Whether we learn Data Science through online courses, tutorials, or jump straight into a hands-on project-based approach, few of us take out the time to try and learn how some of our favorite libraries are built. All we know is that we can import the scikit-learn library, instantiate a Linear Regression model, and call the “.fit()” method on it. What is happening under the hood? How are these different algorithms implemented in an efficient manner?
This webinar will walk through an advanced Python tutorial in which we will be coding up a Linear Regression algorithm from scratch and make it usable in a manner not so different from scikit-learn. We will be learning about Object-Oriented Programming in Python, vectorized operations, and efficient coding strategies that allow for as much future customization as possible. We will be walking through how to convert mathematical formulas into Python code that runs as efficiently as possible.
This webinar is not for the Python beginner, you are expected to know basic Data Science tools and frameworks, such as Pandas, Numpy, Scikit-Learn, etc. You are also expected to know, at least in theory, how Linear Regression works. This webinar will bridge that gap between theory and implementation and in the process teach you some advanced Python tips and tricks.