{
    "data_id": "44535",
    "name": "dionis_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True",
    "exact_name": "dionis_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True",
    "version": 1,
    "version_label": "a9acba40-510b-40fd-aafe-e2c33ebb3a49",
    "description": "Subsampling of the dataset dionis (41167) with\n\nseed=2\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 18:26:11",
    "update_comment": null,
    "last_update": "2022-11-17 18:26:11",
    "licence": "Public",
    "status": "active",
    "error_message": null,
    "url": "https:\/\/api.openml.org\/data\/download\/22111297\/dataset",
    "default_target_attribute": "class",
    "row_id_attribute": null,
    "ignore_attribute": null,
    "runs": 0,
    "suggest": {
        "input": [
            "dionis_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True",
            "Subsampling of the dataset dionis (41167) with seed=2 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,
        "Dimensionality": 0.0305,
        "PercentageOfNumericFeatures": 98.36065573770492,
        "MajorityClassPercentage": 0.6,
        "PercentageOfSymbolicFeatures": 1.639344262295082,
        "MajorityClassSize": 12,
        "MinorityClassPercentage": 0.2,
        "MinorityClassSize": 4,
        "NumberOfBinaryFeatures": 0,
        "PercentageOfBinaryFeatures": 0,
        "PercentageOfInstancesWithMissingValues": 0,
        "AutoCorrelation": 0.0005002501250625312,
        "PercentageOfMissingValues": 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": "1514",
            "missing": "0",
            "min": "5115",
            "max": "9916",
            "mean": "8296",
            "stdev": "1131"
        },
        {
            "name": "V2",
            "index": "1",
            "type": "numeric",
            "distinct": "1640",
            "missing": "0",
            "min": "-7962",
            "max": "7144",
            "mean": "-81",
            "stdev": "1416"
        },
        {
            "name": "V3",
            "index": "2",
            "type": "numeric",
            "distinct": "26",
            "missing": "0",
            "min": "-30541",
            "max": "64892",
            "mean": "10022",
            "stdev": "3150"
        },
        {
            "name": "V4",
            "index": "3",
            "type": "numeric",
            "distinct": "1837",
            "missing": "0",
            "min": "-1882340",
            "max": "168776000",
            "mean": "86105",
            "stdev": "3775510"
        },
        {
            "name": "V5",
            "index": "4",
            "type": "numeric",
            "distinct": "1180",
            "missing": "0",
            "min": "-2188",
            "max": "1892",
            "mean": "80",
            "stdev": "463"
        },
        {
            "name": "V6",
            "index": "5",
            "type": "numeric",
            "distinct": "26",
            "missing": "0",
            "min": "0",
            "max": "24381",
            "mean": "10101",
            "stdev": "1103"
        },
        {
            "name": "V7",
            "index": "6",
            "type": "numeric",
            "distinct": "1352",
            "missing": "0",
            "min": "-625976",
            "max": "2605990",
            "mean": "1129",
            "stdev": "60316"
        },
        {
            "name": "V8",
            "index": "7",
            "type": "numeric",
            "distinct": "1876",
            "missing": "0",
            "min": "-132633000",
            "max": "5547730",
            "mean": "-61453",
            "stdev": "2969999"
        },
        {
            "name": "V9",
            "index": "8",
            "type": "numeric",
            "distinct": "1275",
            "missing": "0",
            "min": "-2031",
            "max": "2965",
            "mean": "139",
            "stdev": "578"
        },
        {
            "name": "V10",
            "index": "9",
            "type": "numeric",
            "distinct": "751",
            "missing": "0",
            "min": "-736",
            "max": "781",
            "mean": "36",
            "stdev": "203"
        },
        {
            "name": "V11",
            "index": "10",
            "type": "numeric",
            "distinct": "1666",
            "missing": "0",
            "min": "635",
            "max": "10000",
            "mean": "6078",
            "stdev": "1508"
        },
        {
            "name": "V12",
            "index": "11",
            "type": "numeric",
            "distinct": "1576",
            "missing": "0",
            "min": "-1590340",
            "max": "57523300",
            "mean": "27644",
            "stdev": "1287057"
        },
        {
            "name": "V13",
            "index": "12",
            "type": "numeric",
            "distinct": "1777",
            "missing": "0",
            "min": "-10000",
            "max": "7062",
            "mean": "-5920",
            "stdev": "3577"
        },
        {
            "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": "1850",
            "missing": "0",
            "min": "-3143010",
            "max": "11222000",
            "mean": "7882",
            "stdev": "282312"
        },
        {
            "name": "V16",
            "index": "15",
            "type": "numeric",
            "distinct": "1437",
