Common strings in unstructured data

adam_barrilleauadam_barrilleau Member Posts: 1 Newbie
I am new to Rapidminer and this is my common use case for looking at using the product.  I have a recordset that has one column of unstructured text.  Within those records there are common dimensions and lengths that have been typed in by sales personnel.  i need to identify similar, common strings and then group & rank those.  It is not a situation where i provide a search string to locate.  I need to have the software identify all the similar strings and then group/rank them.  Any guidance on how to approach this would be greatly appreciated.  Thanks in advance.

Answers

  • kaymankayman Member Posts: 662 Unicorn
    Seems like a combination of different things. Start already with the 'generate attributes' operator and use the prefix / suffix / length options to get a first raw split of your content using the mentioned dimensions and length.

    From there take it further, but without some practical examples it is hard to give further advice, so is it possible to share more details? 
Sign In or Register to comment.