Search code examples
nlpnltk

How do cluster data below using NLP?

My Data looks like this. I would like to clean, vectorize and cluster using NLP. How should I approach the problem? I am pretty new to NLP

 (1113, '10% Off Your Purchase'),
 (1114, '20% Off Juice (Limit 3)'),
 (1120, 'BOGO Sandwich / Bagel'),
 (1138, '$5 Off $15 or More'),
 (1145, 'free 15mL bottle of juice'),
 (1146, 'free 15mL bottle of juice'),
 (1148, "10% Off (can't combine)"),
 (1158, '10% Off or 20% Off Liquid'),
 (1159, 'Free Vape Gift'),
 (1165, '20% Off Any Single Item'),
 (1166, '10% Off Any Single Item'),```
Solution

  • You can generate word vectors and apply a clustering algorithm to cluster the data. Word vectors are good at identifying the context sensitiveness of data.