{ "data_id": "44487", "name": "Australian_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "Australian_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "34ee5172-111e-407c-84b7-73d2e99439c7", "description": "Subsampling of the dataset Australian (40981) 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 18:22:34", "update_comment": null, "last_update": "2022-11-17 18:22:34", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111249\/dataset", "default_target_attribute": "A15", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "Australian_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset Australian (40981) 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": 690, "NumberOfFeatures": 15, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 6, "NumberOfSymbolicFeatures": 9, "PercentageOfBinaryFeatures": 33.33333333333333, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.5195936139332366, "PercentageOfMissingValues": 0, "Dimensionality": 0.021739130434782608, "PercentageOfNumericFeatures": 40, "MajorityClassPercentage": 55.507246376811594, "PercentageOfSymbolicFeatures": 60, "MajorityClassSize": 383, "MinorityClassPercentage": 44.492753623188406, "MinorityClassSize": 307, "NumberOfBinaryFeatures": 5 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Mathematics" } ], "features": [ { "name": "A15", "index": "14", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "383", "0" ], [ "0", "307" ] ] ] }, { "name": "A1", "index": "0", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "121", "101" ], [ "262", "206" ] ] ] }, { "name": "A2", "index": "1", "type": "numeric", "distinct": "350", "missing": "0", "min": "1", "max": "350", "mean": "149", "stdev": "93" }, { "name": "A3", "index": "2", "type": "numeric", "distinct": "215", "missing": "0", "min": "1", "max": "215", "mean": "83", "stdev": "59" }, { "name": "A4", "index": "3", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "118", "45" ], [ "265", "260" ], [ "0", "2" ] ] ] }, { "name": "A5", "index": "4", "type": "nominal", "distinct": "14", "missing": "0", "distr": [ [ "1", "2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14" ], [ [ "46", "7" ], [ "23", "7" ], [ "45", "14" ], [ "37", "14" ], [ "7", "3" ], [ "35", "19" ], [ "22", "16" ], [ "80", "66" ], [ "31", "33" ], [ "11", "14" ], [ "27", "51" ], [ "1", "2" ], [ "12", "29" ], [ "6", "32" ] ] ] }, { "name": "A6", "index": "5", "type": "nominal", "distinct": "8", "missing": "0", "distr": [ [ "1", "2", "3", "4", "5", "7", "8", "9" ], [ [ "49", "8" ], [ "4", "2" ], [ "5", "3" ], [ "235", "173" ], [ "34", "25" ], [ "3", "3" ], [ "51", "87" ], [ "2", "6" ] ] ] }, { "name": "A7", "index": "6", "type": "numeric", "distinct": "132", "missing": "0", "min": "1", "max": "132", "mean": "37", "stdev": "36" }, { "name": "A8", "index": "7", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "306", "23" ], [ "77", "284" ] ] ] }, { "name": "A9", "index": "8", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "297", "98" ], [ "86", "209" ] ] ] }, { "name": "A10", "index": "9", "type": "numeric", "distinct": "23", "missing": "0", "min": "1", "max": "23", "mean": "3", "stdev": "4" }, { "name": "A11", "index": "10", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "213", "161" ], [ "170", "146" ] ] ] }, { "name": "A12", "index": "11", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "42", "15" ], [ "338", "287" ], [ "3", "5" ] ] ] }, { "name": "A13", "index": "12", "type": "numeric", "distinct": "171", "missing": "0", "min": "1", "max": "171", "mean": "59", "stdev": "46" }, { "name": "A14", "index": "13", "type": "numeric", "distinct": "240", "missing": "0", "min": "1", "max": "240", "mean": "55", "stdev": "73" } ], "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 }