{ "data_id": "16", "name": "credit-a", "exact_name": "credit-a", "version": 1, "version_label": "1", "description": "**Author**: \n**Source**: Unknown - \n**Please cite**: \n\n1. Title: Credit Approval\n \n 2. Sources: \n (confidential)\n Submitted by quinlan@cs.su.oz.au\n \n 3. Past Usage:\n \n See Quinlan,\n * \"Simplifying decision trees\", Int J Man-Machine Studies 27,\n Dec 1987, pp. 221-234.\n * \"C4.5: Programs for Machine Learning\", Morgan Kaufmann, Oct 1992\n \n 4. Relevant Information:\n \n This file concerns credit card applications. All attribute names\n and values have been changed to meaningless symbols to protect\n confidentiality of the data.\n \n This dataset is interesting because there is a good mix of\n attributes -- continuous, nominal with small numbers of\n values, and nominal with larger numbers of values. There\n are also a few missing values.\n \n 5. Number of Instances: 690\n \n 6. Number of Attributes: 15 + class attribute\n \n 7. Attribute Information:\n \n A1:\tb, a.\n A2:\tcontinuous.\n A3:\tcontinuous.\n A4:\tu, y, l, t.\n A5:\tg, p, gg.\n A6:\tc, d, cc, i, j, k, m, r, q, w, x, e, aa, ff.\n A7:\tv, h, bb, j, n, z, dd, ff, o.\n A8:\tcontinuous.\n A9:\tt, f.\n A10:\tt, f.\n A11:\tcontinuous.\n A12:\tt, f.\n A13:\tg, p, s.\n A14:\tcontinuous.\n A15:\tcontinuous.\n A16: +,- (class attribute)\n \n 8. Missing Attribute Values:\n 37 cases (5%) have one or more missing values. The missing\n values from particular attributes are:\n \n A1: 12\n A2: 12\n A4: 6\n A5: 6\n A6: 9\n A7: 9\n A14: 13\n \n 9. Class Distribution\n \n +: 307 (44.5%)\n -: 383 (55.5%)", "format": "ARFF", "uploader": "Jan van Rijn", "uploader_id": 1, "visibility": "public", "creator": null, "contributor": null, "date": "2014-04-06 23:21:38", "update_comment": null, "last_update": "2014-04-06 23:21:38", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/29\/dataset_29_credit-a.arff", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 190, "suggest": { "input": [ "credit-a", "1. Title: Credit Approval 2. Sources: (confidential) Submitted by quinlan@cs.su.oz.au 3. Past Usage: See Quinlan, * \"Simplifying decision trees\", Int J Man-Machine Studies 27, Dec 1987, pp. 221-234. * \"C4.5: Programs for Machine Learning\", Morgan Kaufmann, Oct 1992 4. Relevant Information: This file concerns credit card applications. All attribute names and values have been changed to meaningless symbols to protect confidentiality of the data. This dataset is interesting because there is a good " ], "weight": 5 }, "qualities": { "NumberOfInstances": 690, "NumberOfFeatures": 16, "NumberOfClasses": 2, "NumberOfMissingValues": 67, "NumberOfInstancesWithMissingValues": 37, "NumberOfNumericFeatures": 6, "NumberOfSymbolicFeatures": 10, "AutoCorrelation": 0.9782293178519593, "CfsSubsetEval_DecisionStumpAUC": 0.8776120291543702, "CfsSubsetEval_DecisionStumpErrRate": 0.14347826086956522, "CfsSubsetEval_DecisionStumpKappa": 0.7101750574897961, "CfsSubsetEval_NaiveBayesAUC": 0.8776120291543702, "CfsSubsetEval_NaiveBayesErrRate": 0.14347826086956522, "CfsSubsetEval_NaiveBayesKappa": 0.7101750574897961, "CfsSubsetEval_kNN1NAUC": 0.8776120291543702, "CfsSubsetEval_kNN1NErrRate": 0.14347826086956522, "CfsSubsetEval_kNN1NKappa": 0.7101750574897961, "ClassEntropy": 0.9912308989033523, "DecisionStumpAUC": 0.8590375996121823, "DecisionStumpErrRate": 0.14492753623188406, "DecisionStumpKappa": 0.7116180318139644, "Dimensionality": 0.02318840579710145, "EquivalentNumberOfAtts": 10.987754965826467, "J48.00001.AUC": 