Index

_

__call__() (mltb2.fasttext.FastTextLanguageIdentification method) (mltb2.md.MdTextSplitter method) (mltb2.openai.OpenAiTokenCounter method) (mltb2.somajo.JaccardSimilarity method) (mltb2.somajo.SoMaJoSentenceSplitter method) (mltb2.somajo_transformers.TextSplitter method) (mltb2.transformers.TransformersTokenCounter method) __len__() (mltb2.files.FileBasedRestartableBatchDataProcessor method)

_arango_client_factory() (mltb2.arangodb.ArangoConnectionManager method) _check_config_keys() (in module mltb2.arangodb) _chunk_md_by_headline() (in module mltb2.md) _connection_factory() (mltb2.arangodb.ArangoConnectionManager method) _load_colon_data() (in module mltb2.data) _load_colon_label() (in module mltb2.data) _normalize_char_counter() (mltb2.text.TextDistance method) _normalize_counter_to_defaultdict() (in module mltb2.text) _OpenAiAzureChatBase (class in mltb2.openai)

A

AbstractBatchDataManager (class in mltb2.db) arango_collection_backup() (in module mltb2.arangodb)

ArangoBatchDataManager (class in mltb2.arangodb) ArangoConnectionManager (class in mltb2.arangodb) ArangoImportDataManager (class in mltb2.arangodb)

B

BatchDataProcessor (class in mltb2.db)

boxplot() (in module mltb2.plot) boxplot_dict() (in module mltb2.plot)

C

chunk_md() (in module mltb2.md) clean_all_invisible_chars_and_strip() (in module mltb2.text)

clean_all_invisible_chars_and_whitespaces() (in module mltb2.text) create_completions() (mltb2.openai.OpenAiChat method) create_completions_async() (mltb2.openai.OpenAiChat method)

D

detokenize() (in module mltb2.somajo)

distance() (mltb2.text.TextDistance method)

E

extract_all() (in module mltb2.bs) extract_one() (in module mltb2.bs) extract_text() (in module mltb2.bs)

extract_token_class_set() (in module mltb2.somajo) extract_token_set() (mltb2.somajo.TokenExtractor method) extract_url_set() (mltb2.somajo.TokenExtractor method)

F

FastTextLanguageIdentification (class in mltb2.fasttext) fetch_remote_file() (in module mltb2.files) FileBasedRestartableBatchDataProcessor (class in mltb2.files) fit() (mltb2.text.TextDistance method)

from_chat_completion() (mltb2.openai.OpenAiChatResult class method) from_config_file() (mltb2.arangodb.ArangoBatchDataManager class method) (mltb2.arangodb.ArangoImportDataManager class method) from_yaml() (mltb2.openai.OpenAiAzureChat class method) (mltb2.openai.OpenAiChat class method)

G

get_and_create_mltb2_data_dir() (in module mltb2.files)

get_model_path_and_download() (mltb2.fasttext.FastTextLanguageIdentification static method) get_token_set() (mltb2.somajo.JaccardSimilarity method)

H

has_invisible_characters() (in module mltb2.text) has_special_whitespaces() (in module mltb2.text)

has_xml_tag() (in module mltb2.text) html_to_md() (in module mltb2.bs)

I

import_dataframe() (mltb2.arangodb.ArangoImportDataManager method)

import_dicts() (mltb2.arangodb.ArangoImportDataManager method)

J

JaccardSimilarity (class in mltb2.somajo)

K

KFoldLabeledDataset (class in mltb2.transformers)

L

LabeledDataset (class in mltb2.transformers) load_batch() (mltb2.arangodb.ArangoBatchDataManager method) (mltb2.db.AbstractBatchDataManager method)

load_colon() (in module mltb2.data) load_data() (mltb2.files.FileBasedRestartableBatchDataProcessor static method) load_leukemia_big() (in module mltb2.data) load_prostate() (in module mltb2.data)

M

MdTextSplitter (class in mltb2.md) mltb2.arangodb module mltb2.bs module mltb2.data module mltb2.db module mltb2.fasttext module mltb2.files module mltb2.md module mltb2.openai module mltb2.optuna module mltb2.plot module mltb2.somajo module

mltb2.somajo_transformers module mltb2.text module mltb2.transformers module module mltb2.arangodb mltb2.bs mltb2.data mltb2.db mltb2.fasttext mltb2.files mltb2.md mltb2.openai mltb2.optuna mltb2.plot mltb2.somajo mltb2.somajo_transformers mltb2.text mltb2.transformers

O

OpenAiAzureChat (class in mltb2.openai) OpenAiChat (class in mltb2.openai)

OpenAiChatResult (class in mltb2.openai) OpenAiTokenCounter (class in mltb2.openai)

P

prune() (mltb2.optuna.SignificanceRepeatedTrainingPruner method)

R

read_batch() (mltb2.files.FileBasedRestartableBatchDataProcessor method) remove_all() (in module mltb2.bs) remove_invisible_characters() (in module mltb2.text) remove_openai_tokens() (in module mltb2.openai)

replace_multiple_whitespaces() (in module mltb2.text) replace_special_whitespaces() (in module mltb2.text) reverse_swap_urls() (mltb2.somajo.UrlSwapper method) run() (mltb2.db.BatchDataProcessor method)

S

save_batch() (mltb2.arangodb.ArangoBatchDataManager method) (mltb2.db.AbstractBatchDataManager method) (mltb2.files.FileBasedRestartableBatchDataProcessor method) save_last_figure() (in module mltb2.plot) SignificanceRepeatedTrainingPruner (class in mltb2.optuna)

SoMaJoBaseClass (class in mltb2.somajo) SoMaJoSentenceSplitter (class in mltb2.somajo) soup_to_md() (in module mltb2.bs) split() (mltb2.transformers.KFoldLabeledDataset method) swap_urls() (mltb2.somajo.UrlSwapper method)

T

TextDistance (class in mltb2.text) TextSplitter (class in mltb2.somajo_transformers)

TokenExtractor (class in mltb2.somajo) TransformersTokenCounter (class in mltb2.transformers) twin_axes_timeseries_plot() (in module mltb2.plot)

U

UrlSwapper (class in mltb2.somajo)