{ "data_id": "852", "name": "analcatdata_gsssexsurvey", "exact_name": "analcatdata_gsssexsurvey", "version": 2, "version_label": null, "description": "**Author**: \n**Source**: Unknown - Date unknown \n**Please cite**: \n\nBinarized version of the original data set (see version 1). It converts the numeric target feature to a two-class nominal target feature by computing the mean and classifying all instances with a lower target value as positive ('P') and all others as negative ('N').", "format": "ARFF", "uploader": "Joaquin Vanschoren", "uploader_id": 2, "visibility": "public", "creator": null, "contributor": null, "date": "2014-10-04 14:35:21", "update_comment": null, "last_update": "2014-10-04 14:35:21", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/53386\/analcatdata_gsssexsurvey.arff", "kaggle_url": null, "default_target_attribute": "binaryClass", "row_id_attribute": null, "ignore_attribute": null, "runs": 720, "suggest": { "input": [ "analcatdata_gsssexsurvey", "Binarized version of the original data set (see version 1). It converts the numeric target feature to a two-class nominal target feature by computing the mean and classifying all instances with a lower target value as positive ('P') and all others as negative ('N'). " ], "weight": 5 }, "qualities": { "NumberOfInstances": 159, "NumberOfFeatures": 10, "NumberOfClasses": 2, "NumberOfMissingValues": 6, "NumberOfInstancesWithMissingValues": 6, "NumberOfNumericFeatures": 4, "NumberOfSymbolicFeatures": 6, "RandomTreeDepth1Kappa": 0.12680978532201692, "J48.00001.AUC": 0.5508064516129032, "MaxSkewnessOfNumericAtts": 2.9101190601750293, "MinStdDevOfNumericAtts": 2.7122135279436876, "PercentageOfMissingValues": 0.37735849056603776, "Quartile3KurtosisOfNumericAtts": 7.102889743210984, "AutoCorrelation": 0.6772151898734177, "RandomTreeDepth2AUC": 0.5713133640552995, "J48.00001.ErrRate": 0.27044025157232704, "MaxStdDevOfNumericAtts": 17224.50495388568, "MinorityClassPercentage": 22.0125786163522, "PercentageOfNumericFeatures": 40, "Quartile3MeansOfNumericAtts": 18426.685534591194, "CfsSubsetEval_DecisionStumpAUC": 0.5138248847926268, "RandomTreeDepth2ErrRate": 0.34591194968553457, "J48.00001.Kappa": 0.06916269571136825, "MeanAttributeEntropy": 0.5573544652681075, "MinorityClassSize": 35, "PercentageOfSymbolicFeatures": 60, "Quartile3MutualInformation": 0.029759988814275003, "CfsSubsetEval_DecisionStumpErrRate": 0.22641509433962265, "RandomTreeDepth2Kappa": 0.12680978532201692, "J48.0001.AUC": 0.5508064516129032, "MeanKurtosisOfNumericAtts": 2.9282471983564227, "NaiveBayesAUC": 0.46013824884792626, "Quartile1AttributeEntropy": 0.24613269920218278, "Quartile3SkewnessOfNumericAtts": 2.467307268643892, "CfsSubsetEval_DecisionStumpKappa": 0.10084825636192275, "RandomTreeDepth3AUC": 0.5713133640552995, "J48.0001.ErrRate": 0.27044025157232704, "MeanMeansOfNumericAtts": 6153.01467505241, "NaiveBayesErrRate": 0.3333333333333333, "Quartile1KurtosisOfNumericAtts": 0.5328165647292742, "Quartile3StdDevOfNumericAtts": 12921.145000219136, "CfsSubsetEval_NaiveBayesAUC": 0.5138248847926268, "CfsSubsetEval_NaiveBayesErrRate": 0.22641509433962265, "RandomTreeDepth3ErrRate": 0.34591194968553457, "J48.0001.Kappa": 0.06916269571136825, "MeanMutualInformation": 0.014858126354068, "NaiveBayesKappa": -0.06955197360071096, "Quartile1MeansOfNumericAtts": 5.462264150943396, "REPTreeDepth1AUC": 0.4928571428571428, "CfsSubsetEval_NaiveBayesKappa": 0.10084825636192275, "RandomTreeDepth3Kappa": 0.12680978532201692, "J48.001.AUC": 0.5508064516129032, "MeanNoiseToSignalRatio": 36.51175969206303, "NumberOfBinaryFeatures": 6, "Quartile1MutualInformation": 0.003815614595095, "REPTreeDepth1ErrRate": 0.22012578616352202, "CfsSubsetEval_kNN1NAUC": 0.5138248847926268, "StdvNominalAttDistinctValues": 0, "J48.001.ErrRate": 