What is right way of calling Weka ND classifiers (e.g.,
and nestedDichotomies.DataNearBalancedND) on Matlab?
javaMethod('loadPackages','weka.core.WekaPackageManager', false, true,
method = weka.classifiers.meta.nestedDichotomies.ND;
comes with error:
Undefined variable "weka" or class
while the other classifiers working correctly.
Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences,
No.818, South Beijing Road,
Urumqi, Xinjiang, China, 830011.
Am I right that CVparameterSelection is not right choice for search of model
parameters in case of time series forecast ? Because what I observed is
small rmse of train set and big of test set. What is best practice in this
PS: How Auto-Weka manages this ? Is it appropriate for time series ?
Sent from: http://weka.8497.n7.nabble.com/
I am currently implementing an algorithm using the Weka RandomTree with
a numeric class attribute. In my algorithm I need to collect the
prediction associated with each leaf node. The predicted value should be
the first element in the m_ClassDistribution array of the leaf node.
Unfortunately, for some leaves, the m_ClassDistribution array is null. I
already set the "allowUnclassifiedInstances" flag to false, but still
some leaf nodes do not contain a class distribution. I observed this
behavior for the dataset attached. Is it normal that some leaf nodes do
not contain the class distribution? If so, where do I find the
prediction associated with the leaf? Any help would be appreciated.