From the course: Data Science Foundations: Data Assessment for Predictive Modeling

Unlock the full course today

Join today to access over 22,500 courses taught by industry experts or purchase this course individually.

How many potential variables (columns) will I have?

How many potential variables (columns) will I have?

From the course: Data Science Foundations: Data Assessment for Predictive Modeling

Start my 1-month free trial

How many potential variables (columns) will I have?

“

- [Instructor] Okay, we're going to continue in the same dataset. Let's talk about a slightly different but related issue now, which is trying to get a sense of how many of these variables in this customer file will be potentially good input variables in a predictive model, down the line. Well, our ID field isn't going to help us at all in the modeling phase, even though it's critical now. These new variables, these features, we usually call them feature engineering, is the phrase of generating this new information from the original information, those are probably going to be terribly helpful. Gender, possibly, but look, all of this stuff really can't help us at all. The only thing we could hope to do with City is that maybe we have certain promotions going on in some cities and not others. Same kind of thing maybe with State, but look at this, people tend to to think, "Wow, I have dozens of variables. My model is…

Contents