RapidMiner 9.7 is Now Available
Lots of amazing new improvements including true version control! Learn more about what's new here.
Logistic Regression with polynominal attributes
Novice here. My member type is a university professor but not in the data science field.
I am trying to run logistic regression using the data downloaded from here: https://www.kaggle.com/fayomi/advertising. As stated in the data description of the site, the goal is to predict people who are more likely to click the ad. I split the data into training and scoring data.
I want to get some help in how to handle the polynominal attributes in the data set. For example, there are so many Ad Topic Line and City values. When I ran the model, it ran but the results did not look right.
Also, the confidence percentage for ad click (yes, no) was either one or zero for all rows. I feel something might be wrong here.
Thanks for help...