naives bayes prediction

Hi,

I am trying to deploy a Naives bayes network.But in spite of I am getting an dependecy network that relates 3 variables,

I've got an classification Matrix where all the predicted values are the same.

Counts for nai 1 on [Cod Conceito]PredictedMissing (Actual)0 (Actual)1 (Actual)2 (Actual)3 (Actual)4 (Actual)5 (Actual)6 (Actual)7 (Actual)8 (Actual)9 (Actual)Missing0000000000000000000000012057578249911292102237431780271989200000000000300000000000400000000000500000000000600000000000700000000000800000000000900000000000

I tried to deploy the same data on Tanagra's software and I've got predictions on the other values.

I tried to change all the parameters but the results are always the same

thanks in advance

Post This question in the data mining forum: http://forums.microsoft.com/MSDN/ShowForum.aspx?ForumID=81&SiteID=1|||

What happens when you try to use decision trees?

One clarification - our Naive Bayes algorithm is a Naive Bayes classifier, not a Naive Bayes network. This may be the difference between the packages, but I'm not familiar with the package you mentioned.

|||

with decision trees it appears with several nodes but the classification matrix have the same distribution. only value 1 has predicted values

|||

Is the target column modeled as Discrete or Discretized? If Discretized, could you try changing it to discrete?