Index

A

add_step() (bardi.pipeline.Pipeline method)

B

bardi.data.data_handlers module bardi.nlp_engineering.embedding_generator module bardi.nlp_engineering.label_processor module bardi.nlp_engineering.normalizer module bardi.nlp_engineering.pre_tokenizer module bardi.nlp_engineering.regex_library.pathology_report module bardi.nlp_engineering.regex_library.regex_lib module

bardi.nlp_engineering.regex_library.regex_set module bardi.nlp_engineering.splitter module bardi.nlp_engineering.tokenizer_encoder module bardi.nlp_engineering.tokenizer_trainer module bardi.nlp_engineering.vocab_encoder module bardi.pipeline module

C

checkpoint_path (bardi.nlp_engineering.embedding_generator.CPUEmbeddingGenerator attribute) (bardi.nlp_engineering.embedding_generator.EmbeddingGenerator attribute) (bardi.nlp_engineering.tokenizer_trainer.CPUTokenizerTrainer attribute) (bardi.nlp_engineering.tokenizer_trainer.TokenizerTrainer attribute) concat_fields (bardi.nlp_engineering.tokenizer_encoder.CPUTokenizerEncoder attribute) (bardi.nlp_engineering.tokenizer_encoder.TokenizerEncoder attribute) (bardi.nlp_engineering.vocab_encoder.CPUVocabEncoder attribute) (bardi.nlp_engineering.vocab_encoder.VocabEncoder attribute) convert_escape_codes (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) cores (bardi.nlp_engineering.embedding_generator.CPUEmbeddingGenerator attribute) (bardi.nlp_engineering.embedding_generator.EmbeddingGenerator attribute) (bardi.nlp_engineering.tokenizer_encoder.CPUTokenizerEncoder attribute) (bardi.nlp_engineering.tokenizer_encoder.TokenizerEncoder attribute)

corpus_gen_batch_size (bardi.nlp_engineering.tokenizer_trainer.CPUTokenizerTrainer attribute) (bardi.nlp_engineering.tokenizer_trainer.TokenizerTrainer attribute) CPUEmbeddingGenerator (class in bardi.nlp_engineering.embedding_generator) CPULabelProcessor (class in bardi.nlp_engineering.label_processor) CPUNormalizer (class in bardi.nlp_engineering.normalizer) CPUPreTokenizer (class in bardi.nlp_engineering.pre_tokenizer) CPUSplitter (class in bardi.nlp_engineering.splitter) CPUTokenizerEncoder (class in bardi.nlp_engineering.tokenizer_encoder) CPUTokenizerTrainer (class in bardi.nlp_engineering.tokenizer_trainer) CPUVocabEncoder (class in bardi.nlp_engineering.vocab_encoder)

D

data (bardi.data.data_handlers.Dataset attribute) data_filename (bardi.pipeline.Pipeline attribute) data_format (bardi.pipeline.DataWriteConfig attribute) data_format_args (bardi.pipeline.DataWriteConfig attribute)

data_write_config (bardi.pipeline.Pipeline attribute) dataset (bardi.pipeline.Pipeline attribute) Dataset (class in bardi.data.data_handlers) DataWriteConfig (class in bardi.pipeline) default_split_value (bardi.nlp_engineering.splitter.MapSplit attribute)

E

embedding_matrix_format (bardi.nlp_engineering.embedding_generator.EmbeddingGeneratorArtifactsWriteConfig attribute) embedding_matrix_format_args (bardi.nlp_engineering.embedding_generator.EmbeddingGeneratorArtifactsWriteConfig attribute) EmbeddingGenerator (class in bardi.nlp_engineering.embedding_generator)

EmbeddingGeneratorArtifactsWriteConfig (class in bardi.nlp_engineering.embedding_generator) epochs (bardi.nlp_engineering.embedding_generator.CPUEmbeddingGenerator attribute) (bardi.nlp_engineering.embedding_generator.EmbeddingGenerator attribute)

