Alzheimer's Research & Therapy

Table 13 Parameters used for the implementation of the ML workflow

From: Data analysis with Shapley values for automatic subject selection in Alzheimer’s disease data sets using interpretable machine learning

Method	Hyperparameter	Values
RF	n_estimators	50
	criterion	“gini”
	max_depth	None
	min_weight_fraction_leaf	0.0
	max_features	“auto”
	max_leaf_nodes	None
	min_impurity_decrease	0.0
	min_impurity_split	None
	bootstrap	True
	oob_score	False
	class_weight	None
	ccp_alpha	0.0
	max_samples	None
XGBoost	subsample	0.6
	objective	“binary:logistic”
	booster	“gbtree”
	eta	0.3
	gamma	0
	max_depth	6
	min_child_weight	1
	max_delta_step	0
	sampling_method	“uniform”
	colsample_bytree	1
	colsample_bylevel	1
	colsample_bynode	1
	lambda	1
	alpha	0
	tree_method	“auto”
	sketch_eps	0.03
	scale_pos_weight	1
	updater	“grow_colmaker,prune”
	refresh_leaf	1
	process_type	“default”
	grow_policy	“depthwise”
	max_leaves	0
	max_bin	256
	predictor	“auto”
	num_parallel_tree	1
LR	solver	“liblinear”
	penalty	“l2”
	dual	False
	tol	1e-4
	C	1.0
	fit_intercept	True
	intercept_scaling	1
	class_weight	None
	max_iter	5000
	multi_class	“auto”
	warm_start	False
	l1_ratio	None
Data Shapley	number of repetitions	4
	model_family	{“RandomForest”, “logistic”}
	metric	“accuracy”
	num_test	108
	problem	“classification”
	sample weights	None
	save_every	100
	err	0.1
	tolerance	0.01
	g_run	False
	loo_run	True
Kernel SHAP	nsample	3000
	l1_reg	“auto”
	link	“identity”

Back to article page

ISSN: 1758-9193

Contact us

General enquiries: journalsubmissions@springernature.com