            "missing": "0",
            "min": "1345",
            "max": "10000",
            "mean": "8183",
            "stdev": "1607"
        },
        {
            "name": "V17",
            "index": "16",
            "type": "numeric",
            "distinct": "1588",
            "missing": "0",
            "min": "0",
            "max": "10000",
            "mean": "7034",
            "stdev": "1941"
        },
        {
            "name": "V18",
            "index": "17",
            "type": "numeric",
            "distinct": "1529",
            "missing": "0",
            "min": "-392500",
            "max": "22822400",
            "mean": "11362",
            "stdev": "510698"
        },
        {
            "name": "V19",
            "index": "18",
            "type": "numeric",
            "distinct": "1651",
            "missing": "0",
            "min": "-4866",
            "max": "5316",
            "mean": "66",
            "stdev": "1372"
        },
        {
            "name": "V20",
            "index": "19",
            "type": "numeric",
            "distinct": "1086",
            "missing": "0",
            "min": "-1983",
            "max": "2226",
            "mean": "163",
            "stdev": "402"
        },
        {
            "name": "V21",
            "index": "20",
            "type": "numeric",
            "distinct": "970",
            "missing": "0",
            "min": "-1573",
            "max": "1532",
            "mean": "67",
            "stdev": "323"
        },
        {
            "name": "V22",
            "index": "21",
            "type": "numeric",
            "distinct": "1000",
            "missing": "0",
            "min": "2136",
            "max": "10000",
            "mean": "8912",
            "stdev": "1504"
        },
        {
            "name": "V23",
            "index": "22",
            "type": "numeric",
            "distinct": "1851",
            "missing": "0",
            "min": "-11620500",
            "max": "1595250",
            "mean": "-9282",
            "stdev": "314318"
        },
        {
            "name": "V24",
            "index": "23",
            "type": "numeric",
            "distinct": "1528",
            "missing": "0",
            "min": "-238090",
            "max": "14455700",
            "mean": "6957",
            "stdev": "323597"
        },
        {
            "name": "V25",
            "index": "24",
            "type": "numeric",
            "distinct": "627",
            "missing": "0",
            "min": "-473",
            "max": "740",
            "mean": "34",
            "stdev": "157"
        },
        {
            "name": "V26",
            "index": "25",
            "type": "numeric",
            "distinct": "910",
            "missing": "0",
            "min": "-1043",
            "max": "1129",
            "mean": "87",
            "stdev": "274"
        },
        {
            "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": "1730",
            "missing": "0",
            "min": "-5840",
            "max": "11903",
            "mean": "2178",
            "stdev": "2186"
        },
        {
            "name": "V29",
            "index": "28",
            "type": "numeric",
            "distinct": "1647",
            "missing": "0",
            "min": "0",
            "max": "10000",
            "mean": "7132",
            "stdev": "1898"
        },
        {
            "name": "V30",
            "index": "29",
            "type": "numeric",
            "distinct": "1633",
            "missing": "0",
            "min": "-763748",
            "max": "1967970",
            "mean": "-541",
            "stdev": "54541"
        },
        {
            "name": "V31",
            "index": "30",
            "type": "numeric",
            "distinct": "1465",
            "missing": "0",
            "min": "-3223",
            "max": "3588",
            "mean": "128",
            "stdev": "927"
        },
        {
            "name": "V32",
            "index": "31",
            "type": "numeric",
            "distinct": "1287",
            "missing": "0",
            "min": "1981",
            "max": "10000",
            "mean": "8655",
            "stdev": "1366"
        },
        {
            "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": "1631",
            "missing": "0",
            "min": "-3419",
            "max": "4716",
            "mean": "341",
            "stdev": "1398"
        },
        {
            "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": "1514",
            "missing": "0",
            "min": "84",
            "max": "4885",
            "mean": "1704",
            "stdev": "1131"
        },
        {
            "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": "1719",
            "missing": "0",
            "min": "-7063",
            "max": "10000",
            "mean": "6374",
            "stdev": "3398"
        },
        {
            "name": "V39",
            "index": "38",
            "type": "numeric",
            "distinct": "1513",
            "missing": "0",
            "min": "-2921",
            "max": "3248",
            "mean": "106",
            "stdev": "905"
        },
        {
            "name": "V40",
            "index": "39",
            "type": "numeric",
            "distinct": "1511",
            "missing": "0",
