{
    "data_id": "44534",
    "name": "dionis_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True",
    "exact_name": "dionis_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True",
    "version": 1,
    "version_label": "2dc5498e-76eb-4915-8983-cc4ca41d6b86",
    "description": "Subsampling of the dataset dionis (41167) with\n\nseed=1\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 18:26:06",
    "update_comment": null,
    "last_update": "2022-11-17 18:26:06",
    "licence": "Public",
    "status": "active",
    "error_message": null,
    "url": "https:\/\/api.openml.org\/data\/download\/22111296\/dataset",
    "default_target_attribute": "class",
    "row_id_attribute": null,
    "ignore_attribute": null,
    "runs": 0,
    "suggest": {
        "input": [
            "dionis_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True",
            "Subsampling of the dataset dionis (41167) with seed=1 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,
        "MajorityClassSize": 12,
        "MinorityClassPercentage": 0.2,
        "MinorityClassSize": 4,
        "NumberOfBinaryFeatures": 0,
        "PercentageOfBinaryFeatures": 0,
        "PercentageOfInstancesWithMissingValues": 0,
        "AutoCorrelation": 0.0015007503751875938,
        "PercentageOfMissingValues": 0,
        "Dimensionality": 0.0305,
        "PercentageOfNumericFeatures": 98.36065573770492,
        "MajorityClassPercentage": 0.6,
        "PercentageOfSymbolicFeatures": 1.639344262295082
    },
    "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": "1507",
            "missing": "0",
            "min": "5240",
            "max": "9940",
            "mean": "8301",
            "stdev": "1116"
        },
        {
            "name": "V2",
            "index": "1",
            "type": "numeric",
            "distinct": "1633",
            "missing": "0",
            "min": "-7333",
            "max": "6140",
            "mean": "-96",
            "stdev": "1331"
        },
        {
            "name": "V3",
            "index": "2",
            "type": "numeric",
            "distinct": "16",
            "missing": "0",
            "min": "-30561",
            "max": "47496",
            "mean": "10019",
            "stdev": "2663"
        },
        {
            "name": "V4",
            "index": "3",
            "type": "numeric",
            "distinct": "1827",
            "missing": "0",
            "min": "-1239880",
            "max": "2139610",
            "mean": "-67",
            "stdev": "69515"
        },
        {
            "name": "V5",
            "index": "4",
            "type": "numeric",
            "distinct": "1141",
            "missing": "0",
            "min": "-1642",
            "max": "1954",
            "mean": "84",
            "stdev": "462"
        },
        {
            "name": "V6",
            "index": "5",
            "type": "numeric",
            "distinct": "15",
            "missing": "0",
            "min": "0",
            "max": "22543",
            "mean": "10040",
            "stdev": "768"
        },
        {
            "name": "V7",
            "index": "6",
            "type": "numeric",
            "distinct": "1326",
            "missing": "0",
            "min": "-198607",
            "max": "79489",
            "mean": "-72",
            "stdev": "7879"
        },
        {
            "name": "V8",
            "index": "7",
            "type": "numeric",
            "distinct": "1868",
            "missing": "0",
            "min": "-649449",
            "max": "2802290",
            "mean": "3284",
            "stdev": "86091"
        },
        {
            "name": "V9",
            "index": "8",
            "type": "numeric",
            "distinct": "1265",
            "missing": "0",
            "min": "-2292",
            "max": "2841",
            "mean": "140",
            "stdev": "581"
        },
        {
            "name": "V10",
            "index": "9",
            "type": "numeric",
            "distinct": "770",
            "missing": "0",
            "min": "-746",
            "max": "977",
            "mean": "39",
            "stdev": "214"
        },
        {
            "name": "V11",
            "index": "10",
            "type": "numeric",
            "distinct": "1660",
            "missing": "0",
            "min": "1003",
            "max": "10000",
            "mean": "6067",
            "stdev": "1517"
        },
        {
            "name": "V12",
            "index": "11",
            "type": "numeric",
            "distinct": "1542",
            "missing": "0",
            "min": "-224366",
            "max": "710929",
            "mean": "666",
            "stdev": "23919"
        },
        {
            "name": "V13",
            "index": "12",
            "type": "numeric",
            "distinct": "1779",
            "missing": "0",
            "min": "-10000",
            "max": "7003",
            "mean": "-5922",
            "stdev": "3564"
        },
        {
            "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": "1849",
            "missing": "0",
            "min": "-1623920",
            "max": "2256120",
            "mean": "548",
            "stdev": "75099"
        },
        {
            "name": "V16",
            "index": "15",
            "type": "numeric",
