{ "data_id": "44751", "name": "guillermo_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "guillermo_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "98c1177f-ade2-41a7-b8c1-5c524f670b50", "description": "Subsampling of the dataset guillermo (41159) with\n\nseed=3\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 18:48:07", "update_comment": null, "last_update": "2022-11-17 18:48:07", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111513\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "guillermo_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset guillermo (41159) with seed=3 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": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "AutoCorrelation": 0.5222611305652827, "PercentageOfMissingValues": 0, "Dimensionality": 0.0505, "PercentageOfNumericFeatures": 99.00990099009901, "MajorityClassPercentage": 60, "PercentageOfSymbolicFeatures": 0.9900990099009901, "MajorityClassSize": 1200, "MinorityClassPercentage": 40, "MinorityClassSize": 800, "NumberOfBinaryFeatures": 1, "PercentageOfBinaryFeatures": 0.9900990099009901, "PercentageOfInstancesWithMissingValues": 0 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Mathematics" } ], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "1200", "0" ], [ "0", "800" ] ] ] }, { "name": "V7", "index": "0", "type": "numeric", "distinct": "614", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V21", "index": "1", "type": "numeric", "distinct": "1021", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "1" }, { "name": "V130", "index": "2", "type": "numeric", "distinct": "464", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V138", "index": "3", "type": "numeric", "distinct": "735", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V166", "index": "4", "type": "numeric", "distinct": "862", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "V183", "index": "5", "type": "numeric", "distinct": "236", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "V327", "index": "6", "type": "numeric", "distinct": "511", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V360", "index": "7", "type": "numeric", "distinct": "903", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V388", "index": "8", "type": "numeric", "distinct": "412", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V396", "index": "9", "type": "numeric", "distinct": "472", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V440", "index": "10", "type": "numeric", "distinct": "792", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V480", "index": "11", "type": "numeric", "distinct": "716", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V591", "index": "12", "type": "numeric", "distinct": "679", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V673", "index": "13", "type": "numeric", "distinct": "521", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V731", "index": "14", "type": "numeric", "distinct": "732", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V754", "index": "15", "type": "numeric", "distinct": "291", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "V762", "index": "16", "type": "numeric", "distinct": "646", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V810", "index": "17", "type": "numeric", "distinct": "419", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V884", "index": "18", "type": "numeric", "distinct": "737", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V936", "index": "19", "type": "numeric", "distinct": "748", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V965", "index": "20", "type": "numeric", "distinct": "780", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V995", "index": "21", "type": "numeric", "distinct": "749", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V1040", "index": "22", "type": "numeric", "distinct": "983", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V1059", "index": "23", "type": "numeric", "distinct": "459", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V1081", "index": "24", "type": "numeric", "distinct": "445", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V1083", "index": "25", "type": "numeric", "distinct": "428", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V1116", "index": "26", "type": "numeric", "distinct": "649", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V1203", "index": "27", "type": "numeric", "distinct": "666", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V1240", "index": "28", "type": "numeric", "distinct": "320", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V1250", "index": "29", "type": "numeric", "distinct": "852", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "V1266", "index": "30", "type": "numeric", "distinct": "237", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "V1274", "index": "31", "type": "numeric", "distinct": "261", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "0" }, { "name": "V1333", "index": "32", "type": "numeric", "distinct": "619", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V1354", "index": "33", "type": "numeric", "distinct": "708", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V1397", "index": "34", "type": "numeric", "distinct": "709", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "V1398", "index": "35", "type": "numeric", "distinct": "870", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V1594", "index": "36", "type": "numeric", "distinct": "726", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V1651", "index": "37", "type": "numeric", "distinct": "905", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "V1659", "index": "38", "type": "numeric", "distinct": "854", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "1" }, { "name": "V1693", "index": "39", "type": "numeric", "distinct": "778", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "V1774", "index": "40", "type": "numeric", "distinct": "687", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V1819", "index": "41", "type": "numeric", "distinct": "221", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "V1823", "index": "42", "type": "numeric", "distinct": "143", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "V1837", "index": "43", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "V1907", "index": "44", "type": "numeric", "distinct": "614", