<aside> 💡 Jupyter Notebook are great for ML experiments. Jeremy Howard uses one Notebook for each model he builds. He simply duplicates the Notebook, as he explained here. According to him, its the fastest and most simple way to work. Tip: you can work with both notebooks and scripts, as seen in this github folder where we import all scripts into the notebook.
</aside>
You can write code in Python and automatically convert cell to a script. Additonally you can write tests directly in Jupyter using ipytest magic. More details on both check here. Its faster and the code looks better.
The problem with VSCode Notebooks:
<aside> 💡 VSCode Notebooks are great but its difficult to pair them with a .py file. Therefore I rather use Jupyter Notebooks instead!
</aside>
You can boost your VSCode Jupyter Notebooks with the following extensions!!!
Jupyter über den Analytics Server aufrufen