DEVELOPMENT... { "data_id": "44755", "name": "riccardo_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "riccardo_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "5bb5a052-71d4-48a3-ad7f-809c0ddb37fb", "description": "Subsampling of the dataset riccardo (41161) 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": "David Wilson", "uploader_id": 32840, "visibility": "public", "creator": "\"Eddie Bergman\"", "contributor": null, "date": "2022-11-17 18:48:30", "update_comment": null, "last_update": "2022-11-17 18:48:30", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111517\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "riccardo_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset riccardo (41161) 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": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "PercentageOfSymbolicFeatures": 0.9900990099009901, "AutoCorrelation": 0.6223111555777889, "PercentageOfNumericFeatures": 99.00990099009901, "PercentageOfMissingValues": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfBinaryFeatures": 0.9900990099009901, "NumberOfBinaryFeatures": 1, "MinorityClassSize": 500, "MinorityClassPercentage": 25, "MajorityClassSize": 1500, "MajorityClassPercentage": 75, "Dimensionality": 0.0505 }, "tags": [], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "1500", "0" ], [ "0", "500" ] ] ] }, { "name": "V166", "index": "0", "type": "numeric", "distinct": "1033", "missing": "0", "min": "0", "max": "18", "mean": "1", "stdev": "1" }, { "name": "V169", "index": "1", "type": "numeric", "distinct": "1143", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "1" }, { "name": "V233", "index": "2", "type": "numeric", "distinct": "699", "missing": "0", "min": "0", "max": "17", "mean": "1", "stdev": "2" }, { "name": "V245", "index": "3", "type": "numeric", "distinct": "905", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V328", "index": "4", "type": "numeric", "distinct": "962", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V387", "index": "5", "type": "numeric", "distinct": "779", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V415", "index": "6", "type": "numeric", "distinct": "359", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "0" }, { "name": "V433", "index": "7", "type": "numeric", "distinct": "799", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V445", "index": "8", "type": "numeric", "distinct": "938", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V457", "index": "9", "type": "numeric", "distinct": "379", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "0" }, { "name": "V459", "index": "10", "type": "numeric", "distinct": "901", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V634", "index": "11", "type": "numeric", "distinct": "864", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V792", "index": "12", "type": "numeric", "distinct": "839", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V794", "index": "13", "type": "numeric", "distinct": "557", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V849", "index": "14", "type": "numeric", "distinct": "940", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V860", "index": "15", "type": "numeric", "distinct": "824", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V911", "index": "16", "type": "numeric", "distinct": "801", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V929", "index": "17", "type": "numeric", "distinct": "955", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "1" }, { "name": "V951", "index": "18", "type": "numeric", "distinct": "1038", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V1098", "index": "19", "type": "numeric", "distinct": "795", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V1099", "index": "20", "type": "numeric", "distinct": "977", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V1111", "index": "21", "type": "numeric", "distinct": "517", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V1159", "index": "22", "type": "numeric", "distinct": "801", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V1254", "index": "23", "type": "numeric", "distinct": "965", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V1290", "index": "24", "type": "numeric", "distinct": "1029", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V1351", "index": "25", "type": "numeric", "distinct": "773", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V1409", "index": "26", "type": "numeric", "distinct": "1003", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V1411", "index": "27", "type": "numeric", "distinct": "911", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V1454", "index": "28", "type": "numeric", "distinct": "1032", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V1467", "index": "29", "type": "numeric", "distinct": "989", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V1610", "index": "30", "type": "numeric", "distinct": "911", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V1659", "index": "31", "type": "numeric", "distinct": "918", "missing": "0", "min": "0", "max": "13", "mean": "1", "stdev": "1" }, { "name": "V1736", "index": "32", "type": "numeric", "distinct": "1010", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V1739", "index": "33", "type": "numeric", "distinct": "985", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V1787", "index": "34", "type": "numeric", "distinct": "716", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V1827", "index": "35", "type": "numeric", "distinct": "325", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "V1874", "index": "36", "type": "numeric", "distinct": "548", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V1885", "index": "37", "type": "numeric", "distinct": "823", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V1897", "index": "38", "type": "numeric", "distinct": "654", "missing": "0", "min": "0", "max": "12", "mean": "0", "stdev": "1" }, { "name": "V1904", "index": "39", "type": "numeric", "distinct": "1073", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V1913", "index": "40", "type": "numeric", "distinct": "385", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V1937", "index": "41", "type": "numeric", "distinct": "483", "missing": "0", "min": "0", "max": "11", "mean": "0", "stdev": "1" }, { "name": "V2002", "index": "42", "type": "numeric", "distinct": "698", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V2016", "index": "43", "type": "numeric", "distinct": "445", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