*Real project. Result shown above
-
Over 70,000 Supplier names normalized using Python.
-
Included a block of code written by students of Rutgers university for comparison
-
final version is using hard-coded logics and Python CleanCo Package
-
attempted to address matching for further normalization, but results found out not accurate
-
attempted machine learning clustering for further normalization , but results found out not accurate
Github Repository Link
