The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here

Naive Bayes - RapidMiner Operator Reference manual

ozzboyozzboy Member Posts: 1 Learner III
edited September 2019 in Help
I was reading
through the Naive Bayes Model in the RapidMiner Operator Reference (pdf) found here -http://rapidminer.com/documentation/
and had a question.
In the Naive Bayes model (page 653/990) they are calculating the maximum
calculated probability for each label value.
1. They calculate the Posterior probability of label=Yes = >9/14,
2. Value from distribution table when Outlook = sunny and label = yes (i.e.*0.223*)

I understand  posterior probability 9/14, How did they calculate 0.223? How did they arrive at this value?

Please let me know.

Thanks,
Ram
Tagged:

Answers

  • homburghomburg Employee-RapidMiner, Member Posts: 114 RM Data Scientist
    Hi ozzboy,

    the value from the distribution table for the case Outlook = sunny and label = yes  will be calculated as 2 / 9 because there are 2 examples that fit the constraints having 9 times the occurrence of label = yes. The values in the operators manual do slightly differ because they have been computed using the Laplace option. If you disable this default parameter you should get a distribution table containing the expected values.

    Cheers,
    Helge
  • imsophieimsophie Member Posts: 1 Learner II

    How the laplance correction work in this case to derive 0.2333?

Sign In or Register to comment.