{
    "data_id": "44366",
    "name": "california_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True",
    "exact_name": "california_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True",
    "version": 1,
    "version_label": "14f8cae1-857e-4d81-a9b9-0b4a3fffa4d9",
    "description": "Subsampling of the dataset california (44090) with\n\nseed=4\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 17:32:48",
    "update_comment": null,
    "last_update": "2022-11-17 17:32:48",
    "licence": "See source",
    "status": "active",
    "error_message": null,
    "url": "https:\/\/api.openml.org\/data\/download\/22111128\/dataset",
    "kaggle_url": null,
    "default_target_attribute": "price",
    "row_id_attribute": null,
    "ignore_attribute": null,
    "runs": 0,
    "suggest": {
        "input": [
            "california_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True",
            "Subsampling of the dataset california (44090) with seed=4 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.choic "
        ],
        "weight": 5
    },
    "qualities": {
        "NumberOfInstances": 2000,
        "NumberOfFeatures": 9,
        "NumberOfClasses": 2,
        "NumberOfMissingValues": 0,
        "NumberOfInstancesWithMissingValues": 0,
        "NumberOfNumericFeatures": 8,
        "NumberOfSymbolicFeatures": 1,
        "PercentageOfBinaryFeatures": 11.11111111111111,
        "PercentageOfInstancesWithMissingValues": 0,
        "PercentageOfMissingValues": 0,
        "AutoCorrelation": 0.5017508754377189,
        "PercentageOfNumericFeatures": 88.88888888888889,
        "Dimensionality": 0.0045,
        "PercentageOfSymbolicFeatures": 11.11111111111111,
        "MajorityClassPercentage": 50,
        "MajorityClassSize": 1000,
        "MinorityClassPercentage": 50,
        "MinorityClassSize": 1000,
        "NumberOfBinaryFeatures": 1
    },
    "tags": [],
    "features": [
        {
            "name": "price",
            "index": "8",
            "type": "nominal",
            "distinct": "2",
            "missing": "0",
            "target": "1",
            "distr": [
                [
                    "True",
                    "False"
                ],
                [
                    [
                        "1000",
                        "0"
                    ],
                    [
                        "0",
                        "1000"
                    ]
                ]
            ]
        },
        {
            "name": "MedInc",
            "index": "0",
            "type": "numeric",
            "distinct": "1803",
            "missing": "0",
            "min": "0",
            "max": "15",
            "mean": "4",
            "stdev": "2"
        },
        {
            "name": "HouseAge",
            "index": "1",
            "type": "numeric",
            "distinct": "52",
            "missing": "0",
            "min": "1",
            "max": "52",
            "mean": "28",
            "stdev": "13"
        },
        {
            "name": "AveRooms",
            "index": "2",
            "type": "numeric",
            "distinct": "1974",
            "missing": "0",
            "min": "2",
            "max": "56",
            "mean": "5",
            "stdev": "2"
        },
        {
            "name": "AveBedrms",
            "index": "3",
            "type": "numeric",
            "distinct": "1860",
            "missing": "0",
            "min": "0",
            "max": "10",
            "mean": "1",
            "stdev": "0"
        },
        {
            "name": "Population",
            "index": "4",
            "type": "numeric",
            "distinct": "1386",
            "missing": "0",
            "min": "23",
            "max": "13251",
            "mean": "1444",
            "stdev": "1177"
        },
        {
            "name": "AveOccup",
            "index": "5",
            "type": "numeric",
            "distinct": "1981",
            "missing": "0",
            "min": "1",
            "max": "1243",
            "mean": "4",
            "stdev": "28"
        },
        {
            "name": "Latitude",
            "index": "6",
            "type": "numeric",
            "distinct": "499",
            "missing": "0",
            "min": "33",
            "max": "42",
            "mean": "36",
            "stdev": "2"
        },
        {
            "name": "Longitude",
            "index": "7",
            "type": "numeric",
            "distinct": "530",
            "missing": "0",
            "min": "-124",
            "max": "0",
            "mean": "-120",
            "stdev": "2"
        }
    ],
    "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
}