About Article

Consider you’re an e-commerce platform aiming to enhance recommendation personalization. Your data resides in S3.

To refine recommendations, you plan to retrain recommendation models using fresh customer interaction data whenever a new file is added to S3. But how exactly do you do this?

In this article, you will learn how to set up this workflow using Kestra.
Favorite

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.
Favorite

Deploying machine learning models manually can slow down the release process and consume resources, especially when models need frequent updates.

In my latest article and video, you will learn how to use continuous deployment (CD) to automatically deploy a new model to production.

Article.

Video.
Favorite

Continuous integration (CI) is the practice of automatically testing and integrating code changes into a shared repository.

In a machine learning project, CI can be very useful for several reasons:

Catching errors early: CI facilitates the early identification of errors by automatically testing any code changes made.

Faster feedback and decision-making: By providing clear metrics and parameters, CI enables faster decision-making, freeing up reviewer time for more critical tasks.

In my latest article and video, you will learn how to create CI in an ML project.

Article – Video – Code
Favorite

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.
Favorite

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.
Favorite

In this video, you will learn how to create observable and reproducible notebooks with Hex.

Watch the video on YouTube.
Favorite

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.
Favorite

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

Watch the video on YouTube.
Favorite

A regular expression (or RegEx) is a string of text that lets you create patterns to match a text. A complicated RegEx is difficult to read and create. Is there a way that you can write a more human-readable RegEx with ease?

That is when PRegEx comes in handy. PRegEx is a Python package that allows you to construct RegEx patterns in a more human-friendly way.

In my latest article, you will learn how how to use PRegex for different use cases.

Article.

Source code.
Favorite