About Article

In a data science project, writing poorly designed functions can introduce maintenance hurdles and diminish the code’s readability.

In this article, you will learn how to create a function that:

Perform a single, well-defined task

Can be extended without modifying the original code

Are capable of handling inputs with unexpected variations

By following these principles, you’ll be able to create functions that are not only effective but also easy to maintain and understand.

Link to the article.

Getting started is often the most challenging part when building ML projects.

This article will show you how to use a template to create a maintainable and reproducible project, consolidating the best practices I’ve learned over the years.

Article.

Template.

If you want to explain the output of your machine learning model, use SHAP.

In the code above, I use SHAP’s summary plot to visualize the overall impact of features in a DataFrame.

My full article about SHAP.

Link to SHAP.

Jupyter Notebook is not ideal for interpretability, reproducibility, and versioning for numerous reasons. Hex notebooks solve these issues with a graph-based execution model.

Hex links cells through their dependencies and executes only the cells whose dependencies change. The GIF above demonstrates this.

In my latest article, you will learn some useful features of Hex and how to integrate Hex into your data pipeline with Prefect.

Link to the article.

Caching allows you to efficiently reuse the results of tasks that may be expensive to run without actually running the code that defines the task.

In this short video, you will learn how to cache your Python functions with Prefect.

View the video on YouTube.

Pandera is a Python library to validate your pandas DataFrame. In this video, you will learn how to use Pandera to test the inputs and outputs of your functions.

View the video on YouTube.

Pandera basics.

In a data science project, it is important to test your data to make sure they work as you expected.

In this video, you will learn how to test your pandas DataFrame with Pandera.

View the video on YouTube.

Source code.

collections is a built-in Python library to deal with Python dictionaries efficiently. This video will show you how to efficiently count the occurrences of each item in a list using collections Counter.

Watch the video on YouTube.

3Blue1Brown is a famous math YouTube channel created by Grant Sanderson. Wouldn’t it be cool if you can create animations like 3Blue1Brown in Python?

If so, try manim. In my article, you will learn how to create mathematical animations like below using manim.

Link to the article.

Link to the source code.