From the course: Machine Learning and AI: Advanced Decision Trees with SPSS
Unlock the full course today
Join today to access over 23,200 courses taught by industry experts.
How QUEST handles missing data
From the course: Machine Learning and AI: Advanced Decision Trees with SPSS
How QUEST handles missing data
- [Instructor] Let's discuss how Quest handles missing data. Let's go into the type node. We actually saw an example of missing data earlier when we were looking at the embarked variable. However, at the time, modeler was not correctly informing Quest that there's really only three embarkation points. The data makes it appear that there are four: C, Q, S, and unknown. So let's declare that in modeler and see how the algorithm behaves differently. I'm going to simply turn missing on, and when I do, modeler's going to recognize that there's only three embarkation points. I'm going to clear values and read values, and now, as you see, there's only three: C, Q, and S. Let's see how the Quest algorithm behaves differently this time. I'm going to run that. And since the variable in Question is embarkation, I'm going to force it to split on embarked. Take a look at the difference. We have Q and S in node one, and we have only C in node two. So where did the missing data go? Well, Quest uses…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.