{
    "data_id": "44536",
    "name": "dionis_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True",
    "exact_name": "dionis_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True",
    "version": 1,
    "version_label": "def9e3a6-dcfa-45ca-85a7-69bb73fc5cb9",
    "description": "Subsampling of the dataset dionis (41167) with\n\nseed=3\nargs.nrows=2000\nargs.ncols=100\nargs.nclasses=10\nargs.no_stratify=True\nGenerated with the following source code:\n\n\n```python\n    def subsample(\n        self,\n        seed: int,\n        nrows_max: int = 2_000,\n        ncols_max: int = 100,\n        nclasses_max: int = 10,\n        stratified: bool = True,\n    ) -> Dataset:\n        rng = np.random.default_rng(seed)\n\n        x = self.x\n        y = self.y\n\n        # Uniformly sample\n        classes = y.unique()\n        if len(classes) > nclasses_max:\n            vcs = y.value_counts()\n            selected_classes = rng.choice(\n                classes,\n                size=nclasses_max,\n                replace=False,\n                p=vcs \/ sum(vcs),\n            )\n\n            # Select the indices where one of these classes is present\n            idxs = y.index[y.isin(classes)]\n            x = x.iloc[idxs]\n            y = y.iloc[idxs]\n\n        # Uniformly sample columns if required\n        if len(x.columns) > ncols_max:\n            columns_idxs = rng.choice(\n                list(range(len(x.columns))), size=ncols_max, replace=False\n            )\n            sorted_column_idxs = sorted(columns_idxs)\n            selected_columns = list(x.columns[sorted_column_idxs])\n            x = x[selected_columns]\n        else:\n            sorted_column_idxs = list(range(len(x.columns)))\n\n        if len(x) > nrows_max:\n            # Stratify accordingly\n            target_name = y.name\n            data = pd.concat((x, y), axis=\"columns\")\n            _, subset = train_test_split(\n                data,\n                test_size=nrows_max,\n                stratify=data[target_name],\n                shuffle=True,\n                random_state=seed,\n            )\n            x = subset.drop(target_name, axis=\"columns\")\n            y = subset[target_name]\n\n        # We need to convert categorical columns to string for openml\n        categorical_mask = [self.categorical_mask[i] for i in sorted_column_idxs]\n        columns = list(x.columns)\n\n        return Dataset(\n            # Technically this is not the same but it's where it was derived from\n            dataset=self.dataset,\n            x=x,\n            y=y,\n            categorical_mask=categorical_mask,\n            columns=columns,\n        )\n```",
    "format": "arff",
    "uploader": "Eddie Bergman",
    "uploader_id": 32840,
    "visibility": "public",
    "creator": "\"Eddie Bergman\"",
    "contributor": null,
    "date": "2022-11-17 18:26:16",
    "update_comment": null,
    "last_update": "2022-11-17 18:26:16",
    "licence": "Public",
    "status": "active",
    "error_message": null,
    "url": "https:\/\/api.openml.org\/data\/download\/22111298\/dataset",
    "default_target_attribute": "class",
    "row_id_attribute": null,
    "ignore_attribute": null,
    "runs": 0,
    "suggest": {
        "input": [
            "dionis_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True",
            "Subsampling of the dataset dionis (41167) with seed=3 args.nrows=2000 args.ncols=100 args.nclasses=10 args.no_stratify=True Generated with the following source code: ```python def subsample( self, seed: int, nrows_max: int = 2_000, ncols_max: int = 100, nclasses_max: int = 10, stratified: bool = True, ) -> Dataset: rng = np.random.default_rng(seed) x = self.x y = self.y # Uniformly sample classes = y.unique() if len(classes) > nclasses_max: vcs = y.value_counts() selected_classes = rng.choice( c "
        ],
        "weight": 5
    },
    "qualities": {
        "NumberOfInstances": 2000,
        "NumberOfFeatures": 61,
        "NumberOfClasses": 355,
        "NumberOfMissingValues": 0,
        "NumberOfInstancesWithMissingValues": 0,
        "NumberOfNumericFeatures": 60,
        "NumberOfSymbolicFeatures": 1,
        "MinorityClassSize": 4,
        "NumberOfBinaryFeatures": 0,
        "PercentageOfBinaryFeatures": 0,
        "PercentageOfInstancesWithMissingValues": 0,
        "AutoCorrelation": 0.002001000500250125,
        "PercentageOfMissingValues": 0,
        "Dimensionality": 0.0305,
        "PercentageOfNumericFeatures": 98.36065573770492,
        "MajorityClassPercentage": 0.6,
        "PercentageOfSymbolicFeatures": 1.639344262295082,
        "MajorityClassSize": 12,
        "MinorityClassPercentage": 0.2
    },
    "tags": [
        {
            "uploader": "38960",
            "tag": "Statistics"
        }
    ],
    "features": [
        {
            "name": "class",
            "index": "60",
            "type": "nominal",
            "distinct": "355",
            "missing": "0",
            "target": "1",
            "distr": []
        },
        {
            "name": "V1",
            "index": "0",
            "type": "numeric",
            "distinct": "1522",
            "missing": "0",
            "min": "5162",
            "max": "9913",
            "mean": "8340",
            "stdev": "1128"
        },
        {
            "name": "V2",
            "index": "1",
            "type": "numeric",
            "distinct": "1626",
