.dockerignore
.flake8
.gitignore
.pre-commit-config.yaml
Dockerfile
LICENSE.txt
NOTICE.txt
README.md
conftest.py
pyproject.toml
.github/workflows/docker-build.yml
doc/developer.md
docs/.buildinfo
docs/.buildinfo.bak
docs/.nojekyll
docs/CNAME
docs/changelog.html
docs/column_mappings.html
docs/comparison_features.html
docs/comparisons.html
docs/config.html
docs/feature_selection_transforms.html
docs/genindex.html
docs/index.html
docs/installation.html
docs/introduction.html
docs/link_tasks.html
docs/model_exploration.html
docs/models.html
docs/objects.inv
docs/pipeline_features.html
docs/running_the_program.html
docs/search.html
docs/searchindex.js
docs/substitutions.html
docs/use_examples.html
docs/_sources/changelog.md.txt
docs/_sources/column_mappings.md.txt
docs/_sources/comparison_features.md.txt
docs/_sources/comparisons.md.txt
docs/_sources/config.md.txt
docs/_sources/feature_selection_transforms.md.txt
docs/_sources/index.rst.txt
docs/_sources/installation.md.txt
docs/_sources/introduction.md.txt
docs/_sources/link_tasks.md.txt
docs/_sources/model_exploration.md.txt
docs/_sources/models.md.txt
docs/_sources/pipeline_features.md.txt
docs/_sources/running_the_program.md.txt
docs/_sources/substitutions.md.txt
docs/_sources/use_examples.md.txt
docs/_static/alabaster.css
docs/_static/basic.css
docs/_static/custom.css
docs/_static/doctools.js
docs/_static/documentation_options.js
docs/_static/file.png
docs/_static/github-banner.svg
docs/_static/jquery-3.5.1.js
docs/_static/jquery.js
docs/_static/language_data.js
docs/_static/minus.png
docs/_static/plus.png
docs/_static/pygments.css
docs/_static/searchtools.js
docs/_static/sphinx_highlight.js
docs/_static/underscore-1.13.1.js
docs/_static/underscore.js
examples/tutorial/.gitignore
examples/tutorial/README.md
examples/tutorial/tutorial.py
examples/tutorial/tutorial_config.toml
examples/tutorial/data/A.csv
examples/tutorial/data/B.csv
hlink/__init__.py
hlink/errors.py
hlink.egg-info/PKG-INFO
hlink.egg-info/SOURCES.txt
hlink.egg-info/dependency_links.txt
hlink.egg-info/entry_points.txt
hlink.egg-info/requires.txt
hlink.egg-info/top_level.txt
hlink/configs/__init__.py
hlink/configs/load_config.py
hlink/linking/README.md
hlink/linking/__init__.py
hlink/linking/link_run.py
hlink/linking/link_step.py
hlink/linking/link_task.py
hlink/linking/table.py
hlink/linking/table_definitions.csv
hlink/linking/util.py
hlink/linking/core/__init__.py
hlink/linking/core/classifier.py
hlink/linking/core/column_mapping.py
hlink/linking/core/comparison.py
hlink/linking/core/comparison_feature.py
hlink/linking/core/dist_table.py
hlink/linking/core/model_metrics.py
hlink/linking/core/pipeline.py
hlink/linking/core/substitutions.py
hlink/linking/core/threshold.py
hlink/linking/core/transforms.py
hlink/linking/hh_matching/__init__.py
hlink/linking/hh_matching/hh_matching.py
hlink/linking/hh_matching/link_step_block_on_households.py
hlink/linking/hh_matching/link_step_filter.py
hlink/linking/hh_matching/templates/hh_blocked_matches.sql
hlink/linking/hh_matching/templates/hh_potential_matches.sql
hlink/linking/hh_model_exploration/__init__.py
hlink/linking/hh_model_exploration/hh_model_exploration.py
hlink/linking/hh_model_exploration/templates/.gitkeep
hlink/linking/hh_training/__init__.py
hlink/linking/hh_training/hh_training.py
hlink/linking/hh_training/templates/.gitkeep
hlink/linking/matching/__init__.py
hlink/linking/matching/link_step_explode.py
hlink/linking/matching/link_step_match.py
hlink/linking/matching/link_step_score.py
hlink/linking/matching/matching.py
hlink/linking/matching/templates/potential_matches.sql
hlink/linking/matching/templates/potential_matches_count.sql
hlink/linking/matching/templates/potential_matches_universe.sql
hlink/linking/model_exploration/__init__.py
