naver/sqlova

about *.jsonl

Opened this issue · 0 comments

Hello, I've run through the whole program and made a prediction, but the files I predict to use are test. jsonl, test. table. jsonl, test. db and test_jok. jsonl.
Now I want to use my own data to predict. I see your add_csv.py and add_question.py files, and I have two questions about them:

  1. the key of "sql" in *. jsonl, how do I fill in the value inside, like "sel" "agg". Do I need to understand the database and fill it in by myself?
  2. You do not provide the code to generate *_jok.jsonl. But the program needs this file, how do I create it?
    I hope to get your help. Thank you.