{
    "data_id": "1056",
    "name": "mc1",
    "exact_name": "mc1",
    "version": 1,
    "version_label": null,
    "description": "**Author**: Mike Chapman, NASA  \r\n**Source**: [tera-PROMISE](http:\/\/openscience.us\/repo\/defect\/mccabehalsted\/mc1.html) - 2004  \r\n**Please cite**: Sayyad Shirabad, J. and Menzies, T.J. (2005) The PROMISE Repository of Software Engineering Databases. School of Information Technology and Engineering, University of Ottawa, Canada.  \r\n  \r\n**MC1 Software defect prediction**  \r\nOne of the NASA Metrics Data Program defect data sets. The specific type of software is unknown. Data comes from McCabe and Halstead features extractors of source code.  These features were defined in the 70s in an attempt to objectively characterize code features that are associated with software quality.\r\n\r\n### Relevant papers  \r\n\r\n- Shepperd, M. and Qinbao Song and Zhongbin Sun and Mair, C. (2013)\r\nData Quality: Some Comments on the NASA Software Defect Datasets, IEEE Transactions on Software Engineering, 39.\r\n\r\n- Tim Menzies and Justin S. Di Stefano (2004) How Good is Your Blind Spot Sampling Policy? 2004 IEEE Conference on High Assurance\r\nSoftware Engineering.\r\n\r\n- T. Menzies and J. DiStefano and A. Orrego and R. Chapman (2004) Assessing Predictors of Software Defects\", Workshop on Predictive Software Models, Chicago",
    "format": "ARFF",
    "uploader": "Joaquin Vanschoren",
    "uploader_id": 2,
    "visibility": "public",
    "creator": "Mike Chapman",
    "contributor": null,
    "date": "2014-10-06 23:57:25",
    "update_comment": null,
    "last_update": "2014-10-06 23:57:25",
    "licence": "Public",
    "status": "active",
    "error_message": null,
    "url": "https:\/\/www.openml.org\/data\/download\/53939\/mc1.arff",
    "kaggle_url": null,
    "default_target_attribute": "c",
    "row_id_attribute": null,
    "ignore_attribute": null,
    "runs": 815,
    "suggest": {
        "input": [
            "mc1",
            "One of the NASA Metrics Data Program defect data sets. The specific type of software is unknown. Data comes from McCabe and Halstead features extractors of source code. These features were defined in the 70s in an attempt to objectively characterize code features that are associated with software quality. ### Relevant papers - Shepperd, M. and Qinbao Song and Zhongbin Sun and Mair, C. (2013) Data Quality: Some Comments on the NASA Software Defect Datasets, IEEE Transactions on Software Engineeri "
        ],
        "weight": 5
    },
    "qualities": {
        "NumberOfInstances": 9466,
        "NumberOfFeatures": 39,
        "NumberOfClasses": 2,
        "NumberOfMissingValues": 0,
        "NumberOfInstancesWithMissingValues": 0,
        "NumberOfNumericFeatures": 38,
        "NumberOfSymbolicFeatures": 1,
        "Quartile3MutualInformation": null,
        "CfsSubsetEval_DecisionStumpErrRate": 0.006761039509824636,
        "RandomTreeDepth2ErrRate": 0.007606169448552715,
        "J48.00001.Kappa": 0.4018784385761403,
        "MeanAttributeEntropy": null,
        "MinorityClassSize": 68,
        "PercentageOfSymbolicFeatures": 2.564102564102564,
        "Quartile3SkewnessOfNumericAtts": 26.890296534072828,
        "CfsSubsetEval_DecisionStumpKappa": 0.19827221140001644,
        "RandomTreeDepth2Kappa": 0.39624112369424075,
        "J48.0001.AUC": 0.7493224465781205,
        "MeanKurtosisOfNumericAtts": 826.5262774688995,
        "NaiveBayesAUC": 0.8962399248746526,
        "Quartile1AttributeEntropy": null,
        "Quartile3StdDevOfNumericAtts": 18.20769774817049,
        "CfsSubsetEval_NaiveBayesAUC": 0.635311956235995,
        "RandomTreeDepth3AUC": 0.6880109034462902,
        "J48.0001.ErrRate": 0.005915909571096556,
        "MeanMeansOfNumericAtts": 360.55809570540066,
        "NaiveBayesErrRate": 0.06602577646313121,
        "Quartile1KurtosisOfNumericAtts": 42.250723776573174,
        "REPTreeDepth1AUC": 0.7256730155352202,
