Naive Bayes for Numeric Attributes

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

Naive Bayes for Numeric Attributes

Abdrahman0x
Hi all,

I am working with Naive Bayes and could understand the algorithm
mathematically with nominal attributes but couldn't interrupt the results
with numeric attributes. My data is composed of numeric attriute and nominal
class. I found the following in one of the old posts:

1) The prior probability for the class value
2) For each attribute either:
  A) The parameters of the normal distribution computed from the observed
     values (numeric attribute) of the attribute conditioned on the
particular
     class value

But still couldn't understand how to perform the calculation. Can any one
explain with an example please.

Thank you
Abdrahman



--
Sent from: http://weka.8497.n7.nabble.com/
_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
To subscribe, unsubscribe, etc., visit https://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Reply | Threaded
Open this post in threaded view
|

Re: Naive Bayes for Numeric Attributes

Eibe Frank-3
This reply is a bit late, but there is an example in our data mining book, in the section on Simple Probabilistic Modeling.

Note that the WEKA implementation in NaiveBayes is slightly different because the calculation is done using the cumulative distribution function rather than the density function. NaiveBayesSimple in the simpleEducationalLearningSchemes package has an implementation based on the density function.

Cheers,
Eibe

On Wed, Nov 21, 2018 at 4:12 AM Abdrahman0x <[hidden email]> wrote:
Hi all,

I am working with Naive Bayes and could understand the algorithm
mathematically with nominal attributes but couldn't interrupt the results
with numeric attributes. My data is composed of numeric attriute and nominal
class. I found the following in one of the old posts:

1) The prior probability for the class value
2) For each attribute either:
  A) The parameters of the normal distribution computed from the observed
     values (numeric attribute) of the attribute conditioned on the
particular
     class value

But still couldn't understand how to perform the calculation. Can any one
explain with an example please.

Thank you
Abdrahman



--
Sent from: http://weka.8497.n7.nabble.com/
_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
To subscribe, unsubscribe, etc., visit https://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html

_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
To subscribe, unsubscribe, etc., visit https://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html