Python Record Linkage Toolkit - how to retrieve comparator values

65 views Asked by At

I am using Python's name matching tool, recordlinkage

Does anyone know how to retrieve the comparator values from this algorithm?

For example, following the example "Approach 2 - Python Record Linkage Toolkit" in this link https://pbpython.com/record-linking.html, while running the below code:

features = compare.compute(candidates, hospital_accounts, hospital_reimbursement)

Is there a way to save and retrun comparator values as a result of computing similarity between the names in a pair?

According to this Python document https://recordlinkage.readthedocs.io/en/latest/ref-compare.html , recordlinkage.compare.string uses the below method to compute the similarity:

method (str, default 'levenshtein') – An approximate string comparison method. Options are [‘jaro’, ‘jarowinkler’, ‘levenshtein’, ‘damerau_levenshtein’, ‘qgram’, ‘cosine’, ‘smith_waterman’, ‘lcs’]. Default: ‘levenshtein’

Is there any way to retrieve the values from this computation?

Thank you

0

There are 0 answers