F

field (bardi.nlp_engineering.tokenizer_trainer.CPUTokenizerTrainer attribute) (bardi.nlp_engineering.tokenizer_trainer.TokenizerTrainer attribute) field_rename (bardi.nlp_engineering.tokenizer_encoder.CPUTokenizerEncoder attribute) (bardi.nlp_engineering.tokenizer_encoder.TokenizerEncoder attribute) (bardi.nlp_engineering.vocab_encoder.CPUVocabEncoder attribute) (bardi.nlp_engineering.vocab_encoder.VocabEncoder attribute) fields (bardi.nlp_engineering.embedding_generator.CPUEmbeddingGenerator attribute) (bardi.nlp_engineering.embedding_generator.EmbeddingGenerator attribute) (bardi.nlp_engineering.label_processor.CPULabelProcessor attribute) (bardi.nlp_engineering.label_processor.LabelProcessor attribute) (bardi.nlp_engineering.normalizer.CPUNormalizer attribute) (bardi.nlp_engineering.normalizer.Normalizer attribute) (bardi.nlp_engineering.pre_tokenizer.CPUPreTokenizer attribute) (bardi.nlp_engineering.pre_tokenizer.PreTokenizer attribute) (bardi.nlp_engineering.tokenizer_encoder.CPUTokenizerEncoder attribute) (bardi.nlp_engineering.tokenizer_encoder.TokenizerEncoder attribute) (bardi.nlp_engineering.vocab_encoder.CPUVocabEncoder attribute) (bardi.nlp_engineering.vocab_encoder.VocabEncoder attribute)

fix_pluralization (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) from_duckdb() (in module bardi.data.data_handlers) from_file() (in module bardi.data.data_handlers) from_json() (in module bardi.data.data_handlers) from_old_flag (bardi.nlp_engineering.tokenizer_trainer.CPUTokenizerTrainer attribute) (bardi.nlp_engineering.tokenizer_trainer.TokenizerTrainer attribute) from_pandas() (in module bardi.data.data_handlers) from_pyarrow() (in module bardi.data.data_handlers)

G

get_address_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_angle_brackets_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_cassette_name_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_cassettes_spacing_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_dash_digits_spacing_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_dates_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_decimal_segmented_numbers_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_digits_words_spacing_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_dimension_spacing_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_dimensions_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_duration_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_escape_code_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_fix_pluralization_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_large_digits_seq_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_large_float_seq_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_leading_digit_punctuation_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_leading_punctuation_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_letter_num_seq_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_literals_floats_spacing_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_math_spacing_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_measure_spacing_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_multiple_punct_regex() (in module bardi.nlp_engineering.regex_library.regex_lib)

get_parameters() (bardi.data.data_handlers.Dataset method) (bardi.nlp_engineering.embedding_generator.CPUEmbeddingGenerator method) (bardi.nlp_engineering.label_processor.CPULabelProcessor method) (bardi.nlp_engineering.tokenizer_encoder.CPUTokenizerEncoder method) (bardi.nlp_engineering.tokenizer_trainer.CPUTokenizerTrainer method) (bardi.nlp_engineering.vocab_encoder.CPUVocabEncoder method) (bardi.pipeline.Pipeline method) (bardi.pipeline.Step method) get_percent_sign_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_phone_number_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_regex_set() (bardi.nlp_engineering.regex_library.regex_set.RegexSet method) get_spaces_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_special_punct_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_specimen_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_time_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_trailing_punctuation_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_trunc_decimals_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_urls_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_whitespace_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) get_words_with_punct_spacing_regex() (in module bardi.nlp_engineering.regex_library.regex_lib) group_cols (bardi.nlp_engineering.splitter.CPUSplitter attribute) (bardi.nlp_engineering.splitter.NewSplit attribute) (bardi.nlp_engineering.splitter.Splitter attribute)

H

handle_angle_brackets (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) handle_cassettes_spacing (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) handle_dash_digit_spacing (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) handle_digits_words_spacing (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) handle_dimension_spacing (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) handle_leading_digit_punct (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) handle_literals_floats_spacing (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute)

handle_math_spacing (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) handle_measure_spacing (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) handle_whitespaces (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) handle_words_with_punct_spacing (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) hf_cache_dir (bardi.nlp_engineering.tokenizer_encoder.CPUTokenizerEncoder attribute) (bardi.nlp_engineering.tokenizer_encoder.TokenizerEncoder attribute) (bardi.nlp_engineering.tokenizer_trainer.CPUTokenizerTrainer attribute) (bardi.nlp_engineering.tokenizer_trainer.TokenizerTrainer attribute)

