How to do Upsampling of Minority Class in Splunk MLTK?

[sc2019]

I am working on a classification problem in Splunk Machine Learning Toolkit. The data is highly imbalanced. The majority class constitute 99% of the data and the rest is Minority Class. Is there anyway to up sample the minority class in the data or any other methods to add the synthetic data to level the imbalanced classes?

[grana_splunk]

To my knowledge, MLTK do not have any algorithm specific to imbalance dataset but they do have a github app i.e. a repo/app for algorithms: https://splunkbase.splunk.com/app/4403/ and it uses MLTK libraries.

One of the algorithm under github app modifies the DecisionTreeClassifier and has a class weight parameter added to it.

So install github app and make it global and use the following

.| fit CustomDecisionTreeClassifier class_weight="{'Yes':1,'No':0.1}">

Need to check the algo before installing github app, then checkout : https://github.com/splunk/mltk-algo-contrib/blob/master/src/bin/algos_contrib/CustomDecisionTreeClas...