{ "data_id": "844", "name": "breastTumor", "exact_name": "breastTumor", "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 14:35:07", "update_comment": null, "last_update": "2014-10-04 14:35:07", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/53378\/breastTumor.arff", "default_target_attribute": "binaryClass", "row_id_attribute": null, "ignore_attribute": null, "runs": 708, "suggest": { "input": [ "breastTumor", "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": 286, "NumberOfFeatures": 10, "NumberOfClasses": 2, "NumberOfMissingValues": 9, "NumberOfInstancesWithMissingValues": 9, "NumberOfNumericFeatures": 1, "NumberOfSymbolicFeatures": 9, "REPTreeDepth3Kappa": -0.03354908306364618, "DecisionStumpKappa": 0.0678540265872813, "MaxMeansOfNumericAtts": 50.93706293706294, "MinMutualInformation": 7.28260071e-6, "Quartile2SkewnessOfNumericAtts": -0.007125759778074043, "RandomTreeDepth1AUC": 0.48750000000000004, "Dimensionality": 0.03496503496503497, "MaxMutualInformation": 0.09268093049042, "MinNominalAttDistinctValues": 2, "PercentageOfBinaryFeatures": 50, "Quartile2StdDevOfNumericAtts": 9.72370356358709, "RandomTreeDepth1ErrRate": 0.5, "EquivalentNumberOfAtts": 34.365763774329146, "MaxNominalAttDistinctValues": 18, "MinSkewnessOfNumericAtts": -0.007125759778074043, "PercentageOfInstancesWithMissingValues": 3.146853146853147, "Quartile3AttributeEntropy": 1.8804294427008128, "RandomTreeDepth1Kappa": -0.030124426981008555, "J48.00001.AUC": 0.514508032128514, "MaxSkewnessOfNumericAtts": -0.007125759778074043, "MinStdDevOfNumericAtts": 9.72370356358709, "PercentageOfMissingValues": 0.3146853146853147, "Quartile3KurtosisOfNumericAtts": -0.6186325971267403, "AutoCorrelation": 0.519298245614035, "RandomTreeDepth2AUC": 0.48750000000000004, "J48.00001.ErrRate": 0.43006993006993005, "MaxStdDevOfNumericAtts": 9.72370356358709, "MinorityClassPercentage": 41.95804195804196, "PercentageOfNumericFeatures": 10, "Quartile3MeansOfNumericAtts": 50.93706293706294, "CfsSubsetEval_DecisionStumpAUC": 0.5, "RandomTreeDepth2ErrRate": 0.5, "J48.00001.Kappa": 0.010798042854732568, "MeanAttributeEntropy": 1.3288614252947621, "MinorityClassSize": 120, "PercentageOfSymbolicFeatures": 90, "Quartile3MutualInformation": 0.034512938778425, "CfsSubsetEval_DecisionStumpErrRate": 0.4195804195804196, "RandomTreeDepth2Kappa": -0.030124426981008555, "J48.0001.AUC": 0.514508032128514, "MeanKurtosisOfNumericAtts": -0.6186325971267403, "NaiveBayesAUC": 0.6410893574297188, "Quartile1AttributeEntropy": 0.8129355085285219, "Quartile3SkewnessOfNumericAtts": -0.007125759778074043, "CfsSubsetEval_DecisionStumpKappa": 0, "RandomTreeDepth3AUC": 0.48750000000000004, "J48.0001.ErrRate": 0.43006993006993005, "MeanMeansOfNumericAtts": 50.93706293706294, "NaiveBayesErrRate": 0.38461538461538464, "Quartile1KurtosisOfNumericAtts": -0.6186325971267403, "Quartile3StdDevOfNumericAtts": 9.72370356358709, "CfsSubsetEval_NaiveBayesAUC": 0.5, "RandomTreeDepth3ErrRate": 0.5, "J48.0001.Kappa": 0.010798042854732568, "MeanMutualInformation": 0.0285533589999725, "NaiveBayesKappa": 0.22113289760348592, "Quartile1MeansOfNumericAtts": 50.93706293706294, "REPTreeDepth1AUC": 0.48737449799196786, "CfsSubsetEval_NaiveBayesErrRate": 0.4195804195804196, "RandomTreeDepth3Kappa": -0.030124426981008555, "J48.001.AUC": 0.514508032128514, "MeanNoiseToSignalRatio": 45.53958314662881, "NumberOfBinaryFeatures": 5, "Quartile1MutualInformation": 0.0115405362777475, "REPTreeDepth1ErrRate": 0.46853146853146854, "CfsSubsetEval_NaiveBayesKappa": 0, "CfsSubsetEval_kNN1NAUC": 0.5, "StdvNominalAttDistinctValues": 5.220153254455275, "J48.001.ErrRate": 