I

id_to_label (bardi.nlp_engineering.label_processor.CPULabelProcessor attribute), [1] (bardi.nlp_engineering.label_processor.LabelProcessor attribute) id_to_label_args (bardi.nlp_engineering.label_processor.LabelProcessorArtifactsWriteConfig attribute)

id_to_label_format (bardi.nlp_engineering.label_processor.LabelProcessorArtifactsWriteConfig attribute) id_to_token (bardi.nlp_engineering.vocab_encoder.CPUVocabEncoder attribute) (bardi.nlp_engineering.vocab_encoder.VocabEncoder attribute)

L

label_cols (bardi.nlp_engineering.splitter.CPUSplitter attribute) (bardi.nlp_engineering.splitter.NewSplit attribute) (bardi.nlp_engineering.splitter.Splitter attribute) LabelProcessor (class in bardi.nlp_engineering.label_processor) LabelProcessorArtifactsWriteConfig (class in bardi.nlp_engineering.label_processor)

load_saved_model (bardi.nlp_engineering.embedding_generator.CPUEmbeddingGenerator attribute) (bardi.nlp_engineering.embedding_generator.EmbeddingGenerator attribute) lowercase (bardi.nlp_engineering.normalizer.CPUNormalizer attribute) (bardi.nlp_engineering.normalizer.Normalizer attribute) lowercase_substitution (bardi.nlp_engineering.regex_library.regex_set.RegexSet attribute)

M

mapping (bardi.nlp_engineering.label_processor.CPULabelProcessor attribute) MapSplit (class in bardi.nlp_engineering.splitter) method (bardi.nlp_engineering.label_processor.CPULabelProcessor attribute) (bardi.nlp_engineering.label_processor.LabelProcessor attribute) min_alpha (bardi.nlp_engineering.embedding_generator.CPUEmbeddingGenerator attribute) (bardi.nlp_engineering.embedding_generator.EmbeddingGenerator attribute) min_word_count (bardi.nlp_engineering.embedding_generator.CPUEmbeddingGenerator attribute) (bardi.nlp_engineering.embedding_generator.EmbeddingGenerator attribute) model_name (bardi.nlp_engineering.tokenizer_encoder.CPUTokenizerEncoder attribute) (bardi.nlp_engineering.tokenizer_encoder.TokenizerEncoder attribute) module bardi.data.data_handlers bardi.nlp_engineering.embedding_generator bardi.nlp_engineering.label_processor bardi.nlp_engineering.normalizer bardi.nlp_engineering.pre_tokenizer bardi.nlp_engineering.regex_library.pathology_report bardi.nlp_engineering.regex_library.regex_lib bardi.nlp_engineering.regex_library.regex_set bardi.nlp_engineering.splitter bardi.nlp_engineering.tokenizer_encoder bardi.nlp_engineering.tokenizer_trainer bardi.nlp_engineering.vocab_encoder bardi.pipeline

N

negative (bardi.nlp_engineering.embedding_generator.CPUEmbeddingGenerator attribute) (bardi.nlp_engineering.embedding_generator.EmbeddingGenerator attribute) NewSplit (class in bardi.nlp_engineering.splitter)

no_substitution (bardi.nlp_engineering.regex_library.regex_set.RegexSet attribute) Normalizer (class in bardi.nlp_engineering.normalizer) num_splits (bardi.nlp_engineering.splitter.CPUSplitter attribute) (bardi.nlp_engineering.splitter.Splitter attribute)

O

origin_file_path (bardi.data.data_handlers.Dataset attribute) origin_format (bardi.data.data_handlers.Dataset attribute)

origin_query (bardi.data.data_handlers.Dataset attribute) origin_row_count (bardi.data.data_handlers.Dataset attribute)

P

PathologyReportRegexSet (class in bardi.nlp_engineering.regex_library.pathology_report)

Pipeline (class in bardi.pipeline) PreTokenizer (class in bardi.nlp_engineering.pre_tokenizer)

