This site uses different types of cookies, including analytics and functional cookies (its own and from other sites). To change your cookie settings or find out more, click here. If you continue browsing our website, you accept these cookies.
There seems to be a limitation on the number of categorical variables the Naive Bayes tool will predict.
I had a wide set of data:
I used PCA to reduce the number of variables to 2.
I was able to get the Naive Bayes tool to predict the 10 categories perfectly fine on its own.
However, when I ran the same data and model through the Score tool, I kept receiving the following warning:
"Not all records were scored due to missing values in the predictor fields or unknown categorical values."
"0 records were successfully scored and 103 were not."
In an effort to identify the issue, I reduced the amount of categories to 5 and the tool worked perfectly fine; 5 appears to be the maximum.
Does anyone know why the tool stops predicting above 5 categories?
Would you be able to attach your workflow (options => export) so that we can dig a little deeper?