Overview of regression algorithms in River
There is a large number of online regression models available in the River online machine learning package.
A selection of relevant ones are as follows:
LinearRegression
HoeffdingAdaptiveTreeRegressor
SGTRegressor
SRPRegressor
Regression algorithm 1 – LinearRegression
Linear regression is one of the most basic regression models. A simple linear regression is a regression model that fits a straight line through the datapoints. The following graph illustrates this:
Figure 7.3 – A linear model in a scatter plot
This orange line is a result of the following formula:

Here, y represents avg_grades
and x represents nb_hrs_studies
. When fitting the model, the a and b coefficients are estimates. The b coefficient in this formula is called the intercept. It indicates the value of y when x equals 0
. The a coefficient represents the slope of the line. For...