{
    "data_id": "44533",
    "name": "dionis_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True",
    "exact_name": "dionis_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True",
    "version": 1,
    "version_label": "99a1a666-80ce-4599-b833-0ae93856a695",
    "description": "Subsampling of the dataset dionis (41167) with\n\nseed=0\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 18:26:00",
    "update_comment": null,
    "last_update": "2022-11-17 18:26:00",
    "licence": "Public",
    "status": "active",
    "error_message": null,
    "url": "https:\/\/api.openml.org\/data\/download\/22111295\/dataset",
    "default_target_attribute": "class",
    "row_id_attribute": null,
    "ignore_attribute": null,
    "runs": 0,
    "suggest": {
        "input": [
            "dionis_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True",
            "Subsampling of the dataset dionis (41167) with seed=0 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,
        "PercentageOfBinaryFeatures": 0,
        "PercentageOfInstancesWithMissingValues": 0,
        "AutoCorrelation": 0.0030015007503751876,
        "PercentageOfMissingValues": 0,
        "Dimensionality": 0.0305,
        "PercentageOfNumericFeatures": 98.36065573770492,
        "MajorityClassPercentage": 0.6,
        "PercentageOfSymbolicFeatures": 1.639344262295082,
        "MajorityClassSize": 12,
        "MinorityClassPercentage": 0.2,
        "MinorityClassSize": 4,
        "NumberOfBinaryFeatures": 0
    },
    "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": "1505",
            "missing": "0",
            "min": "5031",
            "max": "9944",
            "mean": "8314",
            "stdev": "1114"
        },
        {
            "name": "V2",
            "index": "1",
            "type": "numeric",
            "distinct": "1649",
            "missing": "0",
            "min": "-7236",
            "max": "5413",
            "mean": "-118",
            "stdev": "1362"
        },
        {
            "name": "V3",
            "index": "2",
            "type": "numeric",
            "distinct": "25",
            "missing": "0",
            "min": "-36642",
            "max": "64892",
            "mean": "9961",
            "stdev": "3084"
        },
        {
            "name": "V4",
            "index": "3",
            "type": "numeric",
            "distinct": "1836",
            "missing": "0",
            "min": "-10492300",
            "max": "1238920",
            "mean": "-4084",
            "stdev": "238252"
        },
        {
            "name": "V5",
            "index": "4",
            "type": "numeric",
            "distinct": "1154",
            "missing": "0",
            "min": "-2174",
            "max": "2220",
            "mean": "70",
            "stdev": "470"
        },
        {
            "name": "V6",
            "index": "5",
            "type": "numeric",
            "distinct": "24",
            "missing": "0",
            "min": "0",
            "max": "26833",
            "mean": "10097",
            "stdev": "1040"
        },
        {
            "name": "V7",
            "index": "6",
            "type": "numeric",
            "distinct": "1340",
            "missing": "0",
            "min": "-85832",
            "max": "2157240",
            "mean": "1197",
            "stdev": "48445"
        },
        {
            "name": "V8",
            "index": "7",
            "type": "numeric",
            "distinct": "1837",
            "missing": "0",
            "min": "-765608",
            "max": "211299",
            "mean": "-763",
            "stdev": "28969"
        },
        {
            "name": "V9",
            "index": "8",
            "type": "numeric",
            "distinct": "1287",
            "missing": "0",
            "min": "-2276",
            "max": "3053",
            "mean": "134",
            "stdev": "561"
        },
        {
            "name": "V10",
            "index": "9",
            "type": "numeric",
            "distinct": "742",
            "missing": "0",
            "min": "-846",
            "max": "1019",
            "mean": "45",
            "stdev": "207"
        },
        {
            "name": "V11",
            "index": "10",
            "type": "numeric",
            "distinct": "1664",
            "missing": "0",
            "min": "1011",
            "max": "10000",
            "mean": "6031",
            "stdev": "1485"
        },
        {
            "name": "V12",
            "index": "11",
            "type": "numeric",
            "distinct": "1536",
            "missing": "0",
            "min": "-4588960",
            "max": "460518",
            "mean": "-1792",
            "stdev": "103701"
        },
        {
            "name": "V13",
            "index": "12",
            "type": "numeric",
            "distinct": "1786",
            "missing": "0",
            "min": "-10000",
            "max": "6947",
            "mean": "-5846",
            "stdev": "3570"
        },
        {
            "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": "1853",
            "missing": "0",
            "min": "-3679990",
            "max": "515369",
            "mean": "-2135",
            "stdev": "88737"
        },
        {
            "name": "V16",
            "index": "15",
            "type": "numeric",
