&`i4 &ddlZddlmZddlmZmZmZmZmZddl Z ddl Z ddl m Z ddl mZddlmZddlmZddlmZdd lmZdd lmZdd lmZejeZd Zd e de!de"de#de f dZ$edGddeZdS)N)partial)AnyCallableDictOptionalUnion) Checkpoint)TRAIN_DATASET_KEY)RayTrainReportCallback)LightGBMConfig)LightGBMTrainer) GenDataset)_log_deprecation_warning) PublicAPIa\Passing in `lightgbm.train` kwargs such as `params`, `num_boost_round`, `label_column`, etc. to `LightGBMTrainer` is deprecated in favor of the new API which accepts a `train_loop_per_worker` argument, similar to the other DataParallelTrainer APIs (ex: TorchTrainer). See this issue for more context: https://github.com/ray-project/ray/issues/50042config label_columnnum_boost_round dataset_keyslightgbm_train_kwargsc 4tj}d}|}|rNtj|}|}||z }t d|d|dtjt} | } d|D} d| D} | |d| |}} tj| |}|g}tg}| D]b\}}| |d||}}|tj||||c|tjj|d d |d d tjd||||||d |dS)Nz7Model loaded from checkpoint will train for additional zY iterations (trees) in order to achieve the target number of iterations (num_boost_round=z).cdi|]-}|tk |tj|.S)r raytrainget_dataset_shard).0ks w/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/ray/train/lightgbm/lightgbm_trainer.py z1_lightgbm_train_fn_per_worker..6s@ ! ! ! 39 & &q ) ) ! ! !cbi|],\}}||-Sr) materialize to_pandas)rrds rrz1_lightgbm_train_fn_per_worker..;s2QQQ41a1==??,,..QQQr )axis)label tree_learner data_parallel pre_partitionT)params train_setr valid_sets valid_names init_modelr)rrget_checkpointr get_modelcurrent_iterationloggerinforr r"r#itemsdroplightgbmDatasetappendupdateget_network_params setdefault)rrrrr checkpointstarting_modelremaining_iters starting_iter train_ds_itertrain_df eval_ds_iterseval_dfstrain_Xtrain_yr,r-r. eval_nameeval_dfeval_Xeval_ys r_lightgbm_train_fn_per_workerrKsU))++JN%O  /9*EE&88:: )M9  %) % %  % % %   I//0ABBM((**4466HM RQ=;N;N;P;PQQQH}}\}::H\`. train_loop_config: A configuration ``Dict`` to pass in as an argument to ``train_loop_per_worker``. This is typically used for specifying hyperparameters. lightgbm_config: The configuration for setting up the distributed lightgbm backend. Defaults to using the "rabit" backend. See :class:`~ray.train.lightgbm.LightGBMConfig` for more info. datasets: The Ray Datasets to use for training and validation. dataset_config: The configuration for ingesting the input ``datasets``. By default, all the Ray Datasets are split equally across workers. See :class:`~ray.train.DataConfig` for more details. scaling_config: The configuration for how to scale data parallel training. ``num_workers`` determines how many Python processes are used for training, and ``use_gpu`` determines whether or not each process should use GPUs. See :class:`~ray.train.ScalingConfig` for more info. run_config: The configuration for the execution of the training run. See :class:`~ray.train.RunConfig` for more info. resume_from_checkpoint: A checkpoint to resume training from. This checkpoint can be accessed from within ``train_loop_per_worker`` by calling ``ray.train.get_checkpoint()``. metadata: Dict that should be made available via `ray.train.get_context().get_metadata()` and in `checkpoint.get_metadata()` for checkpoints saved from this Trainer. Must be JSON-serializable. label_column: [Deprecated] Name of the label column. A column with this name must be present in the training dataset. params: [Deprecated] LightGBM training parameters. Refer to `LightGBM documentation `_ for a list of possible parameters. num_boost_round: [Deprecated] Target number of boosting iterations (trees in the model). Note that unlike in ``lightgbm.train``, this is the target number of trees, meaning that if you set ``num_boost_round=10`` and pass a model that has already been trained for 5 iterations, it will be trained for 5 iterations more, instead of 10 more. **train_kwargs: [Deprecated] Additional kwargs passed to ``lightgbm.train()`` function. TN) train_loop_configlightgbm_configscaling_config run_configdatasetsdataset_configresume_from_checkpointmetadatarr+rtrain_loop_per_workerrOrPrQrRrSrTrUrVrr+rc |du}|r|| || | |}| pi}n.| r,td| dtt t ||||||||||  dS)N)rrRrrrSzPPassing `lightgbm.train` kwargs to `LightGBMTrainer` is deprecated. Got kwargs: z^ In your training function, you can call `lightgbm.train(**kwargs)` with arbitrary arguments. ) rWrOrPrQrRrSrTrUrV)_get_legacy_train_fn_per_workerrkeys+LEGACY_LIGHTGBM_TRAINER_DEPRECATION_MESSAGEsuperr __init__)selfrWrOrPrQrRrSrTrUrVrr+r train_kwargs legacy_api __class__s rr]zLightGBMTrainer.__init__s*+d2  $($H$H&2%) /! %I%% !!' "     $A+0022AA? AA    ot$$--"7/+)!)#9 . r rreturnc P|pi}|ts9tdtdt||std|pd}t t |dg}td|D}i}|r&|jj } |jj } | |d<| | nd |d <|s| td i|||d<tt||t|| } | S) z=Get the training function for the legacy LightGBMTrainer API.z`datasets` must be provided for the LightGBMTrainer API if `train_loop_per_worker` is not provided. This dict must contain the training dataset under the key: 'z '. Got keys: z`label_column` must be provided for the LightGBMTrainer API if `train_loop_per_worker` is not provided. This is the column name of the label in the dataset. callbacksc3@K|]}t|tVdSN) isinstancer )rcallbacks r zBLightGBMTrainer._get_legacy_train_fn_per_worker..s>% % =EJx!7 8 8% % % % % % r frequencyNTcheckpoint_at_end)rrrrr)getr ValueErrorlistrZrr[anycheckpoint_configcheckpoint_frequencyrlr9r rrKset) r^rrRrSrrreuser_supplied_callbackcallback_kwargsrrrltrain_fn_per_workers rrYz/LightGBMTrainer._get_legacy_train_fn_per_workers>r||-.. 5+55"(--//22 55  G  */R !LMMM*--k2>> !$% % IR% % % " "   #-#?#T * < N +?OK (&7%B!! / 0& H   3FFoFF G G G-6k*% )%+X"7    #"r r=c*tj|S)z6Retrieve the LightGBM model stored in this checkpoint.)r r1)clsr=s rr1zLightGBMTrainer.get_model6s &/ ;;;r rg)__name__ __module__ __qualname____doc___handles_checkpoint_freq_handles_checkpoint_at_endrrrrr rr ScalingConfig RunConfigstrr DataConfigr rintr]rY classmethodr7Boosterr1 __classcell__)ras@rr r Zs7ffP $!%  2 -148<@48489=7;-1&*+/)-#2 2 2 ' (2t8$hvt|&<< = 2 $D> 2 ".12 !!892 SY012 4Z012 !!562 !) 42 4S>*2 sm2 c3h(!2 ""##2 2 2 2 2 2 h9##9#SY019#4Z01 9# sm 9# "# 9# 4&$, 9#9#9#9#v<<  <<<[<<<<rs77777777777777 111111EEEEEE444444JJJJJJ((((((444444******  8 $ $6,9 999 9  9999x Va<a<a<a<a<+a<a<a<a<a