pdp: An R Package for Constructing Partial Dependence Plots

By Brandon M. Greenwell. 2017

955 citations recorded by the source corpus.

Complex nonparametric models—like neural networks, random forests, and support vector machines—are more common than ever in predictive analytics, especially when dealing with large observational databases that don’t adhere to the strict assumptions imposed by traditional statistical techniques (e.g., multiple linear regression which assumes linearity, homoscedasticity, and normality). Unfortunately, it can be challenging to understand the results of such models and explain them to management. Partial dependence plots offer a simple solution. Partial dependence plots are low-dimensional graphical renderings of the prediction function so that the relationship between the outcome and predictors of interest can be more easily understood. These plots are especially useful in explaining the output from black box models. In this paper, we introduce pdp , a general R package for constructing partial dependence plots.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Environmental Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Przemyslaw Biecek
2. Christoph Molnar
3. Giuseppe Casalicchio
4. Mateusz Staniak
5. Bernd Bischl
6. Alicja Gosiewska
7. Anne-Laure Boulesteix
8. Marco F. Huber

In Computer Vision and Pattern Recognition

1. Przemyslaw Biecek
2. Giuseppe Casalicchio
3. Christoph Molnar
4. Bernd Bischl
5. Mateusz Staniak
6. Frank Hutter
7. Alicja Gosiewska

In Environmental Engineering

1. Przemyslaw Biecek
2. Bernd Bischl
3. Mateusz Staniak
4. Christoph Molnar
5. Giuseppe Casalicchio

Citations in the corpus

• Explanations of model predictions with live and breakDown packages (2018, methodology): “An effective and very elastic implementation of this method is available in the pdp package (Greenwell, 2017).”
• iml: An R package for Interpretable Machine Learning (2018, methodology): “Many of the methods are already implemented in other packages (e.g. (Greenwell 2017), (Gold-stein et al. 2015), (Pedersen and Benesty 2017)), but the iml package implements all of the methods in one place, uses the same syntax and offers consistent functionality and outputs. iml can be used with…”
• Explainable AI (XAI): Core Ideas, Techniques, and Solutions (2022, background): “For example, the following questions can be answered with PDP [18, 25]: What would be the impact of longitude and latitude on prices of houses?”
• DALEX: explainers for complex predictive models (2018, methodology): “This framework covers the most known approaches to model explanation such as Partial Dependence Plots (Greenwell, 2017), Accumulated Local Effects Plots (Apley, 2017), Merging Path Plots (Sitko and Biecek, 2017), Break Down Plots (Biecek, 2018), Permutational Variable Importance Plots (Fisher et al.”