Now that you have a sense of what variables are important and that the data is well behaved with very few outliers, let’s move on to preparing the data for multiple linear regression. This involves handling the categorical variables first and then performing dummy encoding.
You have successfully handled the categorical variables with two levels. But one of the columns – ‘furnishingstatus’ – has three levels. Here, you need to perform dummy encoding.
Coming up
Now that the data has been prepared, let’s do the scaling in the next segment.