{ "data_id": "825", "name": "boston_corrected", "exact_name": "boston_corrected", "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 14:34:34", "update_comment": null, "last_update": "2014-10-04 14:34:34", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/53359\/boston_corrected.arff", "default_target_attribute": "binaryClass", "row_id_attribute": null, "ignore_attribute": null, "runs": 720, "suggest": { "input": [ "boston_corrected", "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": 506, "NumberOfFeatures": 21, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 17, "NumberOfSymbolicFeatures": 4, "REPTreeDepth3Kappa": 0.6252090667261344, "DecisionStumpKappa": 0.6281099000766235, "MaxMeansOfNumericAtts": 2700.355731225293, "MinMutualInformation": 3.211189738e-5, "Quartile2SkewnessOfNumericAtts": 0.29502156787351513, "RandomTreeDepth1AUC": 0.8273621828899206, "Dimensionality": 0.041501976284584984, "MaxMutualInformation": 0.56340275818222, "MinNominalAttDistinctValues": 2, "PercentageOfBinaryFeatures": 9.523809523809524, "Quartile2StdDevOfNumericAtts": 9.182175882166778, "RandomTreeDepth1ErrRate": 0.16600790513833993, "EquivalentNumberOfAtts": 3.8232125032942395, "MaxNominalAttDistinctValues": 92, "MinSkewnessOfNumericAtts": -2.8903737121414426, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": 5.995417701866396, "RandomTreeDepth1Kappa": 0.6635691557567793, "J48.00001.AUC": 0.820611957090114, "MaxSkewnessOfNumericAtts": 5.223148798243853, "MinStdDevOfNumericAtts": 0.06177718406009508, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.7041419072918353, "AutoCorrelation": 0.805940594059406, "RandomTreeDepth2AUC": 0.8273621828899206, "J48.00001.ErrRate": 0.16205533596837945, "MaxStdDevOfNumericAtts": 1380.0368297340956, "MinorityClassPercentage": 44.07114624505929, "PercentageOfNumericFeatures": 80.95238095238095, "Quartile3MeansOfNumericAtts": 161.03745059288536, "CfsSubsetEval_DecisionStumpAUC": 0.8165396377695733, "RandomTreeDepth2ErrRate": 0.16600790513833993, "J48.00001.Kappa": 0.6671533315150252, "MeanAttributeEntropy": 3.031610660116317, "MinorityClassSize": 223, "PercentageOfSymbolicFeatures": 19.047619047619047, "Quartile3MutualInformation": 0.56340275818222, "CfsSubsetEval_DecisionStumpErrRate": 0.18972332015810275, "RandomTreeDepth2Kappa": 0.6635691557567793, "J48.0001.AUC": 0.820611957090114, "MeanKurtosisOfNumericAtts": 2.7991179637716206, "NaiveBayesAUC": 0.9123899568454779, "Quartile1AttributeEntropy": 0.3628184439419491, "Quartile3SkewnessOfNumericAtts": 1.0599394937779052, "CfsSubsetEval_DecisionStumpKappa": 0.6166001041847543, "RandomTreeDepth3AUC": 0.8273621828899206, "J48.0001.ErrRate": 0.16205533596837945, "MeanMeansOfNumericAtts": 229.78229380609142, "NaiveBayesErrRate": 0.16600790513833993, "Quartile1KurtosisOfNumericAtts": -1.1692516612418808, "Quartile3StdDevOfNumericAtts": 59.721862895530734, "CfsSubsetEval_NaiveBayesAUC": 0.8165396377695733, "RandomTreeDepth3ErrRate": 0.16600790513833993, "J48.0001.Kappa": 0.6671533315150252, "MeanMutualInformation": 0.2589010087835033, "NaiveBayesKappa": 0.661963765925973, "Quartile1MeansOfNumericAtts": 5.039838537549407, "REPTreeDepth1AUC": 0.8459886862412651, "CfsSubsetEval_NaiveBayesErrRate": 0.18972332015810275, "RandomTreeDepth3Kappa": 0.6635691557567793, "J48.001.AUC": 0.820611957090114, "MeanNoiseToSignalRatio": 10.709535912435909, "NumberOfBinaryFeatures": 2, "Quartile1MutualInformation": 3.211189738e-5, "REPTreeDepth1ErrRate": 0.18379446640316205, "CfsSubsetEval_NaiveBayesKappa": 0.6166001041847543, "CfsSubsetEval_kNN1NAUC": 0.8165396377695733, "StdvNominalAttDistinctValues": 43.957365708149524, "J48.001.ErrRate": 