0.8928568391151631, "J48.00001.ErrRate": 0.1608695652173913, "J48.00001.Kappa": 0.6739935471238732, "J48.0001.AUC": 0.8928568391151631, "J48.0001.ErrRate": 0.1608695652173913, "J48.0001.Kappa": 0.6739935471238732, "J48.001.AUC": 0.8928568391151631, "J48.001.ErrRate": 0.1608695652173913, "J48.001.Kappa": 0.6739935471238732, "MajorityClassPercentage": 55.507246376811594, "MajorityClassSize": 383, "MaxAttributeEntropy": 3.4964402118046265, "MaxKurtosisOfNumericAtts": 214.66997242752777, "MaxMeansOfNumericAtts": 1017.3855072463792, "MaxMutualInformation": 0.42570942667283, "MaxNominalAttDistinctValues": 14, "MaxSkewnessOfNumericAtts": 13.140655014445356, "MaxStdDevOfNumericAtts": 5210.102598302697, "MeanAttributeEntropy": 1.2537639123535842, "MeanKurtosisOfNumericAtts": 49.931703911167034, "MeanMeansOfNumericAtts": 207.0584299702253, "MeanMutualInformation": 0.09021232289819223, "MeanNoiseToSignalRatio": 12.897922945277674, "MeanNominalAttDistinctValues": 4.2, "MeanSkewnessOfNumericAtts": 4.423867143578692, "MeanStdDevOfNumericAtts": 901.5091409447066, "MinAttributeEntropy": 0.5010395545266964, "MinKurtosisOfNumericAtts": 1.1192361294529984, "MinMeansOfNumericAtts": 2.22340579710145, "MinMutualInformation": 0.0006029571694, "MinNominalAttDistinctValues": 2, "MinSkewnessOfNumericAtts": 1.1458915555559273, "MinStdDevOfNumericAtts": 3.3465133592781324, "MinorityClassPercentage": 44.492753623188406, "MinorityClassSize": 307, "NaiveBayesAUC": 0.8940115780808026, "NaiveBayesErrRate": 0.21594202898550724, "NaiveBayesKappa": 0.5492647768025463, "NumberOfBinaryFeatures": 5, "PercentageOfBinaryFeatures": 31.25, "PercentageOfInstancesWithMissingValues": 5.36231884057971, "PercentageOfMissingValues": 0.6068840579710145, "PercentageOfNumericFeatures": 37.5, "PercentageOfSymbolicFeatures": 62.5, "Quartile1AttributeEntropy": 0.8162006158245964, "Quartile1KurtosisOfNumericAtts": 1.9853254475312268, "Quartile1MeansOfNumericAtts": 2.355851449275366, "Quartile1MutualInformation": 0.005378837210200001, "Quartile1SkewnessOfNumericAtts": 1.403082732387671, "Quartile1StdDevOfNumericAtts": 4.48383336548978, "Quartile2AttributeEntropy": 0.9847953334568664, "Quartile2KurtosisOfNumericAtts": 15.348780875597205, "Quartile2MeansOfNumericAtts": 18.163447864563295, "Quartile2MutualInformation": 0.02960326183246, "Quartile2SkewnessOfNumericAtts": 2.8076616546800306, "Quartile2StdDevOfNumericAtts": 8.468012873399704, "Quartile3AttributeEntropy": 1.39388043097786, "Quartile3KurtosisOfNumericAtts": 91.78956656083423, "Quartile3MeansOfNumericAtts": 392.35745509815314, "Quartile3MutualInformation": 0.13272286566341002, "Quartile3SkewnessOfNumericAtts": 7.149553646695756, "Quartile3StdDevOfNumericAtts": 1432.8807257446028, "REPTreeDepth1AUC": 0.8857766135685188, "REPTreeDepth1ErrRate": 0.14492753623188406, "REPTreeDepth1Kappa": 0.7105146127188972, "REPTreeDepth2AUC": 0.8857766135685188, "REPTreeDepth2ErrRate": 0.14492753623188406, "REPTreeDepth2Kappa": 0.7105146127188972, "REPTreeDepth3AUC": 0.8857766135685188, "REPTreeDepth3ErrRate": 0.14492753623188406, "REPTreeDepth3Kappa": 0.7105146127188972, "RandomTreeDepth1AUC": 0.7672209006951606, "RandomTreeDepth1ErrRate": 0.2492753623188406, "RandomTreeDepth1Kappa": 0.49105006303980503, "RandomTreeDepth2AUC": 0.7672209006951606, "RandomTreeDepth2ErrRate": 0.2492753623188406, "RandomTreeDepth2Kappa": 0.49105006303980503, "RandomTreeDepth3AUC": 0.7672209006951606, "RandomTreeDepth3ErrRate": 0.2492753623188406, "RandomTreeDepth3Kappa": 0.49105006303980503, "StdvNominalAttDistinctValues": 