Dear Group, I was trying to run a small Naive Bayes Classifier program in Python using Python 2.6.5 [Python 2.6.5 (r265:79096, Mar 19 2010, 21:48:26) [MSC v.1500 32 bit (Intel)] on win32] using Windows XP SP2, with an annotated corpus of only 10,000 words. But, even with a 2GB RAM the system comes crashing. I cross cheked it can handle maximum of 1,000 words nicely. Does any one know of any one in this group know how to fix this issue. Best Regards, Subhabrata Banerjee.

asked Apr 04 '11 at 15:58

Subhabrata%20Banerjee's gravatar image

Subhabrata Banerjee
40222224


2 Answers:

Dear Sir, Thank you for your kind answer. I got it now. Best Regards, Subhabrata.

answered Apr 05 '11 at 00:16

Subhabrata%20Banerjee's gravatar image

Subhabrata Banerjee
40222224

Are you using a library or rolling your own? If you are rolling your own and don't have some ridiculous number of classes you should be easily able to handle many more than 10,000 distinct features by storing counts in a dictionary.

answered Apr 04 '11 at 23:12

alto's gravatar image

alto
60351124

Your answer
toggle preview

powered by OSQA

User submitted content is under Creative Commons: Attribution - Share Alike; Other things copyright (C) 2010, MetaOptimize LLC.