Numeric Values

[laiw12]

Hey, we are thinking of using your system in our project. It seems like only categorical attributes are calculated by the privbayes algorithm. The numeric values such as integer/float does not go through privbayes algorithm.

[haoyueping]

The numeric values are first grouped into categories before running the PrivBayes algorithm.

For example, column "age" has 5 values [12, 15, 24, 54, 57, 32], then "age_grouped" can be [10s, 10s, 20s, 50s, 50s, 30s].

In DataSynthesizer, the numeric values are grouped automatically by their histograms. Please let me know if you have any questions.