            "min": "-842824",
            "max": "54392500",
            "mean": "26871",
            "stdev": "1216551"
        },
        {
            "name": "V41",
            "index": "40",
            "type": "numeric",
            "distinct": "1803",
            "missing": "0",
            "min": "-6500500",
            "max": "229439000",
            "mean": "112094",
            "stdev": "5134019"
        },
        {
            "name": "V42",
            "index": "41",
            "type": "numeric",
            "distinct": "1803",
            "missing": "0",
            "min": "-17370700",
            "max": "4431200",
            "mean": "-6922",
            "stdev": "408088"
        },
        {
            "name": "V43",
            "index": "42",
            "type": "numeric",
            "distinct": "1640",
            "missing": "0",
            "min": "-988081",
            "max": "1789010",
            "mean": "531",
            "stdev": "47833"
        },
        {
            "name": "V44",
            "index": "43",
            "type": "numeric",
            "distinct": "1258",
            "missing": "0",
            "min": "-2364",
            "max": "2688",
            "mean": "-728",
            "stdev": "565"
        },
        {
            "name": "V45",
            "index": "44",
            "type": "numeric",
            "distinct": "825",
            "missing": "0",
            "min": "-1228",
            "max": "1275",
            "mean": "54",
            "stdev": "243"
        },
        {
            "name": "V46",
            "index": "45",
            "type": "numeric",
            "distinct": "1743",
            "missing": "0",
            "min": "-228007000",
            "max": "11968400",
            "mean": "-109049",
            "stdev": "5107669"
        },
        {
            "name": "V47",
            "index": "46",
            "type": "numeric",
            "distinct": "790",
            "missing": "0",
            "min": "1889",
            "max": "10000",
            "mean": "9241",
            "stdev": "1231"
        },
        {
            "name": "V48",
            "index": "47",
            "type": "numeric",
            "distinct": "1801",
            "missing": "0",
            "min": "-1375010",
            "max": "55995300",
            "mean": "29151",
            "stdev": "1265071"
        },
        {
            "name": "V49",
            "index": "48",
            "type": "numeric",
            "distinct": "729",
            "missing": "0",
            "min": "-734",
            "max": "704",
            "mean": "37",
            "stdev": "194"
        },
        {
            "name": "V50",
            "index": "49",
            "type": "numeric",
            "distinct": "1850",
            "missing": "0",
            "min": "-123144000",
            "max": "5000550",
            "mean": "-59353",
            "stdev": "2757538"
        },
        {
            "name": "V51",
            "index": "50",
            "type": "numeric",
            "distinct": "1472",
            "missing": "0",
            "min": "652",
            "max": "10000",
            "mean": "7549",
            "stdev": "1699"
        },
        {
            "name": "V52",
            "index": "51",
            "type": "numeric",
            "distinct": "1306",
            "missing": "0",
            "min": "-4082",
            "max": "2594",
            "mean": "408",
            "stdev": "639"
        },
        {
            "name": "V53",
            "index": "52",
            "type": "numeric",
            "distinct": "15",
            "missing": "0",
            "min": "7",
            "max": "22",
            "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": "1551",
            "missing": "0",
            "min": "1179",
            "max": "10000",
            "mean": "7766",
            "stdev": "1781"
        },
        {
            "name": "V56",
            "index": "55",
            "type": "numeric",
            "distinct": "1778",
            "missing": "0",
            "min": "-182258000",
            "max": "4312840",
            "mean": "-91455",
            "stdev": "4079941"
        },
        {
            "name": "V57",
            "index": "56",
            "type": "numeric",
            "distinct": "1713",
            "missing": "0",
            "min": "-239282000",
            "max": "2189510",
            "mean": "-122087",
            "stdev": "5352905"
        },
        {
            "name": "V58",
            "index": "57",
            "type": "numeric",
            "distinct": "1282",
            "missing": "0",
            "min": "-2297",
            "max": "2139",
            "mean": "133",
            "stdev": "640"
        },
        {
            "name": "V59",
            "index": "58",
            "type": "numeric",
            "distinct": "1390",
            "missing": "0",
            "min": "-9934460",
            "max": "134657",
            "mean": "-4934",
            "stdev": "222597"
        },
        {
            "name": "V60",
            "index": "59",
            "type": "numeric",
            "distinct": "663",
            "missing": "0",
            "min": "-619",
            "max": "774",
            "mean": "35",
            "stdev": "166"
        }
    ],
    "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
}