[Beta]: Implementation in Apache Spark of the EM algorithm to estimate parameters of Fellegi-Sunter's canonical model of record linkage.
Project description
splink: Probabilistic record linkage and deduplication at scale
WARNING: Splink is is currently in beta testing. Please feel free to try it, but note this software is not fully tested, and the interface is likely to continue to change.
splink
implements Fellegi-Sunter's canonical model of record linkage in Apache Spark, including EM algorithm to estimate parameters of the model.
The aims of splink
are to:
-
Work at much greater scale than current open source implementations (100 million records +).
-
Get results faster than current open source implementations - with runtimes of less than an hour.
-
Have a highly transparent methodology, so the match scores can be easily explained both graphically and in words
-
Have accuracy similar to some of the best alternatives
Installation
splink
is a Python package. It uses the Spark Python API to execute data linking jobs in a Spark cluster. It has been tested in Apache Spark 2.3 and 2.4.
Install splink using
pip install splink
Interactive demo
You can run demos of splink
in an interactive Jupyter notebook by clicking the button below:
Documentation
The best documentation is currently a series of demonstrations notebooks in the splink_demos repo.
We also provide an interactive splink
settings editor and example settings here
The statistical model behind splink
is the same as that used in the R fastLink package. Accompanying the fastLink package is an academic paper that describes this model. This is the best place to start for users wanting to understand the theory about how splink
works.
You can read a short blog post about splink
here.
Video intro
You can find a short video introducing splink
and running though an introductory demo here.
Acknowledgements
We are very grateful to ADR UK (Administrative Data Research UK) for providing funding for this work as part of the Data First project.
We are also very grateful to colleagues at the UK's Office for National Statistics for their expert advice and peer review of this work.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.