train`. .. code-block:: python {'booster': xgboost.Booster, 'history': {'train': {'logloss': ['0.48253', '0.35953']}, 'eval': {'logloss': ['0.480385', '0.357756']}}} )r@r )rrrbr get_configr1locals) rrAr2rBr3rCrDrFrErGrHr!s rtrArA:sHb F 6;; '') "  (  ryis_df output_shapec&|xrt|dkSNrr)rfrgs rt_can_output_dfrjts  +S&!++ryr predictioncolumnsct||jrt|dd}t|rZddl}|j dk(r"|j i|tjS|j ||tj|}|Sddl }|j dk(r#|j i|tj|S|j ||tj|}|S)z0Return dataframe for prediction when applicable.indexNr)rldtype)rlrorn) rjrgetattrr)cudfsizerrfloat32pandas)rrkrlrfrnrqpds rt_maybe_dataframervxseZ--. gt, t  !#~~b'~OOG5==(J  !#||u}}E$G5==&J rymapped_predictrMzdistributed.Futurer.rc XKt|j}t|dk\r%t|tj r t dtt|tj |r|+t|tjr|j}n|}t j|||d||tjj|}t|dk(r|jdddf}|S|;t|tjtj fr|j!} n|} t|dk(rdg} g} ndg} t|tj r!t#t%t|dz } n't%t|dz D cgc]} | dz } } t|dk(r1t#|j&} t| t"sJ|df| d<nd} tj(|||d|| | | | t*j, }|Scc} ww) NzGUse `da.Array` or `DaskDMatrix` when output has more than 2 dimensions.T)rrBrrF)chunks drop_axisnew_axisro)rdrrkrcrrrrjrrto_dask_dataframemap_partitionsutils make_metailocr to_dask_arrayrrrz map_blocksrrs)rwrMrrrgrrlbase_margin_df predictionsbase_margin_arrayr{r|rrzs rt_direct_predict_implrsDIIK G <A*T2<<"@  U  jr||4lC  "z+rxx'H--/ )N''      ##D)  |  !%**1a40KX U  "z "))R\\2( 5@4M4M4O  +  |  !01sI.0HI$ -c,&7!&; <=+0\1BQ1F+GHaAEHH |  !-1,=Ffd+ ++%a*F1IFmm      --   3IsF%H*' H%3A7H*featuresinplacerc t|tsJtjj d}|j d|}|r)|j }|jddk(rd|d<t|d}|j|fdd i|}t|jdkDr|jdnd} i} t||jrt| D]} d | | < |j| fS) z@Create a dummy test sample to infer output shape for prediction.irB predict_typemarginT output_margin)rvalidate_featuresFf4)rcrrrandom RandomStaterandnrVpopr+rWrkrrjr) rMrrfrrrng test_samplem test_predt n_columnsrrs rt_infer_predict_outputrs h $$ $ ,, " "4 (C))Ax(K ::n % 1&*F? # 5A FeFvFJ'*:+;+;'CCrr pred_leaf pred_contribsapprox_contribspred_interactionsriteration_range strict_shapec  ()Kt||d{} t|ttjt j fsAttttjt j gt|dtdtdtdttdtdtf    f d }t|tjt j frx|j|j!t"| |j$dt|t j d  d{\}}t'|| |d|| d{S|j|j!t"| |j)d d  d{\}}|j*}|j,(|j.)|j0dtd t2t4tfdt6j8f()   f d }g}g}g}g}t;|j<j?}|D]l}|j<|}|jA||jAtC||gz|jA|Dcgc]}||jDc}ntG||D],\}}|j!d||g}|jI|.t;tG||||}tK|d}|D !cgc] \}} }!}| }}!} }}|D !cgc] \}} }!}|  }}!} }}|D !cgc] \}} }!}| }}!} }}g}"tG||D],\}}|j!|| ||g}#|"jI|#.g}$|jM|d{}tO|D]D\}%}&|$jItjP|"|%|&f|ddzt6jRFtjT|$d}'|'S7777cc}wcc}}!} }wcc}}!} }wcc}}!