DEVELOPMENT... { "data_id": "344", "name": "mv", "exact_name": "mv", "version": 1, "version_label": null, "description": "**Author**: Luis Torgo \n**Source**: [original](http:\/\/www.dcc.fc.up.pt\/~ltorgo\/Regression\/DataSets.html) - \n**Please cite**: \n\nThis is an artificial data set with dependencies between the attribute values. The cases are generated using the following method:\n\nX1 : uniformly distributed over [-5,5]\nX2 : uniformly distributed over [-15,-10]\nX3 : IF (X1 > 0) THEN X3 = green\n ELSE X3 = red with probability 0.4 and X4=brown with prob. 0.6\nX4 : IF (X3=green) THEN X4=X1+2X2\n ELSE X4=X1\/2 with prob. 0.3, and X4=X2\/2 with prob. 0.7\nX5 : uniformly distributed over [-1,1]\nX6 : X6=X4*[epsilon], where [epsilon] is uniformly distribute over [0,5]\nX7 : X7=yes with prob. 0.3 and X7=no with prob. 0.7\nX8 : IF (X5 < 0.5) THEN X8 = normal ELSE X8 = large\nX9 : uniformly distributed over [100,500]\nX10 : uniformly distributed integer over the interval [1000,1200]\n \nObtain the value of the target variable Y using the rules:\nIF (X2 > 2 ) THEN Y = 35 - 0.5 X4\n ELSE IF (-2 <= X4 <= 2) THEN Y = 10 - 2 X1\n ELSE IF (X7 = yes) THEN Y = 3 -X1\/X4\n ELSE IF (X8 = normal) THEN Y = X6 + X1\n ELSE Y = X1\/2\n\nSource: collection of regression datasets by Luis Torgo (ltorgo@ncc.up.pt) at http:\/\/www.dcc.fc.up.pt\/~ltorgo\/Regression\/DataSets.html", "format": "ARFF", "uploader": "unknown", "uploader_id": 2, "visibility": "public", "creator": "\"Luis Torgo\"", "contributor": null, "date": "2014-08-26 22:41:01", "update_comment": null, "last_update": "2014-08-26 22:41:01", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/52247\/php2DaFKg", "default_target_attribute": "y", "row_id_attribute": null, "ignore_attribute": null, "runs": 3, "suggest": { "input": [ "mv", "This is an artificial data set with dependencies between the attribute values. The cases are generated using the following method: X1 : uniformly distributed over [-5,5] X2 : uniformly distributed over [-15,-10] X3 : IF (X1 > 0) THEN X3 = green ELSE X3 = red with probability 0.4 and X4=brown with prob. 0.6 X4 : IF (X3=green) THEN X4=X1+2X2 ELSE X4=X1\/2 with prob. 0.3, and X4=X2\/2 with prob. 0.7 X5 : uniformly distributed over [-1,1] X6 : X6=X4*[epsilon], where [epsilon] is uniformly distribute o " ], "weight": 5 }, "qualities": { "NumberOfInstances": 40768, "NumberOfFeatures": 11, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 8, "NumberOfSymbolicFeatures": 3, "AutoCorrelation": -10.418089897558247, "CfsSubsetEval_DecisionStumpAUC": null, "CfsSubsetEval_DecisionStumpErrRate": null, "CfsSubsetEval_DecisionStumpKappa": null, "CfsSubsetEval_NaiveBayesAUC": null, "CfsSubsetEval_NaiveBayesErrRate": null, "CfsSubsetEval_NaiveBayesKappa": null, "CfsSubsetEval_kNN1NAUC": null, "CfsSubsetEval_kNN1NErrRate": null, "CfsSubsetEval_kNN1NKappa": null, "ClassEntropy": null, "DecisionStumpAUC": null, "DecisionStumpErrRate": null, "DecisionStumpKappa": null, "Dimensionality": 0.00026981946624803766, "EquivalentNumberOfAtts": null, "J48.00001.AUC": null, "J48.00001.ErrRate": null, "J48.00001.Kappa": null, "J48.0001.AUC": null, "J48.0001.ErrRate": null, "J48.0001.Kappa": null, "J48.001.AUC": null, "J48.001.ErrRate": null, "J48.001.Kappa": null, "MajorityClassPercentage": null, "MajorityClassSize": null, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": -0.4718562827879351, "MaxMeansOfNumericAtts": 1100.2709723312403, "MaxMutualInformation": null, "MaxNominalAttDistinctValues": 3, "MaxSkewnessOfNumericAtts": 0.9737649773929467, "MaxStdDevOfNumericAtts": 115.27303730661535, "MeanAttributeEntropy": null, "MeanKurtosisOfNumericAtts": -1.0007650142713618, "MeanMeansOfNumericAtts": 170.3379828917901, "MeanMutualInformation": null, "MeanNoiseToSignalRatio": null, "MeanNominalAttDistinctValues": 