{ "data_id": "44753", "name": "riccardo_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "riccardo_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "5592d4ca-6d75-45a4-9c82-768bb456b1dc", "description": "Subsampling of the dataset riccardo (41161) with\n\nseed=0\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 18:48:19", "update_comment": null, "last_update": "2022-11-17 18:48:19", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111515\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "riccardo_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset riccardo (41161) with seed=0 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, "MajorityClassPercentage": 75, "PercentageOfSymbolicFeatures": 0.9900990099009901, "MajorityClassSize": 1500, "MinorityClassPercentage": 25, "MinorityClassSize": 500, "NumberOfBinaryFeatures": 1, "PercentageOfBinaryFeatures": 0.9900990099009901, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.616808404202101, "PercentageOfMissingValues": 0, "Dimensionality": 0.0505, "PercentageOfNumericFeatures": 99.00990099009901 }, "tags": [ { "uploader": "38960", "tag": "Sociology" }, { "uploader": "38960", "tag": "Statistics" } ], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "1500", "0" ], [ "0", "500" ] ] ] }, { "name": "V12", "index": "0", "type": "numeric", "distinct": "751", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V23", "index": "1", "type": "numeric", "distinct": "1062", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V36", "index": "2", "type": "numeric", "distinct": "830", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V70", "index": "3", "type": "numeric", "distinct": "437", "missing": "0", "min": "0", "max": "14", "mean": "0", "stdev": "1" }, { "name": "V94", "index": "4", "type": "numeric", "distinct": "719", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V121", "index": "5", "type": "numeric", "distinct": "897", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V142", "index": "6", "type": "numeric", "distinct": "893", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "1" }, { "name": "V173", "index": "7", "type": "numeric", "distinct": "982", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V209", "index": "8", "type": "numeric", "distinct": "806", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V312", "index": "9", "type": "numeric", "distinct": "844", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V317", "index": "10", "type": "numeric", "distinct": "950", "missing": "0", "min": "0", "max": "14", "mean": "1", "stdev": "2" }, { "name": "V341", "index": "11", "type": "numeric", "distinct": "695", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V361", "index": "12", "type": "numeric", "distinct": "822", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V378", "index": "13", "type": "numeric", "distinct": "607", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V527", "index": "14", "type": "numeric", "distinct": "965", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "1" }, { "name": "V576", "index": "15", "type": "numeric", "distinct": "769", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "V737", "index": "16", "type": "numeric", "distinct": "899", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V743", "index": "17", "type": "numeric", "distinct": "1001", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V975", "index": "18", "type": "numeric", "distinct": "1087", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V1090", "index": "19", "type": "numeric", "distinct": "966", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "1" }, { "name": "V1093", "index": "20", "type": "numeric", "distinct": "890", "missing": "0", "min": "0", "max": "14", "mean": "1", "stdev": "1" }, { "name": "V1132", "index": "21", "type": "numeric", "distinct": "872", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V1134", "index": "22", "type": "numeric", "distinct": "694", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V1170", "index": "23", "type": "numeric", "distinct": "1159", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V1269", "index": "24", "type": "numeric", "distinct": "548", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V1294", "index": "25", "type": "numeric", "distinct": "1032", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "2" }, { "name": "V1325", "index": "26", "type": "numeric", "distinct": "202", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "V1378", "index": "27", "type": "numeric", "distinct": "863", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V1407", "index": "28", "type": "numeric", "distinct": "645", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V1448", "index": "29", "type": "numeric", "distinct": "793", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V1530", "index": "30", "type": "numeric", "distinct": "858", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V1602", "index": "31", "type": "numeric", "distinct": "969", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V1615", "index": "32", "type": "numeric", "distinct": "998", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V1620", "index": "33", "type": "numeric", "distinct": "1191", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "1" }, { "name": "V1630", "index": "34", "type": "numeric", "distinct": "502", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V1657", "index": "35", "type": "numeric", "distinct": "917", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V1664", "index": "36", "type": "numeric", "distinct": "878", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V1679", "index": "37", "type": "numeric", "distinct": "675", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V1709", "index": "38", "type": "numeric", "distinct": "733", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "V1791", "index": "39", "type": "numeric", "distinct": "915", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "1" }, { "name": "V1806", "index": "40", "type": "numeric", "distinct": "1112", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V1959", "index": "41", "type": "numeric", "distinct": "887", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V2038", "index": "42", "type": "numeric", "distinct": "922", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V2075", "index": "43", "type": "numeric", "distinct": "555", "missing": "0", "min": "0", "max": "11", "mean": "0", "stdev": "1" }, { "name": "V2120", "index": "44", "type": "numeric", "distinct": "910", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V2147", "index": "45", "type": "numeric", "distinct": "681", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V2161", "index": "46", "type": "numeric", "distinct": "771", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V2231", "index": "47", "type": "numeric", "distinct": "1023", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V2242", "index": "48", "type": "numeric", "distinct": "805", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V2272", "index": "49", "type": "numeric", "distinct": "1119", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V2291", "index": "50", "type": "numeric", "distinct": "875", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V2292", "index": "51", "type": "numeric", "distinct": "920", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V2341", "index": "52", "type": "numeric", "distinct": "784", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V2361", "index": "53", "type": "numeric", "distinct": "1047", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V2446", "index": "54", "type": "numeric", "distinct": "989", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V2468", "index": "55", "type": "numeric", "distinct": "967", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "V2545", "index": "56", "type": "numeric", "distinct": "1081", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V2554", "index": "57", "type": "numeric", "distinct": "609", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V2613", "index": "58", "type": "numeric", "distinct": "882", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V2664", "index": "59", "type": "numeric", "distinct": "1041", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V2674", "index": "60", "type": "numeric", "distinct": "632", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V2675", "index": "61", "type": "numeric", "distinct": "696", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V2733", "index": "62", "type": "numeric", "distinct": "802", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "1" }, { "name": "V2747", "index": "63", "type": "numeric", "distinct": "878", "missing": "0", "min": "0", "max": "15", "mean": "1", "stdev": "1" }, { "name": "V2769", "index": "64", "type": "numeric", "distinct": "1183", "missing": "0", "min": "0", "max": "15", "mean": "1", "stdev": "1" }, { "name": "V2831", "index": "65", "type": "numeric", "distinct": "931", "missing": "0", "min": "0", "max": "11", "mean": "0", "stdev": "1" }, { "name": "V2845", "index": "66", "type": "numeric", "distinct": "965", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V2878", "index": "67", "type": "numeric", "distinct": "1052", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V2917", "index": "68", "type": "numeric", "distinct": "728", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V2932", "index": "69", "type": "numeric", "distinct": "857", "missing": "0", "min": "0", "max": "14", "mean": "1", "stdev": "1" }, { "name": "V2999", "index": "70", "type": "numeric", "distinct": "793", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V3065", "index": "71", "type": "numeric", "distinct": "987", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V3071", "index": "72", "type": "numeric", "distinct": "49", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "V3073", "index": "73", "type": "numeric", "distinct": "523", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V3077", "index": "74", "type": "numeric", "distinct": "862", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V3081", "index": "75", "type": "numeric", "distinct": "952", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V3084", "index": "76", "type": "numeric", "distinct": "656", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V3232", "index": "77", "type": "numeric", "distinct": "343", "missing": "0", "min": "0", "max": "14", "mean": "0", "stdev": "2" }, { "name": "V3245", "index": "78", "type": "numeric", "distinct": "1013", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V3260", "index": "79", "type": "numeric", "distinct": "1045", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "1" }, { "name": "V3421", "index": "80", "type": "numeric", "distinct": "884", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "1" }, { "name": "V3423", "index": "81", "type": "numeric", "distinct": "441", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "V3442", "index": "82", "type": "numeric", "distinct": "1049", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "2" }, { "name": "V3571", "index": "83", "type": "numeric", "distinct": "931", "missing": "0", "min": "0", "max": "17", "mean": "1", "stdev": "1" }, { "name": "V3578", "index": "84", "type": "numeric", "distinct": "868", "missing": "0", "min": "0", "max": "15", "mean": "0", "stdev": "1" }, { "name": "V3579", "index": "85", "type": "numeric", "distinct": "1177", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V3606", "index": "86", "type": "numeric", "distinct": "1239", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V3620", "index": "87", "type": "numeric", "distinct": "773", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V3652", "index": "88", "type": "numeric", "distinct": "791", "missing": "0", "min": "0", "max": "15", "mean": "0", "stdev": "1" }, { "name": "V3730", "index": "89", "type": "numeric", "distinct": "1048", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V3800", "index": "90", "type": "numeric", "distinct": "950", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "1" }, { "name": "V3818", "index": "91", "type": "numeric", "distinct": "950", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "1" }, { "name": "V3841", "index": "92", "type": "numeric", "distinct": "1005", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "1" }, { "name": "V3943", "index": "93", "type": "numeric", "distinct": "773", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V3993", "index": "94", "type": "numeric", "distinct": "736", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V4043", "index": "95", "type": "numeric", "distinct": "734", "missing": "0", "min": "0", "max": "14", "mean": "1", "stdev": "1" }, { "name": "V4088", "index": "96", "type": "numeric", "distinct": "763", "missing": "0", "min": "0", "max": "12", "mean": "0", "stdev": "1" }, { "name": "V4171", "index": "97", "type": "numeric", "distinct": "1765", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V4239", "index": "98", "type": "numeric", "distinct": "1763", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V4296", "index": "99", "type": "numeric", "distinct": "1752", "missing": "0", "min": "0", "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 }