DEVELOPMENT... { "data_id": "44508", "name": "APSFailure_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "APSFailure_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "dd6c0e1a-6b0e-4b58-a674-4fefd653eccb", "description": "Subsampling of the dataset APSFailure (41138) 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": "David Wilson", "uploader_id": 32840, "visibility": "public", "creator": "\"Eddie Bergman\"", "contributor": null, "date": "2022-11-17 18:24:01", "update_comment": null, "last_update": "2022-11-17 18:24:01", "licence": "CC0", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111270\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "APSFailure_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset APSFailure (41138) 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.choic " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 101, "NumberOfClasses": 2, "NumberOfMissingValues": 19825, "NumberOfInstancesWithMissingValues": 1974, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "PercentageOfSymbolicFeatures": 0.9900990099009901, "AutoCorrelation": 0.9649824912456229, "PercentageOfNumericFeatures": 99.00990099009901, "PercentageOfMissingValues": 9.814356435643564, "PercentageOfInstancesWithMissingValues": 98.7, "PercentageOfBinaryFeatures": 0.9900990099009901, "NumberOfBinaryFeatures": 1, "MinorityClassSize": 36, "MinorityClassPercentage": 1.7999999999999998, "MajorityClassSize": 1964, "MajorityClassPercentage": 98.2, "Dimensionality": 0.0505 }, "tags": [], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "pos", "neg" ], [ [ "36", "0" ], [ "0", "1964" ] ] ] }, { "name": "aa_000", "index": "0", "type": "numeric", "distinct": "1575", "missing": "0", "min": "0", "max": "2220448", "mean": "58063", "stdev": "152254" }, { "name": "ab_000", "index": "1", "type": "numeric", "distinct": "6", "missing": "1532", "min": "0", "max": "36", "mean": "1", "stdev": "2" }, { "name": "ac_000", "index": "2", "type": "numeric", "distinct": "482", "missing": "131", "min": "0", "max": "2130706594", "mean": "347707882", "stdev": "787587384" }, { "name": "ad_000", "index": "3", "type": "numeric", "distinct": "469", "missing": "475", "min": "0", "max": "13764", "mean": "376", "stdev": "858" }, { "name": "af_000", "index": "4", "type": "numeric", "distinct": "36", "missing": "105", "min": "0", "max": "3828", "mean": "9", "stdev": "144" }, { "name": "ag_002", "index": "5", "type": "numeric", "distinct": "92", "missing": "24", "min": "0", "max": "2722536", "mean": "7952", "stdev": "109144" }, { "name": "ag_003", "index": "6", "type": "numeric", "distinct": "389", "missing": "24", "min": "0", "max": "13817782", "mean": "83061", "stdev": "652265" }, { "name": "ag_004", "index": "7", "type": "numeric", "distinct": "1487", "missing": "24", "min": "0", "max": "34831328", "mean": "377728", "stdev": "1872813" }, { "name": "ag_007", "index": "8", "type": "numeric", "distinct": "1408", "missing": "24", "min": "0", "max": "24445908", "mean": "474494", "stdev": "1330423" }, { "name": "ag_008", "index": "9", "type": "numeric", "distinct": "1068", "missing": "24", "min": "0", "max": "4238534", "mean": "30806", "stdev": "137116" }, { "name": "ai_000", "index": "10", "type": "numeric", "distinct": "193", "missing": "20", "min": "0", "max": "8110254", "mean": "11784", "stdev": "202931" }, { "name": "aj_000", "index": "11", "type": "numeric", "distinct": "163", "missing": "20", "min": "0", "max": "3913164", "mean": "2256", "stdev