{ "data_id": "41", "name": "analcatdata_authorship", "exact_name": "analcatdata_authorship", "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 23:51:06", "update_comment": null, "last_update": "2014-09-28 23:51:06", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/52570\/analcatdata_authorship.arff", "default_target_attribute": "Author", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "analcatdata_authorship", "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": 841, "NumberOfFeatures": 71, "NumberOfClasses": 4, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "AutoCorrelation": 0.9964285714285714, "CfsSubsetEval_DecisionStumpAUC": 0.9388364704395656, "CfsSubsetEval_DecisionStumpErrRate": 0.08323424494649227, "CfsSubsetEval_DecisionStumpKappa": 0.8785920221739185, "CfsSubsetEval_NaiveBayesAUC": 0.9388364704395656, "CfsSubsetEval_NaiveBayesErrRate": 0.08323424494649227, "CfsSubsetEval_NaiveBayesKappa": 0.8785920221739185, "CfsSubsetEval_kNN1NAUC": 0.9388364704395656, "CfsSubsetEval_kNN1NErrRate": 0.08323424494649227, "CfsSubsetEval_kNN1NKappa": 0.8785920221739185, "ClassEntropy": 1.787416049226166, "DecisionStumpAUC": 0.7487063032184788, "DecisionStumpErrRate": 0.441141498216409, "DecisionStumpKappa": 0.33926771420100804, "Dimensionality": 0.08442330558858502, "EquivalentNumberOfAtts": null, "J48.00001.AUC": 0.9389434559189358, "J48.00001.ErrRate": 0.08323424494649227, "J48.00001.Kappa": 0.8786025372420279, "J48.0001.AUC": 0.9389434559189358, "J48.0001.ErrRate": 0.08323424494649227, "J48.0001.Kappa": 0.8786025372420279, "J48.001.AUC": 0.9389434559189358, "J48.001.ErrRate": 0.08323424494649227, "J48.001.Kappa": 0.8786025372420279, "MajorityClassPercentage": 37.69322235434007, "MajorityClassSize": 317, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 21.231717234335743, "MaxMeansOfNumericAtts": 77.36028537455405, "MaxMutualInformation": null, "MaxNominalAttDistinctValues": 4, "MaxSkewnessOfNumericAtts": 4.087186736805094, "MaxStdDevOfNumericAtts": 31.071726420905673, "MeanAttributeEntropy": null, "MeanKurtosisOfNumericAtts": 2.359129460351526, "MeanMeansOfNumericAtts": 10.125242058773567, "MeanMutualInformation": null, "MeanNoiseToSignalRatio": null, "MeanNominalAttDistinctValues": 4, "MeanSkewnessOfNumericAtts": 1.1147021119329887, "MeanStdDevOfNumericAtts": 5.3565260839463535, "MinAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.7902615862988753, "MinMeansOfNumericAtts": 0.4447086801426868, "MinMutualInformation": null, "MinNominalAttDistinctValues": 4, "MinSkewnessOfNumericAtts": -0.040708920607288354, "MinStdDevOfNumericAtts": 0.8045103166246655, "MinorityClassPercentage": 6.539833531510107, "MinorityClassSize": 55, "NaiveBayesAUC": 0.9956073167321633, "NaiveBayesErrRate": 0.014268727705112961, "NaiveBayesKappa": 0.9792228968124069, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "PercentageOfNumericFeatures": 98.59154929577466, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile1AttributeEntropy": null, "Quartile1KurtosisOfNumericAtts": 0.3616781435065046, "Quartile1MeansOfNumericAtts": 3.127229488703934, "Quartile1MutualInformation": null, "Quartile1SkewnessOfNumericAtts": 0.7038172484296433, "Quartile1StdDevOfNumericAtts": 2.520372968046287, "Quartile2AttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 1.4141229803280546, "Quartile2MeansOfNumericAtts": 5.030915576694409, "Quartile2MutualInformation": null, "Quartile2SkewnessOfNumericAtts": 1.0322539044597914, "Quartile2StdDevOfNumericAtts": 3.902639766596527, "Quartile3AttributeEntropy": null, "Quartile3KurtosisOfNumericAtts": 2.442383650027078, "Quartile3MeansOfNumericAtts": 11.93638525564807, "Quartile3MutualInformation": null, "Quartile3SkewnessOfNumericAtts": 1.339734579743372, "Quartile3StdDevOfNumericAtts": 6.2079341685674265, "REPTreeDepth1AUC": 0.94584560250496, "REPTreeDepth1ErrRate": 0.10582639714625446, "REPTreeDepth1Kappa": 0.8456546618688718, "REPTreeDepth2AUC": 0.94584560250496, "REPTreeDepth2ErrRate": 0.10582639714625446, "REPTreeDepth2Kappa": 0.8456546618688718, "REPTreeDepth3AUC": 0.94584560250496, "REPTreeDepth3ErrRate": 0.10582639714625446, "REPTreeDepth3Kappa": 0.8456546618688718, "RandomTreeDepth1AUC": 0.8864451921145452, "RandomTreeDepth1ErrRate": 0.15576694411414982, "RandomTreeDepth1Kappa": 0.7726098137881784, "RandomTreeDepth2AUC": 0.8864451921145452, "RandomTreeDepth2ErrRate": 0.15576694411414982, "RandomTreeDepth2Kappa": 0.7726098137881784, "RandomTreeDepth3AUC": 0.8864451921145452, "RandomTreeDepth3ErrRate": 