Towards Data Science
@towardsdatascience.com
The world's leading publication for data science and artificial intelligence professionals.
Website 🌐 towardsdatascience.com
Submit an Article ✍️ https://contributor.insightmediagroup.io
Subscribe to our Newsletter 📩 https://bit.ly/TDS-Newsletter
Website 🌐 towardsdatascience.com
Submit an Article ✍️ https://contributor.insightmediagroup.io
Subscribe to our Newsletter 📩 https://bit.ly/TDS-Newsletter
Integrate GPT-4o into a real-world data pipeline. See how Gustavo Santos uses an LLM to transform raw weather data into personalized dressing suggestions in this practical #Databricks tutorial.
How to Build an AI-Powered Weather ETL Pipeline with Databricks and GPT-4o: From API To Dashboard | Towards Data Science
A step-by-step guide from weather API ETL to dashboard on Databricks
towardsdatascience.com
December 27, 2025 at 1:30 AM
Integrate GPT-4o into a real-world data pipeline. See how Gustavo Santos uses an LLM to transform raw weather data into personalized dressing suggestions in this practical #Databricks tutorial.
Your model might not understand that Monday comes after Sunday. It just sees a jump in numbers. Gustavo Santos shares this guide on cyclical feature encoding to help models learn repeating patterns in time.
Is Your Model Time-Blind? The Case for Cyclical Feature Encoding | Towards Data Science
How cyclical encoding improves machine learning prediction
towardsdatascience.com
December 27, 2025 at 12:15 AM
Your model might not understand that Monday comes after Sunday. It just sees a jump in numbers. Gustavo Santos shares this guide on cyclical feature encoding to help models learn repeating patterns in time.
Understand the intuition behind the Jacobian adjustment using a simple analogy: sand on a rubber sheet. Aniruddha Karajgi makes a complex mathematical concept feel tangible and easy to grasp.
Keeping Probabilities Honest: The Jacobian Adjustment | Towards Data Science
An intuitive explanation of transforming random variables correctly.
towardsdatascience.com
December 26, 2025 at 11:30 PM
Understand the intuition behind the Jacobian adjustment using a simple analogy: sand on a rubber sheet. Aniruddha Karajgi makes a complex mathematical concept feel tangible and easy to grasp.
Improve your ranking metrics by moving beyond MAP and MRR. Discover how Normalized Discounted Cumulative Gain (NDCG) and Expected Reciprocal Rank (ERR) account for position bias and graded relevance in this new article by Shubham Gandhi.
Why MAP and MRR Fail for Search Ranking (and What to Use Instead) | Towards Data Science
MAP and MRR look intuitive, but they quietly break ranking evaluation. Here’s why these metrics mislead—and how better alternatives fix it.
towardsdatascience.com
December 26, 2025 at 10:05 PM
Improve your ranking metrics by moving beyond MAP and MRR. Discover how Normalized Discounted Cumulative Gain (NDCG) and Expected Reciprocal Rank (ERR) account for position bias and graded relevance in this new article by Shubham Gandhi.
Drained by the routine of writing commit messages and creating pull requests? This recent article from Eivind Kjosbakken shows how to automate these #GitHub interactions using an AI agent.
4 Techniques to Optimize AI Coding Efficiency | Towards Data Science
Learn how to code more effectively using AI
towardsdatascience.com
December 26, 2025 at 9:24 PM
Drained by the routine of writing commit messages and creating pull requests? This recent article from Eivind Kjosbakken shows how to automate these #GitHub interactions using an AI agent.
⭐ 2025 Must-Reads: Agents, Python, LLMs + More ⭐
Thinking about drafting a new article over the holidays? Submit here: bit.ly/TDSContributor
Thinking about drafting a new article over the holidays? Submit here: bit.ly/TDSContributor
December 26, 2025 at 8:45 PM
⭐ 2025 Must-Reads: Agents, Python, LLMs + More ⭐
Thinking about drafting a new article over the holidays? Submit here: bit.ly/TDSContributor
Thinking about drafting a new article over the holidays? Submit here: bit.ly/TDSContributor
Learn why discovering a new element requires a different statistical approach than a genomics study. @marcohening.bsky.social clarifies how to choose your p-value correction method based on your goals.
Bonferroni vs. Benjamini-Hochberg: Choosing Your P-Value Correction | Towards Data Science
Multiple hypothesis testing, P-values, and Monte Carlo
towardsdatascience.com
December 26, 2025 at 7:18 PM
Learn why discovering a new element requires a different statistical approach than a genomics study. @marcohening.bsky.social clarifies how to choose your p-value correction method based on your goals.
Understand exactly how a 1D CNN processes text for classification. Angela Shi builds a complete model step-by-step in #Excel to make every component — from embeddings to filters — fully transparent.
The Machine Learning “Advent Calendar” Day 23: 1D CNN for Text in Excel | Towards Data Science
A step-by-step 1D CNN for text, built in Excel, where every filter, weight, and decision is fully visible.
towardsdatascience.com
December 26, 2025 at 6:07 PM
Understand exactly how a 1D CNN processes text for classification. Angela Shi builds a complete model step-by-step in #Excel to make every component — from embeddings to filters — fully transparent.
Reposted by Towards Data Science
Check out my newest article on @towardsdatascience.com
! EDITOR'S PICK! In superheavy element hunting – a border between Physics and Chemistry – atoms become incredibly heavy, and p-values unbelievably small.
#DataScience #Physics
towardsdatascience.com/the-time-10-...
! EDITOR'S PICK! In superheavy element hunting – a border between Physics and Chemistry – atoms become incredibly heavy, and p-values unbelievably small.
#DataScience #Physics
towardsdatascience.com/the-time-10-...
Bonferroni vs. Benjamini-Hochberg: Choosing Your P-Value Correction | Towards Data Science
Multiple hypothesis testing, P-values, and Monte Carlo
towardsdatascience.com
December 24, 2025 at 1:52 PM
Check out my newest article on @towardsdatascience.com
! EDITOR'S PICK! In superheavy element hunting – a border between Physics and Chemistry – atoms become incredibly heavy, and p-values unbelievably small.
#DataScience #Physics
towardsdatascience.com/the-time-10-...
! EDITOR'S PICK! In superheavy element hunting – a border between Physics and Chemistry – atoms become incredibly heavy, and p-values unbelievably small.
#DataScience #Physics
towardsdatascience.com/the-time-10-...
Reposted by Towards Data Science
Think your Python code is slow? Stop guessing. Start measuring.
A practical guide to profiling Python with cProfile and SnakeViz on the @towardsdatascience.com platform,
towardsdatascience.com/think-your-p...
A practical guide to profiling Python with cProfile and SnakeViz on the @towardsdatascience.com platform,
towardsdatascience.com/think-your-p...
Think Your Python Code Is Slow? Stop Guessing and Start Measuring | Towards Data Science
A hands-on tour of using cProfile + SnakeViz to find (and fix) the "hot" paths in your code.
towardsdatascience.com
December 26, 2025 at 5:28 PM
Think your Python code is slow? Stop guessing. Start measuring.
A practical guide to profiling Python with cProfile and SnakeViz on the @towardsdatascience.com platform,
towardsdatascience.com/think-your-p...
A practical guide to profiling Python with cProfile and SnakeViz on the @towardsdatascience.com platform,
towardsdatascience.com/think-your-p...
Reposted by Towards Data Science
Stop chasing security vulnerabilities 🚨 Our new #DevSecOps roadmap focuses on the tools and frameworks that matter: SBOMs, DDoS mitigation, SOAR automation, and compliance.
Roadmap Link 👉 roadmap.sh/devsecops
Roadmap Link 👉 roadmap.sh/devsecops
December 24, 2025 at 9:45 PM
Stop chasing security vulnerabilities 🚨 Our new #DevSecOps roadmap focuses on the tools and frameworks that matter: SBOMs, DDoS mitigation, SOAR automation, and compliance.