        "CfsSubsetEval_NaiveBayesErrRate": 0.006761039509824636,
        "RandomTreeDepth3ErrRate": 0.007606169448552715,
        "J48.0001.Kappa": 0.4018784385761403,
        "MeanMutualInformation": null,
        "NaiveBayesKappa": 0.11187926872142748,
        "Quartile1MeansOfNumericAtts": 0.8345922248045632,
        "REPTreeDepth1ErrRate": 0.006761039509824636,
        "CfsSubsetEval_NaiveBayesKappa": 0.19827221140001644,
        "RandomTreeDepth3Kappa": 0.39624112369424075,
        "J48.001.AUC": 0.7493224465781205,
        "MeanNoiseToSignalRatio": null,
        "NumberOfBinaryFeatures": 1,
        "Quartile1MutualInformation": null,
        "REPTreeDepth1Kappa": 0.19827221140001644,
        "CfsSubsetEval_kNN1NAUC": 0.635311956235995,
        "StdvNominalAttDistinctValues": 0,
        "J48.001.ErrRate": 0.005915909571096556,
        "MeanNominalAttDistinctValues": 2,
        "Quartile1SkewnessOfNumericAtts": 5.335996511289148,
        "REPTreeDepth2AUC": 0.7256730155352202,
        "CfsSubsetEval_kNN1NErrRate": 0.006761039509824636,
        "kNN1NAUC": 0.9052058948712493,
        "J48.001.Kappa": 0.4018784385761403,
        "MeanSkewnessOfNumericAtts": 17.770067223247146,
        "Quartile1StdDevOfNumericAtts": 1.1308723782553525,
        "REPTreeDepth2ErrRate": 0.006761039509824636,
        "CfsSubsetEval_kNN1NKappa": 0.19827221140001644,
        "kNN1NErrRate": 0.007394886963870695,
        "MajorityClassPercentage": 99.28163955208113,
        "MeanStdDevOfNumericAtts": 12709.178607947197,
        "Quartile2AttributeEntropy": null,
        "Quartile2KurtosisOfNumericAtts": 216.1805602712595,
        "REPTreeDepth2Kappa": 0.19827221140001644,
        "ClassEntropy": 0.061481432634126504,
        "kNN1NKappa": 0.42255740264991665,
        "MajorityClassSize": 9398,
        "MinAttributeEntropy": null,
        "Quartile2MeansOfNumericAtts": 1.7913057257553378,
        "REPTreeDepth3AUC": 0.7256730155352202,
        "DecisionStumpAUC": 0.8342724672333287,
        "MaxAttributeEntropy": null,
        "MinKurtosisOfNumericAtts": -1.9570627744160565,
        "Quartile2MutualInformation": null,
        "REPTreeDepth3ErrRate": 0.006761039509824636,
        "DecisionStumpErrRate": 0.007183604479188675,
        "MaxKurtosisOfNumericAtts": 4585.198186427769,
        "MinMeansOfNumericAtts": 0.012360025353898288,
        "Quartile2SkewnessOfNumericAtts": 10.24950686540491,
        "REPTreeDepth3Kappa": 0.19827221140001644,
        "DecisionStumpKappa": 0,
        "MaxMeansOfNumericAtts": 12649.49864673551,
        "MinMutualInformation": null,
        "Quartile2StdDevOfNumericAtts": 6.337704611173707,
        "RandomTreeDepth1AUC": 0.6880109034462902,
        "Dimensionality": 0.004120008451299387,
        "MaxMutualInformation": null,
        "MinNominalAttDistinctValues": 2,
        "PercentageOfBinaryFeatures": 2.564102564102564,
        "Quartile3AttributeEntropy": null,
        "RandomTreeDepth1ErrRate": 0.007606169448552715,
        "EquivalentNumberOfAtts": null,
        "MaxNominalAttDistinctValues": 2,
        "MinSkewnessOfNumericAtts": -1.975756600767764,
        "PercentageOfInstancesWithMissingValues": 0,
        "Quartile3KurtosisOfNumericAtts": 1203.1397673884478,
        "AutoCorrelation": 0.9856312731114633,
        "RandomTreeDepth1Kappa": 0.39624112369424075,
        "J48.00001.AUC": 0.7493224465781205,
        "MaxSkewnessOfNumericAtts": 67.26034868945209,
        "MinStdDevOfNumericAtts": 0.11049228413329988,
        "PercentageOfMissingValues": 0,
        "Quartile3MeansOfNumericAtts": 7.256002007183611,
        "CfsSubsetEval_DecisionStumpAUC": 0.635311956235995,
        "RandomTreeDepth2AUC": 0.6880109034462902,
        "J48.00001.ErrRate": 0.005915909571096556,
        "MaxStdDevOfNumericAtts": 456367.9352694624,
        "MinorityClassPercentage": 0.7183604479188676,
        "PercentageOfNumericFeatures": 97.43589743589743
    },
    "tags": [
        {
            "uploader": "38960",
            "tag": "Computer Science"
        },