            "distinct": "1472",
            "missing": "0",
            "min": "498",
            "max": "10000",
            "mean": "8154",
            "stdev": "1625"
        },
        {
            "name": "V17",
            "index": "16",
            "type": "numeric",
            "distinct": "1608",
            "missing": "0",
            "min": "603",
            "max": "10000",
            "mean": "7054",
            "stdev": "1940"
        },
        {
            "name": "V18",
            "index": "17",
            "type": "numeric",
            "distinct": "1561",
            "missing": "0",
            "min": "-1527440",
            "max": "790599",
            "mean": "-310",
            "stdev": "50546"
        },
        {
            "name": "V19",
            "index": "18",
            "type": "numeric",
            "distinct": "1639",
            "missing": "0",
            "min": "-4451",
            "max": "4211",
            "mean": "61",
            "stdev": "1322"
        },
        {
            "name": "V20",
            "index": "19",
            "type": "numeric",
            "distinct": "1072",
            "missing": "0",
            "min": "-1876",
            "max": "2165",
            "mean": "157",
            "stdev": "391"
        },
        {
            "name": "V21",
            "index": "20",
            "type": "numeric",
            "distinct": "973",
            "missing": "0",
            "min": "-1443",
            "max": "1394",
            "mean": "75",
            "stdev": "332"
        },
        {
            "name": "V22",
            "index": "21",
            "type": "numeric",
            "distinct": "967",
            "missing": "0",
            "min": "150",
            "max": "10000",
            "mean": "8912",
            "stdev": "1502"
        },
        {
            "name": "V23",
            "index": "22",
            "type": "numeric",
            "distinct": "1854",
            "missing": "0",
            "min": "-1539540",
            "max": "1249590",
            "mean": "-2027",
            "stdev": "76168"
        },
        {
            "name": "V24",
            "index": "23",
            "type": "numeric",
            "distinct": "1545",
            "missing": "0",
            "min": "-1304020",
            "max": "1005750",
            "mean": "-379",
            "stdev": "44528"
        },
        {
            "name": "V25",
            "index": "24",
            "type": "numeric",
            "distinct": "631",
            "missing": "0",
            "min": "-652",
            "max": "621",
            "mean": "27",
            "stdev": "156"
        },
        {
            "name": "V26",
            "index": "25",
            "type": "numeric",
            "distinct": "875",
            "missing": "0",
            "min": "-1815",
            "max": "1301",
            "mean": "87",
            "stdev": "273"
        },
        {
            "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": "1717",
            "missing": "0",
            "min": "-5107",
            "max": "9424",
            "mean": "2276",
            "stdev": "2114"
        },
        {
            "name": "V29",
            "index": "28",
            "type": "numeric",
            "distinct": "1622",
            "missing": "0",
            "min": "0",
            "max": "10000",
            "mean": "7124",
            "stdev": "1855"
        },
        {
            "name": "V30",
            "index": "29",
            "type": "numeric",
            "distinct": "1669",
            "missing": "0",
            "min": "-1005270",
            "max": "1446780",
            "mean": "810",
            "stdev": "47440"
        },
        {
            "name": "V31",
            "index": "30",
            "type": "numeric",
            "distinct": "1462",
            "missing": "0",
            "min": "-3446",
            "max": "3665",
            "mean": "114",
            "stdev": "936"
        },
        {
            "name": "V32",
            "index": "31",
            "type": "numeric",
            "distinct": "1273",
            "missing": "0",
            "min": "1769",
            "max": "10000",
            "mean": "8684",
            "stdev": "1377"
        },
        {
            "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": "1606",
            "missing": "0",
            "min": "-3305",
            "max": "4874",
            "mean": "311",
            "stdev": "1405"
        },
        {
            "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": "1507",
            "missing": "0",
            "min": "60",
            "max": "4760",
            "mean": "1699",
            "stdev": "1116"
        },
        {
            "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": "1732",
            "missing": "0",
            "min": "-7035",
            "max": "10000",
            "mean": "6332",
            "stdev": "3485"
        },
        {
            "name": "V39",
            "index": "38",
            "type": "numeric",
            "distinct": "1452",
            "missing": "0",
            "min": "-3015",
            "max": "3581",
            "mean": "114",
            "stdev": "891"
        },
        {
            "name": "V40",
            "index": "39",
            "type": "numeric",
            "distinct": "1509",
