{ "data_id": "506", "name": "analcatdata_gsssexsurvey", "exact_name": "analcatdata_gsssexsurvey", "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: numeric\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": "2014-09-29 00:07:15", "update_comment": null, "last_update": "2014-09-29 00:07:15", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/52618\/analcatdata_gsssexsurvey.arff", "kaggle_url": null, "default_target_attribute": "AIDS_know", "row_id_attribute": null, "ignore_attribute": null, "runs": 18, "suggest": { "input": [ "analcatdata_gsssexsurvey", "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": 159, "NumberOfFeatures": 10, "NumberOfClasses": 0, "NumberOfMissingValues": 6, "NumberOfInstancesWithMissingValues": 6, "NumberOfNumericFeatures": 5, "NumberOfSymbolicFeatures": 5, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3448.5649830178054, "Quartile2KurtosisOfNumericAtts": 1.7507886384047597, "REPTreeDepth2Kappa": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2MeansOfNumericAtts": 13.716981132075471, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": 0.5279947743546121, "Quartile2MutualInformation": null, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 8.886923444813059, "MinMeansOfNumericAtts": 0.3396226415094337, "Quartile2SkewnessOfNumericAtts": 1.1388718940504805, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 24555.55555555555, "MinMutualInformation": null, "PercentageOfBinaryFeatures": 50, "Quartile2StdDevOfNumericAtts": 3.7893019161873753, "RandomTreeDepth1AUC": null, "Dimensionality": 0.06289308176100629, "MaxMutualInformation": null, "MinNominalAttDistinctValues": 2, "PercentageOfInstancesWithMissingValues": 3.7735849056603774, "Quartile3AttributeEntropy": null, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": 2, "MinSkewnessOfNumericAtts": 0.10326629350803894, "PercentageOfMissingValues": 0.37735849056603776, "Quartile3KurtosisOfNumericAtts": 8.359770216193624, "AutoCorrelation": 0.47468354430379744, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 2.9101190601750293, "MinStdDevOfNumericAtts": 0.7533065397135874, "PercentageOfNumericFeatures": 50, "Quartile3MeansOfNumericAtts": 12297.815513626832, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 17224.50495388568, "MinorityClassPercentage": null, "PercentageOfSymbolicFeatures": 50, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 2.792693128500609, "CfsSubsetEval_DecisionStumpKappa": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": 3.9091211561999764, "NaiveBayesAUC": null, "Quartile1KurtosisOfNumericAtts": 0.5376383551039363, "Quartile3StdDevOfNumericAtts": 8617.785046552592, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 4922.47966457023, "NaiveBayesErrRate": null, "Quartile1MeansOfNumericAtts": 1.5251572327044023, "REPTreeDepth1AUC": null, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": null, "CfsSubsetEval_NaiveBayesKappa": null, "RandomTreeDepth3Kappa": null, "J48.001.AUC": null, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 5, "Quartile1SkewnessOfNumericAtts": 0.4995955249738286, "REPTreeDepth1Kappa": null, "CfsSubsetEval_kNN1NAUC": null, "StdvNominalAttDistinctValues": 0, "J48.001.ErrRate": null, "MeanNominalAttDistinctValues": 2, "Quartile1StdDevOfNumericAtts": 1.7327600338286375, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": 1.5446898401998712 }, "tags": [], "topics": [ { "topic": "Book-based", "uploader": "8111" } ], "features": [ { "name": "AIDS_know", "index": "9", "type": "numeric", "distinct": "5", "missing": "0", "target": "1", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "Married", "index": "0", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] }, { "name": "Age", "index": "1", "type": "numeric", "distinct": "45", "missing": "0", "min": "22", "max": "77", "mean": "40", "stdev": "11" }, { "name": "Years_of_education", "index": "2", "type": "numeric", "distinct": "14", "missing": "0", "min": "4", "max": "20", "mean": "14", "stdev": "3" }, { "name": "Male", "index": "3", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] }, { "name": "Religious", "index": "4", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] }, { "name": "Sex_partners", "index": "5", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "20", "mean": "3", "stdev": "4" }, { "name": "Income", "index": "6", "type": "numeric", "distinct": "20", "missing": "6", "min": "500", "max": "85000", "mean": "24556", "stdev": "17225" }, { "name": "Drug_use", "index": "7", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] }, { "name": "Same_sex_relations", "index": "8", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] } ], "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 }