plotD3_rroc: Regression Receiver Operating Characteristic (RROC) in D3...

In auditor: Model Audit - Verification, Validation, and Error Analysis

Regression Receiver Operating Characteristic (RROC) in D3 with r2d3 package.

Description

The basic idea of the ROC curves for regression is to show model asymmetry. The RROC is a plot where on the x-axis we depict total over-estimation and on the y-axis total under-estimation.

Usage

plotD3_rroc(object, ..., scale_plot = FALSE)

Arguments

object	An object of class 'auditor_model_residual' created with model_residual function.
...	Other 'auditor_model_residual' objects to be plotted together.
scale_plot	Logical, indicates whenever the plot should scale with height. By default it's FALSE.

Details

For RROC curves we use a shift, which is an equivalent to the threshold for ROC curves. For each observation we calculate new prediction: \hat{y}'=\hat{y}+s where s is the shift. Therefore, there are different error values for each shift: e_i = \hat{y_i}' - y_i

Over-estimation is calculated as: OVER= \sum(e_i|e_i>0).

Under-estimation is calculated as: UNDER = \sum(e_i|e_i<0).

The shift equals 0 is represented by a dot.

The Area Over the RROC Curve (AOC) equals to the variance of the errors multiplied by frac{n^2}{2}.

Value

a 'r2d3' object

References

Hernández-Orallo, José. 2013. "ROC Curves for Regression". Pattern Recognition 46 (12): 3395–3411.

See Also

plotD3_rroc

Examples

dragons <- DALEX::dragons[1:100, ]

# fit a model
model_lm <- lm(life_length ~ ., data = dragons)

# use DALEX package to wrap up a model into explainer
lm_audit <- audit(model_lm, data = dragons, y = dragons$life_length)

# validate a model with auditor
mr_lm <- model_residual(lm_audit)

# plot results
plotD3_rroc(mr_lm)

library(randomForest)
model_rf <- randomForest(life_length~., data = dragons)
rf_audit <- audit(model_rf, data = dragons, y = dragons$life_length)
mr_rf <- model_residual(rf_audit)
plotD3_rroc(mr_lm, mr_rf)

auditor documentation built on Nov. 2, 2023, 6:13 p.m.