{ "data_id": "44735", "name": "volkert_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "volkert_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "b92ca6a2-c8ba-4fff-8988-907f8eedf016", "description": "Subsampling of the dataset volkert (41166) 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 18:46:47", "update_comment": null, "last_update": "2022-11-17 18:46:47", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111497\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "volkert_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset volkert (41166) 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( " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 101, "NumberOfClasses": 10, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "MinorityClassSize": 47, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.14807403701850924, "PercentageOfMissingValues": 0, "Dimensionality": 0.0505, "PercentageOfNumericFeatures": 99.00990099009901, "MajorityClassPercentage": 21.95, "PercentageOfSymbolicFeatures": 0.9900990099009901, "MajorityClassSize": 439, "MinorityClassPercentage": 2.35 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Mathematics" } ], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "10", "missing": "0", "target": "1", "distr": [ [ "0", "1", "2", "3", "4", "5", "6", "7", "8", "9" ], [ [ "253", "0", "0", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "61", "0", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "395", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "100", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "120", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "323", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "51", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "439", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "0", "47", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "0", "0", "211" ] ] ] }, { "name": "V5", "index": "0", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V6", "index": "1", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V7", "index": "2", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V9", "index": "3", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V10", "index": "4", "type": "numeric", "distinct": "369", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V13", "index": "5", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V15", "index": "6", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V16", "index": "7", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V17", "index": "8", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V18", "index": "9", "type": "numeric", "distinct": "819", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V20", "index": "10", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V22", "index": "11", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V23", "index": "12", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V25", "index": "13", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V26", "index": "14", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V27", "index": "15", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V29", "index": "16", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V30", "index": "17", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V31", "index": "18", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V34", "index": "19", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V36", "index": "20", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V39", "index": "21", "type": "numeric", "distinct": "905", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V40", "index": "22", "type": "numeric", "distinct": "797", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V41", "index": "23", "type": "numeric", "distinct": "716", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V42", "index": "24", "type": "numeric", "distinct": "634", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V43", "index": "25", "type": "numeric", "distinct": "562", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V45", "index": "26", "type": "numeric", "distinct": "451", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V46", "index": "27", "type": "numeric", "distinct": "391", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V47", "index": "28", "type": "numeric", "distinct": "360", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V55", "index": "29", "type": "numeric", "distinct": "168", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V58", "index": "30", "type": "numeric", "distinct": "138", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V59", "index": "31", "type": "numeric", "distinct": "123", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V62", "index": "32", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V64", "index": "33", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V65", "index": "34", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V66", "index": "35", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V67", "index": "36", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V68", "index": "37", "type": "numeric", "distinct": "165", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V69", "index": "38", "type": "numeric", "distinct": "188", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V71", "index": "39", "type": "numeric", "distinct": "557", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V72", "index": "40", "type": "numeric", "distinct": "713", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V73", "index": "41", "type": "numeric", "distinct": "808", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V74", "index": "42", "type": "numeric", "distinct": "849", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V75", "index": "43", "type": "numeric", "distinct": "842", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V76", "index": "44", "type": "numeric", "distinct": "822", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V77", "index": "45", "type": "numeric", "distinct": "748", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V79", "index": "46", "type": "numeric", "distinct": "570", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V80", "index": "47", "type": "numeric", "distinct": "505", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V84", "index": "48", "type": "numeric", "distinct": "185", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V87", "index": "49", "type": "numeric", "distinct": "1844", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "V89", "index": "50", "type": "numeric", "distinct": "1856", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V90", "index": "51", "type": "numeric", "distinct": "1852", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V91", "index": "52", "type": "numeric", "distinct": "1870", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V92", "index": "53", "type": "numeric", "distinct": "1852", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V93", "index": "54", "type": "numeric", "distinct": "1615", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V95", "index": "55", "type": "numeric", "distinct": "1573", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V96", "index": "56", "type": "numeric", "distinct": "1615", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V97", "index": "57", "type": "numeric", "distinct": "1521", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "V100", "index": "58", "type": "numeric", "distinct": "1443", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V101", "index": "59", "type": "numeric", "distinct": "1726", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V103", "index": "60", "type": "numeric", "distinct": "1672", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V104", "index": "61", "type": "numeric", "distinct": "1688", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V106", "index": "62", "type": "numeric", "distinct": "1871", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V108", "index": "63", "type": "numeric", "distinct": "1871", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V109", "index": "64", "type": "numeric", "distinct": "444", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V111", "index": "65", "type": "numeric", "distinct": "309", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V112", "index": "66", "type": "numeric", "distinct": "300", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V113", "index": "67", "type": "numeric", "distinct": "293", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V118", "index": "68", "type": "numeric", "distinct": "276", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V119", "index": "69", "type": "numeric", "distinct": "368", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V122", "index": "70", "type": "numeric", "distinct": "282", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V126", "index": "71", "type": "numeric", "distinct": "387", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V127", "index": "72", "type": "numeric", "distinct": "355", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V128", "index": "73", "type": "numeric", "distinct": "279", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V133", "index": "74", "type": "numeric", "distinct": "304", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V134", "index": "75", "type": "numeric", "distinct": "386", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V136", "index": "76", "type": "numeric", "distinct": "299", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V137", "index": "77", "type": "numeric", "distinct": "327", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V138", "index": "78", "type": "numeric", "distinct": "332", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V140", "index": "79", "type": "numeric", "distinct": "348", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V144", "index": "80", "type": "numeric", "distinct": "504", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V145", "index": "81", "type": "numeric", "distinct": "470", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V146", "index": "82", "type": "numeric", "distinct": "395", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V148", "index": "83", "type": "numeric", "distinct": "357", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V150", "index": "84", "type": "numeric", "distinct": "340", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V154", "index": "85", "type": "numeric", "distinct": "299", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V155", "index": "86", "type": "numeric", "distinct": "377", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V156", "index": "87", "type": "numeric", "distinct": "289", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V157", "index": "88", "type": "numeric", "distinct": "280", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V160", "index": "89", "type": "numeric", "distinct": "276", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V161", "index": "90", "type": "numeric", "distinct": "282", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V163", "index": "91", "type": "numeric", "distinct": "363", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V167", "index": "92", "type": "numeric", "distinct": "277", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V168", "index": "93", "type": "numeric", "distinct": "270", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V170", "index": "94", "type": "numeric", "distinct": "365", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V173", "index": "95", "type": "numeric", "distinct": "305", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V174", "index": "96", "type": "numeric", "distinct": "287", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V175", "index": "97", "type": "numeric", "distinct": "306", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V177", "index": "98", "type": "numeric", "distinct": "293", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V178", "index": "99", "type": "numeric", "distinct": "310", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" } ], "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 }