        {
            "uploader": "38960",
            "tag": "Data Science"
        },
        {
            "uploader": "38960",
            "tag": "Engineering"
        },
        {
            "uploader": "1",
            "tag": "mythbusting_1"
        },
        {
            "uploader": "24659",
            "tag": "PROMISE"
        },
        {
            "uploader": "2",
            "tag": "study_1"
        },
        {
            "uploader": "939",
            "tag": "study_15"
        },
        {
            "uploader": "939",
            "tag": "study_20"
        },
        {
            "uploader": "1",
            "tag": "study_41"
        },
        {
            "uploader": "64",
            "tag": "study_52"
        },
        {
            "uploader": "64",
            "tag": "study_7"
        }
    ],
    "features": [
        {
            "name": "c",
            "index": "38",
            "type": "nominal",
            "distinct": "2",
            "missing": "0",
            "target": "1",
            "distr": [
                [
                    "FALSE",
                    "TRUE"
                ],
                [
                    [
                        "9398",
                        "0"
                    ],
                    [
                        "0",
                        "68"
                    ]
                ]
            ]
        },
        {
            "name": "LOC_BLANK",
            "index": "0",
            "type": "numeric",
            "distinct": "45",
            "missing": "0",
            "min": "0",
            "max": "87",
            "mean": "2",
            "stdev": "5"
        },
        {
            "name": "BRANCH_COUNT",
            "index": "1",
            "type": "numeric",
            "distinct": "50",
            "missing": "0",
            "min": "1",
            "max": "351",
            "mean": "3",
            "stdev": "8"
        },
        {
            "name": "CALL_PAIRS",
            "index": "2",
            "type": "numeric",
            "distinct": "33",
            "missing": "0",
            "min": "0",
            "max": "72",
            "mean": "1",
            "stdev": "3"
        },
        {
            "name": "LOC_CODE_AND_COMMENT",
            "index": "3",
            "type": "numeric",
            "distinct": "35",
            "missing": "0",
            "min": "0",
            "max": "98",
            "mean": "1",
            "stdev": "4"
        },
        {
            "name": "LOC_COMMENTS",
            "index": "4",
            "type": "numeric",
            "distinct": "54",
            "missing": "0",
            "min": "0",
            "max": "117",
            "mean": "2",
            "stdev": "7"
        },
        {
            "name": "CONDITION_COUNT",
            "index": "5",
            "type": "numeric",
            "distinct": "50",
            "missing": "0",
            "min": "0",
            "max": "630",
            "mean": "3",
            "stdev": "13"
        },
        {
            "name": "CYCLOMATIC_COMPLEXITY",
            "index": "6",
            "type": "numeric",
            "distinct": "34",
            "missing": "0",
            "min": "1",
            "max": "192",
            "mean": "2",
            "stdev": "4"
        },
        {
            "name": "CYCLOMATIC_DENSITY",
            "index": "7",
            "type": "numeric",
            "distinct": "60",
            "missing": "0",
            "min": "0",
            "max": "1",
            "mean": "1",
            "stdev": "0"
        },
        {
            "name": "DECISION_COUNT",
            "index": "8",
            "type": "numeric",
            "distinct": "28",
            "missing": "0",
            "min": "0",
            "max": "312",
            "mean": "2",
            "stdev": "6"
        },
        {
            "name": "DESIGN_COMPLEXITY",
            "index": "9",
            "type": "numeric",
            "distinct": "28",
