Remove Numeric and other data from Text Mining

aks
aks New Altair Community Member
edited November 5 in Community Q&A
Hi, I am new user to RP. I have imported a file for sentiment analysis. It is a financial file, I want to remove the number ($, 0, 1, ..9) from the loaded file. Which operator should I use? Thanks in advance.
Tagged:

Answers

  • aks
    aks New Altair Community Member
    RP(Rapidminer Platform)
  • kayman
    kayman New Altair Community Member
    Use the replace token operator.

    If you click the edit icon and then the drop down you have a few pre-selections, usually the punctuation character (replace with spaceor so) works fine in these cases, you may want to add the number range 0-9 also if it's needed



  • Telcontar120
    Telcontar120 New Altair Community Member
    You can also just use the Replace operator on the text before tokenizing and remove [0-9]+ from the attribute(s) in question.