{
    "data_id": "43552",
    "name": "Case-Study-Applicants-for-a-Gold-Digger-position",
    "exact_name": "Case-Study-Applicants-for-a-Gold-Digger-position",
    "version": 1,
    "version_label": "v1.0",
    "description": "Context\nThis dataframe describes applications for a Gold Digger position. According to each applicants's characteristics, can you create the best model to classify whether a candidate is hired or not ?\nIt is a good playground to harden your data science skills and try new models. Ideal to prepare interviews.\nContent\nThis dataframe contains 20000 observations and 11 columns:\n\ndate: date of the application\nage: age of the candidate\ndiplome: highest qualification diploma (bac, licence, master, doctorat)\nspecialite: minor of the diploma (geologie, forage, detective, archeologie,)\nsalaire: salary expectation\ndispo: oui : directly available, non : not directly available\nsexe: female (F) or male (M)\nexp: years of relevant experience\ncheveux: hair color (chatain, brun, blond, roux)\nnote: grade (out of 100) for gold digging exam\nembauche: Has the candidate been hired ? (0 : no, 1 : yes)",
    "format": "arff",
    "uploader": "Onur Yildirim",
    "uploader_id": 30126,
    "visibility": "public",
    "creator": null,
    "contributor": null,
    "date": "2022-03-23 13:49:16",
    "update_comment": null,
    "last_update": "2022-03-23 13:49:16",
    "licence": "CC0: Public Domain",
    "status": "active",
    "error_message": null,
    "url": "https:\/\/www.openml.org\/data\/download\/22102377\/dataset",
    "default_target_attribute": null,
    "row_id_attribute": null,
    "ignore_attribute": null,
    "runs": 0,
    "suggest": {
        "input": [
            "Case-Study-Applicants-for-a-Gold-Digger-position",
            "Context This dataframe describes applications for a Gold Digger position. According to each applicants's characteristics, can you create the best model to classify whether a candidate is hired or not ? It is a good playground to harden your data science skills and try new models. Ideal to prepare interviews. Content This dataframe contains 20000 observations and 11 columns: date: date of the application age: age of the candidate diplome: highest qualification diploma (bac, licence, master, docto "
        ],
        "weight": 5
    },
    "qualities": {
        "NumberOfInstances": 20000,
        "NumberOfFeatures": 12,
        "NumberOfClasses": null,
        "NumberOfMissingValues": 999,
        "NumberOfInstancesWithMissingValues": 979,
        "NumberOfNumericFeatures": 6,
        "NumberOfSymbolicFeatures": 0,
        "Dimensionality": 0.0006,
        "PercentageOfNumericFeatures": 50,
        "MajorityClassPercentage": null,
        "PercentageOfSymbolicFeatures": 0,
        "MajorityClassSize": null,
        "MinorityClassPercentage": null,
        "MinorityClassSize": null,
        "NumberOfBinaryFeatures": 0,
        "PercentageOfBinaryFeatures": 0,
        "PercentageOfInstancesWithMissingValues": 4.8950000000000005,
        "AutoCorrelation": null,
        "PercentageOfMissingValues": 0.41625000000000006
    },
    "tags": [
        {
            "uploader": "38960",
            "tag": "Machine Learning"
        }
    ],
    "features": [
        {
            "name": "Unnamed:_0",
            "index": "0",
            "type": "numeric",
            "distinct": "20000",
            "missing": "0",
            "min": "0",
            "max": "19999",
            "mean": "10000",
            "stdev": "5774"
        },
        {
            "name": "date",
            "index": "1",
            "type": "string",
            "distinct": "1826",
            "missing": "91"
        },
        {
            "name": "cheveux",
            "index": "2",
            "type": "string",
            "distinct": "4",
            "missing": "103"
        },
        {
            "name": "age",
            "index": "3",
            "type": "numeric",
            "distinct": "76",
            "missing": "91",
            "min": "-3",
            "max": "74",
            "mean": "35",
            "stdev": "10"
        },
        {
            "name": "exp",
            "index": "4",
            "type": "numeric",
            "distinct": "25",
            "missing": "96",
            "min": "-2",
            "max": "23",
            "mean": "10",
            "stdev": "3"
        },
        {
            "name": "salaire",
            "index": "5",
            "type": "numeric",
            "distinct": "12326",
            "missing": "95",
            "min": "14128",
            "max": "53977",
            "mean": "34974",
            "stdev": "5003"
        },
        {
            "name": "sexe",
            "index": "6",
            "type": "string",
            "distinct": "2",
            "missing": "100"
        },
        {
            "name": "diplome",
            "index": "7",
            "type": "string",
            "distinct": "4",
            "missing": "110"
        },
        {
            "name": "specialite",
            "index": "8",
            "type": "string",
            "distinct": "4",
            "missing": "93"
        },
        {
            "name": "note",
            "index": "9",
            "type": "numeric",
            "distinct": "6679",
            "missing": "114",
            "min": "9",
            "max": "143",
            "mean": "75",
            "stdev": "17"
        },
        {
            "name": "dispo",
            "index": "10",
            "type": "string",
            "distinct": "2",
            "missing": "106"
        },
        {
            "name": "embauche",
            "index": "11",
            "type": "numeric",
            "distinct": "2",
            "missing": "0",
            "min": "0",
            "max": "1",
            "mean": "0",
            "stdev": "0"
        }
    ],
    "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
}