R

random_seed (bardi.nlp_engineering.splitter.CPUSplitter attribute) (bardi.nlp_engineering.splitter.NewSplit attribute) (bardi.nlp_engineering.splitter.Splitter attribute) regex_set (bardi.nlp_engineering.normalizer.CPUNormalizer attribute) (bardi.nlp_engineering.normalizer.Normalizer attribute) (bardi.nlp_engineering.regex_library.regex_set.RegexSet attribute) regex_str (bardi.nlp_engineering.regex_library.regex_set.RegexSubPair attribute), [1] RegexSet (class in bardi.nlp_engineering.regex_library.regex_set) RegexSubPair (class in bardi.nlp_engineering.regex_library.regex_set) remove_addresses (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) remove_cassette_names (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) remove_dates (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) remove_decimal_seg_numbers (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) remove_dimensions (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) remove_duration_time (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) remove_large_digits_seq (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) remove_large_floats_seq (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) remove_leading_punct (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) remove_letter_num_seq (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) remove_multiple_punct (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) remove_phone_numbers (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) remove_special_punct (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) remove_specimen (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) remove_times (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) remove_trailing_punct (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) remove_urls (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) replace_percent_sign (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute) retain_concat_field (bardi.nlp_engineering.tokenizer_encoder.CPUTokenizerEncoder attribute) (bardi.nlp_engineering.tokenizer_encoder.TokenizerEncoder attribute)

retain_input_fields (bardi.nlp_engineering.label_processor.CPULabelProcessor attribute) (bardi.nlp_engineering.label_processor.LabelProcessor attribute) (bardi.nlp_engineering.normalizer.CPUNormalizer attribute) (bardi.nlp_engineering.normalizer.Normalizer attribute) (bardi.nlp_engineering.pre_tokenizer.CPUPreTokenizer attribute) (bardi.nlp_engineering.pre_tokenizer.PreTokenizer attribute) (bardi.nlp_engineering.tokenizer_encoder.CPUTokenizerEncoder attribute) (bardi.nlp_engineering.tokenizer_encoder.TokenizerEncoder attribute) (bardi.nlp_engineering.vocab_encoder.CPUVocabEncoder attribute) (bardi.nlp_engineering.vocab_encoder.VocabEncoder attribute) return_tensors (bardi.nlp_engineering.tokenizer_encoder.CPUTokenizerEncoder attribute) (bardi.nlp_engineering.tokenizer_encoder.TokenizerEncoder attribute) run() (bardi.nlp_engineering.embedding_generator.CPUEmbeddingGenerator method) (bardi.nlp_engineering.embedding_generator.EmbeddingGenerator method) (bardi.nlp_engineering.label_processor.CPULabelProcessor method) (bardi.nlp_engineering.label_processor.LabelProcessor method) (bardi.nlp_engineering.normalizer.CPUNormalizer method) (bardi.nlp_engineering.normalizer.Normalizer method) (bardi.nlp_engineering.pre_tokenizer.CPUPreTokenizer method) (bardi.nlp_engineering.pre_tokenizer.PreTokenizer method) (bardi.nlp_engineering.splitter.CPUSplitter method) (bardi.nlp_engineering.splitter.Splitter method) (bardi.nlp_engineering.tokenizer_encoder.CPUTokenizerEncoder method) (bardi.nlp_engineering.tokenizer_encoder.TokenizerEncoder method) (bardi.nlp_engineering.tokenizer_trainer.CPUTokenizerTrainer method) (bardi.nlp_engineering.tokenizer_trainer.TokenizerTrainer method) (bardi.nlp_engineering.vocab_encoder.CPUVocabEncoder method) (bardi.nlp_engineering.vocab_encoder.VocabEncoder method) (bardi.pipeline.Step method) run_pipeline() (bardi.pipeline.Pipeline method)

S

sample (bardi.nlp_engineering.embedding_generator.CPUEmbeddingGenerator attribute) (bardi.nlp_engineering.embedding_generator.EmbeddingGenerator attribute) seed (bardi.nlp_engineering.embedding_generator.CPUEmbeddingGenerator attribute) (bardi.nlp_engineering.embedding_generator.EmbeddingGenerator attribute) set_write_config() (bardi.nlp_engineering.embedding_generator.EmbeddingGenerator method) (bardi.nlp_engineering.label_processor.LabelProcessor method) (bardi.nlp_engineering.tokenizer_trainer.TokenizerTrainer method) (bardi.pipeline.Step method) split_mapping (bardi.nlp_engineering.splitter.CPUSplitter attribute) (bardi.nlp_engineering.splitter.MapSplit attribute) (bardi.nlp_engineering.splitter.Splitter attribute)

