search

vintasoftware / entity-embed

PyTorch library for transforming entities like companies, products, etc. into vectors to support scalable Record Linkage / Entity Resolution using Approximate Nearest Neighbors.
https://entity-embed.readthedocs.io/en/latest/
MIT License
147 stars 15 forks source link

Simplify examples #17

Closed fjsj closed 3 years ago

fjsj commented 3 years ago

Left only 2 examples, commented more on them. The benchmarks for f1 scores are still there.

Had to do some changes on defaults and also removed the unused datamodule (renamed PairwiseDataModule to LinkageDataModule, and used only it).

fjsj commented 3 years ago

@rvlb please review closely and try to run the notebooks notebooks/Deduplication-Example.ipynb and notebooks/Record-Linkage-Example.ipynb