The term "Data Cleaning" is used to describe outlier checking, date parsing, missing value imputation to structuring datasets (organizing data values within a dataset) to facilitate analysis.

The latter is commonly referred to as "Data Tidying" but what about the former? I have seen outlier checking, date parsing and missing value imputation referred to as "soft processing", however I wonder if this is a commonly used term.

If I describe a component of data cleaning as "soft processing" is it reasonable to assume that knowledgeable people will know that I am referring to outlier checking, date parsing and missing value imputation?

In the field of Data Science, is there a commonly accepted phrase or term that umbrellas outlier checking, date parsing and missing value imputation.

  • $\begingroup$ Validation, preprocessing... $\endgroup$ – Emre Jul 26 '17 at 19:34
  • $\begingroup$ @Emre is this an answer or a suggestion? $\endgroup$ – grldsndrs Jul 26 '17 at 19:36
  • $\begingroup$ Yes. These are common terms; use what fits. Soft processing is not a clear or common term. $\endgroup$ – Emre Jul 26 '17 at 19:43
  • $\begingroup$ @Emre why not make it an answer?; as opposed to a comment. $\endgroup$ – grldsndrs Jul 26 '17 at 19:54

If you're not modifying anything you can call it validation. If you are, you can call it preprocessing.

| improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.