{
    "data_id": "45551",
    "name": "ATLAS-Higgs-Boson-Machine-Learning-Challenge-2014",
    "exact_name": "ATLAS-Higgs-Boson-Machine-Learning-Challenge-2014",
    "version": 3,
    "version_label": null,
    "description": "This is the datasets from the Kaggle Higgs Boson Machine Learning Challenge 2014. The data was downloaded from the [CERN website](http:\/\/opendata.cern.ch\/record\/328), which also hosts the documentation of the data. \nFurther information about the challenge can be found on [Kaggle](https:\/\/www.kaggle.com\/competitions\/higgs-boson\/), [the challenge website](https:\/\/higgsml.ijclab.in2p3.fr), and the [PMLR competition proceedings](http:\/\/proceedings.mlr.press\/v42\/). \n**Notes:** \n* This version encodes -999 as NaN. \n* This version only contains the data used by the Kaggle competition (first 800k samples)",
    "format": "arff",
    "uploader": "Matthias Feurer",
    "uploader_id": 86,
    "visibility": "public",
    "creator": null,
    "contributor": null,
    "date": "2023-06-04 17:12:47",
    "update_comment": null,
    "last_update": "2023-06-04 17:12:47",
    "licence": "CC0",
    "status": "active",
    "error_message": null,
    "url": "https:\/\/api.openml.org\/data\/download\/22116519\/dataset",
    "default_target_attribute": "Label",
    "row_id_attribute": "EventId",
    "ignore_attribute": "\"Weight\",\"KaggleSet\",\"KaggleWeight\"",
    "runs": 0,
    "suggest": {
        "input": [
            "ATLAS-Higgs-Boson-Machine-Learning-Challenge-2014",
            "This is the datasets from the Kaggle Higgs Boson Machine Learning Challenge 2014. The data was downloaded from the [CERN website](http:\/\/opendata.cern.ch\/record\/328), which also hosts the documentation of the data. Further information about the challenge can be found on [Kaggle](https:\/\/www.kaggle.com\/competitions\/higgs-boson\/), [the challenge website](https:\/\/higgsml.ijclab.in2p3.fr), and the [PMLR competition proceedings](http:\/\/proceedings.mlr.press\/v42\/). * This version encodes -999 as NaN.  "
        ],
        "weight": 5
    },
    "qualities": {
        "NumberOfInstances": 800000,
        "NumberOfFeatures": 31,
        "NumberOfClasses": 2,
        "NumberOfMissingValues": 5053446,
        "NumberOfInstancesWithMissingValues": 581423,
        "NumberOfNumericFeatures": 30,
        "NumberOfSymbolicFeatures": 1,
        "PercentageOfInstancesWithMissingValues": 72.677875,
        "AutoCorrelation": 0.5511756889696112,
        "PercentageOfMissingValues": 20.376798387096773,
        "Dimensionality": 3.875e-5,
        "PercentageOfNumericFeatures": 96.7741935483871,
        "MajorityClassPercentage": 65.828125,
        "PercentageOfSymbolicFeatures": 3.225806451612903,
        "MajorityClassSize": 526625,
        "MinorityClassPercentage": 34.171875,
        "MinorityClassSize": 273375,
        "NumberOfBinaryFeatures": 1,
        "PercentageOfBinaryFeatures": 3.225806451612903
    },
    "tags": [
        {
            "uploader": "38960",
            "tag": "Chemistry"
        },
        {
            "uploader": "38960",
            "tag": "Life Science"
        }
    ],
    "features": [
        {
            "name": "Label",
            "index": "32",
            "type": "nominal",
            "distinct": "2",
            "missing": "0",
            "target": "1",
            "distr": [
                [
                    "b",
                    "s"
                ],
                [
                    [
                        "526625",
                        "0"
                    ],
                    [
                        "0",
                        "273375"
                    ]
                ]
            ]
        },
        {
            "name": "EventId",
            "index": "0",
            "type": "numeric",
            "distinct": "800000",
            "missing": "0",
            "identifier": "1",
            "min": "100000",
            "max": "899999",
            "mean": "500000",
            "stdev": "230940"
        },
        {
            "name": "DER_mass_MMC",
            "index": "1",
            "type": "numeric",
            "distinct": "176176",
            "missing": "121936",
            "min": "9",
            "max": "1949",
            "mean": "122",
            "stdev": "57"
        },
        {
            "name": "DER_mass_transverse_met_lep",
            "index": "2",
            "type": "numeric",
            "distinct": "131451",
            "missing": "0",
            "min": "0",
            "max": "969",
            "mean": "49",
