{
    "data_id": "44664",
    "name": "first-order-theorem-proving_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True",
    "exact_name": "first-order-theorem-proving_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True",
    "version": 1,
    "version_label": "8ed7c2d0-0cf8-4964-b853-964bedffe206",
    "description": "Subsampling of the dataset first-order-theorem-proving (1475) 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 18:41:11",
    "update_comment": null,
    "last_update": "2022-11-17 18:41:11",
    "licence": "Public",
    "status": "active",
    "error_message": null,
    "url": "https:\/\/api.openml.org\/data\/download\/22111426\/dataset",
    "default_target_attribute": "Class",
    "row_id_attribute": null,
    "ignore_attribute": null,
    "runs": 0,
    "suggest": {
        "input": [
            "first-order-theorem-proving_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True",
            "Subsampling of the dataset first-order-theorem-proving (1475) 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_cla "
        ],
        "weight": 5
    },
    "qualities": {
        "NumberOfInstances": 2000,
        "NumberOfFeatures": 52,
        "NumberOfClasses": 6,
        "NumberOfMissingValues": 0,
        "NumberOfInstancesWithMissingValues": 0,
        "NumberOfNumericFeatures": 51,
        "NumberOfSymbolicFeatures": 1,
        "MajorityClassSize": 835,
        "MinorityClassPercentage": 7.95,
        "MinorityClassSize": 159,
        "NumberOfBinaryFeatures": 0,
        "PercentageOfBinaryFeatures": 0,
        "PercentageOfInstancesWithMissingValues": 0,
        "PercentageOfMissingValues": 0,
        "AutoCorrelation": 0.2381190595297649,
        "PercentageOfNumericFeatures": 98.07692307692307,
        "Dimensionality": 0.026,
        "PercentageOfSymbolicFeatures": 1.9230769230769231,
        "MajorityClassPercentage": 41.75
    },
    "tags": [
        {
            "uploader": "38960",
            "tag": "Statistics"
        }
    ],
    "features": [
        {
            "name": "Class",
            "index": "51",
            "type": "nominal",
            "distinct": "6",
            "missing": "0",
            "target": "1",
            "distr": [
                [
                    "1",
                    "2",
                    "3",
                    "4",
                    "5",
                    "6"
                ],
                [
                    [
                        "356",
                        "0",
                        "0",
                        "0",
                        "0",
                        "0"
                    ],
                    [
                        "0",
                        "159",
                        "0",
                        "0",
                        "0",
                        "0"
                    ],
                    [
                        "0",
                        "0",
                        "244",
                        "0",
                        "0",
                        "0"
                    ],
                    [
                        "0",
                        "0",
                        "0",
                        "202",
                        "0",
                        "0"
                    ],
                    [
                        "0",
                        "0",
                        "0",
                        "0",
                        "204",
                        "0"
                    ],
                    [
                        "0",
                        "0",
                        "0",
                        "0",
                        "0",
                        "835"
                    ]
                ]
            ]
        },
        {
            "name": "V1",
            "index": "0",
            "type": "numeric",
            "distinct": "678",
            "missing": "0",
            "min": "-1",
            "max": "2",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V2",
            "index": "1",
            "type": "numeric",
            "distinct": "624",
            "missing": "0",
            "min": "-4",
            "max": "1",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V3",
            "index": "2",
            "type": "numeric",
            "distinct": "613",
            "missing": "0",
            "min": "-1",
            "max": "3",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V4",
            "index": "3",
            "type": "numeric",
            "distinct": "672",
            "missing": "0",
            "min": "-1",
            "max": "3",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V5",
            "index": "4",
            "type": "numeric",
            "distinct": "756",
            "missing": "0",
            "min": "-1",
            "max": "2",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V6",
            "index": "5",
            "type": "numeric",
            "distinct": "556",
            "missing": "0",
            "min": "-1",
            "max": "7",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V7",
            "index": "6",
            "type": "numeric",
            "distinct": "680",
            "missing": "0",
            "min": "-2",
            "max": "1",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V8",
            "index": "7",
            "type": "numeric",
            "distinct": "36",
            "missing": "0",
            "min": "-1",
            "max": "6",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V9",
            "index": "8",
            "type": "numeric",
            "distinct": "897",
            "missing": "0",
            "min": "-1",
            "max": "11",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V10",
            "index": "9",
            "type": "numeric",
            "distinct": "24",
            "missing": "0",
            "min": "-1",
            "max": "11",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V11",
            "index": "10",
            "type": "numeric",
            "distinct": "1134",
            "missing": "0",
            "min": "-2",
            "max": "6",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V12",
            "index": "11",
            "type": "numeric",
            "distinct": "152",
            "missing": "0",
            "min": "0",
            "max": "5",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V13",
            "index": "12",
            "type": "numeric",
            "distinct": "1366",
            "missing": "0",
            "min": "-1",
            "max": "13",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V14",
            "index": "13",
            "type": "numeric",
            "distinct": "78",
            "missing": "0",
            "min": "-3",
            "max": "1",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V15",
            "index": "14",
            "type": "numeric",
            "distinct": "1776",
            "missing": "0",
            "min": "0",
            "max": "15",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V16",
            "index": "15",
            "type": "numeric",
            "distinct": "1357",
            "missing": "0",
            "min": "-2",
            "max": "4",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V17",
            "index": "16",
            "type": "numeric",
            "distinct": "971",
            "missing": "0",
            "min": "0",
            "max": "18",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V18",
            "index": "17",
            "type": "numeric",
