Python Feature Engineering Cookbook

Performing zero-coding – capping the variable at zero

In econometrics and statistics, top-coding and bottom-coding refer to the act of censoring data points, the values of which are above or below a certain number or threshold, respectively. In essence, top and bottom coding is what we have covered in the previous recipe, where we capped the minimum or maximum values of variables at a certain value, which we determined with the mean and standard deviation, the inter-quartile range proximity rule, or the percentiles. Zero-coding is a variant of bottom-coding and refers to the process of capping, usually the lower value of the variable, at zero. It is commonly used for variables that cannot take negative values, such as age or income. In this ...