            "missing": "0",
            "min": "-8329",
            "max": "6140",
            "mean": "-138",
            "stdev": "1385"
        },
        {
            "name": "V3",
            "index": "2",
            "type": "numeric",
            "distinct": "27",
            "missing": "0",
            "min": "-24061",
            "max": "64892",
            "mean": "10081",
            "stdev": "3383"
        },
        {
            "name": "V4",
            "index": "3",
            "type": "numeric",
            "distinct": "1811",
            "missing": "0",
            "min": "-20761400",
            "max": "2641050",
            "mean": "-10560",
            "stdev": "473186"
        },
        {
            "name": "V5",
            "index": "4",
            "type": "numeric",
            "distinct": "1161",
            "missing": "0",
            "min": "-2151",
            "max": "2114",
            "mean": "82",
            "stdev": "473"
        },
        {
            "name": "V6",
            "index": "5",
            "type": "numeric",
            "distinct": "26",
            "missing": "0",
            "min": "0",
            "max": "25951",
            "mean": "10101",
            "stdev": "1141"
        },
        {
            "name": "V7",
            "index": "6",
            "type": "numeric",
            "distinct": "1319",
            "missing": "0",
            "min": "-492464",
            "max": "49629400",
            "mean": "24543",
            "stdev": "1109824"
        },
        {
            "name": "V8",
            "index": "7",
            "type": "numeric",
            "distinct": "1846",
            "missing": "0",
            "min": "-158344000",
            "max": "2119040",
            "mean": "-78454",
            "stdev": "3541301"
        },
        {
            "name": "V9",
            "index": "8",
            "type": "numeric",
            "distinct": "1231",
            "missing": "0",
            "min": "-1891",
            "max": "3044",
            "mean": "142",
            "stdev": "564"
        },
        {
            "name": "V10",
            "index": "9",
            "type": "numeric",
            "distinct": "745",
            "missing": "0",
            "min": "-729",
            "max": "1462",
            "mean": "38",
            "stdev": "207"
        },
        {
            "name": "V11",
            "index": "10",
            "type": "numeric",
            "distinct": "1686",
            "missing": "0",
            "min": "489",
            "max": "10000",
            "mean": "6117",
            "stdev": "1506"
        },
        {
            "name": "V12",
            "index": "11",
            "type": "numeric",
            "distinct": "1536",
            "missing": "0",
            "min": "-226626000",
            "max": "303478",
            "mean": "-115605",
            "stdev": "5068009"
        },
        {
            "name": "V13",
            "index": "12",
            "type": "numeric",
            "distinct": "1804",
            "missing": "0",
            "min": "-10000",
            "max": "7048",
            "mean": "-5788",
            "stdev": "3667"
        },
        {
            "name": "V14",
            "index": "13",
            "type": "numeric",
            "distinct": "1",
            "missing": "0",
            "min": "0",
            "max": "0",
            "mean": "0",
            "stdev": "0"
        },
        {
            "name": "V15",
            "index": "14",
            "type": "numeric",
            "distinct": "1830",
            "missing": "0",
            "min": "-177031000",
            "max": "2123910",
            "mean": "-88910",
            "stdev": "3959267"
        },
        {
            "name": "V16",
            "index": "15",
            "type": "numeric",
            "distinct": "1459",
            "missing": "0",
            "min": "250",
            "max": "10000",
            "mean": "8226",
            "stdev": "1580"
        },
        {
            "name": "V17",
            "index": "16",
            "type": "numeric",
            "distinct": "1598",
            "missing": "0",
            "min": "840",
            "max": "10000",
            "mean": "7051",
            "stdev": "1929"
        },
        {
            "name": "V18",
            "index": "17",
            "type": "numeric",
            "distinct": "1506",
            "missing": "0",
            "min": "-2481000",
            "max": "58234200",
            "mean": "26933",
            "stdev": "1304451"
        },
        {
            "name": "V19",
            "index": "18",
            "type": "numeric",
            "distinct": "1624",
            "missing": "0",
            "min": "-3768",
            "max": "5462",
            "mean": "105",
            "stdev": "1338"
        },
        {
            "name": "V20",
            "index": "19",
            "type": "numeric",
            "distinct": "1073",
            "missing": "0",
            "min": "-1672",
            "max": "2362",
            "mean": "165",
            "stdev": "400"
        },
        {
            "name": "V21",
            "index": "20",
            "type": "numeric",
            "distinct": "962",
            "missing": "0",
            "min": "-1152",
            "max": "1372",
            "mean": "71",
            "stdev": "318"
        },
        {
