Using Pearson correlation to select features

We have actually looked at correlations in this book already, but not in the context of feature selection. We already know that we can invoke a correlation calculation in pandas by calling the following method:

credit_card_default.corr()

The output of the preceding code produces is the following:

As a continuation of the preceding table we have:

The Pearson correlation coefficient (which is the default for pandas) measures the linear relationship between columns. The value of the coefficient varies ...

Get Feature Engineering Made Easy now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.