{ "data_id": "42", "name": "analcatdata_dmft", "exact_name": "analcatdata_dmft", "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: last\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": null, "contributor": null, "date": "2014-09-28 23:51:25", "update_comment": null, "last_update": "2014-09-28 23:51:25", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/52581\/analcatdata_dmft.arff", "default_target_attribute": "Prevention", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "analcatdata_dmft", "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": 797, "NumberOfFeatures": 5, "NumberOfClasses": 6, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 0, "NumberOfSymbolicFeatures": 5, "AutoCorrelation": 0.9937185929648241, "CfsSubsetEval_DecisionStumpAUC": 0.5338517214607543, "CfsSubsetEval_DecisionStumpErrRate": 0.8055207026348808, "CfsSubsetEval_DecisionStumpKappa": 0.031950840204176635, "CfsSubsetEval_NaiveBayesAUC": 0.5338517214607543, "CfsSubsetEval_NaiveBayesErrRate": 0.8055207026348808, "CfsSubsetEval_NaiveBayesKappa": 0.031950840204176635, "CfsSubsetEval_kNN1NAUC": 0.5338517214607543, "CfsSubsetEval_kNN1NErrRate": 0.8055207026348808, "CfsSubsetEval_kNN1NKappa": 0.031950840204176635, "ClassEntropy": 2.5802592077826514, "DecisionStumpAUC": 0.5419986240585961, "DecisionStumpErrRate": 0.8042659974905897, "DecisionStumpKappa": 0.040278555299651714, "Dimensionality": 0.006273525721455458, "EquivalentNumberOfAtts": 61.62421451844615, "J48.00001.AUC": 0.5294740485611763, "J48.00001.ErrRate": 0.8080301129234629, "J48.00001.Kappa": 0.027365460888482098, "J48.0001.AUC": 0.5294740485611763, "J48.0001.ErrRate": 0.8080301129234629, "J48.0001.Kappa": 0.027365460888482098, "J48.001.AUC": 0.5294740485611763, "J48.001.ErrRate": 0.8080301129234629, "J48.001.Kappa": 0.027365460888482098, "MajorityClassPercentage": 19.44792973651192, "MajorityClassSize": 155, "MaxAttributeEntropy": 3.083002700297088, "MaxKurtosisOfNumericAtts": null, "MaxMeansOfNumericAtts": null, "MaxMutualInformation": 0.06165879105093, "MaxNominalAttDistinctValues": 9, "MaxSkewnessOfNumericAtts": null, "MaxStdDevOfNumericAtts": null, "MeanAttributeEntropy": 2.016975283182629, "MeanKurtosisOfNumericAtts": null, "MeanMeansOfNumericAtts": null, "MeanMutualInformation": 0.0418708656645075, "MeanNoiseToSignalRatio": 47.17132990141042, "MeanNominalAttDistinctValues": 5.4, "MeanSkewnessOfNumericAtts": null, "MeanStdDevOfNumericAtts": null, "MinAttributeEntropy": 0.9995900071849526, "MinKurtosisOfNumericAtts": null, "MinMeansOfNumericAtts": null, "MinMutualInformation": 0.00469017722262, "MinNominalAttDistinctValues": 2, "MinSkewnessOfNumericAtts": null, "MinStdDevOfNumericAtts": null, "MinorityClassPercentage": 15.432873274780427, "MinorityClassSize": 123, "NaiveBayesAUC": 0.562494963292207, "NaiveBayesErrRate": 0.767879548306148, "NaiveBayesKappa": 0.0775986293442865, "NumberOfBinaryFeatures": 1, "PercentageOfBinaryFeatures": 20, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "PercentageOfNumericFeatures": 0, "PercentageOfSymbolicFeatures": 100, "Quartile1AttributeEntropy": 1.108792761984236, "Quartile1KurtosisOfNumericAtts": null, "Quartile1MeansOfNumericAtts": null, "Quartile1MutualInformation": 0.014714939644734998, "Quartile1SkewnessOfNumericAtts": null, "Quartile1StdDevOfNumericAtts": null, "Quartile2AttributeEntropy": 1.9926542126242377, "Quartile2KurtosisOfNumericAtts": null, "Quartile2MeansOfNumericAtts": null, "Quartile2MutualInformation": 0.05056724719224, "Quartile2SkewnessOfNumericAtts": null, "Quartile2StdDevOfNumericAtts": null, "Quartile3AttributeEntropy": 