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V2004", "index": "45", "type": "numeric", "distinct": "717", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V2017", "index": "46", "type": "numeric", "distinct": "770", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V2018", "index": "47", "type": "numeric", "distinct": "384", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V2082", "index": "48", "type": "numeric", "distinct": "645", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V2181", "index": "49", "type": "numeric", "distinct": "323", "missing": "0", "min": "0", "max": "12", "mean": "0", "stdev": "1" }, { "name": "V2213", "index": "50", "type": "numeric", "distinct": "585", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V2218", "index": "51", "type": "numeric", "distinct": "377", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V2448", "index": "52", "type": "numeric", "distinct": "573", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V2479", "index": "53", "type": "numeric", "distinct": "445", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V2486", "index": "54", "type": "numeric", "distinct": "724", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V2548", "index": "55", "type": "numeric", "distinct": "368", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V2594", "index": "56", "type": "numeric", "distinct": "406", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "V2595", "index": "57", "type": "numeric", "distinct": "571", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V2615", "index": "58", "type": "numeric", "distinct": "170", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "V2690", "index": "59", "type": "numeric", "distinct": "639", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V2745", "index": "60", "type": "numeric", "distinct": "667", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V2753", "index": "61", "type": "numeric", "distinct": "878", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V2795", "index": "62", "type": "numeric", "distinct": "478", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V2814", "index": "63", "type": "numeric", "distinct": "494", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V2815", "index": "64", "type": "numeric", "distinct": "974", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "V2816", "index": "65", "type": "numeric", "distinct": "836", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V2820", "index": "66", "type": "numeric", "distinct": "667", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V2913", "index": "67", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V2924", "index": "68", "type": "numeric", "distinct": "204", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "0" }, { "name": "V2948", "index": "69", "type": "numeric", "distinct": "679", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V3009", "index": "70", "type": "numeric", "distinct": "794", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V3087", "index": "71", "type": "numeric", "distinct": "761", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "1" }, { "name": "V3096", "index": "72", "type": "numeric", "distinct": "924", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "V3119", "index": "73", "type": "numeric", "distinct": "344", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "V3169", "index": "74", "type": "numeric", "distinct": "471", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V3199", "index": "75", "type": "numeric", "distinct": "514", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V3254", "index": "76", "type": "numeric", "distinct": "781", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V3288", "index": "77", "type": "numeric", "distinct": "540", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V3325", "index": "78", "type": "numeric", "distinct": "640", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "V3367", "index": "79", "type": "numeric", "distinct": "880", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V3406", "index": "80", "type": "numeric", "distinct": "563", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V3514", "index": "81", "type": "numeric", "distinct": "524", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V3551", "index": "82", "type": "numeric", "distinct": "950", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "2" }, { "name": "V3606", "index": "83", "type": "numeric", "distinct": "941", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "V3649", "index": "84", "type": "numeric", "distinct": "548", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V3654", "index": "85", "type": "numeric", "distinct": "708", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V3682", "index": "86", "type": "numeric", "distinct": "512", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V3746", "index": "87", "type": "numeric", "distinct": "817", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "V3769", "index": "88", "type": "numeric", "distinct": "420", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V3787", "index": "89", "type": "numeric", "distinct": "707", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V3915", "index": "90", "type": "numeric", "distinct": "632", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "V3958", "index": "91", "type": "numeric", "distinct": "782", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V3972", "index": "92", "type": "numeric", "distinct": "846", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V3978", "index": "93", "type": "numeric", "distinct": "912", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V4004", "index": "94", "type": "numeric", "distinct": "577", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V4044", "index": "95", "type": "numeric", "distinct": "918", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V4103", "index": "96", "type": "numeric", "distinct": "1220", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V4128", "index": "97", "type": "numeric", "distinct": "1221", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V4280", "index": "98", "type": "numeric", "distinct": "1223", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V4291", "index": "99", "type": "numeric", "distinct": "1218", "missing": "0", "min": "-1", "max": "1", "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 }