OpenML

JavaScript is required to properly view the contents of this page!

Supervised Data Stream Classification on BNG(ionosphere)

Task 185 Supervised Data Stream Classification BNG(ionosphere) 209 runs submitted
0 likes downloaded by 0 people , 0 total downloads 0 issues
Visibility: Public

Issue	#Downvotes for this reason	By

Metric:

209 Runs

Fetching data

Search runs in more detail

ID's

209 results

Jan van Rijn 11 years ago
ran flow moa.WEKAClassifier(1) on task Supervised Data Stream Classification on data set BNG(ionosphere)

0 likes - 0 downloads - 0 reach - area_under_roc_curve: 0.9204, f_measure: 0.8095, kappa: 0.6018, kb_relative_information_score: 610991.2397, mean_absolute_error: 0.1947, mean_prior_absolute_error: 0.5, number_of_instances: 1000000, precision: 0.8282, predictive_accuracy: 0.8059, prior_entropy: 1, ram_hours: 0, recall: 0.8059, relative_absolute_error: 0.3894, root_mean_prior_squared_error: 0.5, root_mean_squared_error: 0.4017, root_relative_squared_error: 0.8034, run_cpu_time: 19.18,

Jan van Rijn 11 years ago
ran flow moa.WEKAClassifier_LinearRegression(1) on task Supervised Data Stream Classification on data set BNG(ionosphere)

0 likes - 0 downloads - 0 reach - area_under_roc_curve: 0.5, f_measure: 0.1896, kb_relative_information_score: -281756, mean_absolute_error: 0.6409, mean_prior_absolute_error: 0.5, number_of_instances: 1000000, precision: 0.1289, predictive_accuracy: 0.359, prior_entropy: 1, ram_hours: 0.0042, recall: 0.359, relative_absolute_error: 1.2818, root_mean_prior_squared_error: 0.5, root_mean_squared_error: 0.8004, root_relative_squared_error: 1.6008, run_cpu_time: 86.18,

Jan van Rijn 11 years ago
ran flow moa.FIMTDD(1) on task Supervised Data Stream Classification on data set BNG(ionosphere)

0 likes - 0 downloads - 0 reach - area_under_roc_curve: 0.5, f_measure: 0.1896, kb_relative_information_score: -282050, mean_absolute_error: 0.641, mean_prior_absolute_error: 0.5, number_of_instances: 1000000, precision: 0.1289, predictive_accuracy: 0.359, prior_entropy: 1, ram_hours: 0, recall: 0.359, relative_absolute_error: 1.2821, root_mean_prior_squared_error: 0.5, root_mean_squared_error: 0.8006, root_relative_squared_error: 1.6013, run_cpu_time: 14.9,

Jan van Rijn 11 years ago
ran flow moa.NaiveBayes(1) on task Supervised Data Stream Classification on data set BNG(ionosphere)

0 likes - 0 downloads - 0 reach - area_under_roc_curve: 0.9218, f_measure: 0.7987, kappa: 0.5849, kb_relative_information_score: 590705.2616, mean_absolute_error: 0.2045, mean_prior_absolute_error: 0.5, number_of_instances: 1000000, precision: 0.8267, predictive_accuracy: 0.7946, prior_entropy: 1, ram_hours: 0, recall: 0.7946, relative_absolute_error: 0.409, root_mean_prior_squared_error: 0.5, root_mean_squared_error: 0.417, root_relative_squared_error: 0.834, run_cpu_time: 18.01,

Jan van Rijn 11 years ago
ran flow moa.LeveragingBag_HoeffdingTree(1) on task Supervised Data Stream Classification on data set BNG(ionosphere)

0 likes - 0 downloads - 0 reach - area_under_roc_curve: 0.9944, f_measure: 0.9664, kappa: 0.9271, kb_relative_information_score: 884747.0801, mean_absolute_error: 0.0639, mean_prior_absolute_error: 0.5, number_of_instances: 1000000, precision: 0.9665, predictive_accuracy: 0.9664, prior_entropy: 1, ram_hours: 0.0168, recall: 0.9664, relative_absolute_error: 0.1278, root_mean_prior_squared_error: 0.5, root_mean_squared_error: 0.1615, root_relative_squared_error: 0.3229, run_cpu_time: 439.14,

