Welcome to the course! Today we will start by investigating one of the most popular conceptions in machine learning - linear regression. We will be digging into this simple supervised learning model using some well-known libraries of Python, which you probably already know.

Let's start!

So what is regression? Before answering this question, let's look at the following scatter plot below. For example, we have done the research, got some data, then visualized it and plotted it on our graph.

We intuitively want to add a line to see what the trend is. But which one would best visualize our dependence? Blue? Green? Or maybe black?

To find the correct answer, we need to use a learning model - linear regression. Let's find out the meaning of this method. Linear regression is an approach for modelling the relationship between variables that you operate in research, finding mathematically the straight line to your data (if we are talking about two-dimensional graphs) to predict future values.

Let's express the equation of this desired line for our plot (so that in the future, we operate with numbers and not with colors on the graph):

Where b is the intercept and k is the slope of the line. x is an independent variable (input), whereas y is our output. Our goal is to find this k and b.