            "stdev": "35"
        },
        {
            "name": "DER_mass_vis",
            "index": "3",
            "type": "numeric",
            "distinct": "153364",
            "missing": "0",
            "min": "6",
            "max": "1349",
            "mean": "81",
            "stdev": "41"
        },
        {
            "name": "DER_pt_h",
            "index": "4",
            "type": "numeric",
            "distinct": "189499",
            "missing": "0",
            "min": "0",
            "max": "2835",
            "mean": "58",
            "stdev": "63"
        },
        {
            "name": "DER_deltaeta_jet_jet",
            "index": "5",
            "type": "numeric",
            "distinct": "7650",
            "missing": "567329",
            "min": "0",
            "max": "9",
            "mean": "2",
            "stdev": "2"
        },
        {
            "name": "DER_mass_jet_jet",
            "index": "6",
            "type": "numeric",
            "distinct": "194275",
            "missing": "567329",
            "min": "14",
            "max": "4975",
            "mean": "372",
            "stdev": "398"
        },
        {
            "name": "DER_prodeta_jet_jet",
            "index": "7",
            "type": "numeric",
            "distinct": "21795",
            "missing": "567329",
            "min": "-19",
            "max": "17",
            "mean": "-1",
            "stdev": "4"
        },
        {
            "name": "DER_deltar_tau_lep",
            "index": "8",
            "type": "numeric",
            "distinct": "5014",
            "missing": "0",
            "min": "0",
            "max": "6",
            "mean": "2",
            "stdev": "1"
        },
        {
            "name": "DER_pt_tot",
            "index": "9",
            "type": "numeric",
            "distinct": "84176",
            "missing": "0",
            "min": "0",
            "max": "2835",
            "mean": "19",
            "stdev": "22"
        },
        {
            "name": "DER_sum_pt",
            "index": "10",
            "type": "numeric",
            "distinct": "283219",
            "missing": "0",
            "min": "46",
            "max": "2079",
            "mean": "159",
            "stdev": "116"
        },
        {
            "name": "DER_pt_ratio_lep_tau",
            "index": "11",
            "type": "numeric",
            "distinct": "7427",
            "missing": "0",
            "min": "0",
            "max": "32",
            "mean": "1",
            "stdev": "1"
        },
        {
            "name": "DER_met_phi_centrality",
            "index": "12",
            "type": "numeric",
            "distinct": "2830",
            "missing": "0",
            "min": "-1",
            "max": "1",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "DER_lep_eta_centrality",
            "index": "13",
            "type": "numeric",
            "distinct": "1001",
            "missing": "567329",
            "min": "0",
            "max": "1",
            "mean": "0",
            "stdev": "0"
        },
        {
            "name": "PRI_tau_pt",
            "index": "14",
            "type": "numeric",
            "distinct": "85907",
            "missing": "0",
            "min": "20",
            "max": "764",
            "mean": "39",
            "stdev": "22"
        },
        {
            "name": "PRI_tau_eta",
            "index": "15",
            "type": "numeric",
            "distinct": "4979",
            "missing": "0",
            "min": "-2",
            "max": "3",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "PRI_tau_phi",
            "index": "16",
            "type": "numeric",
            "distinct": "6286",
            "missing": "0",
            "min": "-3",
            "max": "3",
            "mean": "0",
            "stdev": "2"
        },
        {
            "name": "PRI_lep_pt",
            "index": "17",
            "type": "numeric",
            "distinct": "88154",
            "missing": "0",
            "min": "26",
            "max": "701",
            "mean": "47",
            "stdev": "22"
        },
        {
            "name": "PRI_lep_eta",
            "index": "18",
            "type": "numeric",
            "distinct": "5003",
            "missing": "0",
            "min": "-3",
            "max": "3",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "PRI_lep_phi",
            "index": "19",
            "type": "numeric",
            "distinct": "6286",
            "missing": "0",
            "min": "-3",
