Chapter 2: Examining Bivariate and Multivariate Relationships between Features and Targets

In this chapter, we'll look at the correlation between possible features and target variables. Bivariate exploratory analysis, using crosstabs (two-way frequencies), correlations, scatter plots, and grouped boxplots can uncover key issues for modeling. Common issues include high correlation between features and non-linear relationships between features and the target variable. We will use pandas methods for bivariate analysis and Matplotlib for visualizations in this chapter. We will also discuss the implications of what we find in terms of feature engineering and modeling.

We will also use multivariate techniques to understand the relationship between features. This includes leaning on some machine learning algorithms to identify possibly problematic observations. After, we will provide tentative recommendations for eliminating certain observations from our modeling, as well as for transforming...