{ "data_id": "33", "name": "vowel", "exact_name": "vowel", "version": 2, "version_label": "2", "description": "**Author**: Peter Turney (peter@ai.iit.nrc.ca) \n**Source**: [UCI](https:\/\/archive.ics.uci.edu\/ml\/machine-learning-databases\/undocumented\/connectionist-bench\/vowel\/) - date unknown \n**Please cite**: \n\n**Vowel Recognition Data** \nIn my work on context-sensitive learning, I used the \"Deterding Vowel Recognition Data\", but I found it necessary to reformulate the data. Implicit in the original data is contextual information on the speaker's gender and identity. For my work, it was necessary to make this information explicit. This dataset adds the speaker's sex and identity as new features. \n\nNotes: \n* This is version 2. Version 1 is hidden because it includes a feature dividing the data in train and test set. In OpenML this information is explicitly available in the corresponding task.", "format": "ARFF", "uploader": "Joaquin Vanschoren", "uploader_id": 2, "visibility": "public", "creator": "\"Peter Turney\"", "contributor": "\"\"", "date": "2014-08-22 16:57:30", "update_comment": null, "last_update": "2014-08-22 16:57:30", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/52210\/phpd8EoD9", "default_target_attribute": "Class", "row_id_attribute": "", "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "vowel", "In my work on context-sensitive learning, I used the \"Deterding Vowel Recognition Data\", but I found it necessary to reformulate the data. Implicit in the original data is contextual information on the speaker's gender and identity. For my work, it was necessary to make this information explicit. This dataset adds the speaker's sex and identity as new features. Notes: * This is version 2. Version 1 is hidden because it includes a feature dividing the data in train and test set. In OpenML this in " ], "weight": 5 }, "qualities": { "NumberOfInstances": 990, "NumberOfFeatures": 13, "NumberOfClasses": 11, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 10, "NumberOfSymbolicFeatures": 3, "AutoCorrelation": 0, "CfsSubsetEval_DecisionStumpAUC": 0.8608742985409651, "CfsSubsetEval_DecisionStumpErrRate": 0.30505050505050507, "CfsSubsetEval_DecisionStumpKappa": 0.6644444444444445, "CfsSubsetEval_NaiveBayesAUC": 0.8608742985409651, "CfsSubsetEval_NaiveBayesErrRate": 0.30505050505050507, "CfsSubsetEval_NaiveBayesKappa": 0.6644444444444445, "CfsSubsetEval_kNN1NAUC": 0.8608742985409651, "CfsSubsetEval_kNN1NErrRate": 0.30505050505050507, "CfsSubsetEval_kNN1NKappa": 0.6644444444444445, "ClassEntropy": 3.459431618637298, "DecisionStumpAUC": 0.6774680134680136, "DecisionStumpErrRate": 0.8242424242424242, "DecisionStumpKappa": 0.09333333333333332, "Dimensionality": 0.013131313131313131, "EquivalentNumberOfAtts": null, "J48.00001.AUC": 0.8730314253647586, "J48.00001.ErrRate": 0.3202020202020202, "J48.00001.Kappa": 0.6477777777777778, "J48.0001.AUC": 0.8730314253647586, "J48.0001.ErrRate": 0.3202020202020202, "J48.0001.Kappa": 0.6477777777777778, "J48.001.AUC": 0.8730314253647586, "J48.001.ErrRate": 0.3202020202020202, "J48.001.Kappa": 0.6477777777777778, "MajorityClassPercentage": 9.090909090909092, "MajorityClassSize": 90, "MaxAttributeEntropy": 3.906890595608518, "MaxKurtosisOfNumericAtts": 0.1524368802477145, "MaxMeansOfNumericAtts": 1.881763636363636, "MaxMutualInformation": 0, "MaxNominalAttDistinctValues": 15, "MaxSkewnessOfNumericAtts": 0.3570604221210384, "MaxStdDevOfNumericAtts": 1.1752720041815217, "MeanAttributeEntropy": 