            "max": "3",
            "mean": "0",
            "stdev": "2"
        },
        {
            "name": "PRI_met",
            "index": "20",
            "type": "numeric",
            "distinct": "125278",
            "missing": "0",
            "min": "0",
            "max": "2843",
            "mean": "42",
            "stdev": "33"
        },
        {
            "name": "PRI_met_phi",
            "index": "21",
            "type": "numeric",
            "distinct": "6286",
            "missing": "0",
            "min": "-3",
            "max": "3",
            "mean": "0",
            "stdev": "2"
        },
        {
            "name": "PRI_met_sumet",
            "index": "22",
            "type": "numeric",
            "distinct": "344910",
            "missing": "0",
            "min": "14",
            "max": "2190",
            "mean": "210",
            "stdev": "127"
        },
        {
            "name": "PRI_jet_num",
            "index": "23",
            "type": "numeric",
            "distinct": "4",
            "missing": "0",
            "min": "0",
            "max": "3",
            "mean": "1",
            "stdev": "1"
        },
        {
            "name": "PRI_jet_leading_pt",
            "index": "24",
            "type": "numeric",
            "distinct": "150725",
            "missing": "320069",
            "min": "30",
            "max": "1163",
            "mean": "85",
            "stdev": "61"
        },
        {
            "name": "PRI_jet_leading_eta",
            "index": "25",
            "type": "numeric",
            "distinct": "8897",
            "missing": "320069",
            "min": "-5",
            "max": "5",
            "mean": "0",
            "stdev": "2"
        },
        {
            "name": "PRI_jet_leading_phi",
            "index": "26",
            "type": "numeric",
            "distinct": "6286",
            "missing": "320069",
            "min": "-3",
            "max": "3",
            "mean": "0",
            "stdev": "2"
        },
        {
            "name": "PRI_jet_subleading_pt",
            "index": "27",
            "type": "numeric",
            "distinct": "74366",
            "missing": "567329",
            "min": "30",
            "max": "818",
            "mean": "58",
            "stdev": "32"
        },
        {
            "name": "PRI_jet_subleading_eta",
            "index": "28",
            "type": "numeric",
            "distinct": "8929",
            "missing": "567329",
            "min": "-5",
            "max": "5",
            "mean": "0",
            "stdev": "2"
        },
        {
            "name": "PRI_jet_subleading_phi",
            "index": "29",
            "type": "numeric",
            "distinct": "6286",
            "missing": "567329",
            "min": "-3",
            "max": "3",
            "mean": "0",
            "stdev": "2"
        },
        {
            "name": "PRI_jet_all_pt",
            "index": "30",
            "type": "numeric",
            "distinct": "205282",
            "missing": "0",
            "min": "0",
            "max": "1860",
            "mean": "73",
            "stdev": "98"
        },
        {
            "name": "Weight",
            "index": "31",
            "type": "numeric",
            "distinct": "332024",
            "missing": "0",
            "ignore": "1",
            "min": "0",
            "max": "2",
            "mean": "1",
            "stdev": "1"
        },
        {
            "name": "KaggleSet",
            "index": "33",
            "type": "nominal",
            "distinct": "3",
            "missing": "0",
            "ignore": "1",
            "distr": [
                [
                    "b",
                    "t",
                    "v"
                ],
                [
                    [
                        "65975",
                        "34025"
                    ],
                    [
                        "164333",
                        "85667"
                    ],
                    [
                        "296317",
                        "153683"
                    ]
                ]
            ]
        },
        {
            "name": "KaggleWeight",
            "index": "34",
            "type": "numeric",
            "distinct": "332900",
            "missing": "0",
            "ignore": "1",
            "min": "0",
            "max": "19",
            "mean": "2",
            "stdev": "2"
        }
    ],
    "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
}