DEVELOPMENT... { "data_id": "532", "name": "analcatdata_uktrainacc", "exact_name": "analcatdata_uktrainacc", "version": 1, "version_label": null, "description": "**Author**: Jeffrey S. Simonoff \n**Source**: [StatLib](http:\/\/lib.stat.cmu.edu\/datasets\/) - 2003 \n**Please cite**: Jeffrey S. Simonoff. Analyzing Categorical Data. Springer-Verlag, New York, 2003 \n\nOne of the data sets used in the book \"Analyzing Categorical Data\" by Jeffrey S. Simonoff, Springer-Verlag, New York, 2003. Further details concerning the book, including information on statistical software, are available at the [web site](http:\/\/people.stern.nyu.edu\/jsimonof\/AnalCatData\/).", "format": "ARFF", "uploader": "unknown", "uploader_id": 2, "visibility": "public", "creator": "Jeffrey S. Simonoff", "contributor": null, "date": "2014-09-29 00:08:09", "update_comment": "Year is a row id", "last_update": "2015-04-15 17:17:03", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/52644\/analcatdata_uktrainacc.arff", "default_target_attribute": "", "row_id_attribute": "Year", "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "analcatdata_uktrainacc", "One of the data sets used in the book \"Analyzing Categorical Data\" by Jeffrey S. Simonoff, Springer-Verlag, New York, 2003. Further details concerning the book, including information on statistical software, are available at the [web site](http:\/\/people.stern.nyu.edu\/jsimonof\/AnalCatData\/). " ], "weight": 5 }, "qualities": { "NumberOfInstances": 31, "NumberOfFeatures": 16, "NumberOfClasses": null, "NumberOfMissingValues": 150, "NumberOfInstancesWithMissingValues": 25, "NumberOfNumericFeatures": 16, "NumberOfSymbolicFeatures": 0, "AutoCorrelation": null, "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": 0.5161290322580645, "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": 17.36159607513002, "MaxMeansOfNumericAtts": 66.25806451612904, "MaxMutualInformation": null, "MaxNominalAttDistinctValues": null, "MaxSkewnessOfNumericAtts": 4.029317828860573, "MaxStdDevOfNumericAtts": 24.50078603084057, "MeanAttributeEntropy": null, "MeanKurtosisOfNumericAtts": 3.7925106161496474, "MeanMeansOfNumericAtts": 8.245665994623657, "MeanMutualInformation": null, "MeanNoiseToSignalRatio": null, "MeanNominalAttDistinctValues": null, "MeanSkewnessOfNumericAtts": 1.4578737776394575, "MeanStdDevOfNumericAtts": 5.234490613225842, "MinAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.1284289391619282, "MinMeansOfNumericAtts": 0.25806451612903236, "MinMutualInformation": null, "MinNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.0381948517135466, "MinStdDevOfNumericAtts": 0.01884241383527559, "MinorityClassPercentage": null, "MinorityClassSize": null, "NaiveBayesAUC": null, "NaiveBayesErrRate": null, "NaiveBayesKappa": null, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 80.64516129032258, "PercentageOfMissingValues": 30.241935483870968, "PercentageOfNumericFeatures": 100, "PercentageOfSymbolicFeatures": 0, "Quartile1AttributeEntropy": null, "Quartile1KurtosisOfNumericAtts": 0.9649032301176805, "Quartile1MeansOfNumericAtts": 0.9596774193548387, "Quartile1MutualInformation": null, "Quartile1SkewnessOfNumericAtts": 0.8950134925304402, "Quartile1StdDevOfNumericAtts": 0.8815308213335817, "Quartile2AttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 2.413328744762424, "Quartile2MeansOfNumericAtts": 2.3146774193548385, "Quartile2MutualInformation": null, "Quartile2SkewnessOfNumericAtts": 1.4364872882397297, "Quartile2StdDevOfNumericAtts": 1.9225660971951621, "Quartile3AttributeEntropy": null, "Quartile3KurtosisOfNumericAtts": 4.429375804711229, "Quartile3MeansOfNumericAtts": 8.47983870967742, "Quartile3MutualInformation": null, "Quartile3SkewnessOfNumericAtts": 1.8951165776220122, "Quartile3StdDevOfNumericAtts": 8.519893084450597, "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": [], "topics": [ { "topic": "Book-based", "uploader": "8111" } ], "features": [ { "name": "Accidents_grouped", "index": "8", "type": "numeric", "distinct": "5", "missing": "25", "min": "7", "max": "23", "mean": "13", "stdev": "6" }, { "name": "Non_prev._fatalities", "index": "16", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "71", "mean": "6", "stdev": "14" }, { "name": "Other_fatalities", "index": "15", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "2" }, { "name": "SPAD_fatalities", "index": "14", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "3" }, { "name": "Fatalities", "index": "13", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "73", "mean": "9", "stdev": "14" }, { "name": "Train_km_grouped", "index": "12", "type": "numeric", "distinct": "6", "missing": "25", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Non_grouped", "index": "11", "type": "numeric", "distinct": "6", "missing": "25", "min": "4", "max": "15", "mean": "8", "stdev": "4" }, { "name": "Other_grouped", "index": "10", "type": "numeric", "distinct": "4", "missing": "25", "min": "0", "max": "4", "mean": "1", "stdev": "2" }, { "name": "SPAD_grouped", "index": "9", "type": "numeric", "distinct": "3", "missing": "25", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "Year", "index": "0", "type": "numeric", "distinct": "31", "missing": "0", "identifier": "1", "min": "1", "max": "31", "mean": "16", "stdev": "9" }, { "name": "Year_grouped", "index": "7", "type": "numeric", "distinct": "6", "missing": "25", "min": "3", "max": "29", "mean": "16", "stdev": "9" }, { "name": "Non_preventable", "index": "6", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Other_preventable", "index": "5", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SPAD_preventable", "index": "4", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "Accidents", "index": "3", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "Pct_Mark_I", "index": "2", "type": "numeric", "distinct": "31", "missing": "0", "min": "20", "max": "97", "mean": "66", "stdev": "25" }, { "name": "Train_km", "index": "1", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" } ], "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 }