split_method (bardi.nlp_engineering.splitter.CPUSplitter attribute) (bardi.nlp_engineering.splitter.Splitter attribute) split_pattern (bardi.nlp_engineering.pre_tokenizer.CPUPreTokenizer attribute) (bardi.nlp_engineering.pre_tokenizer.PreTokenizer attribute) split_proportions (bardi.nlp_engineering.splitter.CPUSplitter attribute) (bardi.nlp_engineering.splitter.NewSplit attribute) (bardi.nlp_engineering.splitter.Splitter attribute) split_type (bardi.nlp_engineering.splitter.CPUSplitter attribute) (bardi.nlp_engineering.splitter.Splitter attribute) Splitter (class in bardi.nlp_engineering.splitter) Step (class in bardi.pipeline) sub_str (bardi.nlp_engineering.regex_library.regex_set.RegexSubPair attribute), [1]

T

to_pandas() (in module bardi.data.data_handlers) to_polars() (in module bardi.data.data_handlers) tokenizer_fname (bardi.nlp_engineering.tokenizer_trainer.CPUTokenizerTrainer attribute) (bardi.nlp_engineering.tokenizer_trainer.TokenizerTrainer attribute) tokenizer_model (bardi.nlp_engineering.tokenizer_encoder.CPUTokenizerEncoder attribute) (bardi.nlp_engineering.tokenizer_encoder.TokenizerEncoder attribute) tokenizer_params (bardi.nlp_engineering.tokenizer_encoder.CPUTokenizerEncoder attribute) (bardi.nlp_engineering.tokenizer_encoder.TokenizerEncoder attribute)

tokenizer_type (bardi.nlp_engineering.tokenizer_trainer.CPUTokenizerTrainer attribute) (bardi.nlp_engineering.tokenizer_trainer.TokenizerTrainer attribute) TokenizerEncoder (class in bardi.nlp_engineering.tokenizer_encoder) TokenizerTrainer (class in bardi.nlp_engineering.tokenizer_trainer) TokenizerTrainerArtifactsWriteConfig (class in bardi.nlp_engineering.tokenizer_trainer) trunc_decimals (bardi.nlp_engineering.regex_library.pathology_report.PathologyReportRegexSet attribute)

U

unique_record_cols (bardi.nlp_engineering.splitter.CPUSplitter attribute) (bardi.nlp_engineering.splitter.MapSplit attribute) (bardi.nlp_engineering.splitter.NewSplit attribute) (bardi.nlp_engineering.splitter.Splitter attribute)

V

vector_size (bardi.nlp_engineering.embedding_generator.CPUEmbeddingGenerator attribute) (bardi.nlp_engineering.embedding_generator.EmbeddingGenerator attribute) vocab_exclude_list (bardi.nlp_engineering.embedding_generator.CPUEmbeddingGenerator attribute) (bardi.nlp_engineering.embedding_generator.EmbeddingGenerator attribute) vocab_format (bardi.nlp_engineering.embedding_generator.EmbeddingGeneratorArtifactsWriteConfig attribute) (bardi.nlp_engineering.tokenizer_trainer.TokenizerTrainerArtifactsWriteConfig attribute)

vocab_format_args (bardi.nlp_engineering.embedding_generator.EmbeddingGeneratorArtifactsWriteConfig attribute) (bardi.nlp_engineering.tokenizer_trainer.TokenizerTrainerArtifactsWriteConfig attribute) vocab_size (bardi.nlp_engineering.tokenizer_trainer.CPUTokenizerTrainer attribute) (bardi.nlp_engineering.tokenizer_trainer.TokenizerTrainer attribute) VocabEncoder (class in bardi.nlp_engineering.vocab_encoder)

W

window (bardi.nlp_engineering.embedding_generator.CPUEmbeddingGenerator attribute) (bardi.nlp_engineering.embedding_generator.EmbeddingGenerator attribute) write_artifacts() (bardi.nlp_engineering.embedding_generator.CPUEmbeddingGenerator method) (bardi.nlp_engineering.label_processor.CPULabelProcessor method) (bardi.nlp_engineering.tokenizer_trainer.CPUTokenizerTrainer method) (bardi.pipeline.Step method)

write_data() (bardi.pipeline.Step method) write_file() (in module bardi.data.data_handlers) write_outputs (bardi.pipeline.Pipeline attribute) write_path (bardi.pipeline.Pipeline attribute)