{ "data_id": "475", "name": "analcatdata_germangss", "exact_name": "analcatdata_germangss", "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 23:51:38", "update_comment": null, "last_update": "2014-09-28 23:51:38", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/52587\/analcatdata_germangss.arff", "default_target_attribute": "Political_system", "row_id_attribute": null, "ignore_attribute": null, "runs": 581, "suggest": { "input": [ "analcatdata_germangss", "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": 400, "NumberOfFeatures": 6, "NumberOfClasses": 4, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 1, "NumberOfSymbolicFeatures": 5, "MinMutualInformation": 0, "Quartile2SkewnessOfNumericAtts": 3.2218216628239107, "REPTreeDepth3Kappa": 0.08666666666666667, "DecisionStumpKappa": 0.17, "MaxMeansOfNumericAtts": 15.097499999999993, "MaxMutualInformation": 0, "MinNominalAttDistinctValues": 2, "PercentageOfBinaryFeatures": 33.33333333333333, "Quartile2StdDevOfNumericAtts": 30.025686476264408, "RandomTreeDepth1AUC": 0.5040666666666667, "Dimensionality": 0.015, "MaxNominalAttDistinctValues": 5, "MinSkewnessOfNumericAtts": 3.2218216628239107, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": 2.321928094887362, "RandomTreeDepth1ErrRate": 0.74, "EquivalentNumberOfAtts": null, "MaxSkewnessOfNumericAtts": 3.2218216628239107, "MinStdDevOfNumericAtts": 30.025686476264408, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 11.936416805970012, "AutoCorrelation": 0.9022556390977443, "RandomTreeDepth1Kappa": 0.013333333333333345, "J48.00001.AUC": 0.6440541666666667, "MaxStdDevOfNumericAtts": 30.025686476264408, "MinorityClassPercentage": 25, "PercentageOfNumericFeatures": 16.666666666666664, "Quartile3MeansOfNumericAtts": 15.097499999999993, "CfsSubsetEval_DecisionStumpAUC": 0.6959000000000001, "RandomTreeDepth2AUC": 0.5040666666666667, "J48.00001.ErrRate": 0.6425, "MeanAttributeEntropy": 1.660964047443681, "MinorityClassSize": 100, "PercentageOfSymbolicFeatures": 83.33333333333334, "Quartile3MutualInformation": 0, "CfsSubsetEval_DecisionStumpErrRate": 0.5925, "RandomTreeDepth2ErrRate": 0.74, "J48.00001.Kappa": 0.1433333333333333, "MeanKurtosisOfNumericAtts": 11.936416805970012, "NaiveBayesAUC": 0.6042833333333334, "Quartile1AttributeEntropy": 1, "Quartile3SkewnessOfNumericAtts": 3.2218216628239107, "CfsSubsetEval_DecisionStumpKappa": 0.20999999999999996, "RandomTreeDepth2Kappa": 0.013333333333333345, "J48.0001.AUC": 0.6440541666666667, "MeanMeansOfNumericAtts": 15.097499999999993, "NaiveBayesErrRate": 0.6725, "Quartile1KurtosisOfNumericAtts": 11.936416805970012, "Quartile3StdDevOfNumericAtts": 30.025686476264408, "CfsSubsetEval_NaiveBayesAUC": 0.6959000000000001, "RandomTreeDepth3AUC": 0.5040666666666667, "J48.0001.ErrRate": 0.6425, "MeanMutualInformation": 0, "NaiveBayesKappa": 0.10333333333333335, "Quartile1MeansOfNumericAtts": 15.097499999999993, "REPTreeDepth1AUC": 0.6256958333333332, "CfsSubsetEval_NaiveBayesErrRate": 0.5925, "RandomTreeDepth3ErrRate": 0.74, "J48.0001.Kappa": 0.1433333333333333, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 2, "Quartile1MutualInformation": 0, "REPTreeDepth1ErrRate": 0.685, "CfsSubsetEval_NaiveBayesKappa": 0.20999999999999996, "RandomTreeDepth3Kappa": 0.013333333333333345, "J48.001.AUC": 0.6440541666666667, "MeanNominalAttDistinctValues": 