Variable Importance Plots—An Introduction to the vip Package

Abstract

In the era of "big data", it is becoming more of a challenge to not only build state-of-the-art predictive models, but also gain an understanding of what's really going on in the data. For example, it is often of interest to know which, if any, of the predictors in a fitted model are relatively influential on the predicted outcome. Some modern algorithms-like random forests (RFs) and gradient boosted decision trees (GBMs)-have a natural way of quantifying the importance or relative influence of each feature. Other algorithms-like naive Bayes classifiers and support vector machines-are not capable of doing so and model-agnostic approaches are generally used to measure each predictor's importance. Enter vip, an R package for constructing variable importance scores/plots for many types of supervised learning algorithms using model-specific and novel model-agnostic approaches. We'll also discuss a novel way to display both feature importance and feature effects together using sparklines, a very small line chart conveying the general shape or variation in some feature that can be directly embedded in text or tables. 1 Although "interpretability" is difficult to formally define in the context of ML, we follow Doshi-Velez and Kim (2017) and describe "interpretable" as the ".. . ability to explain or to present in understandable terms to a human." 2 In this context "importance" can be defined in a number of different ways. In general, we can describe it as the extent to which a feature has a "meaningful" impact on the predicted outcome. A more formal definition and treatment can be found in van der Laan (2006). 3 We refer the reader to Poulin et al. (2006), Caruana et al. (2015), Bibal and Frénay (2016), and Bau et al. (2017), for discussions around model structure interpretation.

Spatial and evolutionary predictability of phytochemical diversity

“…S8). (53)]. The variables that ranked in the top 10 in at least two of the three models were retained, i.e., number of nodes, cophenetic Dimension 1 and 2, NDVI quantile 0.95, soil moisture quantile 0.05, soil pH quantile 0.95, annual temperature average quantile 0.95, solar radiation median.…”

Coffee or tea? Examining cross-cultural differences in personality nuances across former colonies of the British Empire

“…Across the Asian countries, differences were much more apparent; the only exception being Malaysia and Singapore with considerable facet level similarities, arguably because of the geographical neighborhood of these countries as well as their strong historical, political, and economic ties. Table 2 shows examples of the most important facet and nuance-level variables in the distinction of some selected countries (for an approach to variable importance measuring see Greenwell et al., 2018). India and the Philippines, for instance, differed considerably in the Openness facets Emotionality, Liberalism, and Artistic Interest, with India scoring higher in the first two and lower in the latter.…”

Survey protocol for exploring video and phone use in Aotearoa New Zealand general practice: considerations for future telehealth

“…This will enable the relative variable importance in contributing to the outcome variance to be considered via importance plots. 27 …”