ROCAUC Score

Overview

Calculates the Area Under the Receiver Operating Characteristic Curve (ROC AUC), which is a measure of the model's ability to distinguish between classes. A higher value indicates better performance.

Usage

Manually

Python

# Calculate RocAuc score for all data

rocauc = roc_auc(df, labels, y_true)
print(rocauc)

Using Fairness Object

result = fo.compute(roc_auc)

Results

0.4722222222222222

These results are obtained by using the input data given in the Create Example Data page under Getting Started

Interpretation

ROC AUC score measures the ability of a binary classification model to rank positive instances higher than negative instances across different threshold values. A higher ROC AUC score indicates better model performance in terms of classification accuracy. 1 is considered perfect, and .5 would be a random guess between classes.