2.3333333333333335, "MeanSkewnessOfNumericAtts": -0.023318235458600955, "MeanStdDevOfNumericAtts": 25.310286503649962, "MinAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.2054637290423134, "MinMeansOfNumericAtts": -12.49774613912873, "MinMutualInformation": null, "MinNominalAttDistinctValues": 2, "MinSkewnessOfNumericAtts": -0.8348427909918515, "MinStdDevOfNumericAtts": 0.5769759982860736, "MinorityClassPercentage": null, "MinorityClassSize": null, "NaiveBayesAUC": null, "NaiveBayesErrRate": null, "NaiveBayesKappa": null, "NumberOfBinaryFeatures": 2, "PercentageOfBinaryFeatures": 18.181818181818183, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "PercentageOfNumericFeatures": 72.72727272727273, "PercentageOfSymbolicFeatures": 27.27272727272727, "Quartile1AttributeEntropy": null, "Quartile1KurtosisOfNumericAtts": -1.2034668370437687, "Quartile1MeansOfNumericAtts": -10.493609424344124, "Quartile1MutualInformation": null, "Quartile1SkewnessOfNumericAtts": -0.24249962337645428, "Quartile1StdDevOfNumericAtts": 1.8060873817739331, "Quartile2AttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": -1.193089413638349, "Quartile2MeansOfNumericAtts": -2.1997195449697164, "Quartile2MutualInformation": null, "Quartile2SkewnessOfNumericAtts": -0.002979197024671408, "Quartile2StdDevOfNumericAtts": 6.7217645505574986, "Quartile3AttributeEntropy": null, "Quartile3KurtosisOfNumericAtts": -0.678237134019248, "Quartile3MeansOfNumericAtts": 224.4201167574889, "Quartile3MutualInformation": null, "Quartile3SkewnessOfNumericAtts": 0.004358178801468839, "Quartile3StdDevOfNumericAtts": 46.23593802971556, "REPTreeDepth1AUC": null, "REPTreeDepth1ErrRate": null, "REPTreeDepth1Kappa": null, "REPTreeDepth2AUC": null, "REPTreeDepth2ErrRate": null, "REPTreeDepth2Kappa": null, "REPTreeDepth3AUC": null, "REPTreeDepth3ErrRate": null, "REPTreeDepth3Kappa": null, "RandomTreeDepth1AUC": null, "RandomTreeDepth1ErrRate": null, "RandomTreeDepth1Kappa": null, "RandomTreeDepth2AUC": null, "RandomTreeDepth2ErrRate": null, "RandomTreeDepth2Kappa": null, "RandomTreeDepth3AUC": null, "RandomTreeDepth3ErrRate": null, "RandomTreeDepth3Kappa": null, "StdvNominalAttDistinctValues": 0.5773502691896258, "kNN1NAUC": null, "kNN1NErrRate": null, "kNN1NKappa": null }, "tags": [ { "tag": "OpenML-Reg19", "uploader": "5243" }, { "tag": "study_130", "uploader": "5824" }, { "tag": "synthetic", "uploader": "5243" } ], "features": [ { "name": "y", "index": "10", "type": "numeric", "distinct": "39029", "missing": "0", "target": "1", "min": "-42", "max": "2", "mean": "-9", "stdev": "10" }, { "name": "x1", "index": "0", "type": "numeric", "distinct": "40105", "missing": "0", "min": "-5", "max": "5", "mean": "0", "stdev": "3" }, { "name": "x2", "index": "1", "type": "numeric", "distinct": "27796", "missing": "0", "min": "-15", "max": "0", "mean": "-12", "stdev": "1" }, { "name": "x3", "index": "2", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "x4", "index": "3", "type": "numeric", "distinct": "39011", "missing": "0", "min": "-7", "max": "2", "mean": "-4", "stdev": "3" }, { "name": "x5", "index": "4", "type": "numeric", "distinct": "40418", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "1" }, { "name": "x6", "index": "5", "type": "numeric", "distinct": "39833", "missing": "0", "min": "-37", "max": "12", "mean": "-11", "stdev": "11" }, { "name": "x7", "index": "6", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] }, { "name": "x8", "index": "7", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] }, { "name": "x9", "index": "8", "type": "numeric", "distinct": "38738", "missing": "0", "min": "100", "max": "500", "mean": "299", "stdev": "115" }, { "name": "x10", "index": "9", "type": "numeric", "distinct": "201", "missing": "0", "min": "1000", "max": "1200", "mean": "1100", "stdev": "58" } ], "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 }