%0 Journal Article %A O’Hara, Niamh %A Reed, Harry %A Afshinnekoo, Ebrahim %A Harvin, Donell %A Caplan, Nora %A Rosen, Gail %A Frye, Brook %A Woloszynek, Stephen %A Ounit, Rachid %A Levy, Shawn %A Butler, Erin %A Mason, Christopher %D 2017 %T Additional file 14: of Metagenomic characterization of ambulances across the USA %U https://springernature.figshare.com/articles/journal_contribution/Additional_file_14_of_Metagenomic_characterization_of_ambulances_across_the_USA/5435458 %R 10.6084/m9.figshare.c.3887422_D5.v1 %2 https://springernature.figshare.com/ndownloader/files/9388474 %K Ambulance %K Classification %K Taxonomy %K Pre-hospital setting %K Hospital-acquired infections %K Nosocomial pathogens %K Antimicrobial resistance %K Microbial ecology %K Metagenomics %K Whole-genome sequencing %X Figure S20. Boxplots of classifier performance over model specific parameter sweeps during training (80/20 split) on overlap data for city class. Classes underwent up sampling and were optimized in terms of mean ROC score. Shown are kappa and balanced accuracy, averaged over classes. rf, random forest; gbm, stochastic gradient boosting; rrf, regularized random forest; c50, c5.0 decision tree, pls, partial least squares; en, elastic net; knn, k-nearest neighbors; svm linear, support vector machine with linear kernel; rbf svm, support vector machine with rbf kernel. (DOCX 97 kb) %I figshare