pyjedai.utils
=============

.. automodule:: pyjedai.utils

   
   .. rubric:: Functions

   .. autosummary::
   
      add_entry
      are_matching
      batch_pairs
      block_with_one_entity
      canonical_swap
      chi_square
      clear_json_file
      common_elements
      cosine
      create_entity_index
      drop_big_blocks_by_size
      drop_single_entity_blocks
      generate_unique_identifier
      get_blocks_cardinality
      get_class_function_arguments
      get_multiples
      get_ngrams
      get_qgram_from_tokenizer_name
      get_reverse_indexing_id
      get_sorted_blocks_shuffled_entities
      has_duplicate_pairs
      is_infinite
      java_math_round
      matching_arguments
      necessary_dfs_supplied
      new_dictionary_from_keys
      print_blocks
      print_candidate_pairs
      print_clusters
      purge_id_column
      read_data_from_json
      retrieve_top_workflows
      reverse_blocks_entity_indexing
      reverse_data_indexing
      reverse_prunned_blocks_entity_indexing
      reverse_raw_blocks_entity_indexing
      sorted_enumerate
      text_cleaning_method
      to_path
      update_top_results
      values_given
      workflows_to_dataframe
   
   .. rubric:: Classes

   .. autosummary::
   
      DatasetScheduler
      EntityScheduler
      FrequencyEvaluator
      PositionIndex
      PredictionData
      SubsetIndexer
      Tokenizer
      WordQgramTokenizer