{
    "data_id": "8",
    "name": "liver-disorders",
    "exact_name": "liver-disorders",
    "version": 1,
    "version_label": "1",
    "description": "**Author**: BUPA Medical Research Ltd. Donor: Richard S. Forsyth   \n**Source**: [UCI](https:\/\/archive.ics.uci.edu\/ml\/datasets\/Liver+Disorders) - 5\/15\/1990  \n**Please cite**: \n\n**BUPA liver disorders**\n \nThe first 5 variables are all blood tests which are thought to be sensitive to liver disorders that might arise from excessive alcohol consumption.  Each line in the dataset constitutes the record of a single male individual. \n\n**Important note:** The 7th field (selector) has been widely misinterpreted in the past as a dependent variable representing presence or absence of a liver disorder. This is incorrect [1]. The 7th field was created by BUPA researchers as a train\/test selector. It is not suitable as a dependent variable for classification. The dataset does not contain any variable representing presence or absence of a liver disorder. Researchers who wish to use this dataset as a classification benchmark should follow the method used in experiments by the donor (Forsyth & Rada, 1986, Machine learning: applications in expert systems and information retrieval) and others (e.g. Turney, 1995, Cost-sensitive classification: Empirical evaluation of a hybrid genetic decision tree induction algorithm), who used the 6th field (drinks), after dichotomising, as a dependent variable for classification. Because of widespread misinterpretation in the past, researchers should take care to state their method clearly.\n \n**Attribute information**  \n    1. mcv mean corpuscular volume  \n    2. alkphos alkaline phosphotase  \n    3. sgpt alanine aminotransferase  \n    4. sgot  aspartate aminotransferase  \n    5. gammagt gamma-glutamyl transpeptidase  \n    6. drinks number of half-pint equivalents of alcoholic beverages drunk per day  \n    7. selector field created by the BUPA researchers to split the data into train\/test sets  \n\n[1] McDermott & Forsyth 2016, Diagnosing a disorder in a classification benchmark, Pattern Recognition Letters, Volume 73. Note Forsyth is named on the UCI page as the original donor of the dataset.",
    "format": "ARFF",
    "uploader": "Jan van Rijn",
    "uploader_id": 1,
    "visibility": "public",
    "creator": "BUPA Medical Research Ltd",
    "contributor": "Richard S. Forsyth",
    "date": "2014-04-06 23:19:46",
    "update_comment": "Selector is the field used to define a pre-defined train-test split, should be ignored.",
    "last_update": "2015-08-21 13:26:43",
    "licence": "Public",
    "status": "active",
    "error_message": null,
    "url": "https:\/\/www.openml.org\/data\/download\/8\/dataset_8_liver-disorders.arff",
    "default_target_attribute": "drinks",
    "row_id_attribute": null,
    "ignore_attribute": "\"selector\"",
    "runs": 238,
    "suggest": {
        "input": [
            "liver-disorders",
            "The first 5 variables are all blood tests which are thought to be sensitive to liver disorders that might arise from excessive alcohol consumption. Each line in the dataset constitutes the record of a single male individual. 1. mcv mean corpuscular volume 2. alkphos alkaline phosphotase 3. sgpt alanine aminotransferase 4. sgot aspartate aminotransferase 5. gammagt gamma-glutamyl transpeptidase 6. drinks number of half-pint equivalents of alcoholic beverages drunk per day 7. selector field create "
        ],
        "weight": 5
    },
    "qualities": {
        "NumberOfInstances": 345,
        "NumberOfFeatures": 6,
        "NumberOfClasses": 0,
        "NumberOfMissingValues": 0,
        "NumberOfInstancesWithMissingValues": 0,
        "NumberOfNumericFeatures": 6,
        "NumberOfSymbolicFeatures": 0,
        "Quartile2AttributeEntropy": null,
        "REPTreeDepth2ErrRate": null,
        "CfsSubsetEval_kNN1NKappa": null,
        "kNN1NErrRate": null,
        "MajorityClassPercentage": null,
        "MeanStdDevOfNumericAtts": 15.827503400802176,
        "MinAttributeEntropy": null,
        "Quartile2KurtosisOfNumericAtts": 5.901776568203553,
        "REPTreeDepth2Kappa": null,
        "ClassEntropy": null,
        "kNN1NKappa": null,
        "MajorityClassSize": null,
        "MinKurtosisOfNumericAtts": 0.7478828309967818,
        "Quartile2MeansOfNumericAtts": 34.344927536231886,
        "REPTreeDepth3AUC": null,
        "DecisionStumpAUC": null,
        "MaxAttributeEntropy": null,
        "MinMeansOfNumericAtts": 3.4550724637681136,
        "Quartile2MutualInformation": null,
        "REPTreeDepth3ErrRate": null,
        "DecisionStumpErrRate": null,
        "MaxKurtosisOfNumericAtts": 13.813911752411268,
        "MinMutualInformation": null,
        "Quartile2SkewnessOfNumericAtts": 1.918445936350417,
        "REPTreeDepth3Kappa": null,
        "DecisionStumpKappa": null,
        "MaxMeansOfNumericAtts": 90.15942028985508,
        "MinNominalAttDistinctValues": null,
        "PercentageOfBinaryFeatures": 0,
        "Quartile2StdDevOfNumericAtts": 14.206082045720775,
        "RandomTreeDepth1AUC": null,
        "Dimensionality": 0.017391304347826087,
        "MaxMutualInformation": null,
        "MinSkewnessOfNumericAtts": -0.38843312376254074,