4.049691346263318, "kNN1NAUC": 0.8184187921517933, "kNN1NErrRate": 0.1782608695652174, "kNN1NKappa": 0.6382815496739548 }, "tags": [ { "tag": "study_14", "uploader": "1" }, { "tag": "study_1", "uploader": "0" }, { "tag": "study_661", "uploader": "0" }, { "tag": "study_395", "uploader": "0" }, { "tag": "study_665", "uploader": "0" }, { "tag": "study_446", "uploader": "0" }, { "tag": "study_480", "uploader": "0" }, { "tag": "study_237", "uploader": "0" }, { "tag": "study_393", "uploader": "0" }, { "tag": "study_134", "uploader": "0" }, { "tag": "study_182", "uploader": "0" }, { "tag": "study_251", "uploader": "0" }, { "tag": "study_769", "uploader": "0" }, { "tag": "study_213", "uploader": "0" } ], "features": [ { "name": "class", "index": "15", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "+", "-" ], [ [ "307", "0" ], [ "0", "383" ] ] ] }, { "name": "A1", "index": "0", "type": "nominal", "distinct": "2", "missing": "12", "distr": [ [ "b", "a" ], [ [ "206", "262" ], [ "98", "112" ] ] ] }, { "name": "A2", "index": "1", "type": "numeric", "distinct": "349", "missing": "12", "min": "14", "max": "80", "mean": "32", "stdev": "12" }, { "name": "A3", "index": "2", "type": "numeric", "distinct": "215", "missing": "0", "min": "0", "max": "28", "mean": "5", "stdev": "5" }, { "name": "A4", "index": "3", "type": "nominal", "distinct": "3", "missing": "6", "distr": [ [ "u", "y", "l", "t" ], [ [ "256", "263" ], [ "45", "118" ], [ "2", "0" ], [ "0", "0" ] ] ] }, { "name": "A5", "index": "4", "type": "nominal", "distinct": "3", "missing": "6", "distr": [ [ "g", "p", "gg" ], [ [ "256", "263" ], [ "45", "118" ], [ "2", "0" ] ] ] }, { "name": "A6", "index": "5", "type": "nominal", "distinct": "14", "missing": "9", "distr": [ [ "c", "d", "cc", "i", "j", "k", "m", "r", "q", "w", "x", "e", "aa", "ff" ], [ [ "62", "75" ], [ "7", "23" ], [ "29", "12" ], [ "14", "45" ], [ "3", "7" ], [ "14", "37" ], [ "16", "22" ], [ "2", "1" ], [ "51", "27" ], [ "33", "31" ], [ "32", "6" ], [ "14", "11" ], [ "19", "35" ], [ "7", "46" ] ] ] }, { "name": "A7", "index": "6", "type": "nominal", "distinct": "9", "missing": "9", "distr": [ [ "v", "h", "bb", "j", "n", "z", "dd", "ff", "o" ], [ [ "169", "230" ], [ "87", "51" ], [ "25", "34" ], [ "3", "5" ], [ "2", "2" ], [ "6", "2" ], [ "2", "4" ], [ "8", "49" ], [ "1", "1" ] ] ] }, { "name": "A8", "index": "7", "type": "numeric", "distinct": "132", "missing": "0", "min": "0", "max": "29", "mean": "2", "stdev": "3" }, { "name": "A9", "index": "8", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "t", "f" ], [ [ "284", "77" ], [ "23", "306" ] ] ] }, { "name": "A10", "index": "9", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "t", "f" ], [ [ "209", "86" ], [ "98", "297" ] ] ] }, { "name": "A11", "index": "10", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "67", "mean": "2", "stdev": "5" }, { "name": "A12", "index": "11", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "t", "f" ], [ [ "146", "170" ], [ "161", "213" ] ] ] }, { "name": "A13", "index": "12", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "g", "p", "s" ], [ [ "287", "338" ], [ "5", "3" ], [ "15", "42" ] ] ] }, { "name": "A14", "index": "13", "type": "numeric", "distinct": "170", "missing": "13", "min": "0", "max": "2000", "mean": "184", "stdev": "174" }, { "name": "A15", "index": "14", "type": "numeric", "distinct": "240", "missing": "0", "min": "0", "max": "100000", "mean": "1017", "stdev": "5210" } ], "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 }