} }w7w)NrM partitionrfrl_r\c  tjdi5t| d}|j|     }t ||||}|cdddS#1swYyxYw)NT)rrr) rrrrrrrrrr~)r rWr+rWrv)rMrrfrlrrpredtrr@rrrrrrrrs rtrwz&_predict_async..mapped_predict0s " " 3] 3 #'A OO+#+ /"3"3 /)$ E%YwFE%   s 8AA"rBF) rrfrrrrrrrrwrMrrrgr) rMrrfrrrrrrrrc  |d}|jdd}tjdi 5t| |d}|j |    }|cdddS#1swYyxYw)NrrT)rrrrr)rrrrrrrrr~)rr rWr+rW)rMrrrrrrrrr@rrrrrrrrs rtdispatched_predictz*_predict_async..dispatched_predictvsF|hh}d3  " " 3] 3 '++#' AOO+#+ /"3"3 /)$ E)   s -A%%A.c&|djdS)Nrr)r)rs rtz _predict_async..stF|'9'9!'<ry)rc |dSrir~)ps rtrz _predict_async..s adry)r)rroraxis)+rrcrPrrrrrr1rr*rrrrrrrrrrrrrrr rerndarrayrrrextendrkrziprsortedgatherrrrs concatenate)*rr@rTrrrrrrrrrr_boosterrw _output_shaperrgrrr all_parts all_orders all_shapes all_workersworkers_addressr list_of_partsrwsparts_with_orderrorderrfarraysrrowsrrrs* ` ````````` @@rt_predict_asyncrs) 'vu55H d["((BLLA Bbhh EtDzRSS%(15@DS NQ 0$2<<01$*NN MM%A r||4+#+ /"3)  %   t*)&    #NN !\\^''+/%  OL! **O&&M&&MllGG4S>emm2IJJK4??//12O&Q  4 '3}- =>O?4884OP Q {I.4 MMQ QQ &AQ>Q?A0Q1Q4Q7Q:QF)rr) rrrrrrrrrc ~t|}|jtfdtjit S)aRun prediction with a trained booster. .. note:: Using ``inplace_predict`` might be faster when some features are not needed. See :py:meth:`xgboost.Booster.predict` for details on various parameters. When output has more than 2 dimensions (shap value, leaf with strict_shape), input should be ``da.Array`` or ``DaskDMatrix``. .. versionadded:: 1.0.0 Parameters ---------- client: Specify the dask client used for training. Use default client returned from dask if it's set to None. model: The trained model. It can be a distributed.Future so user can pre-scatter it onto all workers. data: Input data used for prediction. When input is a dataframe object, prediction output is a series. missing: Used when input data is not DaskDMatrix. Specify the value considered as missing. Returns ------- prediction: dask.array.Array/dask.dataframe.Series When input data is ``dask.array.Array`` or ``DaskDMatrix``, the return value is an array, when input data is ``dask.dataframe.DataFrame``, return value can be ``dask.dataframe.Series``, ``dask.dataframe.DataFrame``, depending on the output shape. r@)rrrr rdre) rrTrrrrrrrrrrs rtrWrWs5f F 6;;~ UV5F5F5H UFH UUryrc  Kt|}t||d{} t|tjt j fs.mapped_predictsm " " 3] 3  00 /)'"3)1J &iWeL   s AArBT)rrfrrrrr)rrrcrrrrrr1rrr*rrrrrrrrr)rr@rTrrrrrrrrMrwrrs ` ```` ` rt_inplace_predict_asyncrs