{ "data_id": "44683", "name": "christine_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "christine_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "f5b0bdd3-626c-4245-b3b3-ce0b9522fecb", "description": "Subsampling of the dataset christine (41142) 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 18:42:41", "update_comment": null, "last_update": "2022-11-17 18:42:41", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111445\/dataset", "kaggle_url": null, "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "christine_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset christine (41142) 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": 96, "NumberOfSymbolicFeatures": 5, "PercentageOfBinaryFeatures": 0.9900990099009901, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "AutoCorrelation": 0.5047523761880941, "PercentageOfNumericFeatures": 95.04950495049505, "Dimensionality": 0.0505, "PercentageOfSymbolicFeatures": 4.9504950495049505, "MajorityClassPercentage": 50, "MajorityClassSize": 1000, "MinorityClassPercentage": 50, "MinorityClassSize": 1000, "NumberOfBinaryFeatures": 1 }, "tags": [], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "1000", "0" ], [ "0", "1000" ] ] ] }, { "name": "V5", "index": "0", "type": "numeric", "distinct": "447", "missing": "0", "min": "137", "max": "875", "mean": "546", "stdev": "98" }, { "name": "V9", "index": "1", "type": "numeric", "distinct": "269", "missing": "0", "min": "48", "max": "580", "mean": "166", "stdev": "59" }, { "name": "V14", "index": "2", "type": "numeric", "distinct": "407", "missing": "0", "min": "15", "max": "724", "mean": "222", "stdev": "93" }, { "name": "V26", "index": "3", "type": "numeric", "distinct": "498", "missing": "0", "min": "0", "max": "725", "mean": "280", "stdev": "148" }, { "name": "V35", "index": "4", "type": "numeric", "distinct": "433", "missing": "0", "min": "0", "max": "792", "mean": "351", "stdev": "95" }, { "name": "V45", "index": "5", "type": "numeric", "distinct": "499", "missing": "0", "min": "0", "max": "721", "mean": "357", "stdev": "113" }, { "name": "V53", "index": "6", "type": "numeric", "distinct": "440", "missing": "0", "min": "0", "max": "623", "mean": "218", "stdev": "103" }, { "name": "V64", "index": "7", "type": "numeric", "distinct": "468", "missing": "0", "min": "52", "max": "845", "mean": "319", "stdev": "108" }, { "name": "V80", "index": "8", "type": "numeric", "distinct": "210", "missing": "0", "min": "287", "max": "999", "mean": "975", "stdev": "59" }, { "name": "V117", "index": "9", "type": "numeric", "distinct": "477", "missing": "0", "min": "76", "max": "733", "mean": "416", "stdev": "110" }, { "name": "V118", "index": "10", "type": "numeric", "distinct": "538", "missing": "0", "min": "135", "max": "904", "mean": "478", "stdev": "125" }, { "name": "V127", "index": "11", "type": "numeric", "distinct": "477", "missing": "0", "min": "0", "max": "929", "mean": "366", "stdev": "117" }, { "name": "V138", "index": "12", "type": "numeric", "distinct": "118", "missing": "0", "min": "0", "max": "999", "mean": "53", "stdev": "74" }, { "name": "V141", "index": "13", "type": "numeric", "distinct": "430", "missing": "0", "min": "263", "max": "971", "mean": "711", "stdev": "113" }, { "name": "V197", "index": "14", "type": "numeric", "distinct": "314", "missing": "0", "min": "66", "max": "971", "mean": "541", "stdev": "70" }, { "name": "V217", "index": "15", "type": "numeric", "distinct": "407", "missing": "0", "min": "8", "max": "652", "mean": "258", "stdev": "90" }, { "name": "V271", "index": "16", "type": "numeric", "distinct": "100", "missing": "0", "min": "196", "max": "884", "mean": "341", "stdev": "72" }, { "name": "V276", "index": "17", "type": "numeric", "distinct": "380", "missing": "0", "min": "0", "max": "999", "mean": "237", "stdev": "131" }, { "name": "V371", "index": "18", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "392", "mean": "16", "stdev": "17" }, { "name": "V408", "index": "19", "type": "numeric", "distinct": "241", "missing": "0", "min": "47", "max": "520", "mean": "144", "stdev": "51" }, { "name": "V413", "index": "20", "type": "numeric", "distinct": "224", "missing": "0", "min": "0", "max": "719", "mean": "118", "stdev": "128" }, { "name": "V416", "index": "21", "type": "numeric", "distinct": "165", "missing": "0", "min": "492", "max": "999", "mean": "977", "stdev": "41" }, { "name": "V430", "index": "22", "type": "numeric", "distinct": "266", "missing": "0", "min": "0", "max": "632", "mean": "73", "stdev": "87" }, { "name": "V432", "index": "23", "type": "numeric", "distinct": "337", "missing": "0", "min": "0", "max": "686", "mean": "169", "stdev": "75" }, { "name": "V472", "index": "24", "type": "numeric", "distinct": "397", "missing": "0", "min": "29", "max": "835", "mean": "319", "stdev": "89" }, { "name": "V475", "index": "25", "type": "numeric", "distinct": "272", "missing": "0", "min": "74", "max": "525", "mean": "179", "stdev": "58" }, { "name": "V499", "index": "26", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "478", "mean": "3", "stdev": "30" }, { "name": "V522", "index": "27", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "614", "mean": "407", "stdev": "70" }, { "name": "V534", "index": "28", "type": "numeric", "distinct": "308", "missing": "0", "min": "73", "max": "594", "mean": "310", "stdev": "77" }, { "name": "V549", "index": "29", "type": "numeric", "distinct": "116", "missing": "0", "min": "0", "max": "591", "mean": "8", "stdev": "31" }, { "name": "V579", "index": "30", "type": "numeric", "distinct": "564", "missing": "0", "min": "2", "max": "873", "mean": "442", "stdev": "134" }, { "name": "V604", "index": "31", "type": "numeric", "distinct": "232", "missing": "0", "min": "25", "max": "601", "mean": "116", "stdev": "50" }, { "name": "V605", "index": "32", "type": "numeric", "distinct": "347", "missing": "0", "min": "114", "max": "681", "mean": "304", "stdev": "74" }, { "name": "V610", "index": "33", "type": "numeric", "distinct": "387", "missing": "0", "min": "0", "max": "662", "mean": "254", "stdev": "81" }, { "name": "V616", "index": "34", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "786", "mean": "36", "stdev": "94" }, { "name": "V617", "index": "35", "type": "numeric", "distinct": "143", "missing": "0", "min": "16", "max": "364", "mean": "75", "stdev": "25" }, { "name": "V623", "index": "36", "type": "numeric", "distinct": "31", "missing": "0", "min": "1", "max": "999", "mean": "176", "stdev": "178" }, { "name": "V636", "index": "37", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "241", "mean": "13", "stdev": "14" }, { "name": "V637", "index": "38", "type": "numeric", "distinct": "358", "missing": "0", "min": "0", "max": "520", "mean": "156", "stdev": "85" }, { "name": "V667", "index": "39", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "408", "mean": "2", "stdev": "14" }, { "name": "V681", "index": "40", "type": "numeric", "distinct": "413", "missing": "0", "min": "29", "max": "861", "mean": "542", "stdev": "99" }, { "name": "V733", "index": "41", "type": "numeric", "distinct": "464", "missing": "0", "min": "112", "max": "801", "mean": "479", "stdev": "104" }, { "name": "V758", "index": "42", "type": "numeric", "distinct": "373", "missing": "0", "min": "43", "max": "521", "mean": "216", "stdev": "82" }, { "name": "V781", "index": "43", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "869", "mean": "381", "stdev": "126" }, { "name": "V783", "index": "44", "type": "numeric", "distinct": "397", "missing": "0", "min": "8", "max": "669", "mean": "137", "stdev": "111" }, { "name": "V787", "index": "45", "type": "numeric", "distinct": "495", "missing": "0", "min": "49", "max": "987", "mean": "358", "stdev": "118" }, { "name": "V819", "index": "46", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "642", "mean": "489", "stdev": "31" }, { "name": "V833", "index": "47", "type": "nominal", "distinct": "1", "missing": "0", "distr": [ [ "0" ], [ [ "1000", "1000" ] ] ] }, { "name": "V844", "index": "48", "type": "numeric", "distinct": "290", "missing": "0", "min": "26", "max": "476", "mean": "144", "stdev": "67" }, { "name": "V845", "index": "49", "type": "numeric", "distinct": "305", "missing": "0", "min": "77", "max": "766", "mean": "335", "stdev": "65" }, { "name": "V852", "index": "50", "type": "numeric", "distinct": "93", "missing": "0", "min": "0", "max": "396", "mean": "17", "stdev": "20" }, { "name": "V859", "index": "51", "type": "numeric", "distinct": "384", "missing": "0", "min": "2", "max": "700", "mean": "186", "stdev": "90" }, { "name": "V867", "index": "52", "type": "numeric", "distinct": "385", "missing": "0", "min": "0", "max": "651", "mean": "377", "stdev": "85" }, { "name": "V871", "index": "53", "type": "numeric", "distinct": "549", "missing": "0", "min": "0", "max": "938", "mean": "314", "stdev": "137" }, { "name": "V925", "index": "54", "type": "numeric", "distinct": "241", "missing": "0", "min": "25", "max": "429", "mean": "143", "stdev": "45" }, { "name": "V928", "index": "55", "type": "numeric", "distinct": "246", "missing": "0", "min": "86", "max": "548", "mean": "221", "stdev": "49" }, { "name": "V941", "index": "56", "type": "numeric", "distinct": "71", "missing": "0", "min": "8", "max": "999", "mean": "380", "stdev": "278" }, { "name": "V964", "index": "57", "type": "numeric", "distinct": "394", "missing": "0", "min": "0", "max": "739", "mean": "331", "stdev": "85" }, { "name": "V977", "index": "58", "type": "numeric", "distinct": "416", "missing": "0", "min": "134", "max": "815", "mean": "565", "stdev": "98" }, { "name": "V980", "index": "59", "type": "numeric", "distinct": "364", "missing": "0", "min": "72", "max": "655", "mean": "265", "stdev": "79" }, { "name": "V982", "index": "60", "type": "numeric", "distinct": "565", "missing": "0", "min": "24", "max": "899", "mean": "438", "stdev": "137" }, { "name": "V1005", "index": "61", "type": "nominal", "distinct": "1", "missing": "0", "distr": [ [ "0" ], [ [ "1000", "1000" ] ] ] }, { "name": "V1018", "index": "62", "type": "numeric", "distinct": "546", "missing": "0", "min": "0", "max": "785", "mean": "228", "stdev": "197" }, { "name": "V1026", "index": "63", "type": "numeric", "distinct": "346", "missing": "0", "min": "18", "max": "577", "mean": "204", "stdev": "77" }, { "name": "V1039", "index": "64", "type": "numeric", "distinct": "459", "missing": "0", "min": "68", "max": "770", "mean": "407", "stdev": "102" }, { "name": "V1046", "index": "65", "type": "numeric", "distinct": "357", "missing": "0", "min": "61", "max": "594", "mean": "267", "stdev": "77" }, { "name": "V1061", "index": "66", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "999", "mean": "87", "stdev": "126" }, { "name": "V1088", "index": "67", "type": "numeric", "distinct": "389", "missing": "0", "min": "26", "max": "667", "mean": "268", "stdev": "86" }, { "name": "V1093", "index": "68", "type": "numeric", "distinct": "243", "missing": "0", "min": "25", "max": "598", "mean": "126", "stdev": "54" }, { "name": "V1101", "index": "69", "type": "numeric", "distinct": "290", "missing": "0", "min": "59", "max": "509", "mean": "199", "stdev": "62" }, { "name": "V1126", "index": "70", "type": "numeric", "distinct": "420", "missing": "0", "min": "0", "max": "673", "mean": "346", "stdev": "91" }, { "name": "V1133", "index": "71", "type": "numeric", "distinct": "444", "missing": "0", "min": "9", "max": "781", "mean": "237", "stdev": "108" }, { "name": "V1143", "index": "72", "type": "numeric", "distinct": "133", "missing": "0", "min": "0", "max": "281", "mean": "36", "stdev": "28" }, { "name": "V1158", "index": "73", "type": "numeric", "distinct": "289", "missing": "0", "min": "14", "max": "634", "mean": "141", "stdev": "61" }, { "name": "V1159", "index": "74", "type": "numeric", "distinct": "444", "missing": "0", "min": "102", "max": "742", "mean": "458", "stdev": "100" }, { "name": "V1165", "index": "75", "type": "numeric", "distinct": "484", "missing": "0", "min": "0", "max": "770", "mean": "140", "stdev": "148" }, { "name": "V1167", "index": "76", "type": "numeric", "distinct": "521", "missing": "0", "min": "56", "max": "855", "mean": "399", "stdev": "126" }, { "name": "V1198", "index": "77", "type": "numeric", "distinct": "542", "missing": "0", "min": "90", "max": "833", "mean": "478", "stdev": "128" }, { "name": "V1213", "index": "78", "type": "numeric", "distinct": "279", "missing": "0", "min": "0", "max": "999", "mean": "947", "stdev": "86" }, { "name": "V1237", "index": "79", "type": "numeric", "distinct": "454", "missing": "0", "min": "143", "max": "864", "mean": "427", "stdev": "118" }, { "name": "V1258", "index": "80", "type": "numeric", "distinct": "347", "missing": "0", "min": "37", "max": "553", "mean": "235", "stdev": "76" }, { "name": "V1272", "index": "81", "type": "numeric", "distinct": "499", "missing": "0", "min": "0", "max": "753", "mean": "419", "stdev": "121" }, { "name": "V1281", "index": "82", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "280", "mean": "19", "stdev": "15" }, { "name": "V1308", "index": "83", "type": "numeric", "distinct": "230", "missing": "0", "min": "0", "max": "345", "mean": "108", "stdev": "46" }, { "name": "V1327", "index": "84", "type": "numeric", "distinct": "391", "missing": "0", "min": "319", "max": "939", "mean": "687", "stdev": "97" }, { "name": "V1340", "index": "85", "type": "numeric", "distinct": "348", "missing": "0", "min": "24", "max": "574", "mean": "230", "stdev": "74" }, { "name": "V1342", "index": "86", "type": "numeric", "distinct": "223", "missing": "0", "min": "545", "max": "998", "mean": "959", "stdev": "58" }, { "name": "V1356", "index": "87", "type": "nominal", "distinct": "1", "missing": "0", "distr": [ [ "0" ], [ [ "1000", "1000" ] ] ] }, { "name": "V1357", "index": "88", "type": "numeric", "distinct": "354", "missing": "0", "min": "21", "max": "584", "mean": "277", "stdev": "84" }, { "name": "V1363", "index": "89", "type": "numeric", "distinct": "457", "missing": "0", "min": "0", "max": "838", "mean": "459", "stdev": "104" }, { "name": "V1402", "index": "90", "type": "numeric", "distinct": "443", "missing": "0", "min": "121", "max": "931", "mean": "590", "stdev": "167" }, { "name": "V1413", "index": "91", "type": "numeric", "distinct": "398", "missing": "0", "min": "49", "max": "612", "mean": "347", "stdev": "87" }, { "name": "V1434", "index": "92", "type": "numeric", "distinct": "118", "missing": "0", "min": "0", "max": "362", "mean": "7", "stdev": "26" }, { "name": "V1450", "index": "93", "type": "numeric", "distinct": "155", "missing": "0", "min": "9", "max": "441", "mean": "79", "stdev": "27" }, { "name": "V1455", "index": "94", "type": "numeric", "distinct": "265", "missing": "0", "min": "23", "max": "650", "mean": "158", "stdev": "58" }, { "name": "V1506", "index": "95", "type": "numeric", "distinct": "513", "missing": "0", "min": "0", "max": "787", "mean": "300", "stdev": "154" }, { "name": "V1508", "index": "96", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "143", "mean": "18", "stdev": "17" }, { "name": "V1516", "index": "97", "type": "numeric", "distinct": "379", "missing": "0", "min": "31", "max": "547", "mean": "252", "stdev": "85" }, { "name": "V1562", "index": "98", "type": "numeric", "distinct": "265", "missing": "0", "min": "22", "max": "935", "mean": "144", "stdev": "54" }, { "name": "V1586", "index": "99", "type": "nominal", "distinct": "1", "missing": "0", "distr": [ [ "0" ], [ [ "1000", "1000" ] ] ] } ], "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 }