DFp2_train: Decision Forest preferred-2 algorithm: Model training

In seldas/Dforest: Decision Forest

Description

Decision Forest algorithm: Model training In Preferred-2 settings, we used KNN instead of Decision Tree

Usage

DFp2_train(X, Y, stop_step = 5, Max_tree = 20, Max_feat = 5, k = 5,
  grace_threshold = 0.01, Filter = F, p_val = 0.05, Method = "bACC",
  Quiet = T)

Arguments

X	Training Dataset
Y	Training data endpoint
stop_step	How many extra step would be processed when performance not improved, 1 means one extra step
Max_tree	Maximum tree number in Forest
Max_feat	maximum occurrence of features in the forest
Filter	doing feature selection before training
p_val	P-value threshold measured by t-test used in feature selection, default is 0.05
Method	Which is used for evaluating training process. MIS: Misclassification rate; ACC: accuracy
Quiet	if TRUE (default), don't show any message during the process
min_leaf	minimum leaves in tree nodes
cp	parameters to pruning decision tree, default is 0.1
Grace_ACC	Grace Value in evaluation: the next model should have a performance (Accuracy) not bad than previous model with threshold
imp_ACC_accu	improvement in evaluation: adding new tree should improve the overall model performance (accuracy) by threshold
Grace_bACC	Grace Value in evaluation: (Balanced Accuracy)
imp_bACC_accu	improvement in evaluation: (Balanced Accuracy)
Grace_MCC	Grace Value in evaluation: (MCC)
imp_MCC_accu	improvement in evaluation: (MCC)
Grace_MIS	Grace Value in evaluation: (MIS)
imp_MIS_accu	improvement in evaluation: (MIS)

Value

Result: Training Model/Performance by KNN

Examples

  ##data(iris)
  X = iris[,1:4]
  Y = iris[,5]
  names(Y)=rownames(X)
  used_model = DF_train(X,Y,stop_step=4, Method = "MCC")

seldas/Dforest documentation built on May 30, 2019, 8:08 p.m.