Open rohan-gt opened 4 years ago
this is something we've been thinking about. i think it breaks into 2 categories, both of which would be valuable
i think validation might be a bit easier to start with and would give us a starting point to think about how to do inference
Hmm validation could be done based on a random sample or to be more thorough scan all values and using a confidence threshold although the latter might be computationally expensive
Is it possible to add smarter variable type inference to detect all the different variable types that Featuretools supports like PhoneNumber, ZipCode etc. using regex or other rules?