0.16205533596837945, "MeanNominalAttDistinctValues": 26.25, "Quartile1SkewnessOfNumericAtts": -0.32059643599302606, "REPTreeDepth1Kappa": 0.6252090667261344, "CfsSubsetEval_kNN1NErrRate": 0.18972332015810275, "kNN1NAUC": 0.8195978386600962, "J48.001.Kappa": 0.6671533315150252, "MeanSkewnessOfNumericAtts": 0.4586573848381726, "Quartile1StdDevOfNumericAtts": 1.4041636350214672, "REPTreeDepth2AUC": 0.8459886862412651, "CfsSubsetEval_kNN1NKappa": 0.6166001041847543, "kNN1NErrRate": 0.17786561264822134, "MajorityClassPercentage": 55.92885375494071, "MeanStdDevOfNumericAtts": 112.01134830963528, "Quartile2AttributeEntropy": 2.7365958345406054, "REPTreeDepth2ErrRate": 0.18379446640316205, "ClassEntropy": 0.9898335738965816, "kNN1NKappa": 0.6391956773201921, "MajorityClassSize": 283, "MinAttributeEntropy": 0.3628184439419491, "Quartile2KurtosisOfNumericAtts": 0.10400249031113384, "REPTreeDepth2Kappa": 0.6252090667261344, "REPTreeDepth3AUC": 0.8459886862412651, "DecisionStumpAUC": 0.8077136383083237, "MaxAttributeEntropy": 5.995417701866396, "MinKurtosisOfNumericAtts": -1.3182194826025475, "Quartile2MeansOfNumericAtts": 22.52885375494071, "REPTreeDepth3ErrRate": 0.18379446640316205, "DecisionStumpErrRate": 0.1857707509881423, "MaxKurtosisOfNumericAtts": 37.130509129522004, "MinMeansOfNumericAtts": -71.05638873517786, "Quartile2MutualInformation": 0.21326815627091 }, "tags": [ { "uploader": "2", "tag": "binarized_regression_problem" }, { "uploader": "38960", "tag": "Chemistry" }, { "uploader": "38960", "tag": "Life Science" }, { "uploader": "1", "tag": "mythbusting_1" }, { "uploader": "2", "tag": "study_1" }, { "uploader": "939", "tag": "study_15" }, { "uploader": "939", "tag": "study_20" }, { "uploader": "1", "tag": "study_41" }, { "uploader": "64", "tag": "study_7" } ], "features": [ { "name": "binaryClass", "index": "20", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "P", "N" ], [ [ "283", "0" ], [ "0", "223" ] ] ] }, { "name": "OBS.", "index": "0", "type": "numeric", "distinct": "506", "missing": "0", "min": "1", "max": "506", "mean": "254", "stdev": "146" }, { "name": "TOWN", "index": "1", "type": "nominal", "distinct": "92", "missing": "0", "distr": [ [ "Arlington", "Ashland", "Bedford", "Belmont", "Beverly", "Boston_Allston-Brighton", "Boston_Back_Bay", "Boston_Beacon_Hill", "Boston_Charlestown", "Boston_Dorchester", "Boston_Downtown", "Boston_East_Boston", "Boston_Forest_Hills", "Boston_Hyde_Park", "Boston_Mattapan", "Boston_North_End", "Boston_Roxbury", "Boston_Savin_Hill", "Boston_South_Boston", "Boston_West_Roxbury", "Braintree", "Brookline", "Burlington", "Cambridge", "Canton", "Chelsea", "Cohasset", "Concord", "Danvers", "Dedham", "Dover", "Duxbury", "Everett", "Framingham", "Hamilton", "Hanover", "Hingham", "Holbrook", "Hull", "Lexington", "Lincoln", "Lynn", "Lynnfield", "Malden", "Manchester", "Marblehead", "Marshfield", "Medfield", "Medford", "Melrose", "Middleton", "Millis", "Milton", "Nahant", "Natick", "Needham", "Newton", "Norfolk", "North_Reading", "Norwell", "Norwood", "Peabody", "Pembroke", "Quincy", "Randolph", "Reading", "Revere", "Rockland", "Salem", "Sargus", "Scituate", "Sharon", "Sherborn", "Somerville", "Stoneham", "Sudbury", "Swampscott", "Topsfield", "Wakefield", "Walpole", "Waltham", "Watertown", "Wayland", "Wellesley", "Wenham", "Weston", "Westwood", "Weymouth", "Wilmington", "Winchester", "Winthrop", "Woburn" ], [ [ "6", "1" ], [ "2", "0" ], [ "2", "0" ], [ "6", "2" ], [ "4", "2" ], [ "3", "5" ], [ "4", "2" ], [ "3", "0" ], [ "0", "6" ], [ "1", "10" ], [ "2", "6" ], [ "0", "12" ], [ "1", "6" ], [ "2", "2" ], [ "0", "6" ], [ "0", "2" ], [ "1", "18" ], [ "0", "23" ], [ "0", "13" ], [ "4", "0" ], [ "7", "1" ], [ "11", "1" ], [ "4", "0" ], [ "15", "15" ], [ "3", "0" ], [ "0", "5" ], [ "1", "0" ], [ "3", "0" ], [ "3", "1" ], [ "3", "2" ], [ "1", "0" ], [ "1", "0" ], [ "0", "7" ], [ "9", "1" ], [ "1", "0" ], [ "1", "0" ], [ "2", "0" ], [ "2", "0" ], [ "1", "0" ], [ "6", "0" ], [ "1", "0" ], [ "7", "15" ], [ "2", "0" ], [ "4", "5" ], [ "1", "0" ], [ "3", "0" ], [ "2", "0" ], [ "1", "0" ], [ "5", "6" ], [ "4", "0" ], [ "0", "1" ], [ "1", "0" ], [ "4", "0" ], [ "1", "0" ], [ "6", "0" ], [ "5", "0" ], [ "17", "1" ], [ "0", "1" ], [ "2", "0" ], [ "1", "0" ], [ "4", "1" ], [ "5", "4" ], [ "2", "0" ], [ "9", "3" ], [ "3", "0" ], [ "4", "0" ], [ "1", "7" ], [ "1", "1" ], [ "1", "6" ], [ "4", "0" ], [ "2", "0" ], [ "3", "0" ], [ "1", "0" ], [ "3", "12" ], [ "3", "0" ], [ "2", "0" ], [ "2", "0" ], [ "1", "0" ], [ "3", "1" ], [ "3", "0" ], [ "4", "7" ], [ "2", "2" ], [ "2", "0" ], [ "4", "0" ], [ "1", "0" ], [ "2", "0" ], [ "3", "0" ], [ "8", "0" ], [ "2", "1" ], [ "5", "0" ], [ "5", "0" ], [ "6", "0" ] ] ] }, { "name": "TOWN_ID", "index": "2", "type": "numeric", "distinct": "92", "missing": "0", "min": "0", "max": "91", "mean": "48", "stdev": "28" }, { "name": "TRACT", "index": "3", "type": "numeric", "distinct": "506", "missing": "0", "min": "1", "max": "5082", "mean": "2700", "stdev": "1380" }, { "name": "LON", "index": "4", "type": "numeric", "distinct": "375", "missing": "0", "min": "-71", "max": "0", "mean": "-71", "stdev": "0" }, { "name": "LAT", "index": "5", "type": "numeric", "distinct": "376", "missing": "0", "min": "42", "max": "42", "mean": "42", "stdev": "0" }, { "name": "MEDV", "index": "6", "type": "numeric", "distinct": "229", "missing": "0", "min": "5", "max": "50", "mean": "23", "stdev": "9" }, { "name": "CMEDV", "index": "7", "type": "numeric", "distinct": "228", "missing": "0", "min": "5", "max": "50", "mean": "23", "stdev": "9" }, { "name": "CRIM", "index": "8", "type": "numeric", "distinct": "504", "missing": "0", "min": "0", "max": "89", "mean": "4", "stdev": "9" }, { "name": "ZN", "index": "9", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "100", "mean": "11", "stdev": "23" }, { "name": "INDUS", "index": "10", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "28", "mean": "11", "stdev": "7" }, { "name": "CHAS", "index": "11", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "263", "208" ], [ "20", "15" ] ] ] }, { "name": "NOX", "index": "12", "type": "numeric", "distinct": "81", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "RM", "index": "13", "type": "numeric", "distinct": "446", "missing": "0", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "AGE", "index": "14", "type": "numeric", "distinct": "356", "missing": "0", "min": "3", "max": "100", "mean": "69", "stdev": "28" }, { "name": "DIS", "index": "15", "type": "numeric", "distinct": "412", "missing": "0", "min": "1", "max": "12", "mean": "4", "stdev": "2" }, { "name": "RAD", "index": "16", "type": "nominal", "distinct": "9", "missing": "0", "distr": [ [ "1", "2", "3", "4", "5", "6", "7", "8", "24" ], [ [ "19", "1" ], [ "17", "7" ], [ "27", "11" ], [ "65", "45" ], [ "83", "32" ], [ "14", "12" ], [ "16", "1" ], [ "21", "3" ], [ "21", "111" ] ] ] }, { "name": "TAX", "index": "17", "type": "numeric", "distinct": "66", "missing": "0", "min": "187", "max": "711", "mean": "408", "stdev": "169" }, { "name": "PTRATIO", "index": "18", "type": "numeric", "distinct": "46", "missing": "0", "min": "13", "max": "22", "mean": "18", "stdev": "2" }, { "name": "B", "index": "19", "type": "numeric", "distinct": "357", "missing": "0", "min": "0", "max": "397", "mean": "357", "stdev": "91" } ], "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 }