API

• emm package
  • Subpackages
    • emm.aggregation package
      • Submodules
      • emm.aggregation.base_entity_aggregation module
      • emm.aggregation.pandas_entity_aggregation module
      • emm.aggregation.spark_entity_aggregation module
      • Module contents
    • emm.base package
      • Submodules
      • emm.base.module module
      • emm.base.pipeline module
      • Module contents
    • emm.data package
      • Submodules
      • emm.data.create_data module
      • emm.data.negative_data_creation module
      • emm.data.noiser module
      • emm.data.prepare_name_pairs module
      • Module contents
    • emm.features package
      • Submodules
      • emm.features.base_feature_extractor module
      • emm.features.features_extra module
      • emm.features.features_lef module
      • emm.features.features_name module
      • emm.features.features_rank module
      • emm.features.features_vocabulary module
      • emm.features.pandas_feature_extractor module
      • Module contents
    • emm.helper package
      • Submodules
      • emm.helper.blocking_functions module
      • emm.helper.custom_path module
      • emm.helper.io module
      • emm.helper.sklearn_pipeline module
      • emm.helper.spark_custom_reader_writer module
      • emm.helper.spark_ml_pipeline module
      • emm.helper.spark_utils module
      • emm.helper.util module
      • Module contents
    • emm.indexing package
      • Submodules
      • emm.indexing.base_indexer module
      • emm.indexing.pandas_candidate_selection module
      • emm.indexing.pandas_cos_sim_matcher module
      • emm.indexing.pandas_naive_indexer module
      • emm.indexing.pandas_normalized_tfidf module
      • emm.indexing.pandas_sni module
      • emm.indexing.spark_candidate_selection module
      • emm.indexing.spark_character_tokenizer module
      • emm.indexing.spark_cos_sim_matcher module
      • emm.indexing.spark_indexing_utils module
      • emm.indexing.spark_normalized_tfidf module
      • emm.indexing.spark_sni module
      • emm.indexing.spark_word_tokenizer module
      • Module contents
    • emm.loggers package
      • Submodules
      • emm.loggers.logger module
      • emm.loggers.timer module
      • Module contents
    • emm.pipeline package
      • Submodules
      • emm.pipeline.base_entity_matching module
      • emm.pipeline.pandas_entity_matching module
      • emm.pipeline.spark_entity_matching module
      • Module contents
    • emm.preprocessing package
      • Submodules
      • emm.preprocessing.abbreviation_util module
      • emm.preprocessing.base_name_preprocessor module
      • emm.preprocessing.functions module
      • emm.preprocessing.pandas_functions module
      • emm.preprocessing.pandas_preprocessor module
      • emm.preprocessing.spark_functions module
      • emm.preprocessing.spark_preprocessor module
      • Module contents
    • emm.supervised_model package
      • Submodules
      • emm.supervised_model.base_supervised_model module
      • emm.supervised_model.pandas_supervised_model module
      • emm.supervised_model.spark_supervised_model module
      • Module contents
    • emm.threshold package
      • Submodules
      • emm.threshold.threshold_decision module
      • Module contents
  • Submodules
  • emm.parameters module
  • emm.resources module
    • data()
    • notebook()
  • emm.version module
  • Module contents
    • PandasEntityMatching
      • PandasEntityMatching.add_aggregation_layer()
      • PandasEntityMatching.add_supervised_model()
      • PandasEntityMatching.create_training_name_pairs()
      • PandasEntityMatching.decrease_window_by_one_step()
      • PandasEntityMatching.fit()
      • PandasEntityMatching.fit_classifier()
      • PandasEntityMatching.increase_window_by_one_step()
      • PandasEntityMatching.initialize()
      • PandasEntityMatching.load()
      • PandasEntityMatching.save()
      • PandasEntityMatching.set_return_sm_features()
      • PandasEntityMatching.test_classifier()
      • PandasEntityMatching.transform()
    • set_logger()