how to develop Notebooks on vscode for git repos?

[MohsenJ]

I am able to use vscode extension + databricks connect to develop Notebooks on my local computer and run them on my databricks cluster. However I can not figure out how to develop the Notebooks that have the file `.py` extension but identified by Databricks as notebooks by their header 

# Databricks notebook source
# COMMAND ----------
import pytest
import os
import sys

 My workflow looks like this at the moment:

1. develop the notebook on Databrick UI
2. push the code to Gitlab
3. (optional) pull the code from gitlab on my local computer, develop, push back, pull from databricks repo

The problem with local development is Databricks Connect can only detect Notebooks as such when they have  .ipynb extension. I wat to be able to develop and run my code on my local computer the same way I do it Databricks UI. 

[Kaniz]

Hi @MohsenJ,

You can indeed develop and run Databricks notebooks with .py extension on your local computer using ...¹.

Here are the steps you need to follow:

1. Enable Databricks Connect integration: You must enable the Databricks Connect integration in the Dat...¹.

2. Open the notebook: For notebooks with filenames that have a .py extension, when you open the noteboo...¹.

3. Run a cell: As you run a cell, its results are shown in a separate tab in the IDE¹.

4. Debug a cell: As you debug, the cell being debugged displays Continue, Stop, and Step Over buttons¹. You can use Visual Studio Code debugging features such as watching variables’ states and viewing the...¹.

Please note that this feature works with Databricks Runtime 13.3 and above¹. All code runs locally, while all code involving DataFrame operations runs on the cluster in the remo...¹.

For more specific instructions, you can refer to the official Databricks documentation¹².

I hope this helps! Let me know if you have any other questions.