hlink/linking/model_exploration/link_step_create_features.py
hlink/linking/model_exploration/link_step_ingest_file.py
hlink/linking/model_exploration/link_step_train_test_models.py
hlink/linking/model_exploration/model_exploration.py
hlink/linking/model_exploration/templates/.gitkeep
hlink/linking/preprocessing/__init__.py
hlink/linking/preprocessing/link_step_prep_dataframes.py
hlink/linking/preprocessing/link_step_register_raw_dfs.py
hlink/linking/preprocessing/preprocessing.py
hlink/linking/preprocessing/templates/attach_family_col.sql
hlink/linking/preprocessing/templates/attach_neighbor_col.sql
hlink/linking/preprocessing/templates/attach_related_col.sql
hlink/linking/preprocessing/templates/attach_related_cols_as_rows.sql
hlink/linking/preprocessing/templates/hh_nbor.sql
hlink/linking/preprocessing/templates/hh_nbor_rank.sql
hlink/linking/preprocessing/templates/training_data_subset.sql
hlink/linking/reporting/__init__.py
hlink/linking/reporting/link_step_export_crosswalk.py
hlink/linking/reporting/link_step_report_r2_percent_linked.py
hlink/linking/reporting/link_step_report_representivity.py
hlink/linking/reporting/reporting.py
hlink/linking/reporting/templates/.gitkeep
hlink/linking/templates/shared/aggregate_features.sql
hlink/linking/templates/shared/all_household_members.sql
hlink/linking/templates/shared/attach_variable.sql
hlink/linking/templates/shared/drop_links.sql
hlink/linking/templates/shared/hh_aggregate_features.sql
hlink/linking/templates/shared/pl_easy_features.sql
hlink/linking/templates/shared/potential_matches_base_features.sql
hlink/linking/templates/shared/scored_potential_matches.sql
hlink/linking/templates/shared/select_columns.sql
hlink/linking/templates/shared/tfam_tables.sql
hlink/linking/templates/shared/training_features.sql
hlink/linking/templates/shared/training_prepped.sql
hlink/linking/templates/shared/includes/all_household_members_selects_a.sql
hlink/linking/templates/shared/includes/all_household_members_selects_b.sql
hlink/linking/training/__init__.py
hlink/linking/training/link_step_create_comparison_features.py
hlink/linking/training/link_step_ingest_file.py
hlink/linking/training/link_step_save_model_metadata.py
hlink/linking/training/link_step_train_and_save_model.py
hlink/linking/training/training.py
hlink/linking/training/templates/.gitkeep
hlink/linking/transformers/__init__.py
hlink/linking/transformers/float_cast_transformer.py
hlink/linking/transformers/rename_prob_column.py
hlink/linking/transformers/rename_vector_attributes.py
hlink/scripts/__init__.py
hlink/scripts/main.py
hlink/scripts/main_loop.py
hlink/scripts/lib/__init__.py
hlink/scripts/lib/conf_validations.py
hlink/scripts/lib/io.py
hlink/scripts/lib/linking_ops.py
hlink/scripts/lib/table_ops.py
hlink/scripts/lib/util.py
hlink/scripts/lib/experimental/__init__.py
hlink/scripts/lib/experimental/reporting.py
hlink/scripts/lib/experimental/tfam.py
hlink/spark/__init__.py
hlink/spark/factory.py
hlink/spark/session.py
hlink/spark/jars/hlink_lib-assembly-1.0.jar
hlink/tests/__init__.py
hlink/tests/conf_validations_test.py
hlink/tests/config_loader_test.py
hlink/tests/conftest.py
hlink/tests/hh_matching_test.py
hlink/tests/hh_model_exploration_test.py
hlink/tests/integration_score_with_trained_models_test.py
hlink/tests/integration_test.py
hlink/tests/linking_util_test.py
hlink/tests/logging_test.py
hlink/tests/main_loop_test.py
hlink/tests/markers.py
hlink/tests/matching_blocking_explode_test.py
hlink/tests/matching_comparison_features_test.py
hlink/tests/matching_geo_distance_test.py
hlink/tests/matching_potential_matches_test.py
hlink/tests/matching_potential_matches_universe_test.py
hlink/tests/matching_scoring_test.py
hlink/tests/matching_test.py
hlink/tests/model_exploration_test.py
hlink/tests/preprocessing_test.py
