{ "data_id": "450", "name": "analcatdata_lawsuit", "exact_name": "analcatdata_lawsuit", "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": "Jeffrey S. Simonoff", "contributor": null, "date": "2014-09-28 23:50:49", "update_comment": null, "last_update": "2014-09-28 23:50:49", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/52562\/analcatdata_lawsuit.arff", "default_target_attribute": "Laid.off", "row_id_attribute": null, "ignore_attribute": null, "runs": 886, "suggest": { "input": [ "analcatdata_lawsuit", "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": 264, "NumberOfFeatures": 5, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 3, "NumberOfSymbolicFeatures": 2, "kNN1NErrRate": 0.01893939393939394, "MajorityClassPercentage": 92.8030303030303, "MeanStdDevOfNumericAtts": 8.88040691003727, "Quartile2AttributeEntropy": 0.9486738067246727, "REPTreeDepth2ErrRate": 0.03409090909090909, "CfsSubsetEval_kNN1NKappa": 0.9169463087248323, "kNN1NKappa": 0.8615771812080538, "MajorityClassSize": 245, "MinAttributeEntropy": 0.9486738067246727, "Quartile2KurtosisOfNumericAtts": 0.7298781823859986, "REPTreeDepth2Kappa": 0.7508389261744969, "ClassEntropy": 0.3732315518923251, "MaxAttributeEntropy": 0.9486738067246727, "MinKurtosisOfNumericAtts": -0.6604656999447958, "Quartile2MeansOfNumericAtts": 20.1819696969697, "REPTreeDepth3AUC": 0.9119226638023631, "DecisionStumpAUC": 0.9385606874328678, "DecisionStumpErrRate": 0.041666666666666664, "MaxKurtosisOfNumericAtts": 1.0176392773975, "MinMeansOfNumericAtts": 12.625719696969696, "Quartile2MutualInformation": 0.04177378642701, "REPTreeDepth3ErrRate": 0.03409090909090909, "DecisionStumpKappa": 0.7440056417489425, "MaxMeansOfNumericAtts": 35.564393939393895, "MinMutualInformation": 0.04177378642701, "Quartile2SkewnessOfNumericAtts": -0.18358522839200747, "REPTreeDepth3Kappa": 0.7508389261744969, "Dimensionality": 0.01893939393939394, "MaxMutualInformation": 0.04177378642701, "MinNominalAttDistinctValues": 2, "PercentageOfBinaryFeatures": 40, "Quartile2StdDevOfNumericAtts": 7.537763297271561, "RandomTreeDepth1AUC": 0.9412459720730397, "EquivalentNumberOfAtts": 8.934587544379312, "MaxNominalAttDistinctValues": 2, "MinSkewnessOfNumericAtts": -0.9745412758921901, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": 0.9486738067246727, "RandomTreeDepth1ErrRate": 0.01893939393939394, "RandomTreeDepth1Kappa": 0.8615771812080538, "J48.00001.AUC": 0.9177228786251342, "MaxSkewnessOfNumericAtts": 0.9444697380163873, "MinStdDevOfNumericAtts": 6.043358663710244, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.0176392773975, "AutoCorrelation": 0.9961977186311787, "RandomTreeDepth2AUC": 0.9412459720730397, "J48.00001.ErrRate": 0.015151515151515152, "MaxStdDevOfNumericAtts": 13.060098769130002, "MinorityClassPercentage": 7.196969696969697, "PercentageOfNumericFeatures": 60, "Quartile3MeansOfNumericAtts": 35.564393939393895, "CfsSubsetEval_DecisionStumpAUC": 0.9568206229860365, "RandomTreeDepth2ErrRate": 0.01893939393939394, "J48.00001.Kappa": 0.8865735767991408, "MeanAttributeEntropy": 0.9486738067246727, "MinorityClassSize": 19, "PercentageOfSymbolicFeatures": 40, "Quartile3MutualInformation": 