{ "data_id": "77", "name": "phoneme", "exact_name": "phoneme", "version": 1, "version_label": null, "description": "**Author**: \n**Source**: KEEL\n**Please cite**: \n\n* Title:\n\nPhoneme dataset\n\n* Abstract:\n\nThe aim of this dataset is to distinguish between nasal (class 0) and oral sounds (class 1). The class distribution is 3,818 samples in class 0 and 1,586 samples in class 1. The phonemes are transcribed as follows: sh as in she, dcl as in dark, iy as the vowel in she, aa as the vowel in dark, and ao as the first vowel in water.\n\n* Attributes information:\n\n@relation phoneme\n@attribute Aa real [-1.7, 4.107]\n@attribute Ao real [-1.327, 4.378]\n@attribute Dcl real [-1.823, 3.199]\n@attribute Iy real [-1.581, 2.826]\n@attribute Sh real [-1.284, 2.719]\n@attribute Class {0, 1}\n@inputs Aa, Ao, Dcl, Iy, Sh\n@outputs Class", "format": "ARFF", "uploader": "Rafael Gomes Mantovani", "uploader_id": 64, "visibility": "public", "creator": null, "contributor": null, "date": "2015-05-25 19:34:17", "update_comment": null, "last_update": "2015-11-09 20:25:20", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/1592281\/php8Mz7BG", "default_target_attribute": "Class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "phoneme", "* Title: Phoneme dataset * Abstract: The aim of this dataset is to distinguish between nasal (class 0) and oral sounds (class 1). The class distribution is 3,818 samples in class 0 and 1,586 samples in class 1. The phonemes are transcribed as follows: sh as in she, dcl as in dark, iy as the vowel in she, aa as the vowel in dark, and ao as the first vowel in water. * Attributes information: @relation phoneme @attribute Aa real [-1.7, 4.107] @attribute Ao real [-1.327, 4.378] @attribute Dcl real [ " ], "weight": 5 }, "qualities": { "NumberOfInstances": 5404, "NumberOfFeatures": 6, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 5, "NumberOfSymbolicFeatures": 1, "AutoCorrelation": 0.5918933925596891, "CfsSubsetEval_DecisionStumpAUC": 0.8550177462963318, "CfsSubsetEval_DecisionStumpErrRate": 0.1815321983715766, "CfsSubsetEval_DecisionStumpKappa": 0.5579430305860378, "CfsSubsetEval_NaiveBayesAUC": 0.8550177462963318, "CfsSubsetEval_NaiveBayesErrRate": 0.1815321983715766, "CfsSubsetEval_NaiveBayesKappa": 0.5579430305860378, "CfsSubsetEval_kNN1NAUC": 0.8550177462963318, "CfsSubsetEval_kNN1NErrRate": 0.1815321983715766, "CfsSubsetEval_kNN1NKappa": 0.5579430305860378, "ClassEntropy": 0.8731822577241406, "DecisionStumpAUC": 0.7404866739285669, "DecisionStumpErrRate": 0.24740932642487046, "DecisionStumpKappa": 0.4488154160690855, "Dimensionality": 0.0011102886750555144, "EquivalentNumberOfAtts": null, "J48.00001.AUC": 0.8678687005272036, "J48.00001.ErrRate": 0.16894892672094744, "J48.00001.Kappa": 0.5893493980716988, "J48.0001.AUC": 0.8678687005272036, "J48.0001.ErrRate": 0.16894892672094744, "J48.0001.Kappa": 0.5893493980716988, "J48.001.AUC": 0.8678687005272036, "J48.001.ErrRate": 0.16894892672094744, "J48.001.Kappa": 0.5893493980716988, "MajorityClassPercentage": 70.65136935603256, "MajorityClassSize": 3818, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 1.7651174033134938, "MaxMeansOfNumericAtts": 6.1065877123851385e-9, "MaxMutualInformation": null, "MaxNominalAttDistinctValues": 2, "MaxSkewnessOfNumericAtts": 1.482393052784835, "MaxStdDevOfNumericAtts": 1.0000000160707985, "MeanAttributeEntropy": null, "MeanKurtosisOfNumericAtts": 0.33974898860956887, "MeanMeansOfNumericAtts": -1.2287194680574282e-8, "MeanMutualInformation": null, "MeanNoiseToSignalRatio": null, "MeanNominalAttDistinctValues": 2, "MeanSkewnessOfNumericAtts": 0.7794652586095029, "MeanStdDevOfNumericAtts": 