        "PercentageOfInstancesWithMissingValues": 0,
        "Quartile3AttributeEntropy": null,
        "RandomTreeDepth1ErrRate": null,
        "EquivalentNumberOfAtts": null,
        "MaxNominalAttDistinctValues": null,
        "MinStdDevOfNumericAtts": 3.337835264577127,
        "PercentageOfMissingValues": 0,
        "Quartile3KurtosisOfNumericAtts": 11.31103980397396,
        "AutoCorrelation": 0.8255813953488372,
        "RandomTreeDepth1Kappa": null,
        "J48.00001.AUC": null,
        "MaxSkewnessOfNumericAtts": 3.063498642355853,
        "MinorityClassPercentage": null,
        "PercentageOfNumericFeatures": 100,
        "Quartile3MeansOfNumericAtts": 74.94202898550725,
        "CfsSubsetEval_DecisionStumpAUC": null,
        "RandomTreeDepth2AUC": null,
        "J48.00001.ErrRate": null,
        "MaxStdDevOfNumericAtts": 39.25461616755085,
        "MinorityClassSize": null,
        "PercentageOfSymbolicFeatures": 0,
        "Quartile3MutualInformation": null,
        "CfsSubsetEval_DecisionStumpErrRate": null,
        "RandomTreeDepth2ErrRate": null,
        "J48.00001.Kappa": null,
        "MeanAttributeEntropy": null,
        "NaiveBayesAUC": null,
        "Quartile1AttributeEntropy": null,
        "Quartile3SkewnessOfNumericAtts": 2.9154448302673353,
        "CfsSubsetEval_DecisionStumpKappa": null,
        "RandomTreeDepth2Kappa": null,
        "J48.0001.AUC": null,
        "MeanKurtosisOfNumericAtts": 6.57117573055445,
        "NaiveBayesErrRate": null,
        "Quartile1KurtosisOfNumericAtts": 2.1256888395117097,
        "Quartile3StdDevOfNumericAtts": 24.44788572159709,
        "CfsSubsetEval_NaiveBayesAUC": null,
        "RandomTreeDepth3AUC": null,
        "J48.0001.ErrRate": null,
        "MeanMeansOfNumericAtts": 42.802898550724635,
        "NaiveBayesKappa": null,
        "Quartile1MeansOfNumericAtts": 19.346376811594208,
        "REPTreeDepth1AUC": null,
        "CfsSubsetEval_NaiveBayesErrRate": null,
        "RandomTreeDepth3ErrRate": null,
        "J48.0001.Kappa": null,
        "MeanMutualInformation": null,
        "NumberOfBinaryFeatures": 0,
        "Quartile1MutualInformation": null,
        "REPTreeDepth1ErrRate": null,
        "CfsSubsetEval_NaiveBayesKappa": null,
        "RandomTreeDepth3Kappa": null,
        "J48.001.AUC": null,
        "MeanNoiseToSignalRatio": null,
        "Quartile1SkewnessOfNumericAtts": 0.4681417978731725,
        "REPTreeDepth1Kappa": null,
        "CfsSubsetEval_kNN1NAUC": null,
        "StdvNominalAttDistinctValues": null,
        "J48.001.ErrRate": null,
        "MeanNominalAttDistinctValues": null,
        "Quartile1StdDevOfNumericAtts": 4.170530797367548,
        "REPTreeDepth2AUC": null,
        "CfsSubsetEval_kNN1NErrRate": null,
        "kNN1NAUC": null,
        "J48.001.Kappa": null,
        "MeanSkewnessOfNumericAtts": 1.6886196204361754
    },
    "tags": [
        {
            "uploader": "38960",
            "tag": "Health"
        },
        {
            "uploader": "38960",
            "tag": "Medicine"
        },
        {
            "uploader": "4209",
            "tag": "study_127"
        },
        {
            "uploader": "64",
            "tag": "study_50"
        },
        {
            "uploader": "4209",
            "tag": "study_88"
        },
        {
            "uploader": "1",
            "tag": "uci"
        }
    ],
    "features": [
        {
            "name": "drinks",
            "index": "5",
            "type": "numeric",
            "distinct": "16",
            "missing": "0",
            "target": "1",
            "min": "0",
            "max": "20",
            "mean": "3",
            "stdev": "3"
        },
        {
            "name": "mcv",
            "index": "0",
            "type": "numeric",
            "distinct": "26",
            "missing": "0",
            "min": "65",
            "max": "103",
            "mean": "90",
            "stdev": "4"
        },
        {
            "name": "alkphos",
            "index": "1",
            "type": "numeric",
            "distinct": "78",
            "missing": "0",
            "min": "23",
            "max": "138",
            "mean": "70",
            "stdev": "18"
        },
        {
            "name": "sgpt",
            "index": "2",
            "type": "numeric",
            "distinct": "67",
            "missing": "0",
            "min": "4",
            "max": "155",
            "mean": "30",
            "stdev": "20"
        },
        {
            "name": "sgot",
            "index": "3",
            "type": "numeric",
            "distinct": "47",
            "missing": "0",
            "min": "5",
            "max": "82",
            "mean": "25",
            "stdev": "10"
        },
        {
            "name": "gammagt",
            "index": "4",
            "type": "numeric",
            "distinct": "94",
            "missing": "0",
            "min": "5",
            "max": "297",
            "mean": "38",
            "stdev": "39"
        },
        {
            "name": "selector",
            "index": "6",
            "type": "nominal",
            "distinct": "2",
            "missing": "0",
            "ignore": "1",
            "distr": []
        }
    ],
    "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
}