Table 5 Comparison of effects of outlier removal, outlier weighted, and outlier keeping 5-fold Cv random forest algorithm results.

From: A novel seven-tier framework for the classification of MEFV missense variants using adaptive and rigid classifiers

Outlier

F1 metrics (mean ± SD)

Outlier removal

0.9869 ± 0.0174

Outlier weighted

0.9667 ± 0.0341

Outlier keeping

0.9708 ± 0.0295

  1. lof = LocalOutlierFactor(n_neighbors = 20, contamination = 0.1, metric=’minkowski’, leaf_size = 20, p = 5).
Back to article page