OpenML-CC18: spambase

Best predictive accuracy per machine-learning flow on the spambase classification task from the OpenML-CC18 suite.

Community results for the spambase classification task from OpenML-CC18, OpenML's curated suite of 72 classification tasks (www.openml.org/t/43). Each subject is a flow — a specific algorithm or pipeline — shown with the best predictive accuracy recorded for it on this task in OpenML's public evaluation listing, under the task's fixed estimation procedure.

Results

predictive_accuracy per subject over 52 measurements, ranked by average.

SubjectAvgMedianMinMaxP95P99Count
sklearn.pipeline.Pipeline(imputation=openmlstudy14.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold…0.96260.96260.96260.96260.96260.96261
sklearn.pipeline.Pipeline(simpleimputer=sklearn.impute._base.SimpleImputer,histgradientboostingclassifier=sklearn.ensemble._hist_gradient_boosting.gradient_boosting.HistGradientBoostingClassifier)(1)0.95980.95980.95980.95980.95980.95981
sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,…0.95890.95890.95890.95890.95890.95891
classif.extraTrees(5)0.95870.95870.95870.95870.95870.95871
weka.MultiBoostAB_LMT(1)0.95870.95870.95870.95870.95870.95871
sklearn.pipeline.Pipeline(simpleimputer=sklearn.impute._base.SimpleImputer,standardscaler=sklearn.preprocessing.data.StandardScaler,randomforestclassifier=sklearn.ensemble.forest.RandomForestClassifi…0.95870.95870.95870.95870.95870.95871
sklearn.model_selection._search_successive_halving.HalvingRandomSearchCV(estimator=sklearn.ensemble._hist_gradient_boosting.gradient_boosting.HistGradientBoostingClassifier)(4)0.95830.95830.95830.95830.95830.95831
sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer2,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_thresho…0.95810.95810.95810.95810.95810.95811
sklearn.model_selection._search_successive_halving.HalvingRandomSearchCV(estimator=sklearn.ensemble._hist_gradient_boosting.gradient_boosting.HistGradientBoostingClassifier)(3)0.95760.95760.95760.95760.95760.95761
sklearn.pipeline.Pipeline(columntransformer=sklearn.compose._column_transformer.ColumnTransformer(numeric=sklearn.pipeline.Pipeline(imputer=sklearn.preprocessing.imputation.Imputer,standardscaler=skl…0.95740.95740.95740.95740.95740.95741
sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshol…0.95740.95740.95740.95740.95740.95741
weka.MultiBoostAB_RandomForest(1)0.95720.95720.95720.95720.95720.95721
weka-randomforest-90.9570.9570.9570.9570.9570.9571
weka-rotationforest-principalcomponents-j48-140.9570.9570.9570.9570.9570.9571
sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.ensemble._hist_gradient_boosting.gradient_boosting.HistGradientBoostingClassifier)(4)0.9570.9570.9570.9570.9570.9571
sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.ensemble._hist_gradient_boosting.gradient_boosting.HistGradientBoostingClassifier)(3)0.9570.9570.9570.9570.9570.9571
mlr.classif.xgboost(9)0.95670.95670.95670.95670.95670.95671
sklearn.pipeline.Pipeline(imputation=openmlstudy14.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold…0.95670.95670.95670.95670.95670.95671
mlr.classif.ranger(9)0.95650.95650.95650.95650.95650.95651
weka.RandomForest(12)0.95650.95650.95650.95650.95650.95651
mlr.classif.xgboost(6)0.95650.95650.95650.95650.95650.95651
mlr.classif.ranger(13)0.95630.95630.95630.95630.95630.95631
weka.FilteredClassifier_MultiSearch_RandomForest(1)0.95630.95630.95630.95630.95630.95631
weka.AdaBoostM1_LMT(2)0.95610.95610.95610.95610.95610.95611
sklearn.ensemble._hist_gradient_boosting.gradient_boosting.HistGradientBoostingClassifier(2)0.95610.95610.95610.95610.95610.95611

…and 27 more subjects.

