Show Menu
Cheatography

R modelling Cheat Sheet (DRAFT) by

R modeling

This is a draft cheat sheet. It is a work in progress and is not finished yet.

Available Models / Parameters

names(getModelInfo()) # available models
modelLookup(model='gbm') # parameters

Cross validation

fitControl <- trainControl(
    method = "cv",
    number = 3)

Data prepar­ation

# for xgboost
train_mm <- as.data.frame(model.matrix(log_SalePrice ~ .-1, 
    data=subset(train, select = -c(SalePrice, Id))))
label_train <- train$log_SalePrice
 

Parameter tuning

gbm.grid <- expand.grid(n.trees=c(2000, 5000), 
                    shrinkage=c(0.01, 0.005), 
                    n.minobsinnode = c(10,50), 
                    interaction.depth=c(7,10))

Fit model

model_gbm<-train(x = train[,vars], y = train[,'log_SalePrice'],
                 method = 'gbm', 
                 trControl = fitControl,
                 tuneGrid = gbm.grid)

Model evaluation

print(model_gbm)
plot(model_gbm)
model_gbm$bestTune
model_gbm$results
varImp(object = model_gbm)
predict(model_gbm, test_data)