Releases: AstraZeneca/rexmex
Releases · AstraZeneca/rexmex
0.1.3 fix scikit-learn dependency
What's Changed
- scikit-learn dependency fix by @dobraczka
- minor type fixes by @kajocina
Full Changelog: v_00102...release-v0.1.3
0.1.2. Unfix pandas version and bug fixes
What's Changed
- Docstring fix by @kajocina in #47
- added CoverageScoreCard to init by @kajocina in #48
- Remove broken link to examples by @benedekrozemberczki in #50
- Unfix pandas version in RexMex requirements by @GavEdwards in #54
- Release 0.1.2 by @GavEdwards in #55
Note: version 0.1.2 due to an issue with creating the 0.1.1 release.
Full Changelog: v_00100...v_00102
0.1.0. Default classification function swap, item and user coverage
0.0.15. Improved tests, binarize annotation, scorecard interface
0.0.14. Metric Annotations 🦖🦖
What's Changed 🦖🦖
- Demonstrate annotating structured metadata to classification functions by @cthoyt in #29
- Add additional classification function annotations by @cthoyt in #35
Full Changelog: v_00013...v_00014
0.0.13. Filter data instances and expose metric calculations
- New method to filter training, testing, and validation instances.
- Exposing the get_performance_metrics() method.
0.0.12 Import Fixes
Fixes the import all
0.0.11. New Ranking Metrics
New ranking metrics added are:
- Geometric Mean Rank
- Mean Rank
- Mean Reciprocal Rank
0.0.10. Ranking Metrics
Adds the following ranking metrics
- Reciprocal Rank
- Mean Reciprocal Rank (MRR)
- Average Precision@K (AP@K)
- Mean Average Percision@K (MAP@K)
- Average Recall@K (AR@K)
- Mean Average Recall@K (MAR@K)
- HITS@K
- Spearman's Rho
- Kendall Tau
- Intra List Similarity
- Personalization
- Novelty
- NPDM
- DCG
- NDCG
0.0.9. Metric set exposure
- The metric sets on scorecards are exposed.