{ "data_id": "44684", "name": "christine_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "christine_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "5dc35a7b-fb98-4a38-877d-78d8bd5b9815", "description": "Subsampling of the dataset christine (41142) with\n\nseed=1\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 18:42:45", "update_comment": null, "last_update": "2022-11-17 18:42:45", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111446\/dataset", "kaggle_url": null, "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "christine_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset christine (41142) with seed=1 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": 1.9801980198019802, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "AutoCorrelation": 0.48724362181090547, "PercentageOfNumericFeatures": 95.04950495049505, "Dimensionality": 0.0505, "PercentageOfSymbolicFeatures": 4.9504950495049505, "MajorityClassPercentage": 50, "MajorityClassSize": 1000, "MinorityClassPercentage": 50, "MinorityClassSize": 1000, "NumberOfBinaryFeatures": 2 }, "tags": [], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "1000", "0" ], [ "0", "1000" ] ] ] }, { "name": "V32", "index": "0", "type": "numeric", "distinct": "60", "missing": "0", "min": "80", "max": "586", "mean": "252", "stdev": "76" }, { "name": "V43", "index": "1", "type": "numeric", "distinct": "34", "missing": "0", "min": "59", "max": "787", "mean": "577", "stdev": "104" }, { "name": "V54", "index": "2", "type": "numeric", "distinct": "351", "missing": "0", "min": "0", "max": "651", "mean": "198", "stdev": "81" }, { "name": "V64", "index": "3", "type": "numeric", "distinct": "475", "missing": "0", "min": "4", "max": "724", "mean": "320", "stdev": "108" }, { "name": "V89", "index": "4", "type": "numeric", "distinct": "197", "missing": "0", "min": "0", "max": "597", "mean": "20", "stdev": "55" }, { "name": "V98", "index": "5", "type": "numeric", "distinct": "367", "missing": "0", "min": "63", "max": "653", "mean": "285", "stdev": "77" }, { "name": "V101", "index": "6", "type": "numeric", "distinct": "390", "missing": "0", "min": "63", "max": "648", "mean": "283", "stdev": "89" }, { "name": "V134", "index": "7", "type": "numeric", "distinct": "264", "missing": "0", "min": "38", "max": "469", "mean": "146", "stdev": "54" }, { "name": "V147", "index": "8", "type": "numeric", "distinct": "210", "missing": "0", "min": "8", "max": "566", "mean": "74", "stdev": "47" }, { "name": "V186", "index": "9", "type": "numeric", "distinct": "539", "missing": "0", "min": "0", "max": "925", "mean": "474", "stdev": "130" }, { "name": "V194", "index": "10", "type": "numeric", "distinct": "503", "missing": "0", "min": "39", "max": "806", "mean": "368", "stdev": "116" }, { "name": "V195", "index": "11", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "501", "mean": "8", "stdev": "32" }, { "name": "V211", "index": "12", "type": "numeric", "distinct": "541", "missing": "0", "min": "85", "max": "870", "mean": "497", "stdev": "126" }, { "name": "V223", "index": "13", "type": "numeric", "distinct": "329", "missing": "0", "min": "114", "max": "712", "mean": "285", "stdev": "72" }, { "name": "V242", "index": "14", "type": "numeric", "distinct": "325", "missing": "0", "min": "59", "max": "725", "mean": "286", "stdev": "66" }, { "name": "V257", "index": "15", "type": "nominal", "distinct": "1", "missing": "0", "distr": [ [ "0" ], [ [ "1000", "1000" ] ] ] }, { "name": "V321", "index": "16", "type": "numeric", "distinct": "193", "missing": "0", "min": "427", "max": "998", "mean": "968", "stdev": "53" }, { "name": "V349", "index": "17", "type": "numeric", "distinct": "449", "missing": "0", "min": "26", "max": "691", "mean": "270", "stdev": "101" }, { "name": "V386", "index": "18", "type": "numeric", "distinct": "435", "missing": "0", "min": "0", "max": "722", "mean": "201", "stdev": "117" }, { "name": "V399", "index": "19", "type": "numeric", "distinct": "395", "missing": "0", "min": "55", "max": "654", "mean": "284", "stdev": "88" }, { "name": "V414", "index": "20", "type": "numeric", "distinct": "264", "missing": "0", "min": "17", "max": "593", "mean": "128", "stdev": "58" }, { "name": "V423", "index": "21", "type": "numeric", "distinct": "252", "missing": "0", "min": "15", "max": "519", "mean": "118", "stdev": "51" }, { "name": "V424", "index": "22", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "627", "mean": "81", "stdev": "90" }, { "name": "V441", "index": "23", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "724", "mean": "77", "stdev": "101" }, { "name": "V444", "index": "24", "type": "numeric", "distinct": "602", "missing": "0", "min": "0", "max": "956", "mean": "410", "stdev": "151" }, { "name": "V466", "index": "25", "type": "numeric", "distinct": "369", "missing": "0", "min": "194", "max": "833", "mean": "480", "stdev": "78" }, { "name": "V469", "index": "26", "type": "numeric", "distinct": "514", "missing": "0", "min": "0", "max": "707", "mean": "315", "stdev": "124" }, { "name": "V475", "index": "27", "type": "numeric", "distinct": "260", "missing": "0", "min": "73", "max": "430", "mean": "179", "stdev": "55" }, { "name": "V483", "index": "28", "type": "numeric", "distinct": "428", "missing": "0", "min": "5", "max": "890", "mean": "209", "stdev": "99" }, { "name": "V515", "index": "29", "type": "numeric", "distinct": "382", "missing": "0", "min": "12", "max": "763", "mean": "220", "stdev": "86" }, { "name": "V516", "index": "30", "type": "numeric", "distinct": "196", "missing": "0", "min": "42", "max": "323", "mean": "114", "stdev": "39" }, { "name": "V561", "index": "31", "type": "numeric", "distinct": "136", "missing": "0", "min": "485", "max": "997", "mean": "978", "stdev": "32" }, { "name": "V583", "index": "32", "type": "numeric", "distinct": "327", "missing": "0", "min": "0", "max": "832", "mean": "355", "stdev": "71" }, { "name": "V595", "index": "33", "type": "numeric", "distinct": "197", "missing": "0", "min": "0", "max": "999", "mean": "977", "stdev": "53" }, { "name": "V603", "index": "34", "type": "numeric", "distinct": "386", "missing": "0", "min": "0", "max": "724", "mean": "95", "stdev": "118" }, { "name": "V634", "index": "35", "type": "numeric", "distinct": "518", "missing": "0", "min": "74", "max": "893", "mean": "340", "stdev": "127" }, { "name": "V636", "index": "36", "type": "numeric", "distinct": "80", "missing": "0", "min": "0", "max": "281", "mean": "14", "stdev": "15" }, { "name": "V656", "index": "37", "type": "numeric", "distinct": "460", "missing": "0", "min": "0", "max": "684", "mean": "220", "stdev": "146" }, { "name": "V673", "index": "38", "type": "numeric", "distinct": "335", "missing": "0", "min": "19", "max": "856", "mean": "178", "stdev": "73" }, { "name": "V680", "index": "39", "type": "numeric", "distinct": "272", "missing": "0", "min": "71", "max": "568", "mean": "171", "stdev": "59" }, { "name": "V688", "index": "40", "type": "nominal", "distinct": "1", "missing": "0", "distr": [ [ "0", "999" ], [ [ "1000", "1000" ], [ "0", "0" ] ] ] }, { "name": "V708", "index": "41", "type": "numeric", "distinct": "213", "missing": "0", "min": "1", "max": "656", "mean": "75", "stdev": "49" }, { "name": "V712", "index": "42", "type": "numeric", "distinct": "294", "missing": "0", "min": "82", "max": "848", "mean": "291", "stdev": "62" }, { "name": "V728", "index": "43", "type": "numeric", "distinct": "337", "missing": "0", "min": "65", "max": "522", "mean": "274", "stdev": "74" }, { "name": "V731", "index": "44", "type": "numeric", "distinct": "429", "missing": "0", "min": "0", "max": "780", "mean": "228", "stdev": "95" }, { "name": "V740", "index": "45", "type": "numeric", "distinct": "377", "missing": "0", "min": "397", "max": "988", "mean": "745", "stdev": "84" }, { "name": "V742", "index": "46", "type": "numeric", "distinct": "374", "missing": "0", "min": "27", "max": "601", "mean": "226", "stdev": "80" }, { "name": "V768", "index": "47", "type": "numeric", "distinct": "247", "missing": "0", "min": "0", "max": "562", "mean": "101", "stdev": "56" }, { "name": "V788", "index": "48", "type": "numeric", "distinct": "497", "missing": "0", "min": "0", "max": "800", "mean": "208", "stdev": "171" }, { "name": "V792", "index": "49", "type": "numeric", "distinct": "381", "missing": "0", "min": "66", "max": "880", "mean": "470", "stdev": "84" }, { "name": "V825", "index": "50", "type": "numeric", "distinct": "275", "missing": "0", "min": "0", "max": "750", "mean": "64", "stdev": "114" }, { "name": "V830", "index": "51", "type": "numeric", "distinct": "375", "missing": "0", "min": "87", "max": "559", "mean": "291", "stdev": "83" }, { "name": "V833", "index": "52", "type": "nominal", "distinct": "1", "missing": "0", "distr": [ [ "0" ], [ [ "1000", "1000" ] ] ] }, { "name": "V840", "index": "53", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "503", "mean": "87", "stdev": "55" }, { "name": "V853", "index": "54", "type": "numeric", