Linear models are one of the most basic ways to model/represent data, and are a good starting point for machine learning. The algorithms are simple and can be comprehended with a basic understanding of maths. LinearRegression fits a linear model with coefficients w = (w_1, ..., w_p) to minimise the residual sum of squares between the observed responses in the dataset, and the responses predicted by the linear approximation. This essentially produces a straight-line of best fit. Do not forget, linear regression can be multi-dimensional.

Linear regression can be easily implemented for simple data that may have a basic correlation in two dimensions, for example water usage by household size, house price data, and cancer predictions. To plot data, Matplotlib, is a convenient Python 2D plotting library.