            "missing": "0",
            "min": "-492182",
            "max": "490054",
            "mean": "544",
            "stdev": "19913"
        },
        {
            "name": "V41",
            "index": "40",
            "type": "numeric",
            "distinct": "1789",
            "missing": "0",
            "min": "-640824",
            "max": "1159450",
            "mean": "3111",
            "stdev": "62944"
        },
        {
            "name": "V42",
            "index": "41",
            "type": "numeric",
            "distinct": "1811",
            "missing": "0",
            "min": "-781874",
            "max": "378900",
            "mean": "-156",
            "stdev": "35694"
        },
        {
            "name": "V43",
            "index": "42",
            "type": "numeric",
            "distinct": "1625",
            "missing": "0",
            "min": "-437977",
            "max": "421563",
            "mean": "-23",
            "stdev": "18452"
        },
        {
            "name": "V44",
            "index": "43",
            "type": "numeric",
            "distinct": "1226",
            "missing": "0",
            "min": "-2439",
            "max": "3097",
            "mean": "-708",
            "stdev": "549"
        },
        {
            "name": "V45",
            "index": "44",
            "type": "numeric",
            "distinct": "814",
            "missing": "0",
            "min": "-1414",
            "max": "926",
            "mean": "48",
            "stdev": "236"
        },
        {
            "name": "V46",
            "index": "45",
            "type": "numeric",
            "distinct": "1728",
            "missing": "0",
            "min": "-3715240",
            "max": "1517180",
            "mean": "-3355",
            "stdev": "98563"
        },
        {
            "name": "V47",
            "index": "46",
            "type": "numeric",
            "distinct": "795",
            "missing": "0",
            "min": "1099",
            "max": "10000",
            "mean": "9242",
            "stdev": "1229"
        },
        {
            "name": "V48",
            "index": "47",
            "type": "numeric",
            "distinct": "1806",
            "missing": "0",
            "min": "-1549790",
            "max": "554151",
            "mean": "-2874",
            "stdev": "51601"
        },
        {
            "name": "V49",
            "index": "48",
            "type": "numeric",
            "distinct": "709",
            "missing": "0",
            "min": "-666",
            "max": "881",
            "mean": "44",
            "stdev": "190"
        },
        {
            "name": "V50",
            "index": "49",
            "type": "numeric",
            "distinct": "1853",
            "missing": "0",
            "min": "-579424",
            "max": "3648080",
            "mean": "4645",
            "stdev": "104418"
        },
        {
            "name": "V51",
            "index": "50",
            "type": "numeric",
            "distinct": "1459",
            "missing": "0",
            "min": "293",
            "max": "10000",
            "mean": "7562",
            "stdev": "1686"
        },
        {
            "name": "V52",
            "index": "51",
            "type": "numeric",
            "distinct": "1280",
            "missing": "0",
            "min": "-4082",
            "max": "2621",
            "mean": "391",
            "stdev": "635"
        },
        {
            "name": "V53",
            "index": "52",
            "type": "numeric",
            "distinct": "15",
            "missing": "0",
            "min": "7",
            "max": "28",
            "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": "1537",
            "missing": "0",
            "min": "294",
            "max": "10000",
            "mean": "7772",
            "stdev": "1833"
        },
        {
            "name": "V56",
            "index": "55",
            "type": "numeric",
            "distinct": "1736",
            "missing": "0",
            "min": "-2225790",
            "max": "1072270",
            "mean": "-2371",
            "stdev": "76885"
        },
        {
            "name": "V57",
            "index": "56",
            "type": "numeric",
            "distinct": "1698",
            "missing": "0",
            "min": "-2312850",
            "max": "435599",
            "mean": "-3071",
            "stdev": "69556"
        },
        {
            "name": "V58",
            "index": "57",
            "type": "numeric",
            "distinct": "1333",
            "missing": "0",
            "min": "-2290",
            "max": "2945",
            "mean": "118",
            "stdev": "657"
        },
        {
            "name": "V59",
            "index": "58",
            "type": "numeric",
            "distinct": "1365",
            "missing": "0",
            "min": "-349421",
            "max": "62538",
            "mean": "-379",
            "stdev": "9743"
        },
        {
            "name": "V60",
            "index": "59",
            "type": "numeric",
            "distinct": "651",
            "missing": "0",
            "min": "-569",
            "max": "715",
            "mean": "36",
            "stdev": "165"
        }
    ],
    "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
}