We are trying to use the best subset model and the lasso model however we get the following error for the models:
Error in leaps.exhaustive(a, really.big): Exhaustive seach will be S L O W, must specify really.big=T
There were missing values in resampled performance measues
The models looks as follows:
best.subset=regsubsets(y_High~ . -X - y_Low - y_Today - y_Direction, data = train, nvmax =5)
library(caret) lasso= train(y_High~ . -X - y_Low - y_Today - y_Direction, data = train, method = "glmnet", trControl = myControl, tuneGrid = expand.grid(alpha = 1, lambda = seq(0.0001, 1, length = 20)))
How are we available to fix those errors?
Our training data has 1400 observations with 96 variables