{ "data_id": "471", "name": "analcatdata_draft", "exact_name": "analcatdata_draft", "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: nominal\nCLASSINDEX: none specific\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": "2014-09-28 23:51:28", "update_comment": "Actual.date is a row id", "last_update": "2015-04-15 17:36:25", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/52583\/analcatdata_draft.arff", "default_target_attribute": "", "row_id_attribute": "Actual.date", "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "analcatdata_draft", "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": 366, "NumberOfFeatures": 5, "NumberOfClasses": null, "NumberOfMissingValues": 2, "NumberOfInstancesWithMissingValues": 2, "NumberOfNumericFeatures": 2, "NumberOfSymbolicFeatures": 3, "MeanSkewnessOfNumericAtts": 0, "Quartile1StdDevOfNumericAtts": 105.5106629682517, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanStdDevOfNumericAtts": 105.65500067023703, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": -1.1999999999999993, "REPTreeDepth2Kappa": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -1.2000000000000008, "Quartile2MeansOfNumericAtts": 183.25, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinMeansOfNumericAtts": 183, "Quartile2MutualInformation": null, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": -1.199999999999998, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 183.5, "MinNominalAttDistinctValues": 12, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 105.65500067023703, "RandomTreeDepth1AUC": null, "Dimensionality": 0.01366120218579235, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": 0, "PercentageOfInstancesWithMissingValues": 0.546448087431694, "Quartile3AttributeEntropy": null, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": 12, "MinStdDevOfNumericAtts": 105.5106629682517, "PercentageOfMissingValues": 0.1092896174863388, "Quartile3KurtosisOfNumericAtts": -1.199999999999998, "AutoCorrelation": null, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 0, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 40, "Quartile3MeansOfNumericAtts": 183.5, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 105.79933837222235, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 60, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0, "CfsSubsetEval_DecisionStumpKappa": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": -1.1999999999999993, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": -1.2000000000000008, "Quartile3StdDevOfNumericAtts": 105.79933837222235, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 183.25, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 183, "REPTreeDepth1AUC": null, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": null, "CfsSubsetEval_NaiveBayesKappa": null, "RandomTreeDepth3Kappa": null, "J48.001.AUC": null, "MeanNominalAttDistinctValues": 12, "Quartile1SkewnessOfNumericAtts": 0, "REPTreeDepth1Kappa": null, "CfsSubsetEval_kNN1NAUC": null, "StdvNominalAttDistinctValues": 0, "J48.001.ErrRate": null }, "tags": [], "topics": [ { "topic": "Book-based", "uploader": "8111" } ], "features": [ { "name": "Actual.date", "index": "0", "type": "numeric", "distinct": "366", "missing": "0", "identifier": "1", "min": "1", "max": "366", "mean": "184", "stdev": "106" }, { "name": "Lottery.pick.1970", "index": "1", "type": "numeric", "distinct": "366", "missing": "0", "min": "1", "max": "366", "mean": "184", "stdev": "106" }, { "name": "Lottery.pick.1971", "index": "2", "type": "numeric", "distinct": "365", "missing": "1", "min": "1", "max": "365", "mean": "183", "stdev": "106" }, { "name": "Month", "index": "3", "type": "nominal", "distinct": "12", "missing": "0", "distr": [] }, { "name": "Month.ordered.picks.1970", "index": "4", "type": "nominal", "distinct": "12", "missing": "0", "distr": [] }, { "name": "Month.ordered.picks.1971", "index": "5", "type": "nominal", "distinct": "12", "missing": "1", "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 }