            "distinct": "1443",
            "missing": "0",
            "min": "1059",
            "max": "10000",
            "mean": "8172",
            "stdev": "1638"
        },
        {
            "name": "V17",
            "index": "16",
            "type": "numeric",
            "distinct": "1610",
            "missing": "0",
            "min": "576",
            "max": "10000",
            "mean": "7024",
            "stdev": "1950"
        },
        {
            "name": "V18",
            "index": "17",
            "type": "numeric",
            "distinct": "1550",
            "missing": "0",
            "min": "-1921680",
            "max": "1227840",
            "mean": "-464",
            "stdev": "53062"
        },
        {
            "name": "V19",
            "index": "18",
            "type": "numeric",
            "distinct": "1641",
            "missing": "0",
            "min": "-4195",
            "max": "6012",
            "mean": "86",
            "stdev": "1344"
        },
        {
            "name": "V20",
            "index": "19",
            "type": "numeric",
            "distinct": "1056",
            "missing": "0",
            "min": "-1521",
            "max": "2387",
            "mean": "166",
            "stdev": "394"
        },
        {
            "name": "V21",
            "index": "20",
            "type": "numeric",
            "distinct": "996",
            "missing": "0",
            "min": "-1305",
            "max": "1614",
            "mean": "84",
            "stdev": "327"
        },
        {
            "name": "V22",
            "index": "21",
            "type": "numeric",
            "distinct": "983",
            "missing": "0",
            "min": "1219",
            "max": "10000",
            "mean": "8876",
            "stdev": "1522"
        },
        {
            "name": "V23",
            "index": "22",
            "type": "numeric",
            "distinct": "1836",
            "missing": "0",
            "min": "-699335",
            "max": "1764280",
            "mean": "634",
            "stdev": "65193"
        },
        {
            "name": "V24",
            "index": "23",
            "type": "numeric",
            "distinct": "1514",
            "missing": "0",
            "min": "-1884790",
            "max": "643459",
            "mean": "-1257",
            "stdev": "49358"
        },
        {
            "name": "V25",
            "index": "24",
            "type": "numeric",
            "distinct": "627",
            "missing": "0",
            "min": "-684",
            "max": "725",
            "mean": "27",
            "stdev": "159"
        },
        {
            "name": "V26",
            "index": "25",
            "type": "numeric",
            "distinct": "894",
            "missing": "0",
            "min": "-1260",
            "max": "1949",
            "mean": "86",
            "stdev": "282"
        },
        {
            "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": "1728",
            "missing": "0",
            "min": "-8235",
            "max": "11860",
            "mean": "2213",
            "stdev": "2218"
        },
        {
            "name": "V29",
            "index": "28",
            "type": "numeric",
            "distinct": "1633",
            "missing": "0",
            "min": "0",
            "max": "10000",
            "mean": "7135",
            "stdev": "1878"
        },
        {
            "name": "V30",
            "index": "29",
            "type": "numeric",
            "distinct": "1671",
            "missing": "0",
            "min": "-287876",
            "max": "1934150",
            "mean": "952",
            "stdev": "47651"
        },
        {
            "name": "V31",
            "index": "30",
            "type": "numeric",
            "distinct": "1477",
            "missing": "0",
            "min": "-3700",
            "max": "3591",
            "mean": "128",
            "stdev": "945"
        },
        {
            "name": "V32",
            "index": "31",
            "type": "numeric",
            "distinct": "1280",
            "missing": "0",
            "min": "2441",
            "max": "10000",
            "mean": "8662",
            "stdev": "1367"
        },
        {
            "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": "1625",
            "missing": "0",
            "min": "-3417",
            "max": "4747",
            "mean": "351",
            "stdev": "1409"
        },
        {
            "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": "1505",
            "missing": "0",
            "min": "56",
            "max": "4969",
            "mean": "1686",
            "stdev": "1114"
        },
        {
            "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": "1744",
            "missing": "0",
            "min": "-7054",
            "max": "10000",
            "mean": "6444",
            "stdev": "3402"
        },
        {
            "name": "V39",
            "index": "38",
            "type": "numeric",
            "distinct": "1461",
            "missing": "0",
            "min": "-2935",
            "max": "3265",
            "mean": "89",
            "stdev": "870"
        },
        {
            "name": "V40",
            "index": "39",
            "type": "numeric",
            "distinct": "1493",