Metrics

  • predictive_accuracy — recorded on each measurement. Best predictive accuracy this flow achieved on the task: the fraction of test instances classified correctly, from 0 to 1. Higher is better

Subjects (52)

  • classif.boosting(6)
  • classif.extraTrees(5)
  • classif.randomForestSRC(7)
  • mlr.classif.gbm.preproc.preproc.tuned(7)
  • mlr.classif.randomForest.preproc(5)
  • mlr.classif.randomForestSRC.preproc(2)
  • mlr.classif.ranger(13)
  • mlr.classif.ranger(15)
  • mlr.classif.ranger(9)
  • mlr.classif.ranger.preproc.preproc.tuned(17)
  • mlr.classif.xgboost(6)
  • mlr.classif.xgboost(9)
  • randomforest(1)
  • sklearn.ensemble.gradient_boosting.GradientBoostingClassifier(3)
  • sklearn.ensemble._hist_gradient_boosting.gradient_boosting.HistGradientBoostingClassifier(2)
  • sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.ensemble._hist_gradient_boosting.gradient_boosting.HistGradientBoostingClassifier)(3)
  • sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.ensemble._hist_gradient_boosting.gradient_boosting.HistGradientBoostingClassifier)(4)
  • sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,…
  • sklearn.model_selection._search_successive_halving.HalvingRandomSearchCV(estimator=sklearn.ensemble._hist_gradient_boosting.gradient_boosting.HistGradientBoostingClassifier)(4)
  • sklearn.model_selection._search_successive_halving.HalvingRandomSearchCV(estimator=sklearn.ensemble._hist_gradient_boosting.gradient_boosting.HistGradientBoostingClassifier)(3)
  • sklearn.pipeline.Pipeline(columntransformer=sklearn.compose._column_transformer.ColumnTransformer(simpleimputer=sklearn.impute._base.SimpleImputer,onehotencoder=sklearn.preprocessing._encoders.OneHot…
  • sklearn.pipeline.Pipeline(columntransformer=sklearn.compose._column_transformer.ColumnTransformer(numeric=sklearn.pipeline.Pipeline(imputer=sklearn.preprocessing.imputation.Imputer,standardscaler=skl…
  • sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer2,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_thresho…
  • sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshol…
  • sklearn.pipeline.Pipeline(imputation=openmlstudy14.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold…
  • sklearn.pipeline.Pipeline(imputation=openmlstudy14.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold…
  • sklearn.pipeline.Pipeline(simpleimputer=sklearn.impute._base.SimpleImputer,histgradientboostingclassifier=sklearn.ensemble._hist_gradient_boosting.gradient_boosting.HistGradientBoostingClassifier)(1)
  • sklearn.pipeline.Pipeline(simpleimputer=sklearn.impute._base.SimpleImputer,standardscaler=sklearn.preprocessing.data.StandardScaler,randomforestclassifier=sklearn.ensemble.forest.RandomForestClassifi…
  • weka.AdaBoostM1_LADTree(1)
  • weka.AdaBoostM1_LADTree(2)
  • weka.AdaBoostM1_LMT(2)
  • weka.AdaBoostM1_RandomForest(1)
  • weka.AdaBoostM1_RandomForest(2)
  • weka.AttributeSelectedClassifier_GainRatioAttributeEval_Ranker_RandomForest(1)
  • weka.AttributeSelectedClassifier_InfoGainAttributeEval_Ranker_RandomForest(2)
  • weka.Bagging_RandomForest(1)
  • weka.Bagging_RandomForest(2)
  • weka.Bagging_RandomTree(1)
  • weka.classifiers.meta.MultiSearch(weka.classifiers.meta.multisearch.RandomSearch,weka.classifiers.meta.FilteredClassifier(weka.filters.MultiFilter(weka.filters.unsupervised.attribute.ReplaceMissingVa…
  • weka.classifiers.trees.RandomForest(1)
  • weka.FilteredClassifier_MultiSearch_RandomForest(1)
  • weka.FilteredClassifier_RandomForest(4)
  • weka.MultiBoostAB_LMT(1)
  • weka.MultiBoostAB_RandomForest(1)
  • weka.MultiBoostAB_RandomTree(1)
  • weka.MultiBoostAB_REPTree(1)
  • weka.RandomForest(1)
  • weka.RandomForest(12)
  • weka.RandomForest(2)
  • weka.RandomForest(5)

…and 2 more.

Published by OpenML.