CHNOBLi

• main module
  • finish_data()
  • main()
• src package
  • Subpackages
    • src.preprocessing package
      • Submodules
      • src.preprocessing.preprocess module
      • Module contents
  • Submodules
  • src.aggregation module
    • abbrev_firstname_match()
    • aggregate_names()
    • aggregate_place()
    • aggregate_places()
    • aggregate_with()
    • clean_lastname()
    • clean_up_aggregation()
    • clean_up_aggregation_places()
    • create_new_aggregated_place()
    • create_new_aggregated_unit()
    • decide_candidates()
    • execute_aggregation()
    • find_place_match()
    • full_firstname_match()
    • map_genitive_places()
    • map_genitive_versions()
    • merge_to_existing_aggregated_unit()
    • only_abbrev_firstname_match()
    • only_firstname_match()
    • only_lastname_match()
    • others_match()
  • src.evaluation module
    • execute_evaluation()
  • src.linking module
    • TaggingPages
      • TaggingPages.pages_for()
    • backend_api_call()
    • compare_to_target_ids_multiplexed()
    • compare_vector_to_text_ids_multiplexed()
    • execute_linking()
    • expand_name()
    • find_links()
    • get_candidates()
    • get_paramanera_token()
    • get_person_context()
    • init_link_progress()
    • link_person()
    • prep_person_entry()
    • prep_person_out()
    • prep_word()
    • remove_obsolete_abbrevs()
  • src.postprocess module
    • add_info_to_entity()
    • add_info_to_place_entity()
    • adjust_information()
    • decide_articles()
    • execute_postprocessing()
    • get_article_info()
    • get_data_paths_iterative()
    • get_found_names()
    • get_structure_info()
    • initialize_found_entry()
    • initialize_found_place_entry()
    • populate_year_dict()
    • process_page()
  • src.tag_flair module
    • CustomSentence
    • CustomToken
    • add_sentences()
    • decide_tag_no_tag_lower_prio()
    • execute_tagging()
    • package_generator_output_paths()
    • setup_flair_tagger()
    • tag_year_data_and_save()
    • write_sentences_to_outfile()
  • Module contents
• utility package
  • Subpackages
  • Submodules
  • utility.compare module
    • compare_gnd_info()
    • compare_linking()
    • compare_linking_person()
    • compare_linking_places()
    • compare_references()
    • compare_tagging()
    • main()
  • utility.evaluation_utils module
    • Paths
      • Paths.check_and_create()
      • Paths.get()
      • Paths.get_jsonl()
      • Paths.save_json()
      • Paths.update()
    • Scores
      • Scores.compute_scores()
      • Scores.get_score()
      • Scores.update_counter()
    • clean_raw()
    • eval_entity()
    • eval_entity_inkb()
    • eval_references()
    • eval_references_inkb()
    • evaluate_person()
    • get_main_name()
    • label_entity()
  • utility.linking_utils module
    • build_person_gnd_query()
    • build_variant_name_query()
    • build_wikidata_query()
    • clean_namestring()
    • convert_dates_wikidata()
    • convert_gnd_format_kibana()
    • convert_wikidata_format_kibana()
    • get_preferred_gnd_entry_wikidata()
    • parse_person_gnd_response()
    • parse_variant_name_response()
    • parse_wikidata_response()
    • prep_name_for_elasticsearch_query()
    • resolve_old_gids()
    • search_person_gnd()
    • search_person_gnd_variantName()
    • search_person_wikidata()
    • warn_multiple_gids()
  • utility.settings module
    • ElasticSettings
      • ElasticSettings.base_url
      • ElasticSettings.index_name_gnd
      • ElasticSettings.index_name_wikidata
      • ElasticSettings.model_config
      • ElasticSettings.password
      • ElasticSettings.username
    • JsonConfigSettingsSource
      • JsonConfigSettingsSource.get_field_value()
      • JsonConfigSettingsSource.prepare_field_value()
    • Settings
      • Settings.ADD_FUZZY_SEARCH
      • Settings.BATCH_SIZE
      • Settings.CLIENT_ID
      • Settings.CLIENT_SECRET
      • Settings.CUSTOM_PATHS
      • Settings.CUSTOM_TAG_PATH
      • Settings.DATA2_MNT
      • Settings.EMBEDDINGS_ENDPOINT
      • Settings.EVAL_TOPK
      • Settings.GND_LIMIT
      • Settings.INKB_SCORE
      • Settings.JOB_ID
      • Settings.LINKED_PERSONS_LIMIT
      • Settings.MILVUS_HOST
      • Settings.MILVUS_PORT
      • Settings.OIDC_TOKEN_URL
      • Settings.PATH_TO_ABBREVIATION_FILE
      • Settings.PATH_TO_CA_CERT
      • Settings.PATH_TO_GROUND_TRUTH
      • Settings.PATH_TO_INPUT_FOLDERS
      • Settings.PATH_TO_NER_MODEL_1
      • Settings.PATH_TO_NER_MODEL_2
      • Settings.PATH_TO_OUTFILE_FOLDER
      • Settings.SENTENCE_BATCH_SIZE
      • Settings.USE_RICH_LOGGING
      • Settings.VD_API_TOKEN
      • Settings.VD_CONTEXT_WINDOW_LEN
      • Settings.VD_CONTEXT_WINDOW_LEN_FULL
      • Settings.VD_MAX_DIST
      • Settings.VD_MAX_RETRIES
      • Settings.VD_QUERY_CHUNK_LEN
      • Settings.VD_TIMEOUT
      • Settings.VD_TIMEOUT_RETRY
      • Settings.WIKIDATA_LIMIT
      • Settings.es
      • Settings.model_config
      • Settings.settings_customise_sources()
  • utility.split_year module
    • check_for_missing_pages()
    • compare_pagenames()
    • cut_pagenumbers()
    • get_pagenumbers()
    • split_directory()
  • utility.utils module
    • check_gpu()
    • erara_xml_to_word_coord()
    • finish_magazine_output()
    • offset_len_to_linking_input()
    • parse_arguments()
    • positive_int()
    • save_data()
    • save_data_intermediate()
    • set_default()
    • start_magazine_output()
    • str2bool()
    • transkribus_xml_to_approx_word_coord()
    • txt_file_to_word_coord()
  • Module contents