F%fe44G dRXXr||4 52<< 8$t*EFFz rxxryy1(2<< CT+EVWXXc    * ! ZZ]T2<<0%+%    KE4&%    S5:  s4GF?E:GGG:G;GGGr)rrrrrrc~t|}|jtfdtjit S)aInplace prediction. See doc in :py:meth:`xgboost.Booster.inplace_predict` for details. .. versionadded:: 1.1.0 Parameters ---------- client: Specify the dask client used for training. Use default client returned from dask if it's set to None. model: See :py:func:`xgboost.dask.predict` for details. data : dask collection. iteration_range: See :py:meth:`xgboost.Booster.predict` for details. predict_type: See :py:meth:`xgboost.Booster.inplace_predict` for details. missing: Value in the input data which needs to be present as a missing value. If None, defaults to np.nan. base_margin: See :py:obj:`xgboost.DMatrix` for details. .. versionadded:: 1.4.0 strict_shape: See :py:meth:`xgboost.Booster.predict` for details. .. versionadded:: 1.4.0 Returns ------- prediction : When input data is ``dask.array.Array``, the return value is an array, when input data is ``dask.dataframe.DataFrame``, return value can be ``dask.dataframe.Series``, ``dask.dataframe.DataFrame``, depending on the output shape. r@)rrrr rdre) rrTrrrrrrrs rtrXrX.sBj F 6;; .4.?.?.A EKX rydevice tree_methodrc,Kdttdtdtffd }td d|i|\}}|d{}|||fSg}|D]<} | d|ur|j | |j | dd{| df>||fS7Q7w) z(A switch function for async environment.rrr\cTtrtd|d|Stddi|S)N)rrrrr~)r:rQrP)rrrrrrs rt _dispatchz2_async_wrap_evaluation_matrices.._dispatchusC  V ,&3;A 3&3F33rycreate_dmatrixNrrBr~)rrPrr>r) rrrrrr train_dmatrixr3awaitedrss ```` rt_async_wrap_evaluation_matricesrls4x ,44 445XIXQWXM5''M }e##G + Q4= NN1  ad AaD)* + ' !!(#s!8BB=B<B =BBDaskScikitLearnBasec#JK ||_|d|_y#d|_wxYww)z-Temporarily set the client for sklearn model.N)r)rTrs rt_set_worker_clientrs%    t s# # #cTeZdZdZdZdddeededdffdZde d e d e d ee d ee def d Z edddddde d e d e d ee d ee def dZ dde d ee defdZ dde d ee defdZdeefdZdefdZeddZej0ddZdededefdZxZS)rz._s Ks)r r _client_syncr)rrs` rtrzDaskScikitLearnBase.__await__s/ 3   #--//rycH|jj}d|vr|d=|S)N_client)__dict__rV)rthiss rt __getstate__z DaskScikitLearnBase.__getstate__s(}}!!