2.9494788749394134, "Quartile3KurtosisOfNumericAtts": null, "Quartile3MeansOfNumericAtts": null, "Quartile3MutualInformation": 0.0603304101565475, "Quartile3SkewnessOfNumericAtts": null, "Quartile3StdDevOfNumericAtts": null, "REPTreeDepth1AUC": 0.5338262069030021, "REPTreeDepth1ErrRate": 0.820577164366374, "REPTreeDepth1Kappa": 0.013378610123678334, "REPTreeDepth2AUC": 0.5338262069030021, "REPTreeDepth2ErrRate": 0.820577164366374, "REPTreeDepth2Kappa": 0.013378610123678334, "REPTreeDepth3AUC": 0.5338262069030021, "REPTreeDepth3ErrRate": 0.820577164366374, "REPTreeDepth3Kappa": 0.013378610123678334, "RandomTreeDepth1AUC": 0.517510171412348, "RandomTreeDepth1ErrRate": 0.8005018820577164, "RandomTreeDepth1Kappa": 0.04096520974866374, "RandomTreeDepth2AUC": 0.517510171412348, "RandomTreeDepth2ErrRate": 0.8005018820577164, "RandomTreeDepth2Kappa": 0.04096520974866374, "RandomTreeDepth3AUC": 0.517510171412348, "RandomTreeDepth3ErrRate": 0.8005018820577164, "RandomTreeDepth3Kappa": 0.04096520974866374, "StdvNominalAttDistinctValues": 2.8809720581775866, "kNN1NAUC": 0.5215002243317042, "kNN1NErrRate": 0.8055207026348808, "kNN1NKappa": 0.034568250643874 }, "tags": [ { "tag": "study_14", "uploader": "1" }, { "tag": "study_1", "uploader": "0" }, { "tag": "study_275", "uploader": "0" }, { "tag": "study_618", "uploader": "0" }, { "tag": "study_480", "uploader": "0" }, { "tag": "study_101", "uploader": "0" }, { "tag": "study_661", "uploader": "0" }, { "tag": "study_102", "uploader": "0" }, { "tag": "study_109", "uploader": "0" }, { "tag": "study_275", "uploader": "0" }, { "tag": "study_249", "uploader": "0" }, { "tag": "study_263", "uploader": "0" }, { "tag": "study_572", "uploader": "0" }, { "tag": "study_579", "uploader": "0" }, { "tag": "study_572", "uploader": "0" } ], "features": [ { "name": "Prevention", "index": "4", "type": "nominal", "distinct": "6", "missing": "0", "target": "1", "distr": [ [ "All_methods", "Diet_enrichment", "Health_education", "Mouthwash", "None", "Oral_hygiene" ], [ [ "127", "0", "0", "0", "0", "0" ], [ "0", "132", "0", "0", "0", "0" ], [ "0", "0", "124", "0", "0", "0" ], [ "0", "0", "0", "155", "0", "0" ], [ "0", "0", "0", "0", "136", "0" ], [ "0", "0", "0", "0", "0", "123" ] ] ] }, { "name": "DMFT.Begin", "index": "0", "type": "nominal", "distinct": "9", "missing": "0", "distr": [ [ "0", "1", "2", "3", "4", "5", "6", "7", "8" ], [ [ "40", "31", "16", "39", "18", "28" ], [ "8", "16", "6", "17", "13", "13" ], [ "18", "9", "19", "11", "16", "23" ], [ "16", "14", "10", "11", "16", "13" ], [ "11", "15", "22", "15", "19", "13" ], [ "8", "14", "14", "22", "20", "5" ], [ "13", "12", "16", "17", "14", "13" ], [ "7", "10", "12", "13", "10", "13" ], [ "6", "11", "9", "10", "10", "2" ] ] ] }, { "name": "DMFT.End", "index": "1", "type": "nominal", "distinct": "7", "missing": "0", "distr": [ [ "0", "1", "2", "3", "4", "5", "6" ], [ [ "53", "30", "28", "57", "26", "37" ], [ "29", "24", "28", "27", "26", "29" ], [ "19", "23", "28", "24", "24", "22" ], [ "10", "26", "21", "20", "26", "13" ], [ "12", "12", "12", "15", "12", "7" ], [ "3", "14", "6", "11", "13", "8" ], [ "1", "3", "1", "1", "9", "7" ] ] ] }, { "name": "Gender", "index": "2", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "Female", "Male" ], [ [ "60", "65", "62", "86", "58", "58" ], [ "67", "67", "62", "69", "78", "65" ] ] ] }, { "name": "Ethnic", "index": "3", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "Black", "Dark", "White" ], [ [ "18", "14", "27", "21", "23", "9" ], [ "55", "64", "28", "61", "63", "31" ], [ "54", "54", "69", "73", "50", "83" ] ] ] } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 11, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 11 }