            "distinct": "93",
            "missing": "0",
            "min": "-2",
            "max": "6",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V19",
            "index": "18",
            "type": "numeric",
            "distinct": "1343",
            "missing": "0",
            "min": "-3",
            "max": "10",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V20",
            "index": "19",
            "type": "numeric",
            "distinct": "80",
            "missing": "0",
            "min": "-3",
            "max": "13",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V21",
            "index": "20",
            "type": "numeric",
            "distinct": "1472",
            "missing": "0",
            "min": "-2",
            "max": "37",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V22",
            "index": "21",
            "type": "numeric",
            "distinct": "81",
            "missing": "0",
            "min": "-2",
            "max": "7",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V23",
            "index": "22",
            "type": "numeric",
            "distinct": "1580",
            "missing": "0",
            "min": "-3",
            "max": "8",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V24",
            "index": "23",
            "type": "numeric",
            "distinct": "88",
            "missing": "0",
            "min": "-1",
            "max": "8",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V25",
            "index": "24",
            "type": "numeric",
            "distinct": "1634",
            "missing": "0",
            "min": "-1",
            "max": "9",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V26",
            "index": "25",
            "type": "numeric",
            "distinct": "431",
            "missing": "0",
            "min": "-1",
            "max": "9",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V27",
            "index": "26",
            "type": "numeric",
            "distinct": "1694",
            "missing": "0",
            "min": "-2",
            "max": "10",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V28",
            "index": "27",
            "type": "numeric",
            "distinct": "513",
            "missing": "0",
            "min": "0",
            "max": "13",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V29",
            "index": "28",
            "type": "numeric",
            "distinct": "1757",
            "missing": "0",
            "min": "-1",
            "max": "16",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V30",
            "index": "29",
            "type": "numeric",
            "distinct": "59",
            "missing": "0",
            "min": "0",
            "max": "6",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V31",
            "index": "30",
            "type": "numeric",
            "distinct": "73",
            "missing": "0",
            "min": "-1",
            "max": "5",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V32",
            "index": "31",
            "type": "numeric",
            "distinct": "78",
            "missing": "0",
            "min": "-3",
            "max": "1",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V33",
            "index": "32",
            "type": "numeric",
            "distinct": "20",
            "missing": "0",
            "min": "0",
            "max": "55",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V34",
            "index": "33",
            "type": "numeric",
            "distinct": "21",
            "missing": "0",
            "min": "0",
            "max": "10",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V35",
            "index": "34",
            "type": "numeric",
            "distinct": "39",
            "missing": "0",
            "min": "0",
            "max": "10",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V36",
            "index": "35",
            "type": "numeric",
            "distinct": "52",
            "missing": "0",
            "min": "0",
            "max": "68",
            "mean": "0",
            "stdev": "2"
        },
        {
            "name": "V37",
            "index": "36",
            "type": "numeric",
            "distinct": "641",
            "missing": "0",
            "min": "0",
            "max": "15",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V38",
            "index": "37",
            "type": "numeric",
            "distinct": "921",
            "missing": "0",
            "min": "-1",
            "max": "13",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V39",
            "index": "38",
            "type": "numeric",
            "distinct": "579",
            "missing": "0",
            "min": "0",
            "max": "16",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V40",
            "index": "39",
            "type": "numeric",
            "distinct": "52",
            "missing": "0",
            "min": "0",
            "max": "29",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V41",
            "index": "40",
            "type": "numeric",
            "distinct": "652",
            "missing": "0",
            "min": "0",
            "max": "15",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V42",
            "index": "41",
            "type": "numeric",
            "distinct": "27",
            "missing": "0",
            "min": "0",
            "max": "31",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V43",
            "index": "42",
            "type": "numeric",
            "distinct": "25",
            "missing": "0",
            "min": "0",
            "max": "54",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V44",
            "index": "43",
            "type": "numeric",
            "distinct": "761",
            "missing": "0",
            "min": "-1",
            "max": "2",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V45",
            "index": "44",
            "type": "numeric",
            "distinct": "969",
            "missing": "0",
            "min": "-2",
            "max": "1",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V46",
            "index": "45",
            "type": "numeric",
            "distinct": "869",
            "missing": "0",
            "min": "-1",
            "max": "3",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V47",
            "index": "46",
            "type": "numeric",
            "distinct": "758",
            "missing": "0",
            "min": "-1",
            "max": "2",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V48",
            "index": "47",
            "type": "numeric",
            "distinct": "746",
            "missing": "0",
            "min": "0",
            "max": "3",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V49",
            "index": "48",
            "type": "numeric",
            "distinct": "1044",
            "missing": "0",
            "min": "-1",
            "max": "2",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V50",
            "index": "49",
            "type": "numeric",
            "distinct": "701",
            "missing": "0",
            "min": "0",
            "max": "10",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "V51",
            "index": "50",
            "type": "numeric",
            "distinct": "1089",
            "missing": "0",
            "min": "-2",
            "max": "1",
            "mean": "0",
            "stdev": "1"
        }
    ],
    "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
}