#  Y ryc0t|j}|S)zThe dask client used in this model. The `Client` object can not be serialized for transmission, so if task is launched from a worker instead of directly from the client process, this attribute needs to be set at that worker. )rr)rrs rtrzDaskScikitLearnBase.clientsT\\* ryc<| |jnd|_||_y)NF) asynchronous _asynchronousr)rclts rtrzDaskScikitLearnBase.client s25S--e ryrc |j}t|dd} tjd}|rWtj 5}t ||5}|jj|fi|d|i}|cdddcdddS|jj|fi|d|jjiS#t$rd}YwxYw#1swYnxYwcdddS#1swYfxYw)zGet the correct client, when method is invoked inside a worker we should use `worker_client' instead of default client. NrFTr) rrprrr worker_clientrrrr)rrrr in_workerrrrs rtrz DaskScikitLearnBase._client_syncs << "4%@L "&&(  ..0F+D&9#T.dkk.. $*9E # ## t{{VVT[[=U=UVV "!  "##  s5B? C'#C7 C'? C  C C C''C0r)r\r)rrr\N)rrrrrrr#rrrJrrIr$rr0rWrrr rr rpropertyrsetterr rrrs@rtrrsFG;?!HZ$8!3!SW! %% %  % o. %".1% %N $"&1548      o.  ".1     *59 ".1 059W W".1W W09S>0d  ]] WWSWSWryz3Implementation of the Scikit-Learn API for XGBoost. estimatorscReZdZdZdededeedeedeeeeefdeeedeeed e e e fd ee e e fd eed efd Zeddddddddddededeedeedeeeeefd ee e e fd ee e ee fdeeedeeed eed dfdZy)rRzAdummy doc string to workaround pylint, replaced by the decorator.ry sample_weightreval_setsample_weight_eval_setbase_margin_eval_setverboserFrr\c0K|j} |j| | | \} } } } tdid|jd|jd|j d|j d|d|ddddd |d |d | d |d |d|ddddd|jd|jd|jd{\}}t|jrt|j}nd}|jjtd|jtj t#| ||j%||| ||j&|j(|j*| d{}|d|_|j/|d|S77&w)Nrrrrrrrrrrrrrr eval_groupeval_qidrrrTrrr@r rAr2rBr3rCrHrErDrGr!rFrMrNr~)get_xgb_params_configure_fitrrrrrrrrcallable objectiver=rrbr rdr1get_num_boosting_roundsrDrGr!_Booster_set_evaluation_resultrrrrrrrrrrFrrArTmetricr2r3rCr s rt _fit_asynczDaskXGBRegressor._fit_async3s$$&151D1D v2 .vv> ;; ;; (( LL        ( $ ,  $: "6  ! "LL# $ $66% &,,'  , DNN #&:4>>&JCC (( ;; ++-$& 88:  "&"<"<nn]]!)  $ *  ##GI$67 ] 4 s%B4F6F7B6F-F.%FFNTrrrrrFrrrctjD cic] \} } | dvs | | } } } |j|jfi| Scc} } wNrrrerrrrrrrrrrrFrrrkrr{s rtfitzDaskXGBRegressor.fitwsR"(!1TAQ>S5S1TT t  9D99U AA)rrrrrJrIrrrrrrr*r6rr0rerr~ryrtrRrR-sLA A A  0 A o. A8E/?*J$KLMA!)/)B CA'x'@AAsDy!AE'8"345A"/2A AH 4815PT.2=AFJDH59: : :  0 : o. :8E/?*J$KLM:%T *+:E'3"89::!)/)B C:'x'@A:"/2: : :ryrRzBImplementation of the scikit-learn API for XGBoost classification.ceZdZdededeedeedeeeeefdeeedeeedee e fd eee e fd eed dfd Z d d d dd d d d ddededeedeedeeeeefdeee e fd eee ee fdeeedeeed eed dfdZdede deedeed ef fd Z ddede deedeed ef dZej&j*e_dede de deedeed ef fd ZxZS)rSrrrrrrrrrFrr\c.K|j} |j| | | \} } } } t|jfid|jd|j d|j d|d|ddddd|d |d | d |d |d |ddddd|jd|jd|jd{\}}t|tjr<|jjtj|d{|_n6|jj|j!d{|_t#|jr|jj%|_t'|jr|jj)|_t+j,|j|_t/|j|_|j0dkDrd| d<|j0| d<nd| d<t3|j4rt7|j4}nd}|jj9t:d|jt=j>tA| ||jC||| ||jD|jF|jH| d{}|d|_%t3|j4s | d|_|jM|d|S7V777Lw)Nrrrrrrrrrrrrrrrrrrrzmulti:softprobr  num_classzbinary:logisticTrrMrN)'rrrrrrrrrrrcrrruniqueclasses_drop_duplicatesr2to_cupyr3rrrrk n_classes_rr r=rrbr rdr1r rDrGr!r r r s rtrzDaskXGBClassifier._fit_asyncs$$&151D1D v2 .vv> KK ;; (( LL        ( $ ,  $: "6  ! "LL# $ $66% &,,'  . a ""&++"5"5biil"CCDM"&++"5"5a6G6G6I"JJDM  & MM113DM $-- ( MM--/DM DMM2 dmm, ??Q "2F; "&//F; "3F;  DNN #&:4>>&JCC (( ;; ++-$& 88:  "&"<"<nn]]!)  $ * '#K0DN ##GI$67 E 0DJ$ sKB2L4L 5ALL 6L>L?FLLAL LLLNTrctjD cic] \} } | dvs | | } } } |j|jfi| Scc} } wrrrs rtrzDaskXGBClassifier.fitsR"(!1TAQ>S5S1TT t  9D99UrrrcK|jdk(r tdt| |d|||d{}t t t jdt j}tt|dd||S7Ow) Nz multi:softmaxzSmulti:softmax doesn't support `predict_proba`. Switch to `multi:softproba` insteadF)rrrrrT)allow_unknown_chunksizesr r) r rrrrrrvstackr<rp)rrrrrrr$rs rt_predict_proba_asyncz&DaskXGBClassifier._predict_proba_asyncs >>_ ,6 w-/#+ .   BII =ryy "'$ a"@&&QQ s2BBABcB|j|j||||S)N)rrrr)rr%)rrrrrs rt predict_probazDaskXGBClassifier.predict_probas1   % %/#+ !  ryrrctKt ||||||d{}|r|St|jdk(r|dkDj t }|St|jdk(sJt |tjsJdtdtfd}tj||d}|S7w) NrrBg?rxr\c&|jdS)NrBr)argmax)r)s rt_argmaxz1DaskXGBClassifier._predict_async.._argmax>sxxQx''ry)r{) rrrkrastyperrcrrrr) rrrrrr pred_probspredsr,rs rtrz DaskXGBClassifier._predict_async#s!71 '/#+ 2     z A %#%--c2E z''(A- --j"((3 33 (3 (3 (MM':CE - sB8B6BB8)TNN)rrrrJrIrrrrrrr*r6rrerr$r%rr'r4rrrrs@rtrSrSs U U U  0 U o. U8E/?*J$KLMU!)/)B CU'x'@AUsDy!UE'8"345U"/2U Uz4815PT.2=AFJDH59: : :  0 : o. :8E/?*J$KLM:%T *+:E'3"89::!)/)B C:'x'@A:"/2: :"R R Ro. R ".1 R  R8#'1548       o.  ".1   *77??M    o. ".1 ryrSzZImplementation of the Scikit-Learn API for XGBoost Ranking. .. versionadded:: 1.4.0 aq allow_group_split : .. versionadded:: 3.0.0 Whether a query group can be split among multiple workers. When set to `False`, inputs must be Dask dataframes or series. If you have many small query groups, this can significantly increase the fragmentation of the data, and the internal DMatrix construction can take longer. zf .. note:: For the dask implementation, group is not supported, use qid instead. )extra_parametersend_notec 2eZdZedddddededeeded df fd Z d e effd Z d e d e dee dee dee deeee e fdeee deee deee deeefdeeeefdee d dfdZeddddddddddddd d e d e dee dee dee dee deeee e fdeee deee deeeefdeeeeefdeee deee dee d dfdZej*j.e_xZS)rTz rank:ndcgFN)r allow_group_splitr!r r3r!rr\c dt|r td||_t|d||d|y)Nz5Custom objective function not supported by XGBRanker.)r r!r~)rrr3rr)rr r3r!rrs rtrzDaskXGBRanker.