For debugging entity matching, it is useful to be able to iterate over clusters of a specific size, e.g. clusters of size 12 given 2 datasets, to investigate the reasons for false positive matches.
For this /evaluation.py should be extended with a method that returns an iterator over clusters of a given size.
Parameters
size: size of clusters to be selected
max: maximum number of clusters (default=none)
For debugging entity matching, it is useful to be able to iterate over clusters of a specific size, e.g. clusters of size 12 given 2 datasets, to investigate the reasons for false positive matches.
For this /evaluation.py should be extended with a method that returns an iterator over clusters of a given size.
Parameters
size: size of clusters to be selected
max: maximum number of clusters (default=none)