{ "data_id": "44555", "name": "vehicle_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "vehicle_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "24dc7c88-74ed-4e81-8674-65e485ebf8e3", "description": "Subsampling of the dataset vehicle (54) 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 18:32:49", "update_comment": null, "last_update": "2022-11-17 18:32:49", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111317\/dataset", "default_target_attribute": "Class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "vehicle_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset vehicle (54) 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( cla " ], "weight": 5 }, "qualities": { "NumberOfInstances": 846, "NumberOfFeatures": 19, "NumberOfClasses": 4, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 18, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "AutoCorrelation": 0.2579881656804734, "PercentageOfNumericFeatures": 94.73684210526315, "Dimensionality": 0.022458628841607566, "PercentageOfSymbolicFeatures": 5.263157894736842, "MajorityClassPercentage": 25.768321513002363, "MajorityClassSize": 218, "MinorityClassPercentage": 23.52245862884161, "MinorityClassSize": 199, "NumberOfBinaryFeatures": 0 }, "tags": [ { "uploader": "38960", "tag": "Statistics" } ], "features": [ { "name": "Class", "index": "18", "type": "nominal", "distinct": "4", "missing": "0", "target": "1", "distr": [ [ "opel", "saab", "bus", "van" ], [ [ "212", "0", "0", "0" ], [ "0", "217", "0", "0" ], [ "0", "0", "218", "0" ], [ "0", "0", "0", "199" ] ] ] }, { "name": "COMPACTNESS", "index": "0", "type": "numeric", "distinct": "44", "missing": "0", "min": "73", "max": "119", "mean": "94", "stdev": "8" }, { "name": "CIRCULARITY", "index": "1", "type": "numeric", "distinct": "27", "missing": "0", "min": "33", "max": "59", "mean": "45", "stdev": "6" }, { "name": "DISTANCE_CIRCULARITY", "index": "2", "type": "numeric", "distinct": "63", "missing": "0", "min": "40", "max": "112", "mean": "82", "stdev": "16" }, { "name": "RADIUS_RATIO", "index": "3", "type": "numeric", "distinct": "134", "missing": "0", "min": "104", "max": "333", "mean": "169", "stdev": "33" }, { "name": "PR.AXIS_ASPECT_RATIO", "index": "4", "type": "numeric", "distinct": "37", "missing": "0", "min": "47", "max": "138", "mean": "62", "stdev": "8" }, { "name": "MAX.LENGTH_ASPECT_RATIO", "index": "5", "type": "numeric", "distinct": "21", "missing": "0", "min": "2", "max": "55", "mean": "9", "stdev": "5" }, { "name": "SCATTER_RATIO", "index": "6", "type": "numeric", "distinct": "131", "missing": "0", "min": "112", "max": "265", "mean": "169", "stdev": "33" }, { "name": "ELONGATEDNESS", "index": "7", "type": "numeric", "distinct": "35", "missing": "0", "min": "26", "max": "61", "mean": "41", "stdev": "8" }, { "name": "PR.AXIS_RECTANGULARITY", "index": "8", "type": "numeric", "distinct": "13", "missing": "0", "min": "17", "max": "29", "mean": "21", "stdev": "3" }, { "name": "MAX.LENGTH_RECTANGULARITY", "index": "9", "type": "numeric", "distinct": "66", "missing": "0", "min": "118", "max": "188", "mean": "148", "stdev": "15" }, { "name": "SCALED_VARIANCE_MAJOR", "index": "10", "type": "numeric", "distinct": "128", "missing": "0", "min": "130", "max": "320", "mean": "189", "stdev": "31" }, { "name": "SCALED_VARIANCE_MINOR", "index": "11", "type": "numeric", "distinct": "424", "missing": "0", "min": "184", "max": "1018", "mean": "440", "stdev": "177" }, { "name": "SCALED_RADIUS_OF_GYRATION", "index": "12", "type": "numeric", "distinct": "143", "missing": "0", "min": "109", "max": "268", "mean": "175", "stdev": "33" }, { "name": "SKEWNESS_ABOUT_MAJOR", "index": "13", "type": "numeric", "distinct": "39", "missing": "0", "min": "59", "max": "135", "mean": "72", "stdev": "7" }, { "name": "SKEWNESS_ABOUT_MINOR", "index": "14", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "22", "mean": "6", "stdev": "5" }, { "name": "KURTOSIS_ABOUT_MAJOR", "index": "15", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "41", "mean": "13", "stdev": "9" }, { "name": "KURTOSIS_ABOUT_MINOR", "index": "16", "type": "numeric", "distinct": "30", "missing": "0", "min": "176", "max": "206", "mean": "189", "stdev": "6" }, { "name": "HOLLOWS_RATIO", "index": "17", "type": "numeric", "distinct": "31", "missing": "0", "min": "181", "max": "211", "mean": "196", "stdev": "7" } ], "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 }