1. 14 Feb, 2022 4 commits
    • Paulo Medeiros's avatar
      Bugfixes, changes to metrics & clustering opts. · 5a8b6aa9
      Paulo Medeiros authored
      Summary of main changes below:
      
      Added:
          - New metrics calculation methods:
              - correlation_aware_euclidean (the new default)
              - haversine_plus_euclidean
              - haversine_plus_manhattan (the only one implemented previously)
          - "unclusterable_data_columns" general config option
          - Allow choice of HDBSCAN's cluster_selection_method
      
      Changed:
          - Default HDBSCAN method from "leaf" to "eom"
          - Default min_samples and min_cluster_size: 5 --> 10
          - Changed internal data normalisation scheme
          - Metrics has now its own section in config file
          - Use a more strict GLOSH outlier removal score threshold
          - Visualised map uses same proj params as the configured in domain
          - Remove unused "tstep" from domain configs
      
      Fixed:
          - InvalidIndexError caught after pandas 1.4.0 update
          - Some crashes in outlier removal methods (solves #5)
          - flakehell cannot import 'MergedConfigParser'
          - Some warnings
      5a8b6aa9
    • Paulo Medeiros's avatar
      Update code version to v0.4.0 · f148f400
      Paulo Medeiros authored
      f148f400
    • Paulo Medeiros's avatar
      More updates to poetry in gitlab-ci · e120ac0b
      Paulo Medeiros authored
      e120ac0b
    • Paulo Medeiros's avatar
      Update poetry installer in gitlab-ci · 61f96141
      Paulo Medeiros authored
      61f96141
  2. 10 Feb, 2022 3 commits
    • Paulo Medeiros's avatar
      Update deps. Adap code accordingly. · d4cadaf6
      Paulo Medeiros authored
      d4cadaf6
    • Paulo Medeiros's avatar
      Tweaks to clustering/outlier removal params. Fixes · 8029cbbe
      Paulo Medeiros authored
      Summary of main changes below:
      
      Changed:
          - Default HDBSCAN method from "leaf" to "eom"
          - Default min_samples and min_cluster_size: 5 --> 10
          - Internal data normalisation scheme.
          - Use a more strict GLOSH outlier removal score threshold
      
      Fixed:
          - flakehell cannot import 'MergedConfigParser'
          - InvalidIndexError caught after pandas 1.4.0 update
      8029cbbe
    • Paulo Medeiros's avatar
      Fix InvalidIndexError: pandas df.at --> df.loc · 1fc97669
      Paulo Medeiros authored
      The code was using the "at" method of pandas DataFrame with multiple
      indices, and that was accepted by pandas < 1.4.0. But their docs do
      say that "at" is for single element access only, whereas "loc" is for
      access to multiple elements.
      1fc97669
  3. 09 Feb, 2022 1 commit
  4. 08 Nov, 2021 6 commits
  5. 05 Nov, 2021 5 commits
  6. 04 Nov, 2021 3 commits
  7. 03 Nov, 2021 5 commits
  8. 25 Oct, 2021 2 commits
  9. 14 Jul, 2021 1 commit
  10. 13 Jul, 2021 1 commit
  11. 12 Jul, 2021 5 commits
  12. 09 Jul, 2021 4 commits