            "name": "V22",
            "index": "21",
            "type": "numeric",
            "distinct": "979",
            "missing": "0",
            "min": "0",
            "max": "10000",
            "mean": "8899",
            "stdev": "1520"
        },
        {
            "name": "V23",
            "index": "22",
            "type": "numeric",
            "distinct": "1816",
            "missing": "0",
            "min": "-1140790",
            "max": "227866000",
            "mean": "138902",
            "stdev": "5149400"
        },
        {
            "name": "V24",
            "index": "23",
            "type": "numeric",
            "distinct": "1473",
            "missing": "0",
            "min": "-2563900",
            "max": "3435100",
            "mean": "390",
            "stdev": "108437"
        },
        {
            "name": "V25",
            "index": "24",
            "type": "numeric",
            "distinct": "620",
            "missing": "0",
            "min": "-594",
            "max": "700",
            "mean": "28",
            "stdev": "156"
        },
        {
            "name": "V26",
            "index": "25",
            "type": "numeric",
            "distinct": "879",
            "missing": "0",
            "min": "-1067",
            "max": "1668",
            "mean": "82",
            "stdev": "276"
        },
        {
            "name": "V27",
            "index": "26",
            "type": "numeric",
            "distinct": "1",
            "missing": "0",
            "min": "0",
            "max": "0",
            "mean": "0",
            "stdev": "0"
        },
        {
            "name": "V28",
            "index": "27",
            "type": "numeric",
            "distinct": "1744",
            "missing": "0",
            "min": "-9828",
            "max": "11903",
            "mean": "2270",
            "stdev": "2221"
        },
        {
            "name": "V29",
            "index": "28",
            "type": "numeric",
            "distinct": "1619",
            "missing": "0",
            "min": "141",
            "max": "10000",
            "mean": "7158",
            "stdev": "1844"
        },
        {
            "name": "V30",
            "index": "29",
            "type": "numeric",
            "distinct": "1643",
            "missing": "0",
            "min": "-2927100",
            "max": "48480000",
            "mean": "25022",
            "stdev": "1088760"
        },
        {
            "name": "V31",
            "index": "30",
            "type": "numeric",
            "distinct": "1461",
            "missing": "0",
            "min": "-3771",
            "max": "2992",
            "mean": "98",
            "stdev": "941"
        },
        {
            "name": "V32",
            "index": "31",
            "type": "numeric",
            "distinct": "1260",
            "missing": "0",
            "min": "2609",
            "max": "10000",
            "mean": "8709",
            "stdev": "1317"
        },
        {
            "name": "V33",
            "index": "32",
            "type": "numeric",
            "distinct": "1",
            "missing": "0",
            "min": "0",
            "max": "0",
            "mean": "0",
            "stdev": "0"
        },
        {
            "name": "V34",
            "index": "33",
            "type": "numeric",
            "distinct": "1610",
            "missing": "0",
            "min": "-3419",
            "max": "4674",
            "mean": "359",
            "stdev": "1393"
        },
        {
            "name": "V35",
            "index": "34",
            "type": "numeric",
            "distinct": "1",
            "missing": "0",
            "min": "0",
            "max": "0",
            "mean": "0",
            "stdev": "0"
        },
        {
            "name": "V36",
            "index": "35",
            "type": "numeric",
            "distinct": "1522",
            "missing": "0",
            "min": "87",
            "max": "4838",
            "mean": "1660",
            "stdev": "1128"
        },
        {
            "name": "V37",
            "index": "36",
            "type": "numeric",
            "distinct": "1",
            "missing": "0",
            "min": "0",
            "max": "0",
            "mean": "0",
            "stdev": "0"
        },
        {
            "name": "V38",
            "index": "37",
            "type": "numeric",
            "distinct": "1757",
            "missing": "0",
            "min": "-6992",
            "max": "10000",
            "mean": "6428",
            "stdev": "3427"
        },
        {
            "name": "V39",
            "index": "38",
            "type": "numeric",
            "distinct": "1485",
            "missing": "0",
            "min": "-2643",
            "max": "3709",
            "mean": "117",
            "stdev": "895"
        },
        {
            "name": "V40",
            "index": "39",
            "type": "numeric",
            "distinct": "1506",
            "missing": "0",
            "min": "-70917400",
            "max": "349843",
            "mean": "-36771",
            "stdev": "1586953"
        },
        {
            "name": "V41",
            "index": "40",
            "type": "numeric",
            "distinct": "1813",
            "missing": "0",
            "min": "-1014260",
            "max": "685646000",
