{ "data_id": "1059", "name": "ar1", "exact_name": "ar1", "version": 1, "version_label": null, "description": "**Author**: \n**Source**: Unknown - Date unknown \n**Please cite**: \n\n%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%\n%%\nThis is a PROMISE Software Engineering Repository data set made publicly\navailable in order to encourage repeatable, refutable, verifiable, and\/or\nimprovable predictive models of software engineering.\n\nIf you publish material based on PROMISE data sets then, please follow\nthe acknowledgment guidelines posted on the PROMISE repository web page\nhttp:\/\/promise.site.uottowa.ca\/SERepository.\n%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%\n--Title: AR1 \/Software Defect Prediction\n--Date: February, 4th, 2009\n--Data from a Turkish white-goods manufacturer\n--Donated by: Software Research Laboratory (Softlab),\nBogazici University, Istanbul, Turkey\n--Website: http:\/\/softlab.boun.edu.tr\n--Contact address: ayse.tosun@boun.edu.tr, bener@boun.edu.tr\n\n--Description:\nEmbedded software in a white-goods product.\nImplemented in C.\nConsists of 121 modules (9 defective \/ 112 defect-free)\n29 static code attributes (McCabe, Halstead and LOC measures) and 1 defect information(false\/true)\nFunction\/method level static code attributes are collected using\nPrest Metrics Extraction and Analysis Tool [1].\n[1] Prest Metrics Extraction and Analysis Tool, available at http:\/\/softlab.boun.edu.tr\/?q=resources&i=tools.", "format": "ARFF", "uploader": "Joaquin Vanschoren", "uploader_id": 2, "visibility": "public", "creator": "Software Research Laboratory (Softlab)", "contributor": null, "date": "2014-10-06 23:57:30", "update_comment": null, "last_update": "2014-10-06 23:57:30", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/53942\/ar1.arff", "default_target_attribute": "defects", "row_id_attribute": null, "ignore_attribute": null, "runs": 756, "suggest": { "input": [ "ar1", "%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %% This is a PROMISE Software Engineering Repository data set made publicly available in order to encourage repeatable, refutable, verifiable, and\/or improvable predictive models of software engineering. If you publish material based on PROMISE data sets then, please follow the acknowledgment guidelines posted on the PROMISE repository web page http:\/\/promise.site.uottowa.ca\/SERepository. %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% " ], "weight": 5 }, "qualities": { "NumberOfInstances": 121, "NumberOfFeatures": 30, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 29, "NumberOfSymbolicFeatures": 1, "MeanSkewnessOfNumericAtts": 2.2481469430333365, "Quartile1StdDevOfNumericAtts": 0.8110315894801738, "REPTreeDepth2AUC": 0.5138888888888888, "CfsSubsetEval_kNN1NErrRate": 0.09090909090909091, "kNN1NAUC": 0.7559523809523809, "J48.001.Kappa": 0, "MeanStdDevOfNumericAtts": 232.2809081868085, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": 0.09090909090909091, "CfsSubsetEval_kNN1NKappa": -0.027799227799228558, "kNN1NErrRate": 0.09917355371900827, "MajorityClassPercentage": 92.56198347107438, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 4.932995663845491, "REPTreeDepth2Kappa": -0.027799227799228558, "ClassEntropy": 0.38206095394044187, "kNN1NKappa": 0.27976190476190493, "MajorityClassSize": 112, "MinKurtosisOfNumericAtts": -1.131168702300494, "Quartile2MeansOfNumericAtts": 4.760330578512398, "REPTreeDepth3AUC": 0.5138888888888888, "DecisionStumpAUC": 0.5962301587301587, "MaxAttributeEntropy": null, "MinMeansOfNumericAtts": 0.06834710743801653, "Quartile2MutualInformation": null, "REPTreeDepth3ErrRate": 0.09090909090909091, "DecisionStumpErrRate": 0.09090909090909091, "MaxKurtosisOfNumericAtts": 47.40533089070607, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": 1.9519620971457996, "REPTreeDepth3Kappa": -0.027799227799228558, "DecisionStumpKappa": -0.027799227799228558, "MaxMeansOfNumericAtts": 2861.796363636364, "MaxMutualInformation": null, "MinNominalAttDistinctValues": 2, "PercentageOfBinaryFeatures": 3.3333333333333335, "Quartile2StdDevOfNumericAtts": 6.1142249350570825, "RandomTreeDepth1AUC": 0.6220238095238096, "Dimensionality": 0.24793388429752067, "MaxNominalAttDistinctValues": 2, "MinSkewnessOfNumericAtts": 0.003959233668651587, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1ErrRate": 0.0743801652892562, "EquivalentNumberOfAtts": null, "MaxSkewnessOfNumericAtts": 6.485990057897478, "MinStdDevOfNumericAtts": 0.08042954585057671, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 9.625117779706356, "AutoCorrelation": 0.875, "RandomTreeDepth1Kappa": 0, "J48.00001.AUC": 0.4722222222222222, "MaxStdDevOfNumericAtts": 5926.753898493113, "MinorityClassPercentage": 7.43801652892562, "PercentageOfNumericFeatures": 96.66666666666667, "Quartile3MeansOfNumericAtts": 20.58677685950413, "CfsSubsetEval_DecisionStumpAUC": 0.5873015873015874, "RandomTreeDepth2AUC": 0.5277777777777778, "J48.00001.ErrRate": 0.0743801652892562, "MeanAttributeEntropy": null, "MinorityClassSize": 9, "PercentageOfSymbolicFeatures": 3.3333333333333335, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": 0.09090909090909091, "RandomTreeDepth2ErrRate": 0.09917355371900827, "J48.00001.Kappa": 0, "MeanKurtosisOfNumericAtts": 8.06905645504017, "NaiveBayesAUC": 0.6842122523940706, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 2.60727583544539, "CfsSubsetEval_DecisionStumpKappa": -0.027799227799228558, "RandomTreeDepth2Kappa": -0.03862660944206056, "J48.0001.AUC": 