Roadmap Link 👉 roadmap.sh/devsecops
Roadmap Link 👉 roadmap.sh/devsecops
Reduce the cognitive tax of a fragmented AI stack. In a new article, Marcus Dawson explores how juggling multiple AI subscriptions and interfaces erodes professional productivity.
ChatLLM Presents a Streamlined Solution to Addressing the Real Bottleneck in AI | Towards Data Science
For the last couple of years, a lot of the conversation around AI has revolved around a single, deceptively simple question: Which model is the best? But the next question was always, the best for…
towardsdatascience.com
December 26, 2025 at 4:47 PM
Reduce the cognitive tax of a fragmented AI stack. In a new article, Marcus Dawson explores how juggling multiple AI subscriptions and interfaces erodes professional productivity.
Ibrahim Salami walks through his 5-step Python workflow for cleaning messy CSV files, showing how to tackle nulls, inconsistencies, and other common data issues efficiently.
I Cleaned a Messy CSV File Using Pandas . Here’s the Exact Process I Follow Every Time. | Towards Data Science
Stop guessing at data cleaning. Use this repeatable 5-step Python workflow to diagnose and fix the most common data flaws.
towardsdatascience.com
December 26, 2025 at 3:03 PM
Ibrahim Salami walks through his 5-step Python workflow for cleaning messy CSV files, showing how to tackle nulls, inconsistencies, and other common data issues efficiently.
Sabrine Bendimerad lays out a realistic roadmap for starting an AI career in 2026, emphasizing real, hands-on projects over hype.
A Realistic Roadmap to Start an AI Career in 2026 | Towards Data Science
How to learn AI in 2026 through real, usable projects
towardsdatascience.com
December 26, 2025 at 5:02 AM
Sabrine Bendimerad lays out a realistic roadmap for starting an AI career in 2026, emphasizing real, hands-on projects over hype.
Meet Aakash Goswami! 👋 Our new author takes us behind the scenes of India's RISAT (Radar Imaging Satellite) program.
Submit your article today ➡️ bit.ly/TDSContributor
Submit your article today ➡️ bit.ly/TDSContributor
RISAT’s Silent Promise: Decoding Disasters with Synthetic Aperture Radar | Towards Data Science
The high-resolution physics turning microwave echoes into real-time flood intelligence
towardsdatascience.com
December 25, 2025 at 10:05 PM
Meet Aakash Goswami! 👋 Our new author takes us behind the scenes of India's RISAT (Radar Imaging Satellite) program.
Submit your article today ➡️ bit.ly/TDSContributor
Submit your article today ➡️ bit.ly/TDSContributor
Partha Sarkar explains how to build cost-efficient, high-recall retrieval systems using GraphRAG and hybrid pipelines.
GraphRAG in Practice: How to Build Cost-Efficient, High-Recall Retrieval Systems | Towards Data Science
Smarter retrieval strategies that outperform dense graphs — with hybrid pipelines and lower cost
towardsdatascience.com
December 25, 2025 at 7:18 PM
Partha Sarkar explains how to build cost-efficient, high-recall retrieval systems using GraphRAG and hybrid pipelines.
Sabrine Bendimerad breaks down Artificial Intelligence, Machine Learning, Deep Learning, and Generative AI, making sense of the AI landscape in 2026.
Artificial Intelligence, Machine Learning, Deep Learning, and Generative AI — Clearly Explained | Towards Data Science
Understanding AI in 2026 — from machine learning to generative models
towardsdatascience.com
December 25, 2025 at 5:28 PM
Sabrine Bendimerad breaks down Artificial Intelligence, Machine Learning, Deep Learning, and Generative AI, making sense of the AI landscape in 2026.
Sabrine Bendimerad shares her perspective as a 10-year AI engineer, exploring whether pursuing a career in data science in 2026 is still a worthwhile choice.
Data Science in 2026: Is It Still Worth It? | Towards Data Science
An honest view from a 10-year AI Engineer
towardsdatascience.com
December 25, 2025 at 3:03 PM
Sabrine Bendimerad shares her perspective as a 10-year AI engineer, exploring whether pursuing a career in data science in 2026 is still a worthwhile choice.