2.4518411137950773, "MeanKurtosisOfNumericAtts": -0.39142721501684635, "MeanMeansOfNumericAtts": -0.10318040404040407, "MeanMutualInformation": 0, "MeanNoiseToSignalRatio": null, "MeanNominalAttDistinctValues": 9.333333333333334, "MeanSkewnessOfNumericAtts": 0.09111527285062525, "MeanStdDevOfNumericAtts": 0.699331810942439, "MinAttributeEntropy": 0.9967916319816366, "MinKurtosisOfNumericAtts": -0.7621395184642852, "MinMeansOfNumericAtts": -3.203740404040404, "MinMutualInformation": 0, "MinNominalAttDistinctValues": 2, "MinSkewnessOfNumericAtts": -0.20615204556382144, "MinStdDevOfNumericAtts": 0.46192683815131974, "MinorityClassPercentage": 9.090909090909092, "MinorityClassSize": 90, "NaiveBayesAUC": 0.9447710437710438, "NaiveBayesErrRate": 0.4161616161616162, "NaiveBayesKappa": 0.5422222222222222, "NumberOfBinaryFeatures": 1, "PercentageOfBinaryFeatures": 7.6923076923076925, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "PercentageOfNumericFeatures": 76.92307692307693, "PercentageOfSymbolicFeatures": 23.076923076923077, "Quartile1AttributeEntropy": 0.9967916319816366, "Quartile1KurtosisOfNumericAtts": -0.5598569198966739, "Quartile1MeansOfNumericAtts": -0.356185606060606, "Quartile1MutualInformation": 0, "Quartile1SkewnessOfNumericAtts": -0.006222604957687408, "Quartile1StdDevOfNumericAtts": 0.5725169123224305, "Quartile2AttributeEntropy": 2.4518411137950773, "Quartile2KurtosisOfNumericAtts": -0.42609939747851944, "Quartile2MeansOfNumericAtts": -0.03785202020202025, "Quartile2MutualInformation": 0, "Quartile2SkewnessOfNumericAtts": 0.06013385313957622, "Quartile2StdDevOfNumericAtts": 0.6342938790535619, "Quartile3AttributeEntropy": 3.906890595608518, "Quartile3KurtosisOfNumericAtts": -0.24255761544063992, "Quartile3MeansOfNumericAtts": 0.5441732323232322, "Quartile3MutualInformation": 0, "Quartile3SkewnessOfNumericAtts": 0.25062290775439544, "Quartile3StdDevOfNumericAtts": 0.7866928081860705, "REPTreeDepth1AUC": 0.8406290684624018, "REPTreeDepth1ErrRate": 0.6393939393939394, "REPTreeDepth1Kappa": 0.29666666666666663, "REPTreeDepth2AUC": 0.8406290684624018, "REPTreeDepth2ErrRate": 0.6393939393939394, "REPTreeDepth2Kappa": 0.29666666666666663, "REPTreeDepth3AUC": 0.8406290684624018, "REPTreeDepth3ErrRate": 0.6393939393939394, "REPTreeDepth3Kappa": 0.29666666666666663, "RandomTreeDepth1AUC": 0.8475173961840627, "RandomTreeDepth1ErrRate": 0.2909090909090909, "RandomTreeDepth1Kappa": 0.68, "RandomTreeDepth2AUC": 0.8475173961840627, "RandomTreeDepth2ErrRate": 0.2909090909090909, "RandomTreeDepth2Kappa": 0.68, "RandomTreeDepth3AUC": 0.8475173961840627, "RandomTreeDepth3ErrRate": 0.2909090909090909, "RandomTreeDepth3Kappa": 0.68, "StdvNominalAttDistinctValues": 6.6583281184793925, "kNN1NAUC": 0.9572222222222221, "kNN1NErrRate": 0.07777777777777778, "kNN1NKappa": 0.9144444444444445 }, "tags": [ { "tag": "study_14", "uploader": "1" }, { "tag": "study_1", "uploader": "0" }, { "tag": "study_284", "uploader": "0" }, { "tag": "study_579", "uploader": "0" }, { "tag": "study_293", "uploader": "0" }, { "tag": "study_344", "uploader": "0" }, { "tag": "study_662", "uploader": "0" }, { "tag": "study_117", "uploader": "0" }, { "tag": "study_538", "uploader": "0" }, { "tag": "study_560", "uploader": "0" }, { "tag": "study_237", "uploader": "0" }, { "tag": "study_328", "uploader": "0" }, { "tag": "study_665", "uploader": "0" }, { "tag": "study_769", "uploader": "0" }, { "tag": "study_263", "uploader": "0" } ], "features": [ { "name": "Class", "index": "12", "type": "nominal", "distinct": "11", "missing": "0", "target": "1", "distr": [ [ "hid", "hId", "hEd", "hAd", "hYd", "had", "hOd", "hod", "hUd", "hud", "hed" ], [ [ "90", "0", "0", "0", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "90", "0", "0", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "90", "0", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "90", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "90", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "90", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "90", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "90", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "0", "90", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "0", "0", "90", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "0", "0", "0", "90" ] ] ] }, { "name": "Speaker_Number", "index": "0", "type": "nominal", "distinct": "15", "missing": "0", "distr": [ [ "Andrew", "Bill", "David", "Mark", "Jo", "Kate", "Penny", "Rose", "Mike", "Nick", "Rich", "Tim", "Sarah", "Sue", "Wendy" ], [ [ "6", "6", "6", "6", "6", "6", "6", "6", "6", "6", "6" ], [ "6", "6", "6", "6", "6", "6", "6", "6", "6", "6", "6" ], [ "6", "6", "6", "6", "6", "6", "6", "6", "6", "6", "6" ], [ "6", "6", "6", "6", "6", "6", "6", "6", "6", "6", "6" ], [ "6", "6", "6", "6", "6", "6", "6", "6", "6", "6", "6" ], [ "6", "6", "6", "6", "6", "6", "6", "6", "6", "6", "6" ], [ "6", "6", "6", "6", "6", "6", "6", "6", "6", "6", "6" ], [ "6", "6", "6", "6", "6", "6", "6", "6", "6", "6", "6" ], [ "6", "6", "6", "6", "6", "6", "6", "6", "6", "6", "6" ], [ "6", "6", "6", "6", "6", "6", "6", "6", "6", "6", "6" ], [ "6", "6", "6", "6", "6", "6", "6", "6", "6", "6", "6" ], [ "6", "6", "6", "6", "6", "6", "6", "6", "6", "6", "6" ], [ "6", "6", "6", "6", "6", "6", "6", "6", "6", "6", "6" ], [ "6", "6", "6", "6", "6", "6", "6", "6", "6", "6", "6" ], [ "6", "6", "6", "6", "6", "6", "6", "6", "6", "6", "6" ] ] ] }, { "name": "Sex", "index": "1", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "Male", "Female" ], [ [ "48", "48", "48", "48", "48", "48", "48", "48", "48", "48", "48" ], [ "42", "42", "42", "42", "42", "42", "42", "42", "42", "42", "42" ] ] ] }, { "name": "Feature_0", "index": "2", "type": "numeric", "distinct": "853", "missing": "0", "min": "-5", "max": "0", "mean": "-3", "stdev": "1" }, { "name": "Feature_1", "index": "3", "type": "numeric", "distinct": "877", "missing": "0", "min": "-1", "max": "5", "mean": "2", "stdev": "1" }, { "name": "Feature_2", "index": "4", "type": "numeric", "distinct": "815", "missing": "0", "min": "-2", "max": "1", "mean": "-1", "stdev": "1" }, { "name": "Feature_3", "index": "5", "type": "numeric", "distinct": "836", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Feature_4", "index": "6", "type": "numeric", "distinct": "803", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Feature_5", "index": "7", "type": "numeric", "distinct": "798", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Feature_6", "index": "8", "type": "numeric", "distinct": "748", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Feature_7", "index": "9", "type": "numeric", "distinct": "794", "missing": "0", "min": "-1", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Feature_8", "index": "10", "type": "numeric", "distinct": "788", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "1" }, { "name": "Feature_9", "index": "11", "type": "numeric", "distinct": "775", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "1" } ], "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 }