{ "data_id": "1182", "name": "BNG(adult)", "exact_name": "BNG(adult)", "version": 1, "version_label": null, "description": "", "format": "ARFF", "uploader": "Jan van Rijn", "uploader_id": 1, "visibility": "public", "creator": "\"Geoffrey Holmes\",\"Bernhard Pfahringer\",\"Jan van Rijn\",\"Joaquin Vanschoren\"", "contributor": null, "date": "2014-11-12 12:15:31", "update_comment": null, "last_update": "2014-11-12 12:15:31", "licence": "public domain", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/150672\/BNG_adult.arff", "kaggle_url": null, "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 44, "suggest": { "input": [ "BNG(adult)", " " ], "weight": 5 }, "qualities": { "NumberOfInstances": 1000000, "NumberOfFeatures": 15, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 2, "NumberOfSymbolicFeatures": 13, "J48.001.Kappa": 0.6060401952867053, "MeanSkewnessOfNumericAtts": 0.35661826571193717, "Quartile1StdDevOfNumericAtts": 2.587520321291833, "REPTreeDepth2AUC": 0.8961146204362871, "CfsSubsetEval_kNN1NErrRate": 0.149543, "kNN1NAUC": 0.7429918281156388, "MajorityClassPercentage": 75.9864, "MeanStdDevOfNumericAtts": 52795.76096027469, "Quartile2AttributeEntropy": 1.5651476434614648, "REPTreeDepth2ErrRate": 0.140242, "CfsSubsetEval_kNN1NKappa": 0.5632164655827764, "kNN1NErrRate": 0.183928, "MajorityClassSize": 759864, "MinAttributeEntropy": 0.3632452492672792, "Quartile2KurtosisOfNumericAtts": 0.7692658266571228, "REPTreeDepth2Kappa": 0.5986938887574305, "ClassEntropy": 0.7952663694885334, "kNN1NKappa": 0.4909040385005095, "MaxAttributeEntropy": 3.4312305958828895, "MinKurtosisOfNumericAtts": 0.4682551047591774, "Quartile2MeansOfNumericAtts": 94886.29247820887, "REPTreeDepth3AUC": 0.8961146204362871, "DecisionStumpAUC": 0.7575701769687652, "MaxKurtosisOfNumericAtts": 1.0702765485550683, "MinMeansOfNumericAtts": 10.065616405859005, "Quartile2MutualInformation": 0.05138320463881001, "REPTreeDepth3ErrRate": 0.140242, "DecisionStumpErrRate": 0.240136, "MaxMeansOfNumericAtts": 189762.51934001187, "MinMutualInformation": 0.00741380648992, "Quartile2SkewnessOfNumericAtts": 0.3566182657119371, "REPTreeDepth3Kappa": 0.5986938887574305, "DecisionStumpKappa": 0, "MaxMutualInformation": 0.16275151300653, "MinNominalAttDistinctValues": 2, "PercentageOfBinaryFeatures": 13.333333333333334, "Quartile2StdDevOfNumericAtts": 52795.76096027469, "RandomTreeDepth1AUC": 0.7537336069729806, "Dimensionality": 1.5e-5, "MaxNominalAttDistinctValues": 41, "MinSkewnessOfNumericAtts": -0.29160787631568763, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": 2.248226748199359, "RandomTreeDepth1ErrRate": 0.183267, "EquivalentNumberOfAtts": 12.65605195066208, "MaxSkewnessOfNumericAtts": 1.004844407739562, "MinStdDevOfNumericAtts": 2.587520321291833, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.0702765485550683, "AutoCorrelation": 0.6353956353956354, "RandomTreeDepth1Kappa": 0.4962864483081828, "J48.00001.AUC": 0.8962882977183866, "MaxStdDevOfNumericAtts": 105588.93440022808, "MinorityClassPercentage": 24.0136, "PercentageOfNumericFeatures": 13.333333333333334, "Quartile3MeansOfNumericAtts": 189762.51934001187, "CfsSubsetEval_DecisionStumpAUC": 0.8868366786459285, "RandomTreeDepth2AUC": 0.7537336069729806, "J48.00001.ErrRate": 0.136747, "MeanAttributeEntropy": 1.6060299008586303, "MinorityClassSize": 240136, "PercentageOfSymbolicFeatures": 86.66666666666667, "Quartile3MutualInformation": 0.08775495655563, "CfsSubsetEval_DecisionStumpErrRate": 0.149543, "RandomTreeDepth2ErrRate": 0.183267, "J48.00001.Kappa": 0.6060401952867053, "MeanKurtosisOfNumericAtts": 0.7692658266571228, "NaiveBayesAUC": 0.9087253685565796, "Quartile1AttributeEntropy": 