            "missing": "0",
            "min": "-204409",
            "max": "319376",
            "mean": "357",
            "stdev": "12375"
        },
        {
            "name": "V41",
            "index": "40",
            "type": "numeric",
            "distinct": "1783",
            "missing": "0",
            "min": "-881099",
            "max": "15242400",
            "mean": "8682",
            "stdev": "343627"
        },
        {
            "name": "V42",
            "index": "41",
            "type": "numeric",
            "distinct": "1816",
            "missing": "0",
            "min": "-2402260",
            "max": "258534",
            "mean": "-2485",
            "stdev": "63622"
        },
        {
            "name": "V43",
            "index": "42",
            "type": "numeric",
            "distinct": "1620",
            "missing": "0",
            "min": "-1391430",
            "max": "194033",
            "mean": "-500",
            "stdev": "32958"
        },
        {
            "name": "V44",
            "index": "43",
            "type": "numeric",
            "distinct": "1250",
            "missing": "0",
            "min": "-2400",
            "max": "3056",
            "mean": "-708",
            "stdev": "542"
        },
        {
            "name": "V45",
            "index": "44",
            "type": "numeric",
            "distinct": "815",
            "missing": "0",
            "min": "-753",
            "max": "948",
            "mean": "60",
            "stdev": "233"
        },
        {
            "name": "V46",
            "index": "45",
            "type": "numeric",
            "distinct": "1741",
            "missing": "0",
            "min": "-16150100",
            "max": "974646",
            "mean": "-8635",
            "stdev": "363464"
        },
        {
            "name": "V47",
            "index": "46",
            "type": "numeric",
            "distinct": "785",
            "missing": "0",
            "min": "2110",
            "max": "10000",
            "mean": "9266",
            "stdev": "1211"
        },
        {
            "name": "V48",
            "index": "47",
            "type": "numeric",
            "distinct": "1801",
            "missing": "0",
            "min": "-1622080",
            "max": "470098",
            "mean": "-2479",
            "stdev": "46368"
        },
        {
            "name": "V49",
            "index": "48",
            "type": "numeric",
            "distinct": "739",
            "missing": "0",
            "min": "-834",
            "max": "743",
            "mean": "43",
            "stdev": "196"
        },
        {
            "name": "V50",
            "index": "49",
            "type": "numeric",
            "distinct": "1859",
            "missing": "0",
            "min": "-1071930",
            "max": "8701230",
            "mean": "3300",
            "stdev": "198506"
        },
        {
            "name": "V51",
            "index": "50",
            "type": "numeric",
            "distinct": "1503",
            "missing": "0",
            "min": "1813",
            "max": "10000",
            "mean": "7524",
            "stdev": "1677"
        },
        {
            "name": "V52",
            "index": "51",
            "type": "numeric",
            "distinct": "1304",
            "missing": "0",
            "min": "-5528",
            "max": "2531",
            "mean": "427",
            "stdev": "647"
        },
        {
            "name": "V53",
            "index": "52",
            "type": "numeric",
            "distinct": "14",
            "missing": "0",
            "min": "7",
            "max": "20",
            "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": "1544",
            "missing": "0",
            "min": "688",
            "max": "10000",
            "mean": "7766",
            "stdev": "1791"
        },
        {
            "name": "V56",
            "index": "55",
            "type": "numeric",
            "distinct": "1766",
            "missing": "0",
            "min": "-1414980",
            "max": "951439",
            "mean": "-2102",
            "stdev": "51389"
        },
        {
            "name": "V57",
            "index": "56",
            "type": "numeric",
            "distinct": "1717",
            "missing": "0",
            "min": "-5781330",
            "max": "908989",
            "mean": "-2212",
            "stdev": "133913"
        },
        {
            "name": "V58",
            "index": "57",
            "type": "numeric",
            "distinct": "1310",
            "missing": "0",
            "min": "-2213",
            "max": "2344",
            "mean": "136",
            "stdev": "631"
        },
        {
            "name": "V59",
            "index": "58",
            "type": "numeric",
            "distinct": "1353",
            "missing": "0",
            "min": "-116216",
            "max": "1159710",
            "mean": "460",
            "stdev": "26190"
        },
        {
            "name": "V60",
            "index": "59",
            "type": "numeric",
            "distinct": "634",
            "missing": "0",
            "min": "-543",
            "max": "667",
            "mean": "28",
            "stdev": "162"
        }
    ],
    "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
}