__init__^s8 I TU U!2 J9xJ6JrycFt|}|jd|S)Nr3)r_wrapper_paramsaddrrArs rtr6zDaskXGBRanker._wrapper_paramsls"(* &' ryrrrrrrrrrrrFrc K|j} |j| | | \}}} } t|jfid|jd|j d|j d|d|ddd|d|d |d | d |d |d |ddd| d|jd|jd|jd{\}}|jjtd|jtjt| ||j|d|| |j |j"||j$d{}|d|_|d|_|S77w)NrrrrrrrrrrrrrrrrrrT)rrr@r rAr2rBr3rCrHrErDrGrFr!rMrN)rrrrrrrrrrrrbr rdr1r rDrGr!r  evals_result_)rrrrrrrrrrrrFrrArTrr2r3r s rtrzDaskXGBRanker._fit_asyncqs $$&151D1D v2 .vv> KK ;; (( LL        ( $ ,  $: "6  ! "LL# $ $66% &,,'  * (( ;; ++-$& 88:  "&"<"<nn]]!)  $ * $Y/ S * s%B2E4E5B E>E?EE) rrrrrrrrrFrrrrrc 2d}|| t|| tddtdttjfd}dt tdt dtt tjfd}|jso||r$||dr||d r||d r ||d sJ||Jt|}t|j||||| \}}}}}| g}g}g}g}| sJt|D]\}\}}| r| |nd}| r| |nd}||sJ| sJ| |}| r$||dr||d r||d r ||d sJ||Jt||k7r!t|j|||||\}}}}}n |||||f\}}}}}|j||f|j|||j|||j||}|} |r|nd} |r|nd} |j|j||||||| | | | | | S)Nz=Use the `qid` instead of the `group` with the dask interface.z`qid` is required for ranking.rr\cNt|tjs tdy)NzJWhen `allow_group_split` is set to False, X is required to be a dataframe.T)rcrrr)rs rtcheck_dfz#DaskXGBRanker.fit..check_dfs'a.$ryrrcZt|tjs|td|dy)Nz*When `allow_group_split` is set to False, z is required to be a series.T)rcrrr)rrs rt check_serz$DaskXGBRanker.fit..check_sers:c299-#/@G##ryrrr)rrr) rrrrrrrrrFrrr)rrIrrrrrerr3rrDrrrrr)rrrrrrrrrrrrFrrrrr=r?X_id new_eval_set new_eval_qidnew_sample_weight_eval_setnew_base_margin_eval_setrXeyewebeqes rtrzDaskXGBRanker.fits&N *"4S/ ! ;=> >  Ibll,C  /* 25  x * + %% c5)a%m_=k=9  : ?q} 44a5D4B +' 5 1AsA}k#! ! -/*+-(x#,X#6bn<<"v~-; KKRR.*BB./Q {-R*BB ''R1 ''+~299"=~077;7<:('2L.RV'1I,d%  OO'##9!5+!  ry)rrrr0rerrr#rrrr6rJrIrrrrr6r*rrr7rrrs@rtrTrTEs2 %"')- K K K :& K  K  K  KS = = = o & =  0 =o.=8E/?*J$KLM=!)/)B C='x'@A=8O45=sDy!=E(G"345="/2= =@ ,0)-3715PT:>8<.3=AFJDH59!w w  w ( w o & w  0w o.w 8E/?*J$KLMw Xo67w 8O45w %T *+w E(C"89:w !)/)B Cw 'x'@Aw "/2!w " #w  w v--''CKKryrTzjImplementation of the Scikit-Learn API for XGBoost Random Forest Regressor. .. versionadded:: 1.4.0 r zI n_estimators : int Number of trees in random forest to fit. )r0cFeZdZedddddddeedeedeed eed eed ed dffd Zd e e efffd Z d e fdZ ddddddddddededeedeedeeeeefdeee efdeeee efdeeedeeedeed dffdZxZS)rUrB皙?h㈵>N learning_rate subsamplecolsample_bynode reg_lambdar!rNrOrPrQr!rr\c 0t|d|||||d|yNrMr~rrrrNrOrPrQr!rrs rtrzDaskXGBRFRegressor.