0.04177378642701, "CfsSubsetEval_DecisionStumpErrRate": 0.011363636363636364, "RandomTreeDepth2Kappa": 0.8615771812080538, "J48.0001.AUC": 0.9177228786251342, "MeanKurtosisOfNumericAtts": 0.362350586612901, "NaiveBayesAUC": 0.989044038668099, "Quartile1AttributeEntropy": 0.9486738067246727, "Quartile3SkewnessOfNumericAtts": 0.9444697380163873, "CfsSubsetEval_DecisionStumpKappa": 0.9169463087248323, "RandomTreeDepth3AUC": 0.9412459720730397, "J48.0001.ErrRate": 0.015151515151515152, "MeanMeansOfNumericAtts": 22.79069444444443, "NaiveBayesErrRate": 0.03787878787878788, "Quartile1KurtosisOfNumericAtts": -0.6604656999447958, "Quartile3StdDevOfNumericAtts": 13.060098769130002, "CfsSubsetEval_NaiveBayesAUC": 0.9568206229860365, "RandomTreeDepth3ErrRate": 0.01893939393939394, "J48.0001.Kappa": 0.8865735767991408, "MeanMutualInformation": 0.04177378642701, "NaiveBayesKappa": 0.7295636140135221, "Quartile1MeansOfNumericAtts": 12.625719696969696, "REPTreeDepth1AUC": 0.9119226638023631, "CfsSubsetEval_NaiveBayesErrRate": 0.011363636363636364, "RandomTreeDepth3Kappa": 0.8615771812080538, "J48.001.AUC": 0.9177228786251342, "MeanNoiseToSignalRatio": 21.709787353900996, "NumberOfBinaryFeatures": 2, "Quartile1MutualInformation": 0.04177378642701, "REPTreeDepth1ErrRate": 0.03409090909090909, "CfsSubsetEval_NaiveBayesKappa": 0.9169463087248323, "StdvNominalAttDistinctValues": 0, "J48.001.ErrRate": 0.015151515151515152, "MeanNominalAttDistinctValues": 2, "Quartile1SkewnessOfNumericAtts": -0.9745412758921901, "REPTreeDepth1Kappa": 0.7508389261744969, "CfsSubsetEval_kNN1NAUC": 0.9568206229860365, "kNN1NAUC": 0.9412459720730397, "J48.001.Kappa": 0.8865735767991408, "MeanSkewnessOfNumericAtts": -0.07121892208927005, "Quartile1StdDevOfNumericAtts": 6.043358663710244, "REPTreeDepth2AUC": 0.9119226638023631, "CfsSubsetEval_kNN1NErrRate": 0.011363636363636364 }, "tags": [ { "tag": "mythbusting_1", "uploader": "1" }, { "tag": "study_1", "uploader": "2" }, { "tag": "study_127", "uploader": "4209" }, { "tag": "study_15", "uploader": "939" }, { "tag": "study_20", "uploader": "939" }, { "tag": "study_41", "uploader": "1" }, { "tag": "study_50", "uploader": "64" }, { "tag": "study_52", "uploader": "64" }, { "tag": "study_7", "uploader": "64" }, { "tag": "study_88", "uploader": "4209" } ], "topics": [ { "topic": "Book-based", "uploader": "8111" } ], "features": [ { "name": "Laid.off", "index": "4", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "245", "0" ], [ "0", "19" ] ] ] }, { "name": "Length.of.service", "index": "0", "type": "numeric", "distinct": "206", "missing": "0", "min": "1", "max": "43", "mean": "13", "stdev": "8" }, { "name": "CAP", "index": "1", "type": "numeric", "distinct": "53", "missing": "0", "min": "6", "max": "60", "mean": "36", "stdev": "13" }, { "name": "PA.normalized", "index": "2", "type": "numeric", "distinct": "29", "missing": "0", "min": "1", "max": "30", "mean": "20", "stdev": "6" }, { "name": "Minority", "index": "3", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "163", "4" ], [ "82", "15" ] ] ] } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 8, "total_downloads": 8, "reach": 8, "reuse": 15, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 15 }