0.15576694411414982, "RandomTreeDepth3Kappa": 0.7726098137881784, "StdvNominalAttDistinctValues": 0, "kNN1NAUC": 0.9935472479387648, "kNN1NErrRate": 0.011890606420927468, "kNN1NKappa": 0.9826989975293099 }, "tags": [ { "uploader": "1159", "tag": "and" }, { "uploader": "1159", "tag": "of" }, { "uploader": "1", "tag": "study_14" }, { "uploader": "1159", "tag": "the" } ], "features": [ { "name": "Author", "index": "70", "type": "nominal", "distinct": "4", "missing": "0", "target": "1", "distr": [ [ "Austen", "London", "Milton", "Shakespeare" ], [ [ "317", "0", "0", "0" ], [ "0", "296", "0", "0" ], [ "0", "0", "55", "0" ], [ "0", "0", "0", "173" ] ] ] }, { "name": "then", "index": "52", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "12", "mean": "3", "stdev": "2" }, { "name": "not", "index": "36", "type": "numeric", "distinct": "37", "missing": "0", "min": "1", "max": "38", "mean": "15", "stdev": "8" }, { "name": "their", "index": "51", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "32", "mean": "5", "stdev": "4" }, { "name": "the", "index": "50", "type": "numeric", "distinct": "137", "missing": "0", "min": "27", "max": "183", "mean": "77", "stdev": "31" }, { "name": "that", "index": "49", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "50", "mean": "20", "stdev": "7" }, { "name": "than", "index": "48", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "3", "stdev": "2" }, { "name": "such", "index": "47", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "3", "stdev": "3" }, { "name": "some", "index": "46", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "2" }, { "name": "so", "index": "45", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "29", "mean": "8", "stdev": "4" }, { "name": "should", "index": "44", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "15", "mean": "2", "stdev": "2" }, { "name": "our", "index": "43", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "33", "mean": "3", "stdev": "5" }, { "name": "or", "index": "42", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "32", "mean": "5", "stdev": "4" }, { "name": "only", "index": "41", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "3", "stdev": "2" }, { "name": "one", "index": "40", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "25", "mean": "4", "stdev": "3" }, { "name": "on", "index": "39", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "27", "mean": "9", "stdev": "5" }, { "name": "of", "index": "38", "type": "numeric", "distinct": "76", "missing": "0", "min": "6", "max": "104", "mean": "46", "stdev": "14" }, { "name": "now", "index": "37", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "15", "mean": "4", "stdev": "3" }, { "name": "no", "index": "35", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "25", "mean": "6", "stdev": "3" }, { "name": "what", "index": "61", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "26", "mean": "6", "stdev": "4" }, { "name": "BookID", "index": "69", "type": "numeric", "distinct": "12", "missing": "0", "min": "1", "max": "12", "mean": "5", "stdev": "3" }, { "name": "your", "index": "68", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "34", "mean": "5", "stdev": "6" }, { "name": "would", "index": "67", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "25", "mean": "5", "stdev": "4" }, { "name": "with", "index": "66", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "38", "mean": "15", "stdev": "5" }, { "name": "will", "index": "65", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "61", "mean": "5", "stdev": "5" }, { "name": "who", "index": "64", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "21", "mean": "3", "stdev": "3" }, { "name": "which", "index": "63", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "20", "mean": "5", "stdev": "4" }, { "name": "when", "index": "62", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "15", "mean": "5", "stdev": "3" }, { "name": "there", "index": "53", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "15", "mean": "5", "stdev": "3" }, { "name": "were", "index": "60", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "32", "mean": "6", "stdev": "5" }, { "name": "was", "index": "59", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "66", "mean": "23", "stdev": "15" }, { "name": "upon", "index": "58", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "2" }, { "name": "up", "index": "57", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "3", "stdev": "3" }, { "name": "to", "index": "56", "type": "numeric", "distinct": "63", "missing": "0", "min": "5", "max": "83", "mean": "45", "stdev": "13" }, { "name": "this", "index": "55", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "28", "mean": "7", "stdev": "5" }, { "name": "things", "index": "54", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "1" }, { "name": "be", "index": "9", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "49", "mean": "12", "stdev": "8" }, { "name": "every", "index": "17", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "11", "mean": "2", "stdev": "2" }, { "name": "even", "index": "16", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "down", "index": "15", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "2" }, { "name": "do", "index": "14", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "23", "mean": "5", "stdev": "4" }, { "name": "can", "index": "13", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "2" }, { "name": "by", "index": "12", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "23", "mean": "8", "stdev": "4" }, { "name": "but", "index": "11", "type": "numeric", "distinct": "25", "missing": "0", "min": "2", "max": "29", "mean": "12", "stdev": "4" }, { "name": "been", "index": "10", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "27", "mean": "5", "stdev": "4" }, { "name": "for", "index": "18", "type": "numeric", "distinct": "27", "missing": "0", "min": "3", "max": "29", "mean": "14", "stdev": "5" }, { "name": "at", "index": "8", "type": "numeric", "distinct": "22", "missing": "0", "min": "1", "max": "29", "mean": "9", "stdev": "4" }, { "name": "as", "index": "7", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "34", "mean": "13", "stdev": "5" }, { "name": "are", "index": "6", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "25", "mean": "4", "stdev": "4" }, { "name": "any", "index": "5", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "15", "mean": "3", "stdev": "3" }, { "name": "and", "index": "4", "type": "numeric", "distinct": "83", "missing": "0", "min": "5", "max": "139", "mean": "57", "stdev": "16" }, { "name": "an", "index": "3", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "78", "mean": "7", "stdev": "9" }, { "name": "also", "index": "2", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "all", "index": "1", "type": "numeric", "distinct": "27", "missing": "0", "min": "1", "max": "30", "mean": "9", "stdev": "4" }, { "name": "in", "index": "26", "type": "numeric", "distinct": "45", "missing": "0", "min": "5", "max": "55", "mean": "26", "stdev": "7" }, { "name": "my", "index": "34", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "62", "mean": "11", "stdev": "11" }, { "name": "must", "index": "33", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "21", "mean": "3", "stdev": "3" }, { "name": "more", "index": "32", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "14", "mean": "4", "stdev": "3" }, { "name": "may", "index": "31", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "15", "mean": "2", "stdev": "2" }, { "name": "its", "index": "30", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "13", "mean": "1", "stdev": "2" }, { "name": "it", "index": "29", "type": "numeric", "distinct": "49", "missing": "0", "min": "0", "max": "57", "mean": "20", "stdev": "9" }, { "name": "is", "index": "28", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "46", "mean": "11", "stdev": "8" }, { "name": "into", "index": "27", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "16", "mean": "3", "stdev": "2" }, { "name": "a", "index": "0", "type": "numeric", "distinct": "57", "missing": "0", "min": "0", "max": "63", "mean": "31", "stdev": "10" }, { "name": "if", "index": "25", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "19", "mean": "4", "stdev": "3" }, { "name": "his", "index": "24", "type": "numeric", "distinct": "54", "missing": "0", "min": "1", "max": "56", "mean": "16", "stdev": "10" }, { "name": "her", "index": "23", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "88", "mean": "16", "stdev": "16" }, { "name": "have", "index": "22", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "34", "mean": "9", "stdev": "6" }, { "name": "has", "index": "21", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "15", "mean": "2", "stdev": "2" }, { "name": "had", "index": "20", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "50", "mean": "12", "stdev": "9" }, { "name": "from", "index": "19", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "26", "mean": "7", "stdev": "4" } ], "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 }