{
    "data_id": "44040",
    "name": "analcatdata_supreme",
    "exact_name": "analcatdata_supreme",
    "version": 3,
    "version_label": null,
    "description": "Dataset used in the tabular data benchmark https:\/\/github.com\/LeoGrin\/tabular-benchmark,  \n                                  transformed in the same way. This dataset belongs to the \"regression on categorical and\n                                  numerical features\" benchmark. Original description: \n \n**Author**:   \n**Source**: Unknown - Date unknown  \n**Please cite**:   \n\nanalcatdata    A collection of data sets used in the book \"Analyzing Categorical Data,\"\nby Jeffrey S. Simonoff, Springer-Verlag, New York, 2003. The submission\nconsists of a zip file containing two versions of each of 84 data sets,\nplus this README file. Each data set is given in comma-delimited ASCII\n(.csv) form, and Microsoft Excel (.xls) form.\n\nNOTICE: These data sets may be used freely for scientific, educational and\/or\nnoncommercial purposes, provided suitable acknowledgment is given (by citing\nthe above-named reference).\n\nFurther details concerning the book, including information on statistical software\n(including sample S-PLUS\/R and SAS code), are available at the web site\n\nhttp:\/\/www.stern.nyu.edu\/~jsimonof\/AnalCatData\n\n\nInformation about the dataset\nCLASSTYPE: numeric\nCLASSINDEX: none specific\n\n\nNote: Quotes, Single-Quotes and Backslashes were removed, Blanks replaced\nwith Underscores",
    "format": "arff",
    "uploader": "Leo Grin",
    "uploader_id": 26324,
    "visibility": "public",
    "creator": "\"Jeffrey S. Simonoff\"",
    "contributor": "\"Leo Grin\"",
    "date": "2022-06-18 13:07:01",
    "update_comment": null,
    "last_update": "2022-06-18 13:07:01",
    "licence": "Public",
    "status": "active",
    "error_message": null,
    "url": "https:\/\/old.openml.org\/data\/download\/22103128\/dataset",
    "default_target_attribute": "Log_exposure",
    "row_id_attribute": null,
    "ignore_attribute": null,
    "runs": 0,
    "suggest": {
        "input": [
            "analcatdata_supreme",
            "Dataset used in the tabular data benchmark https:\/\/github.com\/LeoGrin\/tabular-benchmark, transformed in the same way. This dataset belongs to the \"regression on categorical and numerical features\" benchmark. Original description: analcatdata A collection of data sets used in the book \"Analyzing Categorical Data,\" by Jeffrey S. Simonoff, Springer-Verlag, New York, 2003. The submission consists of a zip file containing two versions of each of 84 data sets, plus this README file. Each data set is g "
        ],
        "weight": 5
    },
    "qualities": {
        "NumberOfInstances": 4052,
        "NumberOfFeatures": 8,
        "NumberOfClasses": 0,
        "NumberOfMissingValues": 0,
        "NumberOfInstancesWithMissingValues": 0,
        "NumberOfNumericFeatures": 3,
        "NumberOfSymbolicFeatures": 5,
        "PercentageOfBinaryFeatures": 62.5,
        "PercentageOfInstancesWithMissingValues": 0,
        "AutoCorrelation": 0.9796642804245866,
        "PercentageOfMissingValues": 0,
        "Dimensionality": 0.0019743336623889436,
        "PercentageOfNumericFeatures": 37.5,
        "MajorityClassPercentage": null,
        "PercentageOfSymbolicFeatures": 62.5,
        "MajorityClassSize": null,
        "MinorityClassPercentage": null,
        "MinorityClassSize": null,
        "NumberOfBinaryFeatures": 5
    },
    "tags": [
        {
            "uploader": "38960",
            "tag": "Computer Systems"
        },
        {
            "uploader": "38960",
            "tag": "Social Media"
        }
    ],
    "features": [
        {
            "name": "Log_exposure",
            "index": "7",
            "type": "numeric",
            "distinct": "10",
            "missing": "0",
            "target": "1",
            "min": "0",
            "max": "2",
            "mean": "2",
            "stdev": "1"
        },
        {
            "name": "Actions_taken",
            "index": "0",
            "type": "numeric",
            "distinct": "10",
            "missing": "0",
            "min": "0",
            "max": "11",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "Liberal",
            "index": "1",
            "type": "nominal",
            "distinct": "2",
            "missing": "0",
            "distr": []
        },
        {
            "name": "Unconstitutional",
            "index": "2",
            "type": "nominal",
            "distinct": "2",
            "missing": "0",
            "distr": []
        },
        {
            "name": "Precedent_alteration",
            "index": "3",
            "type": "nominal",
            "distinct": "2",
            "missing": "0",
            "distr": []
        },
        {
            "name": "Unanimous",
            "index": "4",
            "type": "nominal",
            "distinct": "2",
            "missing": "0",
            "distr": []
        },
        {
            "name": "Year_of_decision",
            "index": "5",
            "type": "numeric",
            "distinct": "36",
            "missing": "0",
            "min": "1953",
            "max": "1988",
            "mean": "1972",
            "stdev": "10"
        },
        {
            "name": "Lower_court_disagreement",
            "index": "6",
            "type": "nominal",
            "distinct": "2",
            "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
}