": "88455" }, { "name": "ak_000", "index": "12", "type": "numeric", "distinct": "9", "missing": "164", "min": "0", "max": "14176", "mean": "21", "stdev": "410" }, { "name": "ao_000", "index": "13", "type": "numeric", "distinct": "1965", "missing": "20", "min": "0", "max": "85195392", "mean": "2927837", "stdev": "7064856" }, { "name": "aq_000", "index": "14", "type": "numeric", "distinct": "1887", "missing": "20", "min": "0", "max": "22252294", "mean": "448067", "stdev": "1349781" }, { "name": "av_000", "index": "15", "type": "numeric", "distinct": "677", "missing": "104", "min": "0", "max": "128120", "mean": "1129", "stdev": "4853" }, { "name": "ay_000", "index": "16", "type": "numeric", "distinct": "14", "missing": "24", "min": "0", "max": "54904", "mean": "213", "stdev": "2790" }, { "name": "ay_005", "index": "17", "type": "numeric", "distinct": "900", "missing": "24", "min": "0", "max": "57169792", "mean": "95026", "stdev": "1337838" }, { "name": "ay_006", "index": "18", "type": "numeric", "distinct": "1369", "missing": "24", "min": "0", "max": "94722586", "mean": "1081534", "stdev": "3981191" }, { "name": "ay_009", "index": "19", "type": "numeric", "distinct": "17", "missing": "24", "min": "0", "max": "452692", "mean": "410", "stdev": "10777" }, { "name": "az_001", "index": "20", "type": "numeric", "distinct": "1051", "missing": "24", "min": "0", "max": "359892", "mean": "3504", "stdev": "13979" }, { "name": "az_002", "index": "21", "type": "numeric", "distinct": "1177", "missing": "24", "min": "0", "max": "545176", "mean": "5835", "stdev": "24986" }, { "name": "az_003", "index": "22", "type": "numeric", "distinct": "1455", "missing": "24", "min": "0", "max": "26486990", "mean": "88247", "stdev": "763096" }, { "name": "az_004", "index": "23", "type": "numeric", "distinct": "1751", "missing": "24", "min": "0", "max": "58680098", "mean": "1416164", "stdev": "4081500" }, { "name": "az_005", "index": "24", "type": "numeric", "distinct": "1918", "missing": "24", "min": "0", "max": "91203606", "mean": "1906749", "stdev": "5637997" }, { "name": "az_006", "index": "25", "type": "numeric", "distinct": "1009", "missing": "24", "min": "0", "max": "15937678", "mean": "82645", "stdev": "656243" }, { "name": "az_007", "index": "26", "type": "numeric", "distinct": "197", "missing": "24", "min": "0", "max": "5158320", "mean": "12631", "stdev": "176656" }, { "name": "az_008", "index": "27", "type": "numeric", "distinct": "74", "missing": "24", "min": "0", "max": "569284", "mean": "793", "stdev": "17721" }, { "name": "ba_000", "index": "28", "type": "numeric", "distinct": "1929", "missing": "25", "min": "0", "max": "62032174", "mean": "1267773", "stdev": "3215208" }, { "name": "ba_001", "index": "29", "type": "numeric", "distinct": "1858", "missing": "25", "min": "0", "max": "28845398", "mean": "824788", "stdev": "2074274" }, { "name": "ba_003", "index": "30", "type": "numeric", "distinct": "1702", "missing": "25", "min": "0", "max": "10493990", "mean": "254204", "stdev": "694587" }, { "name": "ba_004", "index": "31", "type": "numeric", "distinct": "1621", "missing": "25", "min": "0", "max": "11070534", "mean": "190908", "stdev": "537076" }, { "name": "ba_005", "index": "32", "type": "numeric", "distinct": "1561", "missing": "25", "min": "0", "max": "16758932", "mean": "176795", "stdev": "586491" }, { "name": "ba_008", "index": "33", "type": "numeric", "distinct": "739", "missing": "25", "min": "0", "max": "2757872", "mean": "32985