V2030", "index": "44", "type": "numeric", "distinct": "1105", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "1" }, { "name": "V2080", "index": "45", "type": "numeric", "distinct": "915", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "1" }, { "name": "V2129", "index": "46", "type": "numeric", "distinct": "836", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V2134", "index": "47", "type": "numeric", "distinct": "1087", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V2153", "index": "48", "type": "numeric", "distinct": "939", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V2167", "index": "49", "type": "numeric", "distinct": "736", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V2206", "index": "50", "type": "numeric", "distinct": "827", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V2226", "index": "51", "type": "numeric", "distinct": "923", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V2243", "index": "52", "type": "numeric", "distinct": "989", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "2" }, { "name": "V2352", "index": "53", "type": "numeric", "distinct": "845", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V2372", "index": "54", "type": "numeric", "distinct": "489", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "V2421", "index": "55", "type": "numeric", "distinct": "808", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V2458", "index": "56", "type": "numeric", "distinct": "970", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V2525", "index": "57", "type": "numeric", "distinct": "830", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "V2534", "index": "58", "type": "numeric", "distinct": "954", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "1" }, { "name": "V2535", "index": "59", "type": "numeric", "distinct": "443", "missing": "0", "min": "0", "max": "13", "mean": "0", "stdev": "1" }, { "name": "V2536", "index": "60", "type": "numeric", "distinct": "1181", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V2627", "index": "61", "type": "numeric", "distinct": "703", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V2678", "index": "62", "type": "numeric", "distinct": "896", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V2714", "index": "63", "type": "numeric", "distinct": "791", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V2750", "index": "64", "type": "numeric", "distinct": "977", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V2772", "index": "65", "type": "numeric", "distinct": "979", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V2828", "index": "66", "type": "numeric", "distinct": "886", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V2867", "index": "67", "type": "numeric", "distinct": "903", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V2891", "index": "68", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V2898", "index": "69", "type": "numeric", "distinct": "886", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V2937", "index": "70", "type": "numeric", "distinct": "817", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V2950", "index": "71", "type": "numeric", "distinct": "724", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V2969", "index": "72", "type": "numeric", "distinct": "829", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V2979", "index": "73", "type": "numeric", "distinct": "466", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "V3066", "index": "74", "type": "numeric", "distinct": "1024", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "1" }, { "name": "V3163", "index": "75", "type": "numeric", "distinct": "919", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V3292", "index": "76", "type": "numeric", "distinct": "575", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V3299", "index": "77", "type": "numeric", "distinct": "925", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V3352", "index": "78", "type": "numeric", "distinct": "767", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V3422", "index": "79", "type": "numeric", "distinct": "1178", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "1" }, { "name": "V3516", "index": "80", "type": "numeric", "distinct": "718", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V3552", "index": "81", "type": "numeric", "distinct": "702", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V3622", "index": "82", "type": "numeric", "distinct": "1136", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "1" }, { "name": "V3673", "index": "83", "type": "numeric", "distinct": "553", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "V3685", "index": "84", "type": "numeric", "distinct": "938", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "1" }, { "name": "V3707", "index": "85", "type": "numeric", "distinct": "532", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "V3722", "index": "86", "type": "numeric", "distinct": "495", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V3768", "index": "87", "type": "numeric", "distinct": "797", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V3781", "index": "88", "type": "numeric", "distinct": "1046", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V3818", "index": "89", "type": "numeric", "distinct": "932", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V3854", "index": "90", "type": "numeric", "distinct": "603", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V3927", "index": "91", "type": "numeric", "distinct": "1081", "missing": "0", "min": "0", "max": "13", "mean": "1", "stdev": "1" }, { "name": "V3954", "index": "92", "type": "numeric", "distinct": "1056", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V3994", "index": "93", "type": "numeric", "distinct": "996", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "1" }, { "name": "V4078", "index": "94", "type": "numeric", "distinct": "960", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V4093", "index": "95", "type": "numeric", "distinct": "961", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V4146", "index": "96", "type": "numeric", "distinct": "1766", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V4179", "index": "97", "type": "numeric", "distinct": "1779", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V4207", "index": "98", "type": "numeric", "distinct": "1760", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V4292", "index": "99", "type": "numeric", "distinct": "1776", "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 }