R² is a widely used measure of fit, but for many analysts, it is just a number. They believe high R² ➡ Good predictions. This is not always true! . Now I will clarify. 🔽. R-squared

RT @TivadarDanka: My copy is finally here!

RT @TivadarDanka: Conditional probability is the single most important concept in statistics. Why? Because without accounting for prior in….

RT @TivadarDanka: How to build a good understanding of math for machine learning?. I get this question a lot, so I decided to make a comple….

RT @TivadarDanka: Four years ago, I started a project that turned out to be life-altering, and it has just passed a huge milestone. I'm ha….

I share similar tips in my newsletter: Data Ground Up. Link in bio. You can read the full article there and sign up for similar posts.

But when to use it then?. 1️⃣ For quick explorations.2️⃣ Using star to reference rows.

Reusability. In queries like `UNION`, column count, order, and types must match. It's hard to align all those with a SELECT *.

Readability:. SELECT * is a black box. Without running it, you can't know the result structure. Explicit columns make your query easier to read and maintain. Look at these ⬇️ By looking at the 2nd query you already know what you will see.

Indexing:. Indexes are like a map of your data. They make it faster to find what you need. When you use SELECT *, you lose your map.

Performance:. SELECT * fetches everything, including what you don’t need. Smaller queries = faster performance. Ask yourself: “Do I need this column?”.

Reliability:. Changes to a table's schema (adding/removing columns) can break systems relying on SELECT *. Explicitly naming columns keeps queries and apps stable.

SELECT * is the "Hello World" of SQL. But it's a trap. You should avoid it. Here’s why 👇

Hi All,. It's been a while. I turned off content creation a few months ago and had some much-needed time away from it. Several reasons lead to the decision:. - I started to work on an interesting project beside my 9-5. That took priority. I may talk about this later as it is

RT @svpino: How can you build a good understanding of math for machine learning?. Here is a complete roadmap for you. In essence, three fi….

RT @svpino: There's a stunning, simple explanation behind matrix multiplication. This is the first time this clicked on my brain, and it w….

RT @daansan_ml: Let's discuss the simplest retrieval method: "Similarity search". It involves retrieving the top "k" documents that are mo….

RT @svpino: This is the best book for learning the mathematics of Machine Learning. There are two things that make this book different fro….

RT @pawjast: I've amassed a small collection of Python programming tips which I've been posting here on X. Mostly Matplotlib stuff, but n….

The best way to learn coding for data:.