nlpboost

• nlpboost package
  • Subpackages
    • nlpboost.augmentation package
      • Submodules
      • nlpboost.augmentation.TextAugmenterPipeline module
      • nlpboost.augmentation.augmenter_config module
      • Module contents
  • Submodules
  • nlpboost.autotrainer module
    • AutoTrainer
      • AutoTrainer.optuna_hp_search()
      • AutoTrainer.train_one_model_fixed_params()
      • AutoTrainer.train_one_model_optuna()
      • AutoTrainer.train_with_fixed_params()
  • nlpboost.ckpt_cleaner module
    • CkptCleaner
      • CkptCleaner.fix_dir()
      • CkptCleaner.get_best_name()
      • CkptCleaner.remove_dirs()
      • CkptCleaner.save_best()
  • nlpboost.dataset_config module
    • DatasetConfig
      • DatasetConfig.additional_metrics
      • DatasetConfig.alias
      • DatasetConfig.augment_data
      • DatasetConfig.callbacks
      • DatasetConfig.config_num_labels
      • DatasetConfig.custom_eval_func
      • DatasetConfig.data_augmentation_steps
      • DatasetConfig.data_field
      • DatasetConfig.dataset_name
      • DatasetConfig.direction_optimize
      • DatasetConfig.files
      • DatasetConfig.fixed_training_args
      • DatasetConfig.hf_load_kwargs
      • DatasetConfig.id_field_qa
      • DatasetConfig.is_2sents
      • DatasetConfig.is_multilabel
      • DatasetConfig.label_col
      • DatasetConfig.loaded_dataset
      • DatasetConfig.max_length_summary
      • DatasetConfig.metric_optimize
      • DatasetConfig.multilabel_label_names
      • DatasetConfig.num_proc
      • DatasetConfig.partial_split
      • DatasetConfig.pre_func
      • DatasetConfig.pretokenized_dataset
      • DatasetConfig.remove_fields_pre_func
      • DatasetConfig.retrain_at_end
      • DatasetConfig.seed
      • DatasetConfig.sentence1_field
      • DatasetConfig.sentence2_field
      • DatasetConfig.smoke_test
      • DatasetConfig.split
      • DatasetConfig.squad_v2
      • DatasetConfig.summary_field
      • DatasetConfig.task
      • DatasetConfig.test_size
      • DatasetConfig.text_field
      • DatasetConfig.type_load
      • DatasetConfig.val_size
  • nlpboost.default_param_spaces module
    • hp_space_base()
    • hp_space_large()
  • nlpboost.hfdatasets_manager module
    • HFDatasetsManager
      • HFDatasetsManager.get_dataset_and_tag2id()
  • nlpboost.hftransformers_manager module
    • HFTransformersManager
      • HFTransformersManager.get_model_cls()
      • HFTransformersManager.load_config()
      • HFTransformersManager.load_data_collator()
      • HFTransformersManager.load_model_init()
      • HFTransformersManager.load_tokenizer()
      • HFTransformersManager.load_train_args()
      • HFTransformersManager.load_trainer()
    • MultilabelTrainer
      • MultilabelTrainer.compute_loss()
  • nlpboost.metrics module
    • compute_metrics_classification()
    • compute_metrics_multilabel()
    • compute_metrics_ner()
    • compute_metrics_summarization()
  • nlpboost.metrics_plotter module
    • ResultsPlotter
      • ResultsPlotter.plot_metrics()
      • ResultsPlotter.read_metrics()
  • nlpboost.model_config module
    • ModelConfig
      • ModelConfig.additional_params_tokenizer
      • ModelConfig.config_problem_type
      • ModelConfig.custom_config_class
      • ModelConfig.custom_model_class
      • ModelConfig.custom_params_config_model
      • ModelConfig.custom_results_getter
      • ModelConfig.custom_tokenization_func
      • ModelConfig.custom_trainer_cls
      • ModelConfig.decoder_name
      • ModelConfig.do_nothing
      • ModelConfig.dropout_field_name
      • ModelConfig.dropout_vals
      • ModelConfig.early_stopping_summarization
      • ModelConfig.encoder_name
      • ModelConfig.generation_params
      • ModelConfig.hf_hub_username
      • ModelConfig.hp_space
      • ModelConfig.length_penalty
      • ModelConfig.max_length_summary
      • ModelConfig.min_length_summary
      • ModelConfig.model_cls_summarization
      • ModelConfig.n_trials
      • ModelConfig.name
      • ModelConfig.no_repeat_ngram_size
      • ModelConfig.num_beams
      • ModelConfig.only_test
      • ModelConfig.overwrite_training_args
      • ModelConfig.partial_custom_tok_func_call
      • ModelConfig.push_to_hub
      • ModelConfig.random_init_trials
      • ModelConfig.resume_from_checkpoint
      • ModelConfig.save_dir
      • ModelConfig.save_name
      • ModelConfig.test_batch_size
      • ModelConfig.tie_encoder_decoder
      • ModelConfig.trainer_cls_summarization
  • nlpboost.results_getter module
    • ResultsGetter
      • ResultsGetter.general_get_test_results()
      • ResultsGetter.get_test_results_qa()
      • ResultsGetter.get_test_results_summarization()
      • ResultsGetter.postprocess_qa_predictions()
      • ResultsGetter.prepare_validation_features_squad()
  • nlpboost.tokenization_functions module
    • tokenize_classification()
    • tokenize_ner()
    • tokenize_squad()
    • tokenize_summarization()
  • nlpboost.utils module
    • chunks()
    • dict_to_list()
    • filter_empty()
    • get_tags()
    • get_windowed_match_context_answer()
    • joinpaths()
    • match_questions_multiple_answers()
  • Module contents