0.27044025157232704, "MeanNominalAttDistinctValues": 2, "Quartile1SkewnessOfNumericAtts": 0.30143090924093374, "REPTreeDepth1Kappa": 0, "CfsSubsetEval_kNN1NErrRate": 0.22641509433962265, "kNN1NAUC": 0.5290322580645161, "J48.001.Kappa": 0.06916269571136825, "MeanSkewnessOfNumericAtts": 1.2620455010432918, "Quartile1StdDevOfNumericAtts": 2.9814856250046096, "REPTreeDepth2AUC": 0.4928571428571428, "REPTreeDepth2ErrRate": 0.22012578616352202, "CfsSubsetEval_kNN1NKappa": 0.10084825636192275, "kNN1NErrRate": 0.33962264150943394, "MajorityClassPercentage": 77.9874213836478, "MeanStdDevOfNumericAtts": 4310.517902137329, "Quartile2AttributeEntropy": 0.3138129641688651, "REPTreeDepth2Kappa": 0, "ClassEntropy": 0.7603971182966425, "kNN1NKappa": 0.030706705802664026, "MajorityClassSize": 124, "MinAttributeEntropy": 0.2318130500245902, "Quartile2KurtosisOfNumericAtts": 1.1490352871290102, "REPTreeDepth3AUC": 0.4928571428571428, "DecisionStumpAUC": 0.5415898617511521, "MaxAttributeEntropy": 0.9986014218031778, "MinKurtosisOfNumericAtts": 0.5279947743546121, "Quartile2MeansOfNumericAtts": 26.89622641509434, "REPTreeDepth3ErrRate": 0.22012578616352202, "DecisionStumpErrRate": 0.3081761006289308, "MaxKurtosisOfNumericAtts": 8.886923444813059, "MinMeansOfNumericAtts": 2.710691823899371, "Quartile2MutualInformation": 0.0071394249516, "REPTreeDepth3Kappa": 0, "DecisionStumpKappa": 0.05391621129326045, "MaxMeansOfNumericAtts": 24555.55555555555, "MinMutualInformation": 0.00050136970728, "Quartile2SkewnessOfNumericAtts": 1.0173983252450494, "RandomTreeDepth1AUC": 0.5713133640552995, "Dimensionality": 0.06289308176100629, "MaxMutualInformation": 0.04012312136616, "MinNominalAttDistinctValues": 2, "PercentageOfBinaryFeatures": 60, "Quartile2StdDevOfNumericAtts": 7.427220567845081, "RandomTreeDepth1ErrRate": 0.34591194968553457, "EquivalentNumberOfAtts": 51.17718749837214, "MaxNominalAttDistinctValues": 2, "MinSkewnessOfNumericAtts": 0.10326629350803894, "PercentageOfInstancesWithMissingValues": 3.7735849056603774, "Quartile3AttributeEntropy": 0.9903469818836537 }, "tags": [ { "uploader": "38960", "tag": "Data Science" }, { "uploader": "38960", "tag": "Health" }, { "uploader": "1", "tag": "mythbusting_1" }, { "uploader": "38960", "tag": "Sociology" }, { "uploader": "2", "tag": "study_1" }, { "uploader": "939", "tag": "study_15" }, { "uploader": "939", "tag": "study_20" }, { "uploader": "1", "tag": "study_41" } ], "features": [ { "name": "binaryClass", "index": "9", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "P", "N" ], [ [ "124", "0" ], [ "0", "35" ] ] ] }, { "name": "Married", "index": "0", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "49", "18" ], [ "75", "17" ] ] ] }, { "name": "Age", "index": "1", "type": "numeric", "distinct": "45", "missing": "0", "min": "22", "max": "77", "mean": "40", "stdev": "11" }, { "name": "Years_of_education", "index": "2", "type": "numeric", "distinct": "14", "missing": "0", "min": "4", "max": "20", "mean": "14", "stdev": "3" }, { "name": "Male", "index": "3", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "56", "20" ], [ "68", "15" ] ] ] }, { "name": "Religious", "index": "4", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "3", "6" ], [ "121", "29" ] ] ] }, { "name": "Sex_partners", "index": "5", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "20", "mean": "3", "stdev": "4" }, { "name": "Income", "index": "6", "type": "numeric", "distinct": "20", "missing": "6", "min": "500", "max": "85000", "mean": "24556", "stdev": "17225" }, { "name": "Drug_use", "index": "7", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "119", "34" ], [ "5", "1" ] ] ] }, { "name": "Same_sex_relations", "index": "8", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "121", "31" ], [ "3", "4" ] ] ] } ], "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 }