{
    "data_id": "46289",
    "name": "medical_cost",
    "exact_name": "medical_cost",
    "version": 1,
    "version_label": null,
    "description": "From original source:\n-----\n\nContext\nMachine Learning with R by Brett Lantz is a book that provides an introduction to machine learning using R. As far as I can tell, Packt Publishing does not make its datasets available online unless you buy the book and create a user account which can be a problem if you are checking the book out from the library or borrowing the book from a friend. All of these datasets are in the public domain but simply needed some cleaning up and recoding to match the format in the book.\n\nContent\nColumns\n\nage: age of primary beneficiary\n\nsex: insurance contractor gender, female, male\n\nbmi: Body mass index, providing an understanding of body, weights that are relatively high or low relative to height,\nobjective index of body weight (kg \/ m ^ 2) using the ratio of height to weight, ideally 18.5 to 24.9\n\nchildren: Number of children covered by health insurance \/ Number of dependents\n\nsmoker: Smoking\n\nregion: the beneficiary's residential area in the US, northeast, southeast, southwest, northwest.\n\ncharges: Individual medical costs billed by health insurance\n-----",
    "format": "arff",
    "uploader": "Bruno Belucci Teixeira",
    "uploader_id": 30703,
    "visibility": "public",
    "creator": "\"Miri Choi\"",
    "contributor": "\"Bruno Belucci\"",
    "date": "2024-07-23 18:00:52",
    "update_comment": null,
    "last_update": "2024-07-23 18:00:52",
    "licence": "Database: Open Database, Contents: Database Contents",
    "status": "active",
    "error_message": null,
    "url": "https:\/\/api.openml.org\/data\/download\/22120800\/dataset",
    "default_target_attribute": "charges",
    "row_id_attribute": null,
    "ignore_attribute": null,
    "runs": 0,
    "suggest": {
        "input": [
            "medical_cost",
            "From original source: ----- Context Machine Learning with R by Brett Lantz is a book that provides an introduction to machine learning using R. As far as I can tell, Packt Publishing does not make its datasets available online unless you buy the book and create a user account which can be a problem if you are checking the book out from the library or borrowing the book from a friend. All of these datasets are in the public domain but simply needed some cleaning up and recoding to match the forma "
        ],
        "weight": 5
    },
    "qualities": {
        "NumberOfInstances": 1338,
        "NumberOfFeatures": 7,
        "NumberOfClasses": 0,
        "NumberOfMissingValues": 0,
        "NumberOfInstancesWithMissingValues": 0,
        "NumberOfNumericFeatures": 3,
        "NumberOfSymbolicFeatures": 4,
        "AutoCorrelation": -12304.181128181002,
        "PercentageOfMissingValues": 0,
        "Dimensionality": 0.00523168908819133,
        "PercentageOfNumericFeatures": 42.857142857142854,
        "PercentageOfSymbolicFeatures": 57.14285714285714,
        "MajorityClassPercentage": null,
        "MajorityClassSize": null,
        "MinorityClassPercentage": null,
        "MinorityClassSize": null,
        "NumberOfBinaryFeatures": 2,
        "PercentageOfBinaryFeatures": 28.57142857142857,
        "PercentageOfInstancesWithMissingValues": 0
    },
    "tags": [],
    "features": [
        {
            "name": "charges",
            "index": "6",
            "type": "numeric",
            "distinct": "1337",
            "missing": "0",
            "target": "1",
            "min": "1122",
            "max": "63770",
            "mean": "13270",
            "stdev": "12110"
        },
        {
            "name": "age",
            "index": "0",
            "type": "nominal",
            "distinct": "47",
            "missing": "0",
            "distr": []
        },
        {
            "name": "sex",
            "index": "1",
            "type": "nominal",
            "distinct": "2",
            "missing": "0",
            "distr": []
        },
        {
            "name": "bmi",
            "index": "2",
            "type": "numeric",
            "distinct": "548",
            "missing": "0",
            "min": "16",
            "max": "53",
            "mean": "31",
            "stdev": "6"
        },
        {
            "name": "children",
            "index": "3",
            "type": "numeric",
            "distinct": "6",
            "missing": "0",
            "min": "0",
            "max": "5",
            "mean": "1",
            "stdev": "1"
        },
        {
            "name": "smoker",
            "index": "4",
            "type": "nominal",
            "distinct": "2",
            "missing": "0",
            "distr": []
        },
        {
            "name": "region",
            "index": "5",
            "type": "nominal",
            "distinct": "4",
            "missing": "0",
            "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
}