", "stdev": "166581" }, { "name": "ba_009", "index": "34", "type": "numeric", "distinct": "425", "missing": "25", "min": "0", "max": "3474234", "mean": "29766", "stdev": "202132" }, { "name": "bb_000", "index": "35", "type": "numeric", "distinct": "1968", "missing": "24", "min": "0", "max": "140573922", "mean": "4487394", "stdev": "11467327" }, { "name": "bc_000", "index": "36", "type": "numeric", "distinct": "397", "missing": "109", "min": "0", "max": "67928", "mean": "469", "stdev": "2808" }, { "name": "be_000", "index": "37", "type": "numeric", "distinct": "653", "missing": "105", "min": "0", "max": "161154", "mean": "1249", "stdev": "6576" }, { "name": "bi_000", "index": "38", "type": "numeric", "distinct": "1955", "missing": "20", "min": "0", "max": "23185288", "mean": "473998", "stdev": "1451224" }, { "name": "bl_000", "index": "39", "type": "numeric", "distinct": "903", "missing": "934", "min": "0", "max": "1310700", "mean": "319022", "stdev": "312623" }, { "name": "bm_000", "index": "40", "type": "numeric", "distinct": "503", "missing": "1348", "min": "0", "max": "1310700", "mean": "400752", "stdev": "406273" }, { "name": "bn_000", "index": "41", "type": "numeric", "distinct": "344", "missing": "1483", "min": "0", "max": "1310700", "mean": "463023", "stdev": "465417" }, { "name": "bo_000", "index": "42", "type": "numeric", "distinct": "265", "missing": "1557", "min": "0", "max": "1310700", "mean": "512385", "stdev": "499958" }, { "name": "bp_000", "index": "43", "type": "numeric", "distinct": "216", "missing": "1596", "min": "0", "max": "1310700", "mean": "546253", "stdev": "522949" }, { "name": "bq_000", "index": "44", "type": "numeric", "distinct": "177", "missing": "1628", "min": "0", "max": "1310700", "mean": "576413", "stdev": "541100" }, { "name": "bs_000", "index": "45", "type": "numeric", "distinct": "1712", "missing": "25", "min": "0", "max": "809480", "mean": "80062", "stdev": "85701" }, { "name": "bv_000", "index": "46", "type": "numeric", "distinct": "1966", "missing": "26", "min": "0", "max": "140573922", "mean": "4425859", "stdev": "11182897" }, { "name": "by_000", "index": "47", "type": "numeric", "distinct": "1518", "missing": "16", "min": "0", "max": "1002003", "mean": "20703", "stdev": "53487" }, { "name": "bz_000", "index": "48", "type": "numeric", "distinct": "1133", "missing": "109", "min": "0", "max": "10033200", "mean": "76415", "stdev": "431414" }, { "name": "ca_000", "index": "49", "type": "numeric", "distinct": "1762", "missing": "168", "min": "0", "max": "120874", "mean": "38697", "stdev": "37302" }, { "name": "cb_000", "index": "50", "type": "numeric", "distinct": "1905", "missing": "25", "min": "0", "max": "1209140", "mean": "398923", "stdev": "374625" }, { "name": "cd_000", "index": "51", "type": "numeric", "distinct": "1", "missing": "21", "min": "1209600", "max": "1209600", "mean": "1209600", "stdev": "0" }, { "name": "ce_000", "index": "52", "type": "numeric", "distinct": "1409", "missing": "104", "min": "0", "max": "2424882", "mean": "65345", "stdev": "153623" }, { "name": "cg_000", "index": "53", "type": "numeric", "distinct": "187", "missing": "475", "min": "0", "max": "10210", "mean": "88", "stdev": "300" }, { "name": "ch_000", "index": "54", "type": "numeric", "distinct": "1", "missing": "475", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ci_000", "index": "55", "type": "numeric", "distinct": "1971", "missing": "9", "min": "0", "max": "124510239", "mean": "3416553", "