• .github
  • workflows
    • test_examples.yml
    • test_tutorials.yml
• data
  • febrl
    • dataset3.csv
    • dataset4a.csv
    • dataset4b.csv
    • source.txt
  • fake_1000.csv
  • fake_1000.parquet
  • fake_1000_combined.json
  • fake_1000_labels.csv
  • fake_20000.csv
  • fake_df_l.parquet
  • fake_df_l_link_dedupe_test.parquet
  • fake_df_r.parquet
  • fake_df_r_link_dedupe_test.parquet
  • historical_figures_with_errors_50k.parquet
  • pairwise_labels_to_estimate_m.csv
  • transactions_left.parquet
  • transactions_right.parquet
• demo_settings
  • real_time_settings.json
  • saved_model_from_demo.json
• examples
  • athena
    • dashboards
      • 50k_cluster.html
    • deduplicate_50k_synthetic.ipynb
  • duckdb
    • dashboards
      • 50k_cluster.html
      • 50k_deterministic_cluster.html
      • comparison_viewer_transactions.html
    • accuracy_analysis_from_labels_column.ipynb
    • deduplicate_50k_synthetic.ipynb
    • deterministic_dedupe.ipynb
    • febrl3.ipynb
    • febrl4.ipynb
    • link_only.ipynb
    • pairwise_labels.ipynb
    • quick_and_dirty_persons.ipynb
    • real_time_record_linkage.ipynb
    • transactions.ipynb
  • spark
    • deduplicate_1k_synthetic.ipynb
  • sqlite
    • dashboards
      • 50k_cluster.html
    • deduplicate_50k_synthetic.ipynb
• tutorials
  • 00_Tutorial_Introduction.ipynb
  • 01_Prerequisites.ipynb
  • 02_Exploratory_analysis.ipynb
  • 03_Blocking.ipynb
  • 04_Estimating_model_parameters.ipynb
  • 05_Predicting_results.ipynb
  • 06_Visualising_predictions.ipynb
  • 07_Quality_assurance.ipynb
  • cluster_studio.html
  • scv.html
• .gitignore
• README.md
• recreate_venv.sh
• requirements.txt
• runtime.txt
• scv.html