Benjamin Nweke distills hard-won experience into seven Pandas performance tricks every data scientist can put to work immediately.
7 Pandas Performance Tricks Every Data Scientist Should Know | Towards Data Science
What I've learned about making Pandas faster after too many slow notebooks and frozen sessions
towardsdatascience.com
December 25, 2025 at 1:34 AM
Benjamin Nweke distills hard-won experience into seven Pandas performance tricks every data scientist can put to work immediately.
Learn how a new LLM architecture, BitNet b1.58, achieves 41x more energy efficiency and 9x faster throughput than standard models. Moulik Gupta explains the mechanics behind this 1-bit approach.
What Happens When You Build an LLM Using Only 1s and 0s | Towards Data Science
An LLM that's 41× more efficient and 9× faster than today's standard models
towardsdatascience.com
December 24, 2025 at 10:27 PM
Learn how a new LLM architecture, BitNet b1.58, achieves 41x more energy efficiency and 9x faster throughput than standard models. Moulik Gupta explains the mechanics behind this 1-bit approach.
Sherin Sunny joins TDS, bringing his expertise from Walmart to a practical guide on leaf detection. His debut work is a must-read for anyone looking to implement CV solutions in complex workflows.
Submit your article → bit.ly/TDSContributor
Submit your article → bit.ly/TDSContributor
How Deep Feature Embeddings and Euclidean Similarity Power Automatic Plant Leaf Recognition | Towards Data Science
Introduction Automatic plant leaf detection is a remarkable innovation in computer vision and machine learning, enabling the identification of plant species by examining a photograph of the leaves.…
towardsdatascience.com
December 24, 2025 at 7:18 PM
Sherin Sunny joins TDS, bringing his expertise from Walmart to a practical guide on leaf detection. His debut work is a must-read for anyone looking to implement CV solutions in complex workflows.
Submit your article → bit.ly/TDSContributor
Submit your article → bit.ly/TDSContributor
Wondering how to break into AI in 2026? Sabrine Bendimerad explains a practical path with usable projects that actually build skills.
A Realistic Roadmap to Start an AI Career in 2026 | Towards Data Science
How to learn AI in 2026 through real, usable projects
towardsdatascience.com
December 24, 2025 at 5:23 PM
Wondering how to break into AI in 2026? Sabrine Bendimerad explains a practical path with usable projects that actually build skills.
Moulik Gupta explores how a 27M-parameter model is challenging the notion that bigger is always better in AI reasoning tasks.
Your Next ‘Large’ Language Model Might Not Be Large After All | Towards Data Science
A 27M-parameter model just outperformed giants like DeepSeek R1, o3-mini, and Claude 3.7 on reasoning tasks
towardsdatascience.com
December 24, 2025 at 3:04 PM
Moulik Gupta explores how a 27M-parameter model is challenging the notion that bigger is always better in AI reasoning tasks.
Building reliable RAG systems means tackling hallucinations head-on. After finding that trained detectors fell short, Javier Marin developed a new approach using the geometry of text embeddings.
The Geometry of Laziness: What Angles Reveal About AI Hallucinations | Towards Data Science
A story about failing forward, spheres you can’t visualize, and why sometimes the math knows things before we do
towardsdatascience.com
December 24, 2025 at 2:45 AM
Building reliable RAG systems means tackling hallucinations head-on. After finding that trained detectors fell short, Javier Marin developed a new approach using the geometry of text embeddings.
Learn how LLM agents use to-do lists to plan and manage complex tasks. Kenneth Leung's new article breaks down the process and demonstrates its implementation in LangChain with a practical travel booking example.
How Agents Plan Tasks with To-Do Lists | Towards Data Science
Understanding the process behind agentic planning and task management in LangChain
towardsdatascience.com
December 24, 2025 at 1:34 AM
Learn how LLM agents use to-do lists to plan and manage complex tasks. Kenneth Leung's new article breaks down the process and demonstrates its implementation in LangChain with a practical travel booking example.