Linear Algebra with Python and Google Colab

This week, I focused on linear algebra—specifically, how it connects to data science and machine learning. At first, it sounded intimidating, but Chapter 4 of Data Toolkit: Python + Hands-On Math by Todd Kelsey helped break things down in a practical way. I learned that vectors and matrices aren’t just abstract math concepts—they're actually tools that help us represent and work with real-world data. For example, something as simple as representing a house’s size and number of bedrooms as a vector helped me understand how data can be stored and manipulated more efficiently. It’s one thing to hear that linear algebra is essential in machine learning, but seeing it used in Python to calculate averages and normalize data made it feel much more approachable.

One of my biggest takeaways was how vectors and matrices let us perform operations that are essential in building models. I practiced doing some of this in Google Colab using both regular Python lists and the NumPy library. I especially liked how NumPy made calculations faster and cleaner—like when we calculated the average size of a dataset or normalized test scores and ages to fit within a 0 to 1 range. Normalization was a new concept for me, and it clicked when I realized it helps make different types of data comparable, like weight and fuel efficiency in a car dataset. These are small things, but they make a big difference when you're building or training a model that relies on multiple features.

What I also appreciated about this chapter was the encouragement to take things step by step and learn by doing. I’ve never been the strongest in math, but being able to run Python code alongside these math concepts made it feel a lot more manageable. This hands-on approach is helping me see the value of math in a new light—especially in areas like AI and machine learning. I'm still getting used to all the new terms and ideas, but every week it's starting to make more sense.