0.4722222222222222, "MeanMeansOfNumericAtts": 119.6140182388145, "NaiveBayesErrRate": 0.24793388429752067, "Quartile1KurtosisOfNumericAtts": 2.9874746222658204, "Quartile3StdDevOfNumericAtts": 17.43159837254879, "CfsSubsetEval_NaiveBayesAUC": 0.7430555555555556, "RandomTreeDepth3AUC": 0.560515873015873, "J48.0001.ErrRate": 0.0743801652892562, "MeanMutualInformation": null, "NaiveBayesKappa": 0.1094210009813546, "Quartile1MeansOfNumericAtts": 0.5061983471074379, "REPTreeDepth1AUC": 0.5138888888888888, "CfsSubsetEval_NaiveBayesErrRate": 0.09090909090909091, "RandomTreeDepth3ErrRate": 0.09917355371900827, "J48.0001.Kappa": 0, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 1, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": 0.09090909090909091, "CfsSubsetEval_NaiveBayesKappa": -0.027799227799228558, "RandomTreeDepth3Kappa": -0.03862660944206056, "J48.001.AUC": 0.4722222222222222, "MeanNominalAttDistinctValues": 2, "Quartile1SkewnessOfNumericAtts": 1.6278977138679536, "REPTreeDepth1Kappa": -0.027799227799228558, "CfsSubsetEval_kNN1NAUC": 0.5461309523809523, "StdvNominalAttDistinctValues": 0, "J48.001.ErrRate": 0.0743801652892562 }, "tags": [ { "tag": "Chemistry", "uploader": "38960" }, { "tag": "Life Science", "uploader": "38960" }, { "tag": "mythbusting_1", "uploader": "1" }, { "tag": "PROMISE", "uploader": "24659" }, { "tag": "study_1", "uploader": "2" }, { "tag": "study_123", "uploader": "3886" }, { "tag": "study_15", "uploader": "939" }, { "tag": "study_20", "uploader": "939" }, { "tag": "study_41", "uploader": "1" }, { "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" } ], "features": [ { "name": "defects", "index": "29", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "false", "true" ], [ [ "112", "0" ], [ "0", "9" ] ] ] }, { "name": "total_loc", "index": "0", "type": "numeric", "distinct": "41", "missing": "0", "min": "2", "max": "95", "mean": "20", "stdev": "20" }, { "name": "blank_loc", "index": "1", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "comment_loc", "index": "2", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "30", "mean": "5", "stdev": "6" }, { "name": "code_and_comment_loc", "index": "3", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "executable_loc", "index": "4", "type": "numeric", "distinct": "37", "missing": "0", "min": "2", "max": "82", "mean": "15", "stdev": "15" }, { "name": "unique_operands", "index": "5", "type": "numeric", "distinct": "33", "missing": "0", "min": "1", "max": "47", "mean": "12", "stdev": "10" }, { "name": "unique_operators", "index": "6", "type": "numeric", "distinct": "17", "missing": "0", "min": "2", "max": "19", "mean": "8", "stdev": "4" }, { "name": "total_operands", "index": "7", "type": "numeric", "distinct": "49", "missing": "0", "min": "1", "max": "118", "mean": "24", "stdev": "24" }, { "name": "total_operators", "index": "8", "type": "numeric", "distinct": "59", "missing": "0", "min": "3", "max": "184", "mean": "37", "stdev": "36" }, { "name": "halstead_vocabulary", "index": "9", "type": "numeric", "distinct": "42", "missing": "0", "min": "3", "max": "62", "mean": "21", "stdev": "13" }, { "name": "halstead_length", "index": "10", "type": "numeric", "distinct": "71", "missing": "0", "min": "4", "max": "302", "mean": "61", "stdev": "60" }, { "name": "halstead_volume", "index": "11", "type": "numeric", "distinct": "84", "missing": "0", "min": "4", "max": "1210", "mean": "205", "stdev": "241" }, { "name": "halstead_level", "index": "12", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "halstead_difficulty", "index": "13", "type": "numeric", "distinct": "35", "missing": "0", "min": "1", "max": "33", "mean": "8", "stdev": "6" }, { "name": "halstead_effort", "index": "14", "type": "numeric", "distinct": "90", "missing": "0", "min": "4", "max": "40333", "mean": "2862", "stdev": "5927" }, { "name": "halstead_error", "index": "15", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "halstead_time", "index": "16", "type": "numeric", "distinct": "89", "missing": "0", "min": "0", "max": "2241", "mean": "159", "stdev": "329" }, { "name": "branch_count", "index": "17", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "76", "mean": "10", "stdev": "13" }, { "name": "decision_count", "index": "18", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "38", "mean": "5", "stdev": "7" }, { "name": "call_pairs", "index": "19", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "19", "mean": "2", "stdev": "3" }, { "name": "condition_count", "index": "20", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "38", "mean": "4", "stdev": "7" }, { "name": "multiple_condition_count", "index": "21", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "2" }, { "name": "cyclomatic_complexity", "index": "22", "type": "numeric", "distinct": "17", "missing": "0", "min": "1", "max": "28", "mean": "5", "stdev": "5" }, { "name": "cyclomatic_density", "index": "23", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "decision_density", "index": "24", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "design_complexity", "index": "25", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "19", "mean": "2", "stdev": "3" }, { "name": "design_density", "index": "26", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "normalized_cyclomatic_complexity", "index": "27", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "formal_parameters", "index": "28", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 8, "total_downloads": 9, "reach": 8, "reuse": 14, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 14 }