Closed PhilippPro closed 6 years ago
Nearly every task is available two times, if I want to display it. Why nearly every task appears twice?
> tasks = listOMLTasks(number.of.classes = 2L, number.of.missing.values = 0, data.tag = "OpenML100", estimation.procedure = "10-fold Crossvalidation") > tasks[tasks$name %in% "nomao",] task.id task.type data.id name status format estimation.procedure target.feature evaluation.measures cost.matrix quality.measure 111 9977 Supervised Classification 1486 nomao active ARFF 10-fold Crossvalidation Class <NA> <NA> <NA> 555 145854 Supervised Classification 1486 nomao active ARFF 10-fold Crossvalidation Class <NA> <NA> <NA> majority.class.size max.nominal.att.distinct.values minority.class.size number.of.classes number.of.features number.of.instances 111 24621 3 9844 2 119 34465 555 24621 3 9844 2 119 34465 number.of.instances.with.missing.values number.of.missing.values number.of.numeric.features number.of.symbolic.features 111 0 0 89 30 555 0 0 89 30 > table(tasks$name) ada_agnostic Amazon_employee_access Australian bank-marketing 1 2 2 2 banknote-authentication Bioresponse blood-transfusion-service-center Click_prediction_small 2 3 2 2 climate-model-simulation-crashes credit-g diabetes eeg-eye-state 2 5 2 2 electricity gina_agnostic hill-valley ilpd 2 1 2 2 Internet-Advertisements kc1 kc2 kr-vs-kp 3 1 1 2 madelon MagicTelescope monks-problems-1 monks-problems-2 2 1 2 2 monks-problems-3 mozilla4 nomao ozone-level-8hr 2 1 2 2 pc1 pc3 pc4 PhishingWebsites 1 1 1 2 phoneme qsar-biodeg scene spambase 2 2 1 2 steel-plates-fault sylva_agnostic tic-tac-toe wdbc 2 1 2 2 wilt 2
You probably should replace 'data.tag' with 'tag' that gives you all tasks with that tag instead of all tasks on a dataset with that tag.
You are right. Thanks!
Nearly every task is available two times, if I want to display it. Why nearly every task appears twice?