1.000000004616722, "MinAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.8572834809909309, "MinMeansOfNumericAtts": -6.698741675291565e-8, "MinMutualInformation": null, "MinNominalAttDistinctValues": 2, "MinSkewnessOfNumericAtts": 0.2094948505005711, "MinStdDevOfNumericAtts": 0.9999999984765442, "MinorityClassPercentage": 29.348630643967432, "MinorityClassSize": 1586, "NaiveBayesAUC": 0.8173487304115306, "NaiveBayesErrRate": 0.24037749814951886, "NaiveBayesKappa": 0.46338464605596114, "NumberOfBinaryFeatures": 1, "PercentageOfBinaryFeatures": 16.666666666666664, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "PercentageOfNumericFeatures": 83.33333333333334, "PercentageOfSymbolicFeatures": 16.666666666666664, "Quartile1AttributeEntropy": null, "Quartile1KurtosisOfNumericAtts": -0.6590595801379302, "Quartile1MeansOfNumericAtts": -3.821243527730011e-8, "Quartile1MutualInformation": null, "Quartile1SkewnessOfNumericAtts": 0.34288338170102217, "Quartile1StdDevOfNumericAtts": 0.9999999997309185, "Quartile2AttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": -0.3066496518690336, "Quartile2MeansOfNumericAtts": 3.3308660617082098e-9, "Quartile2MutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.4842310006900062, "Quartile2StdDevOfNumericAtts": 1.000000003087631, "Quartile3AttributeEntropy": null, "Quartile3KurtosisOfNumericAtts": 1.6617568775963694, "Quartile3MeansOfNumericAtts": 5.829015545010302e-9, "Quartile3MutualInformation": null, "Quartile3SkewnessOfNumericAtts": 1.363664264477732, "Quartile3StdDevOfNumericAtts": 1.000000010267071, "REPTreeDepth1AUC": 0.8756328290298097, "REPTreeDepth1ErrRate": 0.1659881569207994, "REPTreeDepth1Kappa": 0.5893753379948957, "REPTreeDepth2AUC": 0.8756328290298097, "REPTreeDepth2ErrRate": 0.1659881569207994, "REPTreeDepth2Kappa": 0.5893753379948957, "REPTreeDepth3AUC": 0.8756328290298097, "REPTreeDepth3ErrRate": 0.1659881569207994, "REPTreeDepth3Kappa": 0.5893753379948957, "RandomTreeDepth1AUC": 0.8065602505421655, "RandomTreeDepth1ErrRate": 0.15562546262028126, "RandomTreeDepth1Kappa": 0.6203230053600308, "RandomTreeDepth2AUC": 0.8065602505421655, "RandomTreeDepth2ErrRate": 0.15562546262028126, "RandomTreeDepth2Kappa": 0.6203230053600308, "RandomTreeDepth3AUC": 0.8065602505421655, "RandomTreeDepth3ErrRate": 0.15562546262028126, "RandomTreeDepth3Kappa": 0.6203230053600308, "StdvNominalAttDistinctValues": 0, "kNN1NAUC": 0.8367145868412517, "kNN1NErrRate": 0.12675795706883788, "kNN1NKappa": 0.6877227093332758 }, "tags": [ { "tag": "study_14", "uploader": "1" }, { "tag": "study_1", "uploader": "0" }, { "tag": "study_237", "uploader": "0" }, { "tag": "study_101", "uploader": "0" }, { "tag": "study_201", "uploader": "0" }, { "tag": "study_665", "uploader": "0" }, { "tag": "study_102", "uploader": "0" }, { "tag": "study_105", "uploader": "0" }, { "tag": "study_617", "uploader": "0" } ], "features": [ { "name": "Class", "index": "5", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "1", "2" ], [ [ "3818", "0" ], [ "0", "1586" ] ] ] }, { "name": "V1", "index": "0", "type": "numeric", "distinct": "5336", "missing": "0", "min": "-3", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V2", "index": "1", "type": "numeric", "distinct": "5312", "missing": "0", "min": "-3", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V3", "index": "2", "type": "numeric", "distinct": "5308", "missing": "0", "min": "-3", "max": "3", "mean": "0", "stdev": "1" }, { "name": "V4", "index": "3", "type": "numeric", "distinct": "5336", "missing": "0", "min": "-2", "max": "3", "mean": "0", "stdev": "1" }, { "name": "V5", "index": "4", "type": "numeric", "distinct": "4499", "missing": "0", "min": "-2", "max": "5", "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 }