So far, you have worked with the ‘statsmodels‘ package. This is a great package if you want to fit a line and draw inferences as well. But many times, you may not be interested in the statistics part of linear regression. You might just want to fit a line through the data and make predictions. In such cases, you can use ‘SKLearn’, which involves lesser hassle than ‘statsmodels’. Also, the industry standard as to what package should be used varies widely. Some companies prefer stats models whereas some others prefer SKLearn, so it is better for you if you know about both of these packages.
SKLearn is a ‘lighter’ version of the linear regression packages. The two simple steps to fit a line using SKLearn are as follows:
from sklearn.linear_model import LinearRegression
lm = LinearRegression() # Create a linear regression object
lm.fit(X_train, y_train)Coming up
In the next segment, let’s summarise your learnings from this session.
Report an error