Skip to main content

Advertisement

Table 1 Pipeline parameters tested using grid-search and 10-fold CV

From: Comparative analysis of predictive methods for early assessment of compliance with continuous positive airway pressure therapy

Pipeline step Parameter options
Combine_fs percentile = [5, 10, 20, 30, 40, 50]
Lasso_fs estimator = Logistic Regression
  penalty = “l1”
  C=[5,10,20,30,40,50]
RFE_RF_fs class_weight = ‘balanced’
  n_estimators = 100
  step = [0,1 ]
  n_features_to_select = [0.4,0.6,0.8]
Smote_fs n_neighbors = [3,4,5]
  ratio=‘auto’
  kind=‘regular’
k-NN n_neighbors = [1,3,5,7,9,11]
  weights = [‘uniform’, ‘distance’]
LR C = [0.00001, 0.0001, 0.0005, 0.001, 0.005, 0.01, 0.05, 0.1, 0.5, 1, 5, 10, 15, 30]
  class_weight = [None, ‘balanced’]
  penalty = [‘l1’, ‘l2’]
RF n_estimators = [100,150,200,250,500]
  criterion = [‘entropy’,‘gini’]
  max_depth = [‘None’,4,6]
  class_weight = [None, ‘balanced’]
SVM C = [0.01,0.1,0.5,1,5,10,15,30,50]
  gamma = [0.0001,0.001,0.01, 0.1,1,5]
  kernel = ‘radial’
  class_weight = [None, ’balanced’]
NN alpha = [1e −5, 0.00001, 0.0001, 0.001, 0.01,0.1,1,3,5,10]
  hidden_layer_sizes = [(30,), (50,), (70,), (100,), (150,),
  (30,30),(50,50),(70,70),(100,100),
  (30,30,30),(50,50,50),(70,70,70)]