gbm_reg: Custom function for regression by Gradient Boosting Machine
In AbirChakraborty1/RegFunction: custom function for regression models

Description Usage Arguments Value Author(s)

View source: R/PredFuncAC.R

This function takes training data, tesing data, target variable, tuning parameters, and predict target variable of the training data by GBM regression model.

gbm_reg(train,test,target,
drop = NULL,num_trials=10,
interaction.depth=c(1:7),
n.trees=c(50,100,200,500,700),
shrinkage=c(.1,.01,.001),
n.minobsinnode=c(1,2,5,10),
type='NULL')

`train`	Training Data as a dataframe.
`test`	Testing Data as a dataframe.
`target`	Name of the variable that needs to predict
`drop`	Name of the variable that needs to be dropped before building the model.
`num_trials`	Total number of trails to find best combination of GBM parameters causing minimum error
`interaction.depth`	GBM Tuning parameter: Integer specifying the maximum depth of each tree (i.e., the highest level of variable interactions allowed). A value of 1 implies an additive model, a value of 2 implies a model with up to 2-way interactions, etc. Default is c(1:7)
`n.trees`	GBM Tuning parameter: Integer specifying the total number of trees to fit. This is equivalent to the number of iterations and the number of basis functions in the additive expansion. Default is c(50,100,200,500,700).
`shrinkage`	GBM Tuning parameter: a shrinkage parameter applied to each tree in the expansion. Also known as the learning rate or step-size reduction; 0.001 to 0.1 usually work, but a smaller learning rate typically requires more trees. Default is c(.1,.01,.001)
`minobsinnode`	GBM Tuning parameter: Integer specifying the minimum number of observations in the terminal nodes of the trees. Note that this is the actual number of observations, not the total weight.Default is c(1,2,5,10)
`type`	if type = "tuning", it will return the least error with best value of the best parameter combination,any other value will return the prediction on testing data.