{ "data_id": "4532", "name": "higgs", "exact_name": "higgs", "version": 1, "version_label": null, "description": "**Author**: Daniel Whiteson daniel'@'uci.edu\", Assistant Professor, Physics, Univ. of California Irvine \n**Source**: [UCI](https:\/\/archive.ics.uci.edu\/ml\/datasets\/HIGGS) \n**Please cite**: Baldi, P., P. Sadowski, and D. Whiteson. Searching for Exotic Particles in High-energy Physics with Deep Learning. Nature Communications 5 (July 2, 2014). \n\nData Set Information:\n\nThe data has been produced using Monte Carlo simulations. The first 21 features (columns 2-22) are kinematic properties measured by the particle detectors in the accelerator. The last seven features are functions of the first 21 features; these are high-level features derived by physicists to help discriminate between the two classes. There is an interest in using deep learning methods to obviate the need for physicists to manually develop such features. Benchmark results using Bayesian Decision Trees from a standard physics package and 5-layer neural networks are presented in the original paper. The last 500,000 examples are used as a test set.\n\n\nAttribute Information:\n\nThe first column is the class label (1 for signal, 0 for background), followed by the 28 features (21 low-level features then 7 high-level features): lepton pT, lepton eta, lepton phi, missing energy magnitude, missing energy phi, jet 1 pt, jet 1 eta, jet 1 phi, jet 1 b-tag, jet 2 pt, jet 2 eta, jet 2 phi, jet 2 b-tag, jet 3 pt, jet 3 eta, jet 3 phi, jet 3 b-tag, jet 4 pt, jet 4 eta, jet 4 phi, jet 4 b-tag, m_jj, m_jjj, m_lv, m_jlv, m_bb, m_wbb, m_wwbb. For more detailed information about each feature see the original paper.\n\n\nRelevant Papers:\n\nBaldi, P., P. Sadowski, and D. Whiteson. “Searching for Exotic Particles in High-energy Physics with Deep Learning. Nature Communications 5 (July 2, 2014).\n\n", "format": "ARFF", "uploader": "Hilda Fabiola Bernard", "uploader_id": 874, "visibility": "public", "creator": "\"Daniel Whiteson daniel '@' uci.edu\",\"Assistant Professor\",\"Physics\",\"Univ. of California Irvine\"", "contributor": null, "date": "2016-02-16 14:46:54", "update_comment": null, "last_update": "2016-02-16 14:46:54", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/1798100\/phpIk6oDJ", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "higgs", "Data Set Information: The data has been produced using Monte Carlo simulations. The first 21 features (columns 2-22) are kinematic properties measured by the particle detectors in the accelerator. The last seven features are functions of the first 21 features; these are high-level features derived by physicists to help discriminate between the two classes. There is an interest in using deep learning methods to obviate the need for physicists to manually develop such features. Benchmark results u " ], "weight": 5 }, "qualities": { "NumberOfInstances": 98050, "NumberOfFeatures": 29, "NumberOfClasses": 0, "NumberOfMissingValues": 9, "NumberOfInstancesWithMissingValues": 1, "NumberOfNumericFeatures": 29, "NumberOfSymbolicFeatures": 0, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 1.0501287597024396, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.4296647013596655, "RandomTreeDepth1AUC": null, "Dimensionality": 0.00029576746557878636, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.0046571460092226, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.11449793943225124, "PercentageOfInstancesWithMissingValues": 0.0010198878123406426, "Quartile3AttributeEntropy": null, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 5.981690289185084, "MinStdDevOfNumericAtts": 0.16456533466462578, "PercentageOfMissingValues": 0.0003165169072781304, "Quartile3KurtosisOfNumericAtts": 10.201079560689937, "AutoCorrelation": 0.5012085793837775, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 1.3968091904244635, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 100, "Quartile3MeansOfNumericAtts": 1.0012816038780938, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 0, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": 7.55701341358166, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 2.197291705261518, "CfsSubsetEval_DecisionStumpKappa": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 0.6046525441800488, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": -1.2016281646027998, "Quartile3StdDevOfNumericAtts": 1.0085504415893336, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": -0.0002134655869219495, "REPTreeDepth1AUC": null, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3Kappa": null, "J48.001.AUC": null, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": null, "CfsSubsetEval_NaiveBayesKappa": null, "CfsSubsetEval_kNN1NAUC": null, "StdvNominalAttDistinctValues": null, "J48.001.ErrRate": null, "MeanNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": 