Jan van Rijn 11 years ago
ran flow moa.HoeffdingTree(1) on task Supervised Data Stream Classification on data set BNG(ionosphere)

0 likes - 0 downloads - 0 reach - area_under_roc_curve: 0.9807, f_measure: 0.9461, kappa: 0.8831, kb_relative_information_score: 858528.8436, mean_absolute_error: 0.0758, mean_prior_absolute_error: 0.5, number_of_instances: 1000000, precision: 0.9462, predictive_accuracy: 0.9461, prior_entropy: 1, ram_hours: 0, recall: 0.9461, relative_absolute_error: 0.1515, root_mean_prior_squared_error: 0.5, root_mean_squared_error: 0.21, root_relative_squared_error: 0.4199, run_cpu_time: 23.3,

Jan van Rijn 11 years ago
ran flow moa.LeveragingBag_kNN(1) on task Supervised Data Stream Classification on data set BNG(ionosphere)

0 likes - 0 downloads - 0 reach - area_under_roc_curve: 0.9558, f_measure: 0.8494, kappa: 0.6661, kb_relative_information_score: 669741.6098, mean_absolute_error: 0.1695, mean_prior_absolute_error: 0.5, number_of_instances: 1000000, precision: 0.8706, predictive_accuracy: 0.8572, prior_entropy: 1, ram_hours: 0.0027, recall: 0.8572, relative_absolute_error: 0.339, root_mean_prior_squared_error: 0.5, root_mean_squared_error: 0.3199, root_relative_squared_error: 0.6398, run_cpu_time: 14073.8,

Jan van Rijn 11 years ago
ran flow moa.kNN(1) on task Supervised Data Stream Classification on data set BNG(ionosphere)

0 likes - 0 downloads - 0 reach - area_under_roc_curve: 0.9555, f_measure: 0.8513, kappa: 0.6703, kb_relative_information_score: 669720.5567, mean_absolute_error: 0.1695, mean_prior_absolute_error: 0.5, number_of_instances: 1000000, precision: 0.8716, predictive_accuracy: 0.8588, prior_entropy: 1, ram_hours: 0.0001, recall: 0.8588, relative_absolute_error: 0.339, root_mean_prior_squared_error: 0.5, root_mean_squared_error: 0.32, root_relative_squared_error: 0.6399, run_cpu_time: 720.26,

Jan van Rijn 11 years ago
ran flow moa.SGD(1) on task Supervised Data Stream Classification on data set BNG(ionosphere)

0 likes - 0 downloads - 0 reach - area_under_roc_curve: 0.8162, f_measure: 0.853, kappa: 0.6742, kb_relative_information_score: 718680, mean_absolute_error: 0.1407, mean_prior_absolute_error: 0.5, number_of_instances: 1000000, precision: 0.868, predictive_accuracy: 0.8593, prior_entropy: 1, ram_hours: 0, recall: 0.8593, relative_absolute_error: 0.2813, root_mean_prior_squared_error: 0.5, root_mean_squared_error: 0.375, root_relative_squared_error: 0.7501, run_cpu_time: 14.2,

Metric:

Timeline

Plotting contribution timeline

Leaderboard

Rank	Name	Top Score	Entries	Highest rank

Note: The leaderboard ignores resubmissions of previous solutions, as well as parameter variations that do not improve performance.

Challenge

Given a dataset with a nominal target, various data samples of increasing size are defined. A model is build for each individual data sample; from this a learning curve can be drawn.

Given inputs

estimation_procedure	Interleaved Test then Train
source_data	BNG(ionosphere) (1)
target_feature	class

Expected outputs

evaluations	A list of user-defined evaluations of the task as key-value pairs.	KeyValue (optional)
predictions	The desired output format	Predictions (optional)

How to submit runs

Using your favorite machine learning environment

Download this task directly in your environment and automatically upload your results

OpenML bootcamp

From your own software

Use one of our APIs to download data from OpenML and upload your results

OpenML APIs

Sign in