Henry Z.

Dead link inside https://github.com/zinggAI/zingg/blob/main/examples/databricks/FebrlExample.ipynb this docu. inputPipe = CsvPipe("testFebrl", "/FileStore/tables/test.csv", schema) also wondering what should be the pipe method name if I want to connect with SQL server via JDBC. No such documentation found for databrick.

Q11: In our customer data, we have individual column like SuiteNumber, Address, CIty, Province, PostalCode and WhenCreated. We found that there are customers who happen to share the same address because 1) they from the same household, 2) they happen to rent the same appointment unit. To tell whether it is a case 1 or 2, we found that WhenCreated is quite accurate, for records have same address but created within 1 month, they usually from the same household, for records created more than 6 month apart, they usually are case 2). Wondering does Zingg can do match logic like this?

Q10: will the "match" result also include the ones in the training set? I found out that if I put a pair of matched records in the training set and retrain the model then rerun the match again, those records that used in training set will not be marked as dup in the results.

Q9: When build the training data, I saw that z_isMatch is either 0 or 1, does it also support "don't know"? Maybe I should exclude don't know records from the training set?

Question 8: for the output, what format is supported? Can I write to a SQL table? if so, do I need to define the schema for the result table or it will automatic create the table?

Dead link: https://docs.zingg.ai/docs/security.html