__init__=0  '-!    rycBt|}|j|d<|SNnum_parallel_treerr n_estimatorsr8s rtrz!DaskXGBRFRegressor.get_xgb_paramsQ&')&*&7&7"# rycyNrBr~rs rtr z*DaskXGBRFRegressor.get_num_boosting_roundsVryTrrrrrrrrFrrrctjD cic] \} } | dvs | | } } } t|j|jt |di| |Scc} } wNrr~rerr;rDrGrrrrrrrrrrFrrrrrr{rs rtrzDaskXGBRFRegressor.fitZ_"(!1TAQ>S5S1TT455t~~F  d U A#A#rrrr0rrr#rrr rerrr rJrIrrrrr*r6rrrs@rtrUrU0s *+%(,/&*)-   E?  #5/  UO  :&      &S#X 4815PT.2=AFJDH59    0  o. 8E/?*J$KLM%T *+E'3"89:!)/)B C'x'@A"/2 ryrUzkImplementation of the Scikit-Learn API for XGBoost Random Forest Classifier. .. versionadded:: 1.4.0 cFeZdZedddddddeedeedeed eed eed ed dffd Zd e e efffd Z d e fdZ ddddddddddededeedeedeeeeefdeee efdeeee efdeeedeeedeed dffdZxZS)rVrBrKrLNrMrNrOrPrQr!rr\c 0t|d|||||d|yrSrTrUs rtrzDaskXGBRFClassifier.__init__{rVrycBt|}|j|d<|SrXrZr8s rtrz"DaskXGBRFClassifier.get_xgb_paramsr\rycyr^r~rs rtr z+DaskXGBRFClassifier.get_num_boosting_roundsr_ryTrrrrrrrrFrrrctjD cic] \} } | dvs | | } } } t|j|jt |di| |Scc} } wrarbrcs rtrzDaskXGBRFClassifier.fitrdrerfrs@rtrVrVns *+%(,/&*)-   E?  #5/  UO  :&      &S#X 4815PT.2=AFJDH59    0  o. 8E/?*J$KLM%T *+E'3"89:!)/)B C'x'@A"/2 ryrV)NN) )rlogging collectionsr contextlibr functoolsrr threadingrtypingrr r r r r rrrrrrrrrrrrrrrrrrrr dask.delayedrrrr _data_utilsr!_typingr"r#r$callbackr%r&r#r'CollArgsr(rcompatr)corer*r+r,r-r.r/r0r1rr2r3sklearnr4r5r6r7r8r9r:r;r<r=r>r?trackerr@trainingrArXrCrDrrErFrGrHrrrrI__annotations__rJrK__all__ getLoggerrlrrernrxrOrrPrrrrQr-r1r8r?rrbrjrvrrrrrrrWrrXrrrrRrSrTrUrVr~ryrtrs 2f#%-(   !$@@'-*1    0    #,0XX"288R\\299#DEE"((BLL01 1  F   + ,-- hsmXeCHo%>>? @-c]- -`SMU38_-c]    U*88 U!56;O"ppf : t_D ) *D 2x< D Dc] D  DN9+9~)-%) & &&d38n %&z" &  #uS#X  &R4(4S>24    (% S8H2I)J K  #Y K #YK 4K Kg gS>gd38n % g cN g  gg HU;#345 6g ) g$C=gT "g g!123gF#gz"g l!gT  6 :>#+/#'%)6:&*%)6 6 cN6 6 6 HU;#345 6 6 ) 6$C=6 6T "6!1236F#6z"6 66r,$,e,, )-c;?BRR"R  R /* R S/ R sCx.RRj" " #",0";?"KN" 5c?DcN *+", ).w>R/R)S0W WS>W $ 44 5W  W  WWWWWWW$WWWt  YY!#"&,3V ) *3V w(<< =3V  V# $3V  3V  3V3V3V3V3V3V$3V3V 3V3Vl> >S>> $ 44 5 >  > $ >>>>/*>>>B '-YY"-1: ) *: w(<< =: : $ :  :::/*:: ::z" ) *" SM"#"c] "  "  ;eK,<&=!>? ?@ ": *>UW(UWp= g?VW:')<W:W:tH7t)+>t tn 7 %0P(N$7P(10P(f  k /)/ /d  k /+/ /ry