{ "data_id": "44738", "name": "robert_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "robert_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "f1a721a3-0e72-4b68-9afe-bf8b412843bd", "description": "Subsampling of the dataset robert (41165) 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 18:47:03", "update_comment": null, "last_update": "2022-11-17 18:47:03", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111500\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "robert_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset robert (41165) 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( c " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 101, "NumberOfClasses": 10, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "PercentageOfMissingValues": 0, "AutoCorrelation": 0.0975487743871936, "PercentageOfNumericFeatures": 99.00990099009901, "Dimensionality": 0.0505, "PercentageOfSymbolicFeatures": 0.9900990099009901, "MajorityClassPercentage": 10.45, "MajorityClassSize": 209, "MinorityClassPercentage": 9.6, "MinorityClassSize": 192, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Statistics" } ], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "10", "missing": "0", "target": "1", "distr": [ [ "0", "1", "2", "3", "4", "5", "6", "7", "8", "9" ], [ [ "198", "0", "0", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "192", "0", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "196", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "199", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "209", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "206", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "197", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "200", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "0", "196", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "0", "0", "207" ] ] ] }, { "name": "V20", "index": "0", "type": "numeric", "distinct": "589", "missing": "0", "min": "144", "max": "900", "mean": "424", "stdev": "231" }, { "name": "V39", "index": "1", "type": "numeric", "distinct": "533", "missing": "0", "min": "79", "max": "814", "mean": "397", "stdev": "125" }, { "name": "V60", "index": "2", "type": "numeric", "distinct": "535", "missing": "0", "min": "0", "max": "895", "mean": "315", "stdev": "240" }, { "name": "V118", "index": "3", "type": "numeric", "distinct": "253", "missing": "0", "min": "0", "max": "900", "mean": "447", "stdev": "211" }, { "name": "V158", "index": "4", "type": "numeric", "distinct": "639", "missing": "0", "min": "46", "max": "848", "mean": "465", "stdev": "161" }, { "name": "V203", "index": "5", "type": "numeric", "distinct": "665", "missing": "0", "min": "76", "max": "889", "mean": "552", "stdev": "187" }, { "name": "V240", "index": "6", "type": "numeric", "distinct": "254", "missing": "0", "min": "0", "max": "900", "mean": "455", "stdev": "214" }, { "name": "V292", "index": "7", "type": "numeric", "distinct": "630", "missing": "0", "min": "46", "max": "873", "mean": "590", "stdev": "179" }, { "name": "V350", "index": "8", "type": "numeric", "distinct": "609", "missing": "0", "min": "79", "max": "850", "mean": "445", "stdev": "152" }, { "name": "V524", "index": "9", "type": "numeric", "distinct": "644", "missing": "0", "min": "44", "max": "881", "mean": "589", "stdev": "186" }, { "name": "V535", "index": "10", "type": "numeric", "distinct": "543", "missing": "0", "min": "0", "max": "898", "mean": "323", "stdev": "238" }, { "name": "V574", "index": "11", "type": "numeric", "distinct": "554", "missing": "0", "min": "0", "max": "898", "mean": "292", "stdev": "255" }, { "name": "V605", "index": "12", "type": "numeric", "distinct": "564", "missing": "0", "min": "0", "max": "897", "mean": "318", "stdev": "238" }, { "name": "V637", "index": "13", "type": "numeric", "distinct": "253", "missing": "0", "min": "0", "max": "900", "mean": "524", "stdev": "226" }, { "name": "V888", "index": "14", "type": "numeric", "distinct": "614", "missing": "0", "min": "0", "max": "900", "mean": "240", "stdev": "209" }, { "name": "V969", "index": "15", "type": "numeric", "distinct": "664", "missing": "0", "min": "54", "max": "859", "mean": "394", "stdev": "188" }, { "name": "V1246", "index": "16", "type": "numeric", "distinct": "658", "missing": "0", "min": "31", "max": "856", "mean": "409", "stdev": "174" }, { "name": "V1253", "index": "17", "type": "numeric", "distinct": "717", "missing": "0", "min": "34", "max": "860", "mean": "508", "stdev": "207" }, { "name": "V1635", "index": "18", "type": "numeric", "distinct": "420", "missing": "0", "min": "151", "max": "781", "mean": "388", "stdev": "101" }, { "name": "V1829", "index": "19", "type": "numeric", "distinct": "620", "missing": "0", "min": "0", "max": "900", "mean": "244", "stdev": "207" }, { "name": "V1840", "index": "20", "type": "numeric", "distinct": "494", "missing": "0", "min": "91", "max": "799", "mean": "518", "stdev": "119" }, { "name": "V1899", "index": "21", "type": "numeric", "distinct": "687", "missing": "0", "min": "37", "max": "863", "mean": "421", "stdev": "180" }, { "name": "V1917", "index": "22", "type": "numeric", "distinct": "524", "missing": "0", "min": "0", "max": "898", "mean": "270", "stdev": "255" }, { "name": "V1975", "index": "23", "type": "numeric", "distinct": "640", "missing": "0", "min": "43", "max": "874", "mean": "602", "stdev": "187" }, { "name": "V2140", "index": "24", "type": "numeric", "distinct": "604", "missing": "0", "min": "95", "max": "857", "mean": "475", "stdev": "147" }, { "name": "V2188", "index": "25", "type": "numeric", "distinct": "483", "missing": "0", "min": "133", "max": "900", "mean": "336", "stdev": "192" }, { "name": "V2226", "index": "26", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "900", "mean": "532", "stdev": "235" }, { "name": "V2313", "index": "27", "type": "numeric", "distinct": "478", "missing": "0", "min": "136", "max": "736", "mean": "465", "stdev": "113" }, { "name": "V2360", "index": "28", "type": "numeric", "distinct": "574", "missing": "0", "min": "132", "max": "900", "mean": "407", "stdev": "229" }, { "name": "V2429", "index": "29", "type": "numeric", "distinct": "544", "missing": "0", "min": "0", "max": "899", "mean": "272", "stdev": "243" }, { "name": "V2569", "index": "30", "type": "numeric", "distinct": "585", "missing": "0", "min": "55", "max": "875", "mean": "660", "stdev": "179" }, { "name": "V2693", "index": "31", "type": "numeric", "distinct": "485", "missing": "0", "min": "117", "max": "807", "mean": "444", "stdev": "113" }, { "name": "V2716", "index": "32", "type": "numeric", "distinct": "532", "missing": "0", "min": "92", "max": "813", "mean": "458", "stdev": "125" }, { "name": "V2717", "index": "33", "type": "numeric", "distinct": "632", "missing": "0", "min": "40", "max": "874", "mean": "476", "stdev": "160" }, { "name": "V2745", "index": "34", "type": "numeric", "distinct": "559", "missing": "0", "min": "131", "max": "900", "mean": "396", "stdev": "219" }, { "name": "V2787", "index": "35", "type": "numeric", "distinct": "567", "missing": "0", "min": "137", "max": "900", "mean": "391", "stdev": "222" }, { "name": "V2809", "index": "36", "type": "numeric", "distinct": "620", "missing": "0", "min": "0", "max": "900", "mean": "246", "stdev": "191" }, { "name": "V2816", "index": "37", "type": "numeric", "distinct": "719", "missing": "0", "min": "26", "max": "877", "mean": "461", "stdev": "194" }, { "name": "V2880", "index": "38", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "900", "mean": "540", "stdev": "243" }, { "name": "V3018", "index": "39", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "900", "mean": "463", "stdev": "215" }, { "name": "V3034", "index": "40", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "900", "mean": "502", "stdev": "218" }, { "name": "V3297", "index": "41", "type": "numeric", "distinct": "543", "missing": "0", "min": "0", "max": "898", "mean": "312", "stdev": "246" }, { "name": "V3435", "index": "42", "type": "numeric", "distinct": "614", "missing": "0", "min": "146", "max": "900", "mean": "447", "stdev": "241" }, { "name": "V3486", "index": "43", "type": "numeric", "distinct": "591", "missing": "0", "min": "65", "max": "861", "mean": "475", "stdev": "147" }, { "name": "V3583", "index": "44", "type": "numeric", "distinct": "599", "missing": "0", "min": "66", "max": "880", "mean": "484", "stdev": "147" }, { "name": "V3626", "index": "45", "type": "numeric", "distinct": "245", "missing": "0", "min": "4", "max": "900", "mean": "497", "stdev": "204" }, { "name": "V3631", "index": "46", "type": "numeric", "distinct": "499", "missing": "0", "min": "134", "max": "900", "mean": "345", "stdev": "205" }, { "name": "V3757", "index": "47", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "900", "mean": "482", "stdev": "209" }, { "name": "V3767", "index": "48", "type": "numeric", "distinct": "590", "missing": "0", "min": "85", "max": "848", "mean": "354", "stdev": "157" }, { "name": "V3815", "index": "49", "type": "numeric", "distinct": "533", "missing": "0", "min": "0", "max": "899", "mean": "280", "stdev": "259" }, { "name": "V3864", "index": "50", "type": "numeric", "distinct": "663", "missing": "0", "min": "37", "max": "854", "mean": "457", "stdev": "178" }, { "name": "V3870", "index": "51", "type": "numeric", "distinct": "681", "missing": "0", "min": "58", "max": "884", "mean": "439", "stdev": "179" }, { "name": "V3951", "index": "52", "type": "numeric", "distinct": "255", "missing": "0", "min": "0", "max": "900", "mean": "539", "stdev": "246" }, { "name": "V3987", "index": "53", "type": "numeric", "distinct": "558", "missing": "0", "min": "0", "max": "897", "mean": "314", "stdev": "239" }, { "name": "V4105", "index": "54", "type": "numeric", "distinct": "565", "missing": "0", "min": "62", "max": "879", "mean": "489", "stdev": "132" }, { "name": "V4150", "index": "55", "type": "numeric", "distinct": "561", "missing": "0", "min": "0", "max": "898", "mean": "311", "stdev": "254" }, { "name": "V4271", "index": "56", "type": "numeric", "distinct": "551", "missing": "0", "min": "0", "max": "895", "mean": "311", "stdev": "246" }, { "name": "V4316", "index": "57", "type": "numeric", "distinct": "694", "missing": "0", "min": "39", "max": "887", "mean": "443", "stdev": "191" }, { "name": "V4401", "index": "58", "type": "numeric", "distinct": "253", "missing": "0", "min": "0", "max": "900", "mean": "497", "stdev": "225" }, { "name": "V4485", "index": "59", "type": "numeric", "distinct": "545", "missing": "0", "min": "126", "max": "900", "mean": "362", "stdev": "206" }, { "name": "V4500", "index": "60", "type": "numeric", "distinct": "488", "missing": "0", "min": "121", "max": "744", "mean": "478", "stdev": "119" }, { "name": "V4524", "index": "61", "type": "numeric", "distinct": "638", "missing": "0", "min": "46", "max": "882", "mean": "596", "stdev": "182" }, { "name": "V4618", "index": "62", "type": "numeric", "distinct": "703", "missing": "0", "min": "29", "max": "893", "mean": "498", "stdev": "186" }, { "name": "V4627", "index": "63", "type": "numeric", "distinct": "628", "missing": "0", "min": "71", "max": "880", "mean": "455", "stdev": "154" }, { "name": "V4658", "index": "64", "type": "numeric", "distinct": "478", "missing": "0", "min": "134", "max": "900", "mean": "325", "stdev": "187" }, { "name": "V4779", "index": "65", "type": "numeric", "distinct": "612", "missing": "0", "min": "0", "max": "900", "mean": "242", "stdev": "195" }, { "name": "V4793", "index": "66", "type": "numeric", "distinct": "521", "missing": "0", "min": "93", "max": "814", "mean": "463", "stdev": "117" }, { "name": "V4831", "index": "67", "type": "numeric", "distinct": "529", "missing": "0", "min": "0", "max": "898", "mean": "269", "stdev": "249" }, { "name": "V4908", "index": "68", "type": "numeric", "distinct": "545", "missing": "0", "min": "0", "max": "899", "mean": "277", "stdev": "258" }, { "name": "V4931", "index": "69", "type": "numeric", "distinct": "580", "missing": "0", "min": "95", "max": "861", "mean": "491", "stdev": "138" }, { "name": "V5043", "index": "70", "type": "numeric", "distinct": "536", "missing": "0", "min": "0", "max": "897", "mean": "314", "stdev": "242" }, { "name": "V5139", "index": "71", "type": "numeric", "distinct": "600", "missing": "0", "min": "0", "max": "900", "mean": "242", "stdev": "192" }, { "name": "V5158", "index": "72", "type": "numeric", "distinct": "625", "missing": "0", "min": "0", "max": "900", "mean": "246", "stdev": "193" }, { "name": "V5170", "index": "73", "type": "numeric", "distinct": "655", "missing": "0", "min": "49", "max": "855", "mean": "378", "stdev": "181" }, { "name": "V5172", "index": "74", "type": "numeric", "distinct": "682", "missing": "0", "min": "57", "max": "841", "mean": "425", "stdev": "189" }, { "name": "V5192", "index": "75", "type": "numeric", "distinct": "546", "missing": "0", "min": "0", "max": "898", "mean": "314", "stdev": "243" }, { "name": "V5203", "index": "76", "type": "numeric", "distinct": "550", "missing": "0", "min": "0", "max": "898", "mean": "278", "stdev": "249" }, { "name": "V5453", "index": "77", "type": "numeric", "distinct": "534", "missing": "0", "min": "0", "max": "897", "mean": "272", "stdev": "240" }, { "name": "V5464", "index": "78", "type": "numeric", "distinct": "624", "missing": "0", "min": "54", "max": "889", "mean": "475", "stdev": "151" }, { "name": "V5469", "index": "79", "type": "numeric", "distinct": "664", "missing": "0", "min": "54", "max": "858", "mean": "548", "stdev": "194" }, { "name": "V5760", "index": "80", "type": "numeric", "distinct": "551", "missing": "0", "min": "0", "max": "899", "mean": "294", "stdev": "242" }, { "name": "V5783", "index": "81", "type": "numeric", "distinct": "649", "missing": "0", "min": "35", "max": "871", "mean": "417", "stdev": "173" }, { "name": "V5811", "index": "82", "type": "numeric", "distinct": "604", "missing": "0", "min": "0", "max": "900", "mean": "234", "stdev": "191" }, { "name": "V5996", "index": "83", "type": "numeric", "distinct": "601", "missing": "0", "min": "56", "max": "849", "mean": "495", "stdev": "156" }, { "name": "V6018", "index": "84", "type": "numeric", "distinct": "622", "missing": "0", "min": "46", "max": "852", "mean": "496", "stdev": "162" }, { "name": "V6037", "index": "85", "type": "numeric", "distinct": "596", "missing": "0", "min": "0", "max": "900", "mean": "240", "stdev": "183" }, { "name": "V6041", "index": "86", "type": "numeric", "distinct": "540", "missing": "0", "min": "136", "max": "900", "mean": "370", "stdev": "214" }, { "name": "V6062", "index": "87", "type": "numeric", "distinct": "638", "missing": "0", "min": "88", "max": "861", "mean": "471", "stdev": "166" }, { "name": "V6110", "index": "88", "type": "numeric", "distinct": "619", "missing": "0", "min": "80", "max": "875", "mean": "624", "stdev": "189" }, { "name": "V6158", "index": "89", "type": "numeric", "distinct": "248", "missing": "0", "min": "4", "max": "900", "mean": "494", "stdev": "214" }, { "name": "V6271", "index": "90", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "900", "mean": "489", "stdev": "209" }, { "name": "V6383", "index": "91", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "900", "mean": "507", "stdev": "219" }, { "name": "V6403", "index": "92", "type": "numeric", "distinct": "628", "missing": "0", "min": "75", "max": "823", "mean": "378", "stdev": "169" }, { "name": "V6492", "index": "93", "type": "numeric", "distinct": "593", "missing": "0", "min": "124", "max": "900", "mean": "427", "stdev": "235" }, { "name": "V6658", "index": "94", "type": "numeric", "distinct": "528", "missing": "0", "min": "124", "max": "809", "mean": "412", "stdev": "134" }, { "name": "V6705", "index": "95", "type": "numeric", "distinct": "602", "missing": "0", "min": "0", "max": "900", "mean": "232", "stdev": "201" }, { "name": "V6802", "index": "96", "type": "numeric", "distinct": "537", "missing": "0", "min": "0", "max": "899", "mean": "295", "stdev": "265" }, { "name": "V6907", "index": "97", "type": "numeric", "distinct": "600", "missing": "0", "min": "0", "max": "900", "mean": "242", "stdev": "201" }, { "name": "V7019", "index": "98", "type": "numeric", "distinct": "628", "missing": "0", "min": "69", "max": "853", "mean": "493", "stdev": "163" }, { "name": "V7135", "index": "99", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "900", "mean": "474", "stdev": "209" } ], "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 }