2014-02-21 14:43 GMT+01:00 Florian Lindner <[email protected]>: > Hello, > > I use the MultinomialNB classifier for mail classification. Classes are like > Notifications, Bulk Mail und Server Status Messages. Additionally there is > unclassified mail, which is my normal mail that doesn't fit in one of these > categories. > > What is the best learning strategy? Keeping these mails untrained or create a > category Normal and train it to this category?
The choice is yours: it depends if your goal is to keep unclassified mail as such in your inbox or if your goal is to classify them all as Notifications, Bulk Mail und Server Status Messages. -- Olivier http://twitter.com/ogrisel - http://github.com/ogrisel ------------------------------------------------------------------------------ Managing the Performance of Cloud-Based Applications Take advantage of what the Cloud has to offer - Avoid Common Pitfalls. Read the Whitepaper. http://pubads.g.doubleclick.net/gampad/clk?id=121054471&iu=/4140/ostg.clktrk _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
