0

I am trying to do L2-regularized MLR on a data set using caret. Following is what I have done so far to achieve this:

r_squared <-  function ( pred, actual){
    mean_actual = mean (actual)
    ss_e = sum ((pred - actual )^2)
    ss_total = sum ((actual-mean_actual)^2 )
    r_squared = 1 - (ss_e/ss_total)
}

df = as.data.frame(matrix(rnorm(10000, 10, 3), 1000))
colnames(df)[1] = "response"
set.seed(753)
inTraining <- createDataPartition(df[["response"]], p = .75, list = FALSE)
training <- df[inTraining,]
testing  <- df[-inTraining,]
testing_response <- base::subset(testing,
                                 select = c(paste ("response")))
gridsearch_for_lambda =  data.frame (alpha = 0, 
                                      lambda = c (2^c(-15:15), 3^c(-15:15)))
regression_formula = as.formula (paste ("response", "~ ", " .", sep = " "))
train_control = trainControl (method="cv", number =10,
                              savePredictions =TRUE , allowParallel = FALSE )
model = train (regression_formula,
                           data = training,
                           trControl = train_control,
                           method = "glmnet",
                           tuneGrid =gridsearch_for_lambda,
                           preProcess = NULL
            )
prediction = predict (model, newdata = testing)
testing_response[["predicted"]] = prediction
r_sq = round (r_squared(testing_response[["predicted"]],
              testing_response[["response"]] ),3)

Here I am concerned about assurance that the model I am using for prediction is the best one (the optimal tuned lambda value).

P.S.: The data is sampled from random normal distribution, which is not giving a good R^2 value, but I want to get the idea correctly

milos.ai
  • 3,882
  • 7
  • 31
  • 33
satyanarayan rao
  • 111
  • 4
  • 9
  • This is definitely not a SO question. Model selection is a religion, i.e. no objective of telling which model is the best. There are some who swears by r2 (or adj r2) while others go with information criteria. – Adam Quek May 20 '16 at 01:44
  • +1 @AdamQuek. But in this given context, at least I would like to make sure that the model is best among the mentioned lambda in the gridsearch. btw, by "SO" what do you mean? – satyanarayan rao May 20 '16 at 01:50
  • Aah, sorry @AdamQuek, I should have put this question in Cross Validated not in SO. – satyanarayan rao May 20 '16 at 02:45

0 Answers0