0.8112551633552831, "Quartile3SkewnessOfNumericAtts": 1.004844407739562, "CfsSubsetEval_DecisionStumpKappa": 0.5632164655827764, "RandomTreeDepth2Kappa": 0.4962864483081828, "J48.0001.AUC": 0.8962882977183866, "MeanMeansOfNumericAtts": 94886.29247820887, "NaiveBayesErrRate": 0.161335, "Quartile1KurtosisOfNumericAtts": 0.4682551047591774, "Quartile3StdDevOfNumericAtts": 105588.93440022808, "CfsSubsetEval_NaiveBayesAUC": 0.8868366786459285, "RandomTreeDepth3AUC": 0.7537336069729806, "J48.0001.ErrRate": 0.136747, "MeanMutualInformation": 0.06283684458540251, "NaiveBayesKappa": 0.5929226583662526, "Quartile1MeansOfNumericAtts": 10.065616405859005, "REPTreeDepth1AUC": 0.8961146204362871, "CfsSubsetEval_NaiveBayesErrRate": 0.149543, "RandomTreeDepth3ErrRate": 0.183267, "J48.0001.Kappa": 0.6060401952867053, "MeanNoiseToSignalRatio": 24.558729300543582, "NumberOfBinaryFeatures": 2, "Quartile1MutualInformation": 0.01624295172754, "REPTreeDepth1ErrRate": 0.140242, "CfsSubsetEval_NaiveBayesKappa": 0.5632164655827764, "RandomTreeDepth3Kappa": 0.4962864483081828, "J48.001.AUC": 0.8962882977183866, "MeanNominalAttDistinctValues": 9.307692307692308, "Quartile1SkewnessOfNumericAtts": -0.29160787631568763, "REPTreeDepth1Kappa": 0.5986938887574305, "CfsSubsetEval_kNN1NAUC": 0.8868366786459285, "StdvNominalAttDistinctValues": 10.363273416128512, "J48.001.ErrRate": 0.136747 }, "tags": [ { "uploader": "2", "tag": "artificial" }, { "uploader": "1", "tag": "BNG" }, { "uploader": "38960", "tag": "Social Sciences" }, { "uploader": "869", "tag": "study_69" } ], "features": [ { "name": "class", "index": "14", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ ">50K", "<=50K" ], [ [ "240136", "0" ], [ "0", "759864" ] ] ] }, { "name": "age", "index": "0", "type": "nominal", "distinct": "5", "missing": "0", "distr": [ [ "0", "1", "2", "3", "4" ], [ [ "3472", "193032" ], [ "48634", "212210" ], [ "84964", "159756" ], [ "66989", "102894" ], [ "36077", "91972" ] ] ] }, { "name": "workclass", "index": "1", "type": "nominal", "distinct": "8", "missing": "0", "distr": [ [ "Private", "Self-emp-not-inc", "Self-emp-inc", "Federal-gov", "Local-gov", "State-gov", "Without-pay", "Never-worked" ], [ [ "157398", "593856" ], [ "21968", "56733" ], [ "19234", "15399" ], [ "11517", "17881" ], [ "19015", "45609" ], [ "10865", "29760" ], [ "86", "402" ], [ "53", "224" ] ] ] }, { "name": "fnlwgt", "index": "2", "type": "numeric", "distinct": "999999", "missing": "0", "min": "-56527", "max": "767553", "mean": "189763", "stdev": "105589" }, { "name": "education", "index": "3", "type": "nominal", "distinct": "16", "missing": "0", "distr": [ [ "Bachelors", "Some-college", "11th", "HS-grad", "Prof-school", "Assoc-acdm", "Assoc-voc", "9th", "7th-8th", "12th", "Masters", "1st-4th", "10th", "Doctorate", "5th-6th", "Preschool" ], [ [ "67230", "95406" ], [ "41795", "179769" ], [ "2123", "35376" ], [ "50803", "270110" ], [ "12726", "4600" ], [ "8728", "24298" ], [ "10933", "31517" ], [ "1122", "14923" ], [ "1453", "18368" ], [ "1196", "12714" ], [ "29481", "24875" ], [ "446", "5125" ], [ "2029", "27009" ], [ "8976", "3586" ], [ "787", "10260" ], [ "308", "1928" ] ] ] }, { "name": "education-num", "index": "4", "type": "numeric", "distinct": "442785", "missing": "0", "min": "-2", "max": "17", "mean": "10", "stdev": "3" }, { "name": "marital-status", "index": "5", "type": "nominal", "distinct": "7", "missing": "0", "distr": [ [ "Married-civ-spouse", "Divorced", "Never-married", "Separated", "Widowed", "Married-spouse-absent", "Married-AF-spouse" ], [ [ "203596", "252261" ], [ "14015", "121887" ], [ "15272", "315212" ], [ "2350", "29307" ], [ "2918", "28615" ], [ "1425", "11843" ], [ "560", "739" ] ] ] }, { "name": "occupation", "index": "6", "type": "nominal", "distinct": "14", "missing": "0", "distr": [ [ "Tech-support", "Craft-repair", "Other-service", "Sales", "Exec-managerial", "Prof-specialty", "Handlers-cleaners", "Machine-op-inspct", "Adm-clerical", "Farming-fishing", "Transport-moving", "Priv-house-serv", "Protective-serv", "Armed-Forces" ], [ [ "9658", "22024" ], [ "28426", "95445" ], [ "5456", "95692" ], [ "29312", "81060" ], [ "55024", "63139" ], [ "56422", "114832" ], [ "4275", "41034" ], [ "8810", "55645" ], [ "16254", "97544" ], [ "4713", "28140" ], [ "11050", "39592" ], [ "1750", "7147" ], [ "7276", "15806" ], [ "1710", "2764" ] ] ] }, { "name": "relationship", "index": "7", "type": "nominal", "distinct": "6", "missing": "0", "distr": [ [ "Wife", "Own-child", "Husband", "Not-in-family", "Other-relative", "Unmarried" ], [ [ "22547", "25414" ], [ "2509", "152897" ], [ "180528", "221470" ], [ "26595", "231347" ], [ "1380", "29754" ], [ "6577", "98982" ] ] ] }, { "name": "race", "index": "8", "type": "nominal", "distinct": "5", "missing": "0", "distr": [ [ "White", "Asian-Pac-Islander", "Amer-Indian-Eskimo", "Other", "Black" ], [ [ "217009", "637258" ], [ "8568", "22821" ], [ "1421", "8775" ], [ "1352", "7806" ], [ "11786", "83204" ] ] ] }, { "name": "sex", "index": "9", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "Female", "Male" ], [ [ "37051", "277108" ], [ "203085", "482756" ] ] ] }, { "name": "capitalgain", "index": "10", "type": "nominal", "distinct": "5", "missing": "0", "distr": [ [ "0", "1", "2", "3", "4" ], [ [ "188499", "728052" ], [ "2968", "19487" ], [ "14503", "11768" ], [ "11066", "134" ], [ "23100", "423" ] ] ] }, { "name": "capitalloss", "index": "11", "type": "nominal", "distinct": "5", "missing": "0", "distr": [ [ "0", "1", "2", "3", "4" ], [ [ "216475", "736414" ], [ "1883", "6036" ], [ "6299", "9674" ], [ "11335", "5088" ], [ "4144", "2652" ] ] ] }, { "name": "hoursperweek", "index": "12", "type": "nominal", "distinct": "5", "missing": "0", "distr": [ [ "0", "1", "2", "3", "4" ], [ [ "7416", "79923" ], [ "12701", "106380" ], [ "129149", "442062" ], [ "77078", "107717" ], [ "13792", "23782" ] ] ] }, { "name": "native-country", "index": "13", "type": "nominal", "distinct": "41", "missing": "0", "distr": [ [ "United-States", "Cambodia", "England", "Puerto-Rico", "Canada", "Germany", "Outlying-US(Guam-USVI-etc)", "India", "Japan", "Greece", "South", "China", "Cuba", "Iran", "Honduras", "Philippines", "Italy", "Poland", "Jamaica", "Vietnam", "Mexico", "Portugal", "Ireland", "France", "Dominican-Republic", "Laos", "Ecuador", "Taiwan", "Haiti", "Columbia", "Hungary", "Guatemala", "Nicaragua", "Scotland", "Thailand", "Yugoslavia", "El-Salvador", "Trinadad&Tobago", "Peru", "Hong", "Holand-Netherlands" ], [ [ "222500", "689483" ], [ "200", "441" ], [ "981", "1678" ], [ "425", "3402" ], [ "1386", "2466" ], [ "1250", "3009" ], [ "62", "518" ], [ "1308", "1872" ], [ "666", "1273" ], [ "392", "667" ], [ "443", "1961" ], [ "779", "1802" ], [ "763", "2149" ], [ "490", "787" ], [ "76", "422" ], [ "1739", "4320" ], [ "727", "1411" ], [ "396", "1493" ], [ "334", "1857" ], [ "203", "1652" ], [ "1015", "18351" ], [ "305", "1159" ], [ "300", "617" ], [ "383", "471" ], [ "139", "2014" ], [ "89", "467" ], [ "205", "842" ], [ "572", "786" ], [ "218", "1377" ], [ "131", "1690" ], [ "164", "298" ], [ "125", "1788" ], [ "110", "1035" ], [ "104", "414" ], [ "156", "563" ], [ "222", "323" ], [ "285", "2965" ], [ "78", "596" ], [ "150", "910" ], [ "223", "466" ], [ "42", "69" ] ] ] } ], "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 }