0.0008337769964050249, "REPTreeDepth1Kappa": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": 1.306653704605097, "Quartile1StdDevOfNumericAtts": 0.49319720426926084, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 0.7639803163712949, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": -0.033841779627087565, "REPTreeDepth2Kappa": null, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.9869307512100667, "Quartile2MeansOfNumericAtts": 0.9859320647202234, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 63.889738287879354, "MinMeansOfNumericAtts": -0.007896418321767898, "Quartile2MutualInformation": null }, "tags": [ { "uploader": "38960", "tag": "Geography" }, { "uploader": "38960", "tag": "Life Science" } ], "features": [ { "name": "class", "index": "0", "type": "numeric", "distinct": "2", "missing": "0", "target": "1", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "lepton_pT", "index": "1", "type": "numeric", "distinct": "13044", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "lepton_eta", "index": "2", "type": "numeric", "distinct": "4919", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "lepton_phi", "index": "3", "type": "numeric", "distinct": "6284", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "missing_energy_magnitude", "index": "4", "type": "numeric", "distinct": "92943", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "missing_energy_phi", "index": "5", "type": "numeric", "distinct": "92777", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "jet1pt", "index": "6", "type": "numeric", "distinct": "20297", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "0" }, { "name": "jet1eta", "index": "7", "type": "numeric", "distinct": "5712", "missing": "0", "min": "-3", "max": "3", "mean": "0", "stdev": "1" }, { "name": "jet1phi", "index": "8", "type": "numeric", "distinct": "6284", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "jet1b-tag", "index": "9", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "jet2pt", "index": "10", "type": "numeric", "distinct": "16512", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "0" }, { "name": "jet2eta", "index": "11", "type": "numeric", "distinct": "5804", "missing": "0", "min": "-3", "max": "3", "mean": "0", "stdev": "1" }, { "name": "jet2phi", "index": "12", "type": "numeric", "distinct": "6284", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "jet2b-tag", "index": "13", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "jet3pt", "index": "14", "type": "numeric", "distinct": "12428", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "0" }, { "name": "jet3eta", "index": "15", "type": "numeric", "distinct": "5913", "missing": "0", "min": "-3", "max": "3", "mean": "0", "stdev": "1" }, { "name": "jet3phi", "index": "16", "type": "numeric", "distinct": "6284", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "jet3b-tag", "index": "17", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "jet4pt", "index": "18", "type": "numeric", "distinct": "9389", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "jet4eta", "index": "19", "type": "numeric", "distinct": "5974", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "jet4phi", "index": "20", "type": "numeric", "distinct": "6284", "missing": "1", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "jet4b-tag", "index": "21", "type": "numeric", "distinct": "3", "missing": "1", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "m_jj", "index": "22", "type": "numeric", "distinct": "89763", "missing": "1", "min": "0", "max": "18", "mean": "1", "stdev": "1" }, { "name": "m_jjj", "index": "23", "type": "numeric", "distinct": "68881", "missing": "1", "min": "0", "max": "10", "mean": "1", "stdev": "0" }, { "name": "m_lv", "index": "24", "type": "numeric", "distinct": "45482", "missing": "1", "min": "0", "max": "5", "mean": "1", "stdev": "0" }, { "name": "m_jlv", "index": "25", "type": "numeric", "distinct": "76814", "missing": "1", "min": "0", "max": "7", "mean": "1", "stdev": "0" }, { "name": "m_bb", "index": "26", "type": "numeric", "distinct": "82416", "missing": "1", "min": "0", "max": "12", "mean": "1", "stdev": "1" }, { "name": "m_wbb", "index": "27", "type": "numeric", "distinct": "83123", "missing": "1", "min": "0", "max": "7", "mean": "1", "stdev": "0" }, { "name": "m_wwbb", "index": "28", "type": "numeric", "distinct": "85937", "missing": "1", "min": "0", "max": "6", "mean": "1", "stdev": "0" } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 0, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 0 }