hlink/tests/reporting_test.py
hlink/tests/scala_udf_test.py
hlink/tests/spark_connection_test.py
hlink/tests/spark_factory_test.py
hlink/tests/table_test.py
hlink/tests/training_test.py
hlink/tests/transformers_test.py
hlink/tests/conf/duplicate_col_maps.toml
hlink/tests/conf/duplicate_comp_features.toml
hlink/tests/conf/duplicate_feature_sel.toml
hlink/tests/conf/integration.toml
hlink/tests/conf/missing_datasource_a.toml
hlink/tests/conf/missing_datasource_b.toml
hlink/tests/conf/no_id_column_a.toml
hlink/tests/conf/no_id_column_b.toml
hlink/tests/conf/test.json
hlink/tests/conf/test1.toml
hlink/tests/conf/test_conf_flag_run.json
hlink/tests/conf/test_run.json
hlink/tests/core/__init__.py
hlink/tests/core/classifier_test.py
hlink/tests/core/column_mapping_test.py
hlink/tests/core/comparison_feature_test.py
hlink/tests/core/comparison_test.py
hlink/tests/core/model_metrics_test.py
hlink/tests/core/pipeline_test.py
hlink/tests/core/substitutions_test.py
hlink/tests/core/threshold_test.py
hlink/tests/core/transforms_test.py
hlink/tests/input_data/19thc_nativity_test_hhs.csv
hlink/tests/input_data/19thc_nativity_test_hhs_a.csv
hlink/tests/input_data/19thc_nativity_test_hhs_b.csv
hlink/tests/input_data/birthyr_replace.csv
hlink/tests/input_data/calc_mfbpl_a.csv
hlink/tests/input_data/calc_mfbpl_b.csv
hlink/tests/input_data/county_distances.csv
hlink/tests/input_data/female.csv
hlink/tests/input_data/ha_source.csv
hlink/tests/input_data/handle_null.csv
hlink/tests/input_data/hb_source.csv
hlink/tests/input_data/hh_matching_a.csv
hlink/tests/input_data/hh_matching_b.csv
hlink/tests/input_data/hh_predicted_matches_reporting.csv
hlink/tests/input_data/hh_year_a.csv
hlink/tests/input_data/hh_year_b.csv
hlink/tests/input_data/hhpm_agg_test.csv
hlink/tests/input_data/households_b.parquet
hlink/tests/input_data/integration_a.csv
hlink/tests/input_data/integration_b.csv
hlink/tests/input_data/jw_blocking_test_a.csv
hlink/tests/input_data/jw_blocking_test_b.csv
hlink/tests/input_data/male.csv
hlink/tests/input_data/matched_men.csv
hlink/tests/input_data/matching_or_group_test_a.csv
hlink/tests/input_data/matching_or_group_test_b.csv
hlink/tests/input_data/matching_test_a.csv
hlink/tests/input_data/matching_test_b.csv
hlink/tests/input_data/nativity_test_data_a.csv
hlink/tests/input_data/nativity_test_data_b.csv
hlink/tests/input_data/new_hh_test_td.csv
hlink/tests/input_data/popularity.csv
hlink/tests/input_data/potential_matches.csv
hlink/tests/input_data/potential_matches_agg.csv
hlink/tests/input_data/potential_matches_ids_only.csv
hlink/tests/input_data/potential_matches_sql_condition_marst_warn.csv
hlink/tests/input_data/predicted_matches_reporting.csv
hlink/tests/input_data/predicted_matches_test.csv
hlink/tests/input_data/prepped_df_a_agg.csv
hlink/tests/input_data/prepped_df_b_agg.csv
hlink/tests/input_data/prepped_df_reporting.csv
hlink/tests/input_data/raw_df_reporting.csv
hlink/tests/input_data/region.csv
hlink/tests/input_data/regioncode.csv
hlink/tests/input_data/rel_rows_test_a.csv
hlink/tests/input_data/rel_rows_test_b.csv
hlink/tests/input_data/reporting_hh_predicted_matches.csv
hlink/tests/input_data/reporting_predicted_matches.csv
hlink/tests/input_data/reporting_prepped_df_a.csv
hlink/tests/input_data/representivity.csv
hlink/tests/input_data/scored_matches_household_test.csv
hlink/tests/input_data/scored_matches_test_data.csv
hlink/tests/input_data/sql_condition_marst_warn_a.csv
hlink/tests/input_data/sql_condition_marst_warn_b.csv
hlink/tests/input_data/statedist.csv
hlink/tests/input_data/street_abbrevs.csv
hlink/tests/input_data/street_abbrevs_most_common.csv
hlink/tests/input_data/test_csv_data_a.csv
hlink/tests/input_data/test_csv_data_b.csv
hlink/tests/input_data/test_prepped_data_a.csv
