Timeline for What is the Probability Distribution of NLTK Naive Bayes?
Current License: CC BY-SA 3.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| May 23, 2017 at 12:39 | history | edited | CommunityBot |
replaced http://stackoverflow.com/ with https://stackoverflow.com/
|
|
| Jul 30, 2014 at 16:43 | history | edited | gung - Reinstate Monica | CC BY-SA 3.0 |
formatted & edited
|
| Jul 30, 2014 at 15:49 | answer | added | small_data88 | timeline score: 2 | |
| Jun 28, 2014 at 15:48 | comment | added | HIGGINS | Sir, It may also be an interesting case, like, "Binning data has the advantages of simplicity and avoiding the need to make any particular explicit assumptions about the mathematical distribution (such as Gaussian or Poisson) of the data" in msdn.microsoft.com/en-us/magazine/jj891056.aspx. NLTK Google Group has no answer though. Regards, Subhabrata Banerjee. | |
| Jun 28, 2014 at 15:26 | comment | added | HIGGINS | Thank you for your kind answer. I am no great in Python rather may be very silly at times. Multinomial may be the answer, if it tackles Binomial issues it may as Binomial is a special case of Multinomial. If Gaussian is required I'll pick up Scikit. Regards, Subhabrata Banerjee. | |
| Jun 28, 2014 at 14:29 | comment | added | shadowtalker | Why do you think it isn't multinomial? I don't know NLTK and I'm not great with Python but the source code makes it look like it's just binning the features and adding up frequencies, i.e. it's multinomial. | |
| Jun 28, 2014 at 11:38 | history | asked | HIGGINS | CC BY-SA 3.0 |