            "mean": "343549",
            "stdev": "15331618"
        },
        {
            "name": "V42",
            "index": "41",
            "type": "numeric",
            "distinct": "1812",
            "missing": "0",
            "min": "-533800000",
            "max": "1896350",
            "mean": "-267045",
            "stdev": "11936317"
        },
        {
            "name": "V43",
            "index": "42",
            "type": "numeric",
            "distinct": "1626",
            "missing": "0",
            "min": "-170505000",
            "max": "114458",
            "mean": "-87577",
            "stdev": "3813056"
        },
        {
            "name": "V44",
            "index": "43",
            "type": "numeric",
            "distinct": "1262",
            "missing": "0",
            "min": "-2461",
            "max": "2433",
            "mean": "-714",
            "stdev": "571"
        },
        {
            "name": "V45",
            "index": "44",
            "type": "numeric",
            "distinct": "816",
            "missing": "0",
            "min": "-1020",
            "max": "1067",
            "mean": "48",
            "stdev": "233"
        },
        {
            "name": "V46",
            "index": "45",
            "type": "numeric",
            "distinct": "1736",
            "missing": "0",
            "min": "-593054",
            "max": "187997000",
            "mean": "93998",
            "stdev": "4203978"
        },
        {
            "name": "V47",
            "index": "46",
            "type": "numeric",
            "distinct": "770",
            "missing": "0",
            "min": "1030",
            "max": "10000",
            "mean": "9256",
            "stdev": "1224"
        },
        {
            "name": "V48",
            "index": "47",
            "type": "numeric",
            "distinct": "1802",
            "missing": "0",
            "min": "-3245260",
            "max": "274831000",
            "mean": "140627",
            "stdev": "6148721"
        },
        {
            "name": "V49",
            "index": "48",
            "type": "numeric",
            "distinct": "712",
            "missing": "0",
            "min": "-670",
            "max": "735",
            "mean": "43",
            "stdev": "189"
        },
        {
            "name": "V50",
            "index": "49",
            "type": "numeric",
            "distinct": "1855",
            "missing": "0",
            "min": "-297637000",
            "max": "3212170",
            "mean": "-149047",
            "stdev": "6656173"
        },
        {
            "name": "V51",
            "index": "50",
            "type": "numeric",
            "distinct": "1488",
            "missing": "0",
            "min": "1282",
            "max": "10000",
            "mean": "7508",
            "stdev": "1688"
        },
        {
            "name": "V52",
            "index": "51",
            "type": "numeric",
            "distinct": "1276",
            "missing": "0",
            "min": "-4082",
            "max": "2901",
            "mean": "383",
            "stdev": "630"
        },
        {
            "name": "V53",
            "index": "52",
            "type": "numeric",
            "distinct": "13",
            "missing": "0",
            "min": "7",
            "max": "21",
            "mean": "9",
            "stdev": "2"
        },
        {
            "name": "V54",
            "index": "53",
            "type": "numeric",
            "distinct": "1",
            "missing": "0",
            "min": "0",
            "max": "0",
            "mean": "0",
            "stdev": "0"
        },
        {
            "name": "V55",
            "index": "54",
            "type": "numeric",
            "distinct": "1526",
            "missing": "0",
            "min": "960",
            "max": "10000",
            "mean": "7855",
            "stdev": "1770"
        },
        {
            "name": "V56",
            "index": "55",
            "type": "numeric",
            "distinct": "1754",
            "missing": "0",
            "min": "-727603",
            "max": "371403000",
            "mean": "186149",
            "stdev": "8305005"
        },
        {
            "name": "V57",
            "index": "56",
            "type": "numeric",
            "distinct": "1699",
            "missing": "0",
            "min": "-461056000",
            "max": "1003540",
            "mean": "-229666",
            "stdev": "10309615"
        },
        {
            "name": "V58",
            "index": "57",
            "type": "numeric",
            "distinct": "1308",
            "missing": "0",
            "min": "-2628",
            "max": "2807",
            "mean": "139",
            "stdev": "637"
        },
        {
            "name": "V59",
            "index": "58",
            "type": "numeric",
            "distinct": "1363",
            "missing": "0",
            "min": "-48467600",
            "max": "482046",
            "mean": "-23977",
            "stdev": "1083851"
        },
        {
            "name": "V60",
            "index": "59",
            "type": "numeric",
            "distinct": "668",
            "missing": "0",
            "min": "-643",
            "max": "690",
            "mean": "37",
            "stdev": "171"
        }
    ],
    "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
}