On 01/24/2012 10:49 AM, Olivier Grisel wrote: > 2012/1/24 Dimitrios Pritsos<[email protected]>: >> Thank you very much for the advice. I will try this too(today!). >> however, it seems that I might need to use the partial_fit() in the near >> feature after I will collect/crawl a new corpus. >> So a question is, my result (20%) was due to some short of bug in >> partial_fit() or my incorrect use of this function? > Unless you dataset is really big (e.g. ~1e6 samples), you will need to > pass through your chunked dataset many times when using partial_fit > before reaching convergence.
I think that was my mistake, I was passing every chunk only one time. Although my n_itr was 40 in my quick-n-dirty test. > The fit method is implemented by using the same underlying method is > for partial_fit so you should get the same results of accuracy if you > reuse the same hypeparamaters in the constructor such as alpha. > Thanks again. ------------------------------------------------------------------------------ Keep Your Developer Skills Current with LearnDevNow! The most comprehensive online learning library for Microsoft developers is just $99.99! Visual Studio, SharePoint, SQL - plus HTML5, CSS3, MVC3, Metro Style Apps, more. Free future releases when you subscribe now! http://p.sf.net/sfu/learndevnow-d2d _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