            "missing": "0",
            "min": "1",
            "max": "186",
            "mean": "2",
            "stdev": "3"
        },
        {
            "name": "DESIGN_DENSITY",
            "index": "10",
            "type": "numeric",
            "distinct": "2",
            "missing": "0",
            "min": "0",
            "max": "1",
            "mean": "1",
            "stdev": "0"
        },
        {
            "name": "EDGE_COUNT",
            "index": "11",
            "type": "numeric",
            "distinct": "103",
            "missing": "0",
            "min": "1",
            "max": "929",
            "mean": "7",
            "stdev": "20"
        },
        {
            "name": "ESSENTIAL_COMPLEXITY",
            "index": "12",
            "type": "numeric",
            "distinct": "18",
            "missing": "0",
            "min": "1",
            "max": "22",
            "mean": "1",
            "stdev": "1"
        },
        {
            "name": "ESSENTIAL_DENSITY",
            "index": "13",
            "type": "numeric",
            "distinct": "2",
            "missing": "0",
            "min": "0",
            "max": "1",
            "mean": "0",
            "stdev": "0"
        },
        {
            "name": "LOC_EXECUTABLE",
            "index": "14",
            "type": "numeric",
            "distinct": "106",
            "missing": "0",
            "min": "0",
            "max": "578",
            "mean": "6",
            "stdev": "17"
        },
        {
            "name": "PARAMETER_COUNT",
            "index": "15",
            "type": "numeric",
            "distinct": "11",
            "missing": "0",
            "min": "0",
            "max": "10",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "GLOBAL_DATA_COMPLEXITY",
            "index": "16",
            "type": "numeric",
            "distinct": "24",
            "missing": "0",
            "min": "0",
            "max": "192",
            "mean": "1",
            "stdev": "3"
        },
        {
            "name": "GLOBAL_DATA_DENSITY",
            "index": "17",
            "type": "numeric",
            "distinct": "2",
            "missing": "0",
            "min": "0",
            "max": "1",
            "mean": "0",
            "stdev": "0"
        },
        {
            "name": "HALSTEAD_CONTENT",
            "index": "18",
            "type": "numeric",
            "distinct": "1026",
            "missing": "0",
            "min": "0",
            "max": "253",
            "mean": "14",
            "stdev": "18"
        },
        {
            "name": "HALSTEAD_DIFFICULTY",
            "index": "19",
            "type": "numeric",
            "distinct": "677",
            "missing": "0",
            "min": "0",
            "max": "834",
            "mean": "6",
            "stdev": "16"
        },
        {
            "name": "HALSTEAD_EFFORT",
            "index": "20",
            "type": "numeric",
            "distinct": "1148",
            "missing": "0",
            "min": "0",
            "max": "31159818",
            "mean": "12649",
            "stdev": "456368"
        },
        {
            "name": "HALSTEAD_ERROR_EST",
            "index": "21",
            "type": "numeric",
            "distinct": "121",
            "missing": "0",
            "min": "0",
            "max": "12",
            "mean": "0",
            "stdev": "0"
        },
        {
            "name": "HALSTEAD_LENGTH",
            "index": "22",
            "type": "numeric",
            "distinct": "290",
            "missing": "0",
            "min": "0",
            "max": "5227",
            "mean": "35",
            "stdev": "114"
        },
        {
            "name": "HALSTEAD_LEVEL",
            "index": "23",
            "type": "numeric",
            "distinct": "50",
            "missing": "0",
            "min": "0",
            "max": "2",
            "mean": "0",
            "stdev": "0"
