Table 1. Transitive closure calibration.
Directed | Undirected | ||||
---|---|---|---|---|---|
k-NN | RF | k-NN | RF | ||
House | Metric | 96 | 99 | 97 | 99 |
House | Ultra-metric | 56 | 57 | 53 | 57 |
Senate | Metric | 70 | 100 | 96 | 100 |
Senate | Ultra-metric | 49 | 39 | 70 | 61 |
Area under Receiver Operating Characteristic (ROC) curve of two classifiers, random forests (RF) and k-nearest neighbors (k-NN) on the ideological classification task.