3.6, "Quartile1SkewnessOfNumericAtts": 3.2218216628239107, "REPTreeDepth1Kappa": 0.08666666666666667, "CfsSubsetEval_kNN1NAUC": 0.6959000000000001, "StdvNominalAttDistinctValues": 1.51657508881031, "J48.001.ErrRate": 0.6425, "MeanSkewnessOfNumericAtts": 3.2218216628239107, "Quartile1StdDevOfNumericAtts": 30.025686476264408, "REPTreeDepth2AUC": 0.6256958333333332, "CfsSubsetEval_kNN1NErrRate": 0.5925, "kNN1NAUC": 0.359175, "J48.001.Kappa": 0.1433333333333333, "MeanStdDevOfNumericAtts": 30.025686476264408, "Quartile2AttributeEntropy": 1.660964047443681, "REPTreeDepth2ErrRate": 0.685, "CfsSubsetEval_kNN1NKappa": 0.20999999999999996, "kNN1NErrRate": 0.9325, "MajorityClassPercentage": 25, "MinAttributeEntropy": 1, "Quartile2KurtosisOfNumericAtts": 11.936416805970012, "REPTreeDepth2Kappa": 0.08666666666666667, "ClassEntropy": 2, "kNN1NKappa": -0.24333333333333332, "MajorityClassSize": 100, "MinKurtosisOfNumericAtts": 11.936416805970012, "Quartile2MeansOfNumericAtts": 15.097499999999993, "REPTreeDepth3AUC": 0.6256958333333332, "DecisionStumpAUC": 0.6175, "MaxAttributeEntropy": 2.321928094887362, "MinMeansOfNumericAtts": 15.097499999999993, "Quartile2MutualInformation": 0, "REPTreeDepth3ErrRate": 0.685, "DecisionStumpErrRate": 0.6225, "MaxKurtosisOfNumericAtts": 11.936416805970012 }, "tags": [ { "tag": "study_1", "uploader": "2" }, { "tag": "study_127", "uploader": "4209" }, { "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" }, { "tag": "study_236", "uploader": "0" }, { "tag": "study_442", "uploader": "0" }, { "tag": "study_443", "uploader": "0" }, { "tag": "study_444", "uploader": "0" }, { "tag": "study_445", "uploader": "0" }, { "tag": "study_268", "uploader": "0" } ], "topics": [ { "topic": "Book-based", "uploader": "8111" } ], "features": [ { "name": "Political_system", "index": "0", "type": "nominal", "distinct": "4", "missing": "0", "target": "1", "distr": [ [ "Poorly", "Very_poorly", "Very_well", "Well" ], [ [ "100", "0", "0", "0" ], [ "0", "100", "0", "0" ], [ "0", "0", "100", "0" ], [ "0", "0", "0", "100" ] ] ] }, { "name": "Age", "index": "1", "type": "nominal", "distinct": "5", "missing": "0", "distr": [ [ "19-29", "30-44", "45-59", "60-74", "75+" ], [ [ "20", "20", "20", "20" ], [ "20", "20", "20", "20" ], [ "20", "20", "20", "20" ], [ "20", "20", "20", "20" ], [ "20", "20", "20", "20" ] ] ] }, { "name": "Time_of_survey", "index": "2", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1991", "1992" ], [ [ "50", "50", "50", "50" ], [ "50", "50", "50", "50" ] ] ] }, { "name": "Schooling", "index": "3", "type": "nominal", "distinct": "5", "missing": "0", "distr": [ [ "Basic", "Basic_incomplete", "Intensive", "Medium", "Upper_medium" ], [ [ "20", "20", "20", "20" ], [ "20", "20", "20", "20" ], [ "20", "20", "20", "20" ], [ "20", "20", "20", "20" ], [ "20", "20", "20", "20" ] ] ] }, { "name": "Region", "index": "4", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "East_Germany", "West_Germany" ], [ [ "50", "50", "50", "50" ], [ "50", "50", "50", "50" ] ] ] }, { "name": "Count", "index": "5", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "198", "mean": "15", "stdev": "30" } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 5, "total_downloads": 5, "reach": 5, "reuse": 14, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 14 }