This lesson requires a premium membership to access.
Premium membership includes unlimited access to all courses, quizzes, downloadable resources, and future content updates.
Now, we will tune RandomForest model. Like SVM, we tune parameter based on 5% downsampling data. The procedure is exactly the same as for SVM model. Below we have reproduced the code for Random Forest model.
1set.seed(300)
2#down sampling again so than we get more info when stacking
3samp = downSample(data_train[-getIndexsOfColumns(data_train, c( "loan_status") )],data_train$loan_status,yname="loan_status")
4#choose small data for tuning
5train_index_tuning = createDataPartition(samp$loan_status,p = 0.05,list=FALSE,times=1)
6#choose small data for re-train
7train_index_training = createDataPartition(samp$loan_status,p = 0.1,list=FALSE,times=1)
8rfGrid = expand.grid(
9 .mtry = as.integer(seq(2,ncol(samp), (ncol(samp) - 2)/4))
10 )
11#Install random forest package
12library(randomForest)
13rfTuned = train(
14 samp[train_index_tuning,-getIndexsOfColumns(samp,"loan_status")],
15 y = samp[train_index_tuning,"loan_status"],
16 method = "rf",
17 tuneGrid = rfGrid,
18 metric = "ROC",
19 trControl = ctrl,
20 preProcess = NULL,
21 ntree = 100
22 )
23plot(rfTuned)
24