Introduction

Project Topic:
Use datapackage (v2) to describe LTSER tabular data specifications and perform data quality validations

This program shows the validation of the CSV dataset generated by the research and checks the correctness and accuracy of the data. The tools used are as follows:

• Python frictionless package: used to generate dataset specification and perform dataset verification.

• Python tkinter package: used to create user interfaces to facilitate users to operate various program functions.

• Google Gemini API: Use a large language model to generate the constraints values ​​of each field in the dataset.

After the program production is completed, data quality inspection will be performed on some datasets stored on the depositar by the LTSER Taiwan Program.