stdev": "8782994" }, { "name": "cj_000", "index": "56", "type": "numeric", "distinct": "398", "missing": "9", "min": "0", "max": "31147299", "mean": "113117", "stdev": "1208916" }, { "name": "cl_000", "index": "57", "type": "numeric", "distinct": "119", "missing": "323", "min": "0", "max": "124416", "mean": "324", "stdev": "4828" }, { "name": "cm_000", "index": "58", "type": "numeric", "distinct": "348", "missing": "332", "min": "0", "max": "19460", "mean": "248", "stdev": "925" }, { "name": "cn_000", "index": "59", "type": "numeric", "distinct": "63", "missing": "25", "min": "0", "max": "1803010", "mean": "2316", "stdev": "46398" }, { "name": "cn_001", "index": "60", "type": "numeric", "distinct": "286", "missing": "25", "min": "0", "max": "4627448", "mean": "22037", "stdev": "208047" }, { "name": "cn_002", "index": "61", "type": "numeric", "distinct": "900", "missing": "25", "min": "0", "max": "17741250", "mean": "153473", "stdev": "998857" }, { "name": "cn_004", "index": "62", "type": "numeric", "distinct": "1914", "missing": "25", "min": "0", "max": "53748940", "mean": "1165482", "stdev": "3089575" }, { "name": "cn_005", "index": "63", "type": "numeric", "distinct": "1849", "missing": "25", "min": "0", "max": "46743208", "mean": "1232544", "stdev": "2933071" }, { "name": "cn_009", "index": "64", "type": "numeric", "distinct": "511", "missing": "25", "min": "0", "max": "30344094", "mean": "18642", "stdev": "684179" }, { "name": "cp_000", "index": "65", "type": "numeric", "distinct": "349", "missing": "109", "min": "0", "max": "61406", "mean": "385", "stdev": "2333" }, { "name": "cq_000", "index": "66", "type": "numeric", "distinct": "1966", "missing": "26", "min": "0", "max": "140573922", "mean": "4425859", "stdev": "11182897" }, { "name": "cr_000", "index": "67", "type": "numeric", "distinct": "4", "missing": "1532", "min": "0", "max": "1988", "mean": "5", "stdev": "92" }, { "name": "cs_001", "index": "68", "type": "numeric", "distinct": "675", "missing": "24", "min": "0", "max": "40600", "mean": "712", "stdev": "1950" }, { "name": "cs_004", "index": "69", "type": "numeric", "distinct": "1813", "missing": "24", "min": "0", "max": "32520246", "mean": "438002", "stdev": "2008231" }, { "name": "cs_005", "index": "70", "type": "numeric", "distinct": "1912", "missing": "24", "min": "0", "max": "85703584", "mean": "2019517", "stdev": "5095672" }, { "name": "cs_007", "index": "71", "type": "numeric", "distinct": "1598", "missing": "24", "min": "0", "max": "503530", "mean": "13309", "stdev": "23441" }, { "name": "cs_008", "index": "72", "type": "numeric", "distinct": "277", "missing": "24", "min": "0", "max": "2318", "mean": "113", "stdev": "195" }, { "name": "cs_009", "index": "73", "type": "numeric", "distinct": "10", "missing": "24", "min": "0", "max": "26", "mean": "0", "stdev": "1" }, { "name": "ct_000", "index": "74", "type": "numeric", "distinct": "596", "missing": "425", "min": "0", "max": "36272", "mean": "642", "stdev": "1655" }, { "name": "cv_000", "index": "75", "type": "numeric", "distinct": "1521", "missing": "425", "min": "0", "max": "48798824", "mean": "1903146", "stdev": "3602681" }, { "name": "da_000", "index": "76", "type": "numeric", "distinct": "17", "missing": "425", "min": "0", "max": "1060", "mean": "2", "stdev": "36" }, { "name": "de_000", "index": "77", "type": "numeric", "distinct": "435", "missing": "109", "min": "0", "max": "20230", "mean": "345", "stdev": "990" }, { "name": "dj_000", "index": "78", "type": "numeric", "distinct": "5", "missing": "151", "min": "0", "max": "1320", "mean": "1", "stdev": "31" }, { "name": "dk_000", "index": "79", "type": "numeric", "distinct": "10", "missing": "151", "min": "0", "max": "2364918", "mean": "1458", "stdev": "55498" }, { "name": "dl_000", "index": "80", "type": "numeric", "distinct": "10", "missing": "151", "min": "0", "max": "4480650", "mean": "2742", "stdev": "104971" }, { "name": "dm_000", "index": "81", "type": "numeric", "distinct": "10", "missing": "151", "min": "0", "max": "3897440", "mean": "2454", "stdev": "90975" }, { "name": "dn_000", "index": "82", "type": "numeric", "distinct": "1619", "missing": "26", "min": "0", "max": "2037710", "mean": "33980", "stdev": "106249" }, { "name": "dp_000", "index": "83", "type": "numeric", "distinct": "1132", "missing": "109", "min": "0", "max": "221644", "mean": "6193", "stdev": "11892" }, { "name": "dq_000", "index": "84", "type": "numeric", "distinct": "448", "missing": "109", "min": "0", "max": "2147483647", "mean": "4264016", "stdev": "80101581" }, { "name": "dt_000", "index": "85", "type": "numeric", "distinct": "1321", "missing": "109", "min": "0", "max": "498568", "mean": "14485", "stdev": "33309" }, { "name": "du_000", "index": "86", "type": "numeric", "distinct": "1512", "missing": "109", "min": "0", "max": "229693680", "mean": "3501079", "stdev": "10502387" }, { "name": "dz_000", "index": "87", "type": "numeric", "distinct": "6", "missing": "109", "min": "0", "max": "52", "mean": "0", "stdev": "1" }, { "name": "ea_000", "index": "88", "type": "numeric", "distinct": "15", "missing": "109", "min": "0", "max": "1502", "mean": "1", "stdev": "36" }, { "name": "eb_000", "index": "89", "type": "numeric", "distinct": "1087", "missing": "151", "min": "0", "max": "592675950", "mean": "8288184", "stdev": "32018287" }, { "name": "ec_00", "index": "90", "type": "numeric", "distinct": "1550", "missing": "350", "min": "0", "max": "53376", "mean": "1206", "stdev": "2981" }, { "name": "ed_000", "index": "91", "type": "numeric", "distinct": "847", "missing": "323", "min": "0", "max": "70460", "mean": "1315", "stdev": "3275" }, { "name": "ee_000", "index": "92", "type": "numeric", "distinct": "1918", "missing": "24", "min": "0", "max": "36304344", "mean": "676605", "stdev": "1982653" }, { "name": "ee_001", "index": "93", "type": "numeric", "distinct": "1890", "missing": "24", "min": "0", "max": "49357300", "mean": "710041", "stdev": "2135671" }, { "name": "ee_002", "index": "94", "type": "numeric", "distinct": "1781", "missing": "24", "min": "0", "max": "20150044", "mean": "415454", "stdev": "1098656" }, { "name": "ee_005", "index": "95", "type": "numeric", "distinct": "1659", "missing": "24", "min": "0", "max": "15507068", "mean": "368639", "stdev": "975280" }, { "name": "ee_006", "index": "96", "type": "numeric", "distinct": "1580", "missing": "24", "min": "0", "max": "28276990", "mean": "301646", "stdev": "1086502" }, { "name": "ee_008", "index": "97", "type": "numeric", "distinct": "1200", "missing": "24", "min": "0", "max": "14560586", "mean": "132190", "stdev": "559818" }, { "name": "ee_009", "index": "98", "type": "numeric", "distinct": "686", "missing": "24", "min": "0", "max": "1109238", "mean": "7635", "stdev": "40953" }, { "name": "eg_000", "index": "99", "type": "numeric", "distinct": "8", "missing": "109", "min": "0", "max": "48", "mean": "0", "stdev": "2" } ], "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 }