Run pca_hp_300

Same as baseline_hp_300 except that the 300 highest priority sites are ranked based on PCA distance instead of the combined.metric.

Run pca_lp_300

Same as baseline_lp_300 except the data points are ranked by HP/LP using only the PCA distance.

Run pca_hp_200

Same as baseline_hp_200 but sites are ranked by PCA distance instead of combined metric

Run pca_lp_200

Same as baseline_lp_200 but with training and predict data based on ranking data points by PCA distance only.

Run pca_hp_100

Same as baseline_hp_100 but with HP ranking determined by PCA distance alone.

Run pca_lp_100

Same as baseline_lp_100 except LP sites are ranked by PCA dist, not combined metric.

Run baseline_lp_300

Train ML models on the 300 lowest priority points and evaluate them on the 84 medium priority points.

Run baseline_hp_300

Train ML models with the 300 highest priority points and evaluate them on the 84 medium priority points.

Run baseline_lp_200

Train ML models on the 200 lowest priority sites and evaluate the ML models with the 84 medium priority sites.

Run baseline_hp_200

Train ML models with the 200 most high priority points and evaluate them with the 84 medium priority points.