Wraps all three methods

This function is a wrapper for the feature_selection function

wrapper_feat_select(
  X,
  y,
  params_glmnet = NULL,
  params_xgboost = NULL,
  params_ranger = NULL,
  xgb_sort = NULL,
  CV_folds = 5,
  stratified_regr = FALSE,
  scale_coefs_glmnet = FALSE,
  cores_glmnet = NULL,
  params_features = NULL,
  verbose = FALSE
)

Arguments

X	a sparse Matrix, a matrix or a data frame
y	a vector of length representing the response variable
params_glmnet	a list of parameters for the glmnet model
params_xgboost	a list of parameters for the xgboost model
params_ranger	a list of parameters for the ranger model
xgb_sort	sort the xgboost features by "Gain", "Cover" or "Frequency" ( defaults to "Frequency")
CV_folds	a number specifying the number of folds for cross validation
stratified_regr	a boolean determining if the folds in regression should be stratified
scale_coefs_glmnet	if TRUE, less important coefficients will be smaller than the more important ones (ranking/plotting by magnitude possible)
cores_glmnet	an integer determining the number of cores to register in glmnet
params_features	is a list of parameters for the wrapper function
verbose	outputs info

Value

a list containing the important features of each method. If union in the params_feature list is enabled, then it also returns the average importance of all methods.

Details

This function returns the importance of the methods specified and if union in the params_feature list is TRUE then it also returns the average importance of all methods. Furthermore the user can limit the number of features using the keep_number_feat parameter of the params_feature list.

Examples

if (FALSE) {

#...........
# regression
#...........

data(iris)

X = iris[, -5]
y = X[, 1]
X = X[, -1]

params_glmnet = list(alpha = 1, 
                     family = 'gaussian', 
                     nfolds = 3, 
                     parallel = TRUE)


params_xgboost = list( params = list("objective" = "reg:linear", 
                                     "bst:eta" = 0.01, 
                                     "subsample" = 0.65, 
                                     "max_depth" = 5,
                                     "colsample_bytree" = 0.65,
                                     "nthread" = 2),
                       nrounds = 100, 
                       print.every.n = 50, 
                       verbose = 0, 
                       maximize = FALSE)


params_ranger = list(probability = FALSE, 
                     num.trees = 100, 
                     verbose = TRUE, 
                     classification = FALSE,
                     mtry = 3,
                     min.node.size = 10,
                     num.threads = 2, 
                     importance = 'permutation')


params_features = list(keep_number_feat = NULL, 
                       union = TRUE)

feat = wrapper_feat_select(X, 
                           y, 
                           params_glmnet = params_glmnet, 
                           params_xgboost = params_xgboost, 
                           params_ranger = params_ranger,
                            xgb_sort = NULL,
                           CV_folds = 10, 
                           stratified_regr = FALSE, 
                           cores_glmnet = 2, 
                           params_features = params_features)
}