{ "data_id": "459", "name": "analcatdata_asbestos", "exact_name": "analcatdata_asbestos", "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: 1\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 23:51:07", "update_comment": null, "last_update": "2014-09-28 23:51:07", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/52571\/analcatdata_asbestos.arff", "default_target_attribute": "Task", "row_id_attribute": null, "ignore_attribute": null, "runs": 694, "suggest": { "input": [ "analcatdata_asbestos", "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": 83, "NumberOfFeatures": 4, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 1, "NumberOfSymbolicFeatures": 3, "MeanSkewnessOfNumericAtts": 0.025082469040279297, "Quartile1StdDevOfNumericAtts": 75.88386234376878, "REPTreeDepth2AUC": 0.6630434782608695, "CfsSubsetEval_kNN1NErrRate": 0.21686746987951808, "kNN1NAUC": 0.7834900117508813, "J48.001.Kappa": 0.5199537304800463, "MeanStdDevOfNumericAtts": 75.88386234376878, "Quartile2AttributeEntropy": 1.129631700604039, "REPTreeDepth2ErrRate": 0.3614457831325301, "CfsSubsetEval_kNN1NKappa": 0.5701956271576524, "kNN1NErrRate": 0.24096385542168675, "MajorityClassPercentage": 55.42168674698795, "MinAttributeEntropy": 0.9763102872004581, "Quartile2KurtosisOfNumericAtts": -1.2403333647323869, "REPTreeDepth2Kappa": 0.23195558297347296, "ClassEntropy": 0.9915017866855544, "kNN1NKappa": 0.5224395857307249, "MajorityClassSize": 46, "MinKurtosisOfNumericAtts": -1.2403333647323869, "Quartile2MeansOfNumericAtts": 147.0722891566265, "REPTreeDepth3AUC": 0.6630434782608695, "DecisionStumpAUC": 0.753231492361927, "MaxAttributeEntropy": 1.28295311400762, "MinMeansOfNumericAtts": 147.0722891566265, "Quartile2MutualInformation": 0.218964544898045, "REPTreeDepth3ErrRate": 0.3614457831325301, "DecisionStumpErrRate": 0.24096385542168675, "MaxKurtosisOfNumericAtts": -1.2403333647323869, "MinMutualInformation": 0.15607925061011, "Quartile2SkewnessOfNumericAtts": 0.025082469040279297, "REPTreeDepth3Kappa": 0.23195558297347296, "DecisionStumpKappa": 0.5297450424929179, "MaxMeansOfNumericAtts": 147.0722891566265, "MinNominalAttDistinctValues": 2, "PercentageOfBinaryFeatures": 50, "Quartile2StdDevOfNumericAtts": 75.88386234376878, "RandomTreeDepth1AUC": 0.7605757931844889, "Dimensionality": 0.04819277108433735, "MaxMutualInformation": 0.28184983918598, "MinSkewnessOfNumericAtts": 0.025082469040279297, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": 1.28295311400762, "RandomTreeDepth1ErrRate": 0.25301204819277107, "EquivalentNumberOfAtts": 4.5281385036432305, "MaxNominalAttDistinctValues": 3, "MinStdDevOfNumericAtts": 75.88386234376878, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -1.2403333647323869, "AutoCorrelation": 0.6585365853658537, "RandomTreeDepth1Kappa": 0.4998565279770445, "J48.00001.AUC": 0.7523501762632199, "MaxSkewnessOfNumericAtts": 0.025082469040279297, "MinorityClassPercentage": 44.57831325301205, "PercentageOfNumericFeatures": 25, "Quartile3MeansOfNumericAtts": 147.0722891566265, "CfsSubsetEval_DecisionStumpAUC": 0.7917156286721504, "RandomTreeDepth2AUC": 0.7605757931844889, "J48.00001.ErrRate": 0.24096385542168675, "MaxStdDevOfNumericAtts": 75.88386234376878, "MinorityClassSize": 37, "PercentageOfSymbolicFeatures": 75, "Quartile3MutualInformation": 0.28184983918598, "CfsSubsetEval_DecisionStumpErrRate": 0.21686746987951808, "RandomTreeDepth2ErrRate": 0.25301204819277107, "J48.00001.Kappa": 0.5199537304800463, "MeanAttributeEntropy": 1.129631700604039, "NaiveBayesAUC": 0.8490011750881314, "Quartile1AttributeEntropy": 0.9763102872004581, "Quartile3SkewnessOfNumericAtts": 0.025082469040279297, "CfsSubsetEval_DecisionStumpKappa": 0.5701956271576524, "RandomTreeDepth2Kappa": 0.4998565279770445, "J48.0001.AUC": 0.7523501762632199, "MeanKurtosisOfNumericAtts": -1.2403333647323869, "NaiveBayesErrRate": 0.21686746987951808, "Quartile1KurtosisOfNumericAtts": -1.2403333647323869, "Quartile3StdDevOfNumericAtts": 75.88386234376878, "CfsSubsetEval_NaiveBayesAUC": 0.7917156286721504, "RandomTreeDepth3AUC": 0.7605757931844889, "J48.0001.ErrRate": 0.24096385542168675, "MeanMeansOfNumericAtts": 147.0722891566265, "MeanMutualInformation": 0.218964544898045, "NaiveBayesKappa": 0.5656976744186045, "Quartile1MeansOfNumericAtts": 147.0722891566265, "REPTreeDepth1AUC": 0.6630434782608695, "CfsSubsetEval_NaiveBayesErrRate": 0.21686746987951808, "RandomTreeDepth3ErrRate": 0.25301204819277107, "J48.0001.Kappa": 0.5199537304800463, "MeanNoiseToSignalRatio": 4.158970833063507, "NumberOfBinaryFeatures": 2, "Quartile1MutualInformation": 0.15607925061011, "REPTreeDepth1ErrRate": 0.3614457831325301, "CfsSubsetEval_NaiveBayesKappa": 0.5701956271576524, "RandomTreeDepth3Kappa": 0.4998565279770445, "J48.001.AUC": 0.7523501762632199, "MeanNominalAttDistinctValues": 2.3333333333333335, "Quartile1SkewnessOfNumericAtts": 0.025082469040279297, "REPTreeDepth1Kappa": 0.23195558297347296, "CfsSubsetEval_kNN1NAUC": 0.7917156286721504, "StdvNominalAttDistinctValues": 0.5773502691896258, "J48.001.ErrRate": 0.24096385542168675 }, "tags": [ { "tag": "mythbusting_1", "uploader": "1" }, { "tag": "study_1", "uploader": "2" }, { "tag": "study_15", "uploader": "939" }, { "tag": "study_20", "uploader": "939" }, { "tag": "study_41", "uploader": "1" } ], "topics": [ { "topic": "Book-based", "uploader": "8111" } ], "features": [ { "name": "Task", "index": "0", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "Insulation", "Tile" ], [ [ "46", "0" ], [ "0", "37" ] ] ] }, { "name": "Ventilation", "index": "1", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "General", "Negative_pressure" ], [ [ "28", "6" ], [ "18", "31" ] ] ] }, { "name": "Duration", "index": "2", "type": "numeric", "distinct": "63", "missing": "0", "min": "30", "max": "300", "mean": "147", "stdev": "76" }, { "name": "Exposure", "index": "3", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "(1)_Low_exposure", "(2)_Action_level", "(3)_Above_legal_limit" ], [ [ "13", "32" ], [ "4", "2" ], [ "29", "3" ] ] ] } ], "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 }