{ "data_id": "822", "name": "cal_housing", "exact_name": "cal_housing", "version": 1, "version_label": null, "description": "**Author**: \r\n**Source**: Unknown - Date unknown \r\n**Please cite**: \r\n\r\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').\r\n\r\nNote: Deactivated because this looks like a duplicate of https:\/\/www.openml.org\/d\/823 (but somehow a different binarization?)", "format": "ARFF", "uploader": "Joaquin Vanschoren", "uploader_id": 2, "visibility": "public", "creator": null, "contributor": null, "date": "2014-10-04 14:34:28", "update_comment": null, "last_update": "2014-10-04 14:34:28", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/53356\/cal_housing.arff", "default_target_attribute": "binaryClass", "row_id_attribute": null, "ignore_attribute": null, "runs": 679, "suggest": { "input": [ "cal_housing", "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'). Note: Deactivated because this looks like a duplicate of https:\/\/www.openml.org\/d\/823 (but somehow a different binarization?) " ], "weight": 5 }, "qualities": { "NumberOfInstances": 20640, "NumberOfFeatures": 9, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 8, "NumberOfSymbolicFeatures": 1, "REPTreeDepth3Kappa": 0.7201213244799253, "DecisionStumpKappa": 0.48417449682168373, "MaxMeansOfNumericAtts": 2635.7630813953506, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": 2.528547206900776, "RandomTreeDepth1AUC": 0.8233719361014341, "Dimensionality": 0.00043604651162790697, "MaxMutualInformation": null, "MinNominalAttDistinctValues": 2, "PercentageOfBinaryFeatures": 11.11111111111111, "Quartile2StdDevOfNumericAtts": 197.45765522186082, "RandomTreeDepth1ErrRate": 0.17059108527131783, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": 2, "MinSkewnessOfNumericAtts": -0.2978012079524013, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1Kappa": 0.646512561805085, "J48.00001.AUC": 0.8924511504802416, "MaxSkewnessOfNumericAtts": 4.935858226727127, "MinStdDevOfNumericAtts": 1.899821717945271, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 29.987692264321552, "AutoCorrelation": 0.8698095837976646, "RandomTreeDepth2AUC": 0.8233719361014341, "J48.00001.ErrRate": 0.13541666666666666, "MaxStdDevOfNumericAtts": 2181.6152515827876, "MinorityClassPercentage": 40.625, "PercentageOfNumericFeatures": 88.88888888888889, "Quartile3MeansOfNumericAtts": 1203.5820615310004, "CfsSubsetEval_DecisionStumpAUC": 0.8663382645711643, "RandomTreeDepth2ErrRate": 0.17059108527131783, "J48.00001.Kappa": 0.7172590822300622, "MeanAttributeEntropy": null, "MinorityClassSize": 8385, "PercentageOfSymbolicFeatures": 11.11111111111111, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": 0.18415697674418605, "RandomTreeDepth2Kappa": 0.646512561805085, "J48.0001.AUC": 0.8924511504802416, "MeanKurtosisOfNumericAtts": 18.983688746334753, "NaiveBayesAUC": 0.8380903391323853, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 3.9737757760709904, "CfsSubsetEval_DecisionStumpKappa": 0.6126418771735391, "RandomTreeDepth3AUC": 0.8233719361014341, "J48.0001.ErrRate": 0.13541666666666666, "MeanMeansOfNumericAtts": 630.9062292241998, "NaiveBayesErrRate": 0.24481589147286822, "Quartile1KurtosisOfNumericAtts": -1.0384770495201974, "Quartile3StdDevOfNumericAtts": 954.6585678097883, "CfsSubsetEval_NaiveBayesAUC": 0.8663382645711643, "RandomTreeDepth3ErrRate": 0.17059108527131783, "J48.0001.Kappa": 0.7172590822300622, "MeanMutualInformation": null, "NaiveBayesKappa": 0.4654182866513264, "Quartile1MeansOfNumericAtts": 