{ "data_id": "521", "name": "analcatdata_ncaa", "exact_name": "analcatdata_ncaa", "version": 1, "version_label": null, "description": "**Author**: \n**Source**: Unknown - Date unknown \n**Please cite**: \n\nanalcatdata A collection of data sets used in the book \"Analyzing Categorical Data,\"\nby Jeffrey S. Simonoff, Springer-Verlag, New York, 2003. The submission\nconsists of a zip file containing two versions of each of 84 data sets,\nplus this README file. Each data set is given in comma-delimited ASCII\n(.csv) form, and Microsoft Excel (.xls) form.\n\nNOTICE: These data sets may be used freely for scientific, educational and\/or\nnoncommercial purposes, provided suitable acknowledgment is given (by citing\nthe above-named reference).\n\nFurther details concerning the book, including information on statistical software\n(including sample S-PLUS\/R and SAS code), are available at the web site\n\nhttp:\/\/www.stern.nyu.edu\/~jsimonof\/AnalCatData\n\n\nInformation about the dataset\nCLASSTYPE: numeric\nCLASSINDEX: 3 or 4\n\n\nNote: Quotes, Single-Quotes and Backslashes were removed, Blanks replaced\nwith Underscores", "format": "ARFF", "uploader": "Joaquin Vanschoren", "uploader_id": 2, "visibility": "public", "creator": "Jeffrey S. Simonoff", "contributor": null, "date": "2014-09-29 00:07:48", "update_comment": "set target feature", "last_update": "2014-10-07 01:16:58", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/52633\/analcatdata_ncaa.arff", "default_target_attribute": "Team_1_wins", "row_id_attribute": null, "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "analcatdata_ncaa", "analcatdata A collection of data sets used in the book \"Analyzing Categorical Data,\" by Jeffrey S. Simonoff, Springer-Verlag, New York, 2003. The submission consists of a zip file containing two versions of each of 84 data sets, plus this README file. Each data set is given in comma-delimited ASCII (.csv) form, and Microsoft Excel (.xls) form. NOTICE: These data sets may be used freely for scientific, educational and\/or noncommercial purposes, provided suitable acknowledgment is given (by citing " ], "weight": 5 }, "qualities": { "NumberOfInstances": 120, "NumberOfFeatures": 20, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 4, "NumberOfSymbolicFeatures": 16, "MeanSkewnessOfNumericAtts": 1.650805039432067, "Quartile1StdDevOfNumericAtts": 3.651483716701106, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanStdDevOfNumericAtts": 5.3038776790006255, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 3.5685487875808777, "REPTreeDepth2Kappa": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -0.5898305084745759, "Quartile2MeansOfNumericAtts": 5.037500000000003, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinMeansOfNumericAtts": 1.5916666666666668, "Quartile2MutualInformation": null, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 17.27843234960774, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": 1.7028316686917273, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 11.333333333333336, "MinNominalAttDistinctValues": 2, "PercentageOfBinaryFeatures": 10, "Quartile2StdDevOfNumericAtts": 3.855453757157097, "RandomTreeDepth1AUC": null, "Dimensionality": 0.16666666666666666, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -0.57557285703933, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": 3, "MinStdDevOfNumericAtts": 3.651483716701106, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 14.890556283114885, "AutoCorrelation": -6.168067226890757, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 3.773129677384143, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 20, "Quartile3MeansOfNumericAtts": 9.91666666666667, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 9.853119484987202, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 80, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 3.5373698781241396, "CfsSubsetEval_DecisionStumpKappa": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": 5.95642485407373, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": -0.5898305084745724, "Quartile3StdDevOfNumericAtts": 8.404695563143672, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 5.750000000000002, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 2.295833333333334, "REPTreeDepth1AUC": null, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 2, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": null, "CfsSubsetEval_NaiveBayesKappa": null, "RandomTreeDepth3Kappa": null, "J48.001.AUC": null, "MeanNominalAttDistinctValues": 2.875, "Quartile1SkewnessOfNumericAtts": -0.2877864285196665, "REPTreeDepth1Kappa": null, "CfsSubsetEval_kNN1NAUC": null, "StdvNominalAttDistinctValues": 0.3415650255319866, "J48.001.ErrRate": null }, "tags": [ { "tag": "study_239", "uploader": "0" } ], "topics": [ { "topic": "Book-based", "uploader": "8111" } ], "features": [ { "name": "Team_1_wins", "index": "2", "type": "numeric", "distinct": "22", "missing": "0", "target": "1", "min": "0", "max": "48", "mean": "4", "stdev": "10" }, { "name": "Seed_team_1", "index": "0", "type": "numeric", "distinct": "15", "missing": "0", "min": "1", "max": "15", "mean": "6", "stdev": "4" }, { "name": "Seed_team_2", "index": "1", "type": "numeric", "distinct": "15", "missing": "0", "min": "2", "max": "16", "mean": "11", "stdev": "4" }, { "name": "Team_1_losses", "index": "3", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "28", "mean": "2", "stdev": "4" }, { "name": "X1", "index": "4", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] }, { "name": "X2", "index": "5", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "X3", "index": "6", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "X4", "index": "7", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "X5", "index": "8", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "X6", "index": "9", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "X7", "index": "10", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "X8", "index": "11", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "X9", "index": "12", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "X10", "index": "13", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "X11", "index": "14", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "X12", "index": "15", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "X13", "index": "16", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "X14", "index": "17", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "X15", "index": "18", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "X16", "index": "19", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] } ], "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 }