0.43006993006993005, "MeanNominalAttDistinctValues": 4.333333333333334, "Quartile1SkewnessOfNumericAtts": -0.007125759778074043, "REPTreeDepth1Kappa": -0.03354908306364618, "CfsSubsetEval_kNN1NErrRate": 0.4195804195804196, "kNN1NAUC": 0.45135542168674697, "J48.001.Kappa": 0.010798042854732568, "MeanSkewnessOfNumericAtts": -0.007125759778074043, "Quartile1StdDevOfNumericAtts": 9.72370356358709, "REPTreeDepth2AUC": 0.48737449799196786, "CfsSubsetEval_kNN1NKappa": 0, "kNN1NErrRate": 0.534965034965035, "MajorityClassPercentage": 58.04195804195804, "MeanStdDevOfNumericAtts": 9.72370356358709, "Quartile2AttributeEntropy": 1.066879145069899, "REPTreeDepth2ErrRate": 0.46853146853146854, "ClassEntropy": 0.98125799035667, "kNN1NKappa": -0.0699300699300699, "MajorityClassSize": 166, "MinAttributeEntropy": 0.7134566956859694, "Quartile2KurtosisOfNumericAtts": -0.6186325971267403, "REPTreeDepth2Kappa": -0.03354908306364618, "REPTreeDepth3AUC": 0.48737449799196786, "DecisionStumpAUC": 0.5510793172690763, "MaxAttributeEntropy": 2.583085632169829, "MinKurtosisOfNumericAtts": -0.6186325971267403, "Quartile2MeansOfNumericAtts": 50.93706293706294, "REPTreeDepth3ErrRate": 0.46853146853146854, "DecisionStumpErrRate": 0.44405594405594406, "MaxKurtosisOfNumericAtts": -0.6186325971267403, "MinMeansOfNumericAtts": 50.93706293706294, "Quartile2MutualInformation": 0.02099871752818 }, "tags": [ { "uploader": "1", "tag": "binarized" }, { "uploader": "38960", "tag": "Chemistry" }, { "uploader": "38960", "tag": "Life Science" }, { "uploader": "1", "tag": "mythbusting_1" }, { "uploader": "2", "tag": "study_1" }, { "uploader": "3886", "tag": "study_123" }, { "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" ], [ [ "120", "0" ], [ "0", "166" ] ] ] }, { "name": "age", "index": "0", "type": "numeric", "distinct": "44", "missing": "0", "min": "29", "max": "74", "mean": "51", "stdev": "10" }, { "name": "menopause", "index": "1", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "premenopausal", ">=40", "<40" ], [ [ "58", "93" ], [ "57", "71" ], [ "5", "2" ] ] ] }, { "name": "inv-nodes", "index": "2", "type": "nominal", "distinct": "18", "missing": "0", "distr": [ [ "0", "2", "3", "1", "7", "10", "16", "5", "8", "6", "4", "25", "9", "17", "15", "13", "14", "11" ], [ [ "78", "69" ], [ "8", "20" ], [ "6", "12" ], [ "14", "24" ], [ "0", "6" ], [ "0", "5" ], [ "0", "2" ], [ "3", "9" ], [ "2", "3" ], [ "1", "5" ], [ "4", "2" ], [ "1", "0" ], [ "0", "2" ], [ "1", "1" ], [ "0", "2" ], [ "1", "1" ], [ "0", "1" ], [ "1", "2" ] ] ] }, { "name": "node-caps", "index": "3", "type": "nominal", "distinct": "2", "missing": "8", "distr": [ [ "no", "yes" ], [ [ "103", "119" ], [ "14", "42" ] ] ] }, { "name": "deg-malig", "index": "4", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "3", "2" ], [ [ "38", "33" ], [ "22", "63" ], [ "60", "70" ] ] ] }, { "name": "breast", "index": "5", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "right", "left" ], [ [ "56", "78" ], [ "64", "88" ] ] ] }, { "name": "breast-quad", "index": "6", "type": "nominal", "distinct": "5", "missing": "1", "distr": [ [ "left-lower", "right-lower", "left-upper", "right-upper", "central" ], [ [ "48", "62" ], [ "11", "13" ], [ "40", "57" ], [ "7", "26" ], [ "14", "7" ] ] ] }, { "name": "irradiation", "index": "7", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "no", "yes" ], [ [ "101", "117" ], [ "19", "49" ] ] ] }, { "name": "recurrence", "index": "8", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "n", "r" ], [ [ "95", "106" ], [ "25", "60" ] ] ] } ], "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 }