Towards Data Science (Medium)

  • Introducing Server-Sent Events in Python

    A simpler path to coding real-time web applications. The post Introducing Server-Sent Events in Python appeared first on Towards Data Science.

  • On Adding a Start Value to a Waterfall Chart in Power BI

    A waterfall chart can be a powerful tool for conveying information. But it has some limitations. The post On Adding a Start Value to a Waterfall Chart in Power BI appeared first on Towards Data Science.

  • Hands-On with Agents SDK: Multi-Agent Collaboration

    Explore the handoff and agents-as-tools patterns, their use cases, and how to customize them using OpenAI Agents SDK and Streamlit. The post Hands-On with Agents SDK: Multi-Agent Collaboration appeared first on Towards Data Science.

  • Does the Code Work or Not? 

    A common misconception about the working state of code in data, AI or software engineering fields. The post Does the Code Work or Not?  appeared first on Towards Data Science.

  • Mastering NLP with spaCy – Part 2

    POS tagging, dependency parser and named entity recognition. The post Mastering NLP with spaCy – Part 2 appeared first on Towards Data Science.

  • How Computers “See” Molecules

    Generative Molecular Design (Part 1): common molecular representations in data science. The post How Computers “See” Molecules appeared first on Towards Data Science.

  • “I think of analysts as data wizards who help their product teams solve problems”

    Mariya Mansurova explains how hands-on learning, agentic AI, and engineering habits shape her writing and work. The post “I think of analysts as data wizards who help their product teams solve problems” appeared first on Towards Data Science.

  • When Models Stop Listening: How Feature Collapse Quietly Erodes Machine Learning Systems

    Models don't just fail with noise; they fail in silence, by narrowing their attention to the point of fragility. The post When Models Stop Listening: How Feature Collapse Quietly Erodes Machine Learning Systems appeared first on Towards Data Science.

  • FastSAM  for Image Segmentation Tasks — Explained Simply

    Image segmentation is a popular task in computer vision, with the goal of partitioning an input image into multiple regions, where each region represents a separate object. Several classic approaches from the past involved taking a model backbone (e.g., U-Net) and fine-tuning it on specialized datasets. While fine-tuning works well, the emergence of GPT-2 and The post FastSAM  for Image Segmentation Tasks — Explained Simply appeared first on Towards Data Science.

  • How to Benchmark LLMs – ARC AGI 3

    Learn how to LLMs are benchmarked, and try out the newly released ARC AGI 3 The post How to Benchmark LLMs – ARC AGI 3 appeared first on Towards Data Science.