{
    "data_id": "44044",
    "name": "diamonds",
    "exact_name": "diamonds",
    "version": 4,
    "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 \nThis classic dataset contains the prices and other attributes of almost 54,000 diamonds. It's a great dataset for beginners learning to work with data analysis and visualization.\n\nContent\nprice price in US dollars (\\$326--\\$18,823)\n\ncarat weight of the diamond (0.2--5.01)\n\ncut quality of the cut (Fair, Good, Very Good, Premium, Ideal)\n\ncolor diamond colour, from J (worst) to D (best)\n\nclarity a measurement of how clear the diamond is (I1 (worst), SI2, SI1, VS2, VS1, VVS2, VVS1, IF (best))\n\nx length in mm (0--10.74)\n\ny width in mm (0--58.9)\n\nz depth in mm (0--31.8)\n\ndepth total depth percentage = z \/ mean(x, y) = 2 * z \/ (x + y) (43--79)\n\ntable width of top of diamond relative to widest point (43--95)",
    "format": "arff",
    "uploader": "Leo Grin",
    "uploader_id": 26324,
    "visibility": "public",
    "creator": null,
    "contributor": "\"Leo Grin\"",
    "date": "2022-06-18 13:09:10",
    "update_comment": null,
    "last_update": "2022-06-18 13:09:10",
    "licence": "public domain",
    "status": "active",
    "error_message": null,
    "url": "https:\/\/old.openml.org\/data\/download\/22103132\/dataset",
    "default_target_attribute": "price",
    "row_id_attribute": null,
    "ignore_attribute": null,
    "runs": 0,
    "suggest": {
        "input": [
            "diamonds",
            "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: This classic dataset contains the prices and other attributes of almost 54,000 diamonds. It's a great dataset for beginners learning to work with data analysis and visualization. Content price price in US dollars (\\$326--\\$18,823) carat weight of the diamond (0.2--5.01) "
        ],
        "weight": 5
    },
    "qualities": {
        "NumberOfInstances": 53940,
        "NumberOfFeatures": 10,
        "NumberOfClasses": 0,
        "NumberOfMissingValues": 0,
        "NumberOfInstancesWithMissingValues": 0,
        "NumberOfNumericFeatures": 7,
        "NumberOfSymbolicFeatures": 3,
        "MinorityClassSize": null,
        "NumberOfBinaryFeatures": 0,
        "PercentageOfBinaryFeatures": 0,
        "PercentageOfInstancesWithMissingValues": 0,
        "AutoCorrelation": 0.9897643952458033,
        "PercentageOfMissingValues": 0,
        "Dimensionality": 0.0001853911753800519,
        "PercentageOfNumericFeatures": 70,
        "MajorityClassPercentage": null,
        "PercentageOfSymbolicFeatures": 30,
        "MajorityClassSize": null,
        "MinorityClassPercentage": null
    },
    "tags": [
        {
            "uploader": "38960",
            "tag": "Computer Systems"
        },
        {
            "uploader": "38960",
            "tag": "Machine Learning"
        }
    ],
    "features": [
        {
            "name": "price",
            "index": "9",
            "type": "numeric",
            "distinct": "11602",
            "missing": "0",
            "target": "1",
            "min": "6",
            "max": "10",
            "mean": "8",
            "stdev": "1"
        },
        {
            "name": "carat",
            "index": "0",
            "type": "numeric",
            "distinct": "273",
            "missing": "0",
            "min": "0",
            "max": "5",
            "mean": "1",
            "stdev": "0"
        },
        {
            "name": "cut",
            "index": "1",
            "type": "nominal",
            "distinct": "5",
            "missing": "0",
            "distr": []
        },
        {
            "name": "color",
            "index": "2",
            "type": "nominal",
            "distinct": "7",
            "missing": "0",
            "distr": []
        },
        {
            "name": "clarity",
            "index": "3",
            "type": "nominal",
            "distinct": "8",
            "missing": "0",
            "distr": []
        },
        {
            "name": "depth",
            "index": "4",
            "type": "numeric",
            "distinct": "184",
            "missing": "0",
            "min": "43",
            "max": "79",
            "mean": "62",
            "stdev": "1"
        },
        {
            "name": "table",
            "index": "5",
            "type": "numeric",
            "distinct": "127",
            "missing": "0",
            "min": "43",
            "max": "95",
            "mean": "57",
            "stdev": "2"
        },
        {
            "name": "x",
            "index": "6",
            "type": "numeric",
            "distinct": "554",
            "missing": "0",
            "min": "0",
            "max": "11",
            "mean": "6",
            "stdev": "1"
        },
        {
            "name": "y",
            "index": "7",
            "type": "numeric",
            "distinct": "552",
            "missing": "0",
            "min": "0",
            "max": "59",
            "mean": "6",
            "stdev": "1"
        },
        {
            "name": "z",
            "index": "8",
            "type": "numeric",
            "distinct": "375",
            "missing": "0",
            "min": "0",
            "max": "32",
            "mean": "4",
            "stdev": "1"
        }
    ],
    "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
}