DEVELOPMENT... { "data_id": "530", "name": "analcatdata_olympic2000", "exact_name": "analcatdata_olympic2000", "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: none specific\n\n\nNote: Quotes, Single-Quotes and Backslashes were removed, Blanks replaced\nwith Underscores", "format": "ARFF", "uploader": "unknown", "uploader_id": 2, "visibility": "public", "creator": "Jeffrey S. Simonoff", "contributor": null, "date": "2014-09-29 00:08:05", "update_comment": "set target feature", "last_update": "2014-10-07 01:26:08", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/52642\/analcatdata_olympic2000.arff", "default_target_attribute": "GDP", "row_id_attribute": null, "ignore_attribute": "\"Country\"", "runs": 2, "suggest": { "input": [ "analcatdata_olympic2000", "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": 66, "NumberOfFeatures": 12, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 12, "NumberOfSymbolicFeatures": 0, "AutoCorrelation": -518039.90769230766, "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": 0.18181818181818182, "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": 27.925030816313093, "MaxMeansOfNumericAtts": 430533.7575757574, "MaxMutualInformation": null, "MaxNominalAttDistinctValues": null, "MaxSkewnessOfNumericAtts": 5.184800754997159, "MaxStdDevOfNumericAtts": 1149215.3347947935, "MeanAttributeEntropy": null, "MeanKurtosisOfNumericAtts": 8.086700839142182, "MeanMeansOfNumericAtts": 41668.17455306938, "MeanMutualInformation": null, "MeanNoiseToSignalRatio": null, "MeanNominalAttDistinctValues": null, "MeanSkewnessOfNumericAtts": 2.113269220354325, "MeanStdDevOfNumericAtts": 112060.62882882942, "MinAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.8290891381178347, "MinMeansOfNumericAtts": 1.765936704969697, "MinMutualInformation": null, "MinNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.4507426519576207, "MinStdDevOfNumericAtts": 0.9874860641047748, "MinorityClassPercentage": null, "MinorityClassSize": null, "NaiveBayesAUC": null, "NaiveBayesErrRate": null, "NaiveBayesKappa": null, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "PercentageOfNumericFeatures": 100, "PercentageOfSymbolicFeatures": 0, "Quartile1AttributeEntropy": null, "Quartile1KurtosisOfNumericAtts": 0.5585538989142672, "Quartile1MeansOfNumericAtts": 4.552556336579545, "Quartile1MutualInformation": null, "Quartile1SkewnessOfNumericAtts": 0.295822437400826, "Quartile1StdDevOfNumericAtts": 1.6449828467963674, "Quartile2AttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 6.428088403711136, "Quartile2MeansOfNumericAtts": 10.544085875606061, "Quartile2MutualInformation": null, "Quartile2SkewnessOfNumericAtts": 2.4634963814516704, "Quartile2StdDevOfNumericAtts": 7.024807144136327, "Quartile3AttributeEntropy": null, "Quartile3KurtosisOfNumericAtts": 9.50054135729425, "Quartile3MeansOfNumericAtts": 119.46969696969703, "Quartile3MutualInformation": null, "Quartile3SkewnessOfNumericAtts": 2.8644450844654354, "Quartile3StdDevOfNumericAtts": 114.7712170586021, "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": null, "kNN1NAUC": null, "kNN1NErrRate": null, "kNN1NKappa": null }, "tags": [ { "tag": "study_239", "uploader": "0" } ], "topics": [ { "topic": "Book-based", "uploader": "8111" } ], "features": [ { "name": "GDP", "index": "7", "type": "numeric", "distinct": "66", "missing": "0", "target": "1", "min": "1472", "max": "7567100", "mean": "430534", "stdev": "1149215" }, { "name": "Country", "index": "0", "type": "nominal", "distinct": "66", "missing": "0", "ignore": "1", "distr": [] }, { "name": "Gold2000", "index": "1", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "39", "mean": "5", "stdev": "8" }, { "name": "Silver2000", "index": "2", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "28", "mean": "4", "stdev": "6" }, { "name": "Bronze2000", "index": "3", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "33", "mean": "5", "stdev": "7" }, { "name": "Total2000", "index": "4", "type": "numeric", "distinct": "28", "missing": "0", "min": "1", "max": "97", "mean": "14", "stdev": "19" }, { "name": "Population", "index": "5", "type": "numeric", "distinct": "66", "missing": "0", "min": "296", "max": "1255698", "mean": "69262", "stdev": "195302" }, { "name": "Athletes", "index": "6", "type": "numeric", "distinct": "57", "missing": "0", "min": "5", "max": "664", "mean": "155", "stdev": "147" }, { "name": "Total1996", "index": "8", "type": "numeric", "distinct": "26", "missing": "0", "min": "1", "max": "101", "mean": "13", "stdev": "18" }, { "name": "Log1996", "index": "9", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "Log.population", "index": "10", "type": "numeric", "distinct": "66", "missing": "0", "min": "6", "max": "14", "mean": "10", "stdev": "2" }, { "name": "Log.GDP", "index": "11", "type": "numeric", "distinct": "66", "missing": "0", "min": "7", "max": "16", "mean": "11", "stdev": "2" }, { "name": "Log.athletes", "index": "12", "type": "numeric", "distinct": "57", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "1" } ], "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 }