Text Preprocessing

As part of scheduling training to create a model,

In the Text preprocessing pane of the new TDO window, you can remove extraneous text from the Training Messages of a Training Data Object. You create filters (patterns) that search for text and perform various deletion operations. This can be helpful when the e-mails that you want to use for training contain significant amounts of text is:

• Irrelevant or misleading for classification purposes, and
• Identifiable by a regular expression.

Use the Text preprocessing pane:

Text Preprocessing

1. Click the plus-sign icon to create a new rule.
2. Types of rule:
   • DELETE AFTER—Search for a match to the pattern body, then delete all text after and including the matching text.
     
   • DELETE BEFORE—Search for a match to the pattern body, then delete all text before and including the matching text.
     
   • DELETE ALL IF FIND—Search for a match to the pattern body, then delete the entire e-mail that includes the matching text.
     
   • DELETE ALL IF NOT FIND—Search for a match to the pattern body, then delete the entire e-mail if it does not include the matching text.
     
   • DELETE PATTERN—Search for a match to the pattern body, then delete only the text that matches the pattern.
3. Test the pattern. Enter text, the result appears. If you modify the rule, you'll have to enter the text again to see the result from the modified rule.