hlink/tests/input_data/test_prepped_data_b.csv
hlink/tests/input_data/test_street_names_data.csv
hlink/tests/input_data/threshold_ratio_test.csv
hlink/tests/input_data/threshold_ratio_test_data_2.csv
hlink/tests/input_data/training_data.csv
hlink/tests/input_data/training_data_doubled.csv
hlink/tests/input_data/training_data_households.csv
hlink/tests/input_data/training_data_households.parquet
hlink/tests/input_data/training_data_long.csv
hlink/tests/input_data/training_data_long_a.csv
hlink/tests/input_data/training_data_long_b.csv
hlink/tests/input_data/conf_validation/a.csv
hlink/tests/input_data/conf_validation/b.csv
hlink/tests/input_data/conf_validation/empty.csv
hlink/tests/input_data/crosswalk/hh_predicted_matches.csv
hlink/tests/input_data/crosswalk/predicted_matches.csv
hlink/tests/input_data/crosswalk/raw_df_a.csv
hlink/tests/input_data/crosswalk/raw_df_b.csv
hlink/tests/input_data/test_parquet_data_a.parquet/._SUCCESS.crc
hlink/tests/input_data/test_parquet_data_a.parquet/.part-00000-8465f06e-9bb0-4817-81eb-813ccf07429a-c000.snappy.parquet.crc
hlink/tests/input_data/test_parquet_data_a.parquet/_SUCCESS
hlink/tests/input_data/test_parquet_data_a.parquet/part-00000-8465f06e-9bb0-4817-81eb-813ccf07429a-c000.snappy.parquet
hlink/tests/input_data/test_parquet_data_b.parquet/._SUCCESS.crc
hlink/tests/input_data/test_parquet_data_b.parquet/.part-00000-bb515275-04b4-4a16-80f1-5cc21450b93f-c000.snappy.parquet.crc
hlink/tests/input_data/test_parquet_data_b.parquet/_SUCCESS
hlink/tests/input_data/test_parquet_data_b.parquet/part-00000-bb515275-04b4-4a16-80f1-5cc21450b93f-c000.snappy.parquet
hlink/tests/plugins/__init__.py
hlink/tests/plugins/datasources.py
hlink/tests/plugins/external_data_paths.py
hlink/tests/validation_data/crosswalks/crosswalk.csv
hlink/tests/validation_data/crosswalks/crosswalk_with_round.csv
hlink/tests/validation_data/training_p_all.parquet/._SUCCESS.crc
hlink/tests/validation_data/training_p_all.parquet/.part-00000-6c9e5760-174a-4652-b687-6823087ed5bf-c000.snappy.parquet.crc
hlink/tests/validation_data/training_p_all.parquet/_SUCCESS
hlink/tests/validation_data/training_p_all.parquet/part-00000-6c9e5760-174a-4652-b687-6823087ed5bf-c000.snappy.parquet
scala_jar/build.sbt
scala_jar/project/assembly.sbt
scala_jar/project/build.properties
scala_jar/src/main/scala/com/isrdi/udfs/ArrayToString.scala
scala_jar/src/main/scala/com/isrdi/udfs/AttachHHColumn.scala
scala_jar/src/main/scala/com/isrdi/udfs/AttachRelatedRows.scala
scala_jar/src/main/scala/com/isrdi/udfs/ExtraChildren.scala
scala_jar/src/main/scala/com/isrdi/udfs/ExtractNeighbors.scala
scala_jar/src/main/scala/com/isrdi/udfs/HHCompare.scala
scala_jar/src/main/scala/com/isrdi/udfs/HHDrop.scala
scala_jar/src/main/scala/com/isrdi/udfs/HHGetFirstValue.scala
scala_jar/src/main/scala/com/isrdi/udfs/HasMatchingElement.scala
scala_jar/src/main/scala/com/isrdi/udfs/JWCompare.scala
scala_jar/src/main/scala/com/isrdi/udfs/JWRate.scala
scala_jar/src/main/scala/com/isrdi/udfs/JWRelatedRows.scala
scala_jar/src/main/scala/com/isrdi/udfs/MaxJWCompare.scala
scala_jar/src/main/scala/com/isrdi/udfs/ParseProbabilityVector.scala
scala_jar/src/main/scala/com/isrdi/udfs/SerJaroWinklerSimilarity.scala
scala_jar/src/main/scala/com/isrdi/udfs/VectorToString.scala
sphinx-docs/Makefile
sphinx-docs/changelog.md
sphinx-docs/column_mappings.md
sphinx-docs/comparison_features.md
sphinx-docs/comparisons.md
sphinx-docs/conf.py
sphinx-docs/config.md
sphinx-docs/feature_selection_transforms.md
sphinx-docs/index.rst
sphinx-docs/installation.md
sphinx-docs/introduction.md
sphinx-docs/link_tasks.md
sphinx-docs/make.bat
sphinx-docs/model_exploration.md
sphinx-docs/models.md
sphinx-docs/pipeline_features.md
sphinx-docs/running_the_program.md
sphinx-docs/substitutions.md
sphinx-docs/use_examples.md