In Miner, I have three different training data sets (all with the same features) that I am taking specific samples from for undersampling/oversampling purposes. Once I have ran the sample nodes, I append the three different data sets together with the append node to create a new training data set. Similarly, I use the append node on two different validation data sets to create a single new validation set. I would like to run a decision tree model using the new training and validation data sets. However, when I try running the decision tree node, I get a run time error. I am also getting a runtime error when trying to run a stat explore node. I have checked to see if my two datasets are free of issues, and they are. For the decision tree node, I am getting system error -S-, and for the stat explore node I am getting system error 3000. Am I using the append node improperly? Below is an image of my process flow.
Use this tutorial as a handy guide to weigh the pros and cons of these commonly used machine learning algorithms.
Find more tutorials on the SAS Users YouTube channel.
-
770 views
-
0 likes
-
-
