...
Julien Heiduk
Julien Heiduk

Julien Heiduk

Let's talk about recommandation systems and ML in real-world business scenarios.

Graph Embeddings with Cleora

In the realm of data science, understanding relationships among entities is critical. Cleora shines in this context by efficiently modeling relationships

Graph Embeddings with Cleora

Similar and complementary candidates generator

In this tutorial, we’ll explore how to leverage Word2Vec to find words that are similar or complementary. We’ll discuss two specific approaches - the IN-OUT approach and the OUT-OUT approach - both of which are useful for various applications, including recommender systems.

Similar and complementary candidates generator

Polars Introduction: Efficient Data Manipulation Compared to Pandas

Polars offers a faster and more memory-efficient alternative to Pandas for data manipulation tasks, particularly with large datasets, due to its use of parallel processing, lazy evaluation, and Arrow memory format, making it an ideal tool for data engineers and scientists seeking enhanced performance.

Polars Introduction: Efficient Data Manipulation Compared to Pandas

ZenML Pipeline Tutorial Part 3: Understanding Artefacts and Adding Inference Steps

In this tutorial, we will dive deep into the concept of artefacts in ZenML pipelines. We’ll explain how to define and use them, with a focus on the newly added inference step in an existing pipeline…

ZenML Pipeline Tutorial Part 3: Understanding Artefacts and Adding Inference Steps

ZenML Pipeline Tutorial Part 2: Adding MLflow to a ZenML Pipeline

In this tutorial, we will integrate MLflow into a ZenML pipeline for tracking machine learning experiments. MLflow is an open-source platform to manage the ML lifecycle, including experimentation, reproducibility, and deployment…

ZenML Pipeline Tutorial Part 2: Adding MLflow to a ZenML Pipeline