Exploring Linear Regression: A Comparison of Scikit-learn and Custom Gradient Descent

Introduction

In this notebook, we will explore linear regression, a fundamental algorithm in machine learning used to model the relationship between a dependent variable and one or more independent variables.

Specifically, we will:

• Utilize Scikit-learn’s LinearRegression implementation to quickly create and train a linear model.
• Code our own version of gradient descent from scratch to understand the underlying mathematics and mechanics of linear regression.

We will apply both methods to a univariate linear regression problem, where:

• X represents the years of experience of employees.
• Y represents the corresponding salary amounts.

Objective

The primary goal is to compare the results of Scikit-learn’s built-in linear regression with our manually coded gradient descent. By doing this, we can gain a better understanding of how the algorithms work from scratch.

What you'll learn:

• How to implement and use Scikit-learn's LinearRegression to fit a simple linear model.
• How to code gradient descent from scratch, step by step, to solve the same problem.
• Compare the results of both approaches and evaluate their performance.

Let's dive into the world of linear regression and discover how the two approaches fare when applied to the years of experience vs. salary dataset!