10.062874860707332, "REPTreeDepth1AUC": 0.9198566926670312, "CfsSubsetEval_NaiveBayesErrRate": 0.18415697674418605, "RandomTreeDepth3Kappa": 0.646512561805085, "J48.001.AUC": 0.8924511504802416, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 1, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": 0.13439922480620156, "CfsSubsetEval_NaiveBayesKappa": 0.6126418771735391, "CfsSubsetEval_kNN1NAUC": 0.8663382645711643, "StdvNominalAttDistinctValues": 0, "J48.001.ErrRate": 0.13541666666666666, "MeanNominalAttDistinctValues": 2, "Quartile1SkewnessOfNumericAtts": 0.16173622912686558, "REPTreeDepth1Kappa": 0.7201213244799253, "CfsSubsetEval_kNN1NErrRate": 0.18415697674418605, "kNN1NAUC": 0.811442739227317, "J48.001.Kappa": 0.7172590822300622, "MeanSkewnessOfNumericAtts": 2.227731409613117, "Quartile1StdDevOfNumericAtts": 2.0366368919912334, "REPTreeDepth2AUC": 0.9198566926670312, "CfsSubsetEval_kNN1NKappa": 0.6126418771735391, "kNN1NErrRate": 0.1806201550387597, "MajorityClassPercentage": 59.375, "MeanStdDevOfNumericAtts": 517.0349869467358, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": 0.13439922480620156, "ClassEntropy": 0.9744894033980523, "kNN1NKappa": 0.6245790927915509, "MajorityClassSize": 12255, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 13.43800975947856, "REPTreeDepth2Kappa": 0.7201213244799253, "REPTreeDepth3AUC": 0.9198566926670312, "DecisionStumpAUC": 0.7290632983701784, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.3301523662288983, "Quartile2MeansOfNumericAtts": 267.58577083333427, "REPTreeDepth3ErrRate": 0.13439922480620156, "DecisionStumpErrRate": 0.23638565891472868, "MaxKurtosisOfNumericAtts": 73.55311639416632, "MinMeansOfNumericAtts": -119.56970445736434, "Quartile2MutualInformation": null }, "tags": [ { "tag": "binarized_regression_problem", "uploader": "2" }, { "tag": "mythbusting_1", "uploader": "1" }, { "tag": "study_1", "uploader": "2" }, { "tag": "study_15", "uploader": "939" }, { "tag": "study_20", "uploader": "939" }, { "tag": "study_41", "uploader": "1" }, { "tag": "study_7", "uploader": "64" } ], "features": [ { "name": "binaryClass", "index": "8", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "P", "N" ], [ [ "12255", "0" ], [ "0", "8385" ] ] ] }, { "name": "longitude", "index": "0", "type": "numeric", "distinct": "844", "missing": "0", "min": "-124", "max": "0", "mean": "-120", "stdev": "2" }, { "name": "latitude", "index": "1", "type": "numeric", "distinct": "862", "missing": "0", "min": "33", "max": "42", "mean": "36", "stdev": "2" }, { "name": "housingMedianAge", "index": "2", "type": "numeric", "distinct": "52", "missing": "0", "min": "1", "max": "52", "mean": "29", "stdev": "13" }, { "name": "totalRooms", "index": "3", "type": "numeric", "distinct": "5926", "missing": "0", "min": "2", "max": "39320", "mean": "2636", "stdev": "2182" }, { "name": "totalBedrooms", "index": "4", "type": "numeric", "distinct": "1928", "missing": "0", "min": "1", "max": "6445", "mean": "538", "stdev": "421" }, { "name": "population", "index": "5", "type": "numeric", "distinct": "3888", "missing": "0", "min": "3", "max": "35682", "mean": "1425", "stdev": "1132" }, { "name": "households", "index": "6", "type": "numeric", "distinct": "1815", "missing": "0", "min": "1", "max": "6082", "mean": "500", "stdev": "382" }, { "name": "medianIncome", "index": "7", "type": "numeric", "distinct": "12928", "missing": "0", "min": "0", "max": "15", "mean": "4", "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 }