xgboost (version 0.4-4)

xgb.cv: Cross Validation

Description

The cross valudation function of xgboost

Usage

xgb.cv(params = list(), data, nrounds, nfold, label = NULL, missing = NULL, prediction = FALSE, showsd = TRUE, metrics = list(), obj = NULL, feval = NULL, stratified = TRUE, folds = NULL, verbose = T, print.every.n = 1L, early.stop.round = NULL, maximize = NULL, ...)

Arguments

params

the list of parameters. Commonly used ones are:

• objective objective function, common ones are
  • reg:linear linear regression
  • binary:logistic logistic regression for classification

• eta step size of each boosting step
• max.depth maximum depth of the tree
• nthread number of thread used in training, if not set, all threads are used

See xgb.train for further details. See also demo/ for walkthrough example in R.

data

takes an xgb.DMatrix or Matrix as the input.

nrounds

the max number of iterations

nfold

the original dataset is randomly partitioned into nfold equal size subsamples.

label

option field, when data is Matrix

missing

Missing is only used when input is dense matrix, pick a float value that represents missing value. Sometime a data use 0 or other extreme value to represents missing values.

prediction

A logical value indicating whether to return the prediction vector.

showsd

boolean, whether show standard deviation of cross validation

metrics,

list of evaluation metrics to be used in corss validation, when it is not specified, the evaluation metric is chosen according to objective function. Possible options are:

• error binary classification error rate
• rmse Rooted mean square error
• logloss negative log-likelihood function
• auc Area under curve
• merror Exact matching error, used to evaluate multi-class classification

obj

customized objective function. Returns gradient and second order gradient with given prediction and dtrain.

feval

custimized evaluation function. Returns list(metric='metric-name', value='metric-value') with given prediction and dtrain.

stratified

boolean whether sampling of folds should be stratified by the values of labels in data

folds

list provides a possibility of using a list of pre-defined CV folds (each element must be a vector of fold's indices). If folds are supplied, the nfold and stratified parameters would be ignored.

verbose

boolean, print the statistics during the process

print.every.n

Print every N progress messages when verbose>0. Default is 1 which means all messages are printed.

early.stop.round

If NULL, the early stopping function is not triggered. If set to an integer k, training with a validation set will stop if the performance keeps getting worse consecutively for k rounds.

maximize

If feval and early.stop.round are set, then maximize must be set as well. maximize=TRUE means the larger the evaluation score the better.

...

other parameters to pass to params.

Value

If prediction = TRUE, a list with the following elements is returned:

• dt a data.table with each mean and standard deviation stat for training set and test set
• pred an array or matrix (for multiclass classification) with predictions for each CV-fold for the model having been trained on the data in all other folds.

If prediction = FALSE, just a data.table with each mean and standard deviation stat for training set and test set is returned.

Details

The original sample is randomly partitioned into nfold equal size subsamples.

Of the nfold subsamples, a single subsample is retained as the validation data for testing the model, and the remaining nfold - 1 subsamples are used as training data.

The cross-validation process is then repeated nrounds times, with each of the nfold subsamples used exactly once as the validation data.

All observations are used for both training and validation.

Adapted from http://en.wikipedia.org/wiki/Cross-validation_%28statistics%29#k-fold_cross-validation

Examples

data(agaricus.train, package='xgboost')
dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
history <- xgb.cv(data = dtrain, nround=3, nthread = 2, nfold = 5, metrics=list("rmse","auc"),
                  max.depth =3, eta = 1, objective = "binary:logistic")
print(history)