mlr (version 2.3)

makeMeasure: Construct performance measure.

Description

A measure object encapsulates a function to evaluate the performance of a prediction. Information about already implemented measures can be obtained here: measures.

A learner is trained on a a training set d1, results in a model m, predicts another set d2 (which may be a different one or the training set), resulting in the prediction. The performance measure can now be defined using all of the information of the original task, the fitted model and the prediction.

Object slots: [object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]

Usage

makeMeasure(id, minimize, properties = character(0L), fun,
  extra.args = list(), aggr = test.mean, best = NULL, worst = NULL,
  name = id, note = "")

Value

[Measure].

See Also

Other performance: G1, G2, acc, auc, bac, ber, cindex, db, dunn, f1, fdr, featperc, fn, fnr, fp, fpr, gmean, gpr, mae, mcc, mcp, meancosts, measureACC, measureAUC, measureBAC, measureFDR, measureFN, measureFNR, measureFP, measureFPR, measureGMEAN, measureGPR, measureMAE, measureMCC, measureMEDAE, measureMEDSE, measureMMCE, measureMSE, measureNPV, measurePPV, measureRMSE, measureSAE, measureSSE, measureTN, measureTNR, measureTP, measureTPR, measures, medae, medse, mmce, mse, multiclass.auc, npv, ppv, rmse, sae, silhouette, sse, timeboth, timepredict, timetrain, tn, tnr, tp, tpr; makeCostMeasure; makeCustomResampledMeasure; performance

Examples

f = function(task, model, pred, extra.args)
  sum((pred$data$response - pred$data$truth)^2)
makeMeasure(id = "my.sse", minimize = TRUE, properties = c("regr", "response"), fun = f)