        },
        {
            "name": "HALSTEAD_PROG_TIME",
            "index": "24",
            "type": "numeric",
            "distinct": "1138",
            "missing": "0",
            "min": "0",
            "max": "1731101",
            "mean": "703",
            "stdev": "25354"
        },
        {
            "name": "HALSTEAD_VOLUME",
            "index": "25",
            "type": "numeric",
            "distinct": "880",
            "missing": "0",
            "min": "0",
            "max": "37372",
            "mean": "175",
            "stdev": "763"
        },
        {
            "name": "MAINTENANCE_SEVERITY",
            "index": "26",
            "type": "numeric",
            "distinct": "2",
            "missing": "0",
            "min": "0",
            "max": "1",
            "mean": "1",
            "stdev": "0"
        },
        {
            "name": "MODIFIED_CONDITION_COUNT",
            "index": "27",
            "type": "numeric",
            "distinct": "32",
            "missing": "0",
            "min": "0",
            "max": "159",
            "mean": "1",
            "stdev": "3"
        },
        {
            "name": "MULTIPLE_CONDITION_COUNT",
            "index": "28",
            "type": "numeric",
            "distinct": "50",
            "missing": "0",
            "min": "0",
            "max": "315",
            "mean": "2",
            "stdev": "6"
        },
        {
            "name": "NODE_COUNT",
            "index": "29",
            "type": "numeric",
            "distinct": "88",
            "missing": "0",
            "min": "2",
            "max": "739",
            "mean": "7",
            "stdev": "16"
        },
        {
            "name": "NORMALIZED_CYLOMATIC_COMPLEXITY",
            "index": "30",
            "type": "numeric",
            "distinct": "48",
            "missing": "0",
            "min": "0",
            "max": "2",
            "mean": "1",
            "stdev": "0"
        },
        {
            "name": "NUM_OPERANDS",
            "index": "31",
            "type": "numeric",
            "distinct": "184",
            "missing": "0",
            "min": "0",
            "max": "2279",
            "mean": "14",
            "stdev": "48"
        },
        {
            "name": "NUM_OPERATORS",
            "index": "32",
            "type": "numeric",
            "distinct": "220",
            "missing": "0",
            "min": "0",
            "max": "2948",
            "mean": "21",
            "stdev": "66"
        },
        {
            "name": "NUM_UNIQUE_OPERANDS",
            "index": "33",
            "type": "numeric",
            "distinct": "82",
            "missing": "0",
            "min": "0",
            "max": "197",
            "mean": "6",
            "stdev": "10"
        },
        {
            "name": "NUM_UNIQUE_OPERATORS",
            "index": "34",
            "type": "numeric",
            "distinct": "46",
            "missing": "0",
            "min": "0",
            "max": "100",
            "mean": "6",
            "stdev": "5"
        },
        {
            "name": "NUMBER_OF_LINES",
            "index": "35",
            "type": "numeric",
            "distinct": "147",
            "missing": "0",
            "min": "1",
            "max": "727",
            "mean": "12",
            "stdev": "28"
        },
        {
            "name": "PERCENT_COMMENTS",
            "index": "36",
            "type": "numeric",
            "distinct": "322",
            "missing": "0",
            "min": "0",
            "max": "96",
            "mean": "8",
            "stdev": "17"
        },
        {
            "name": "LOC_TOTAL",
            "index": "37",
            "type": "numeric",
            "distinct": "112",
            "missing": "0",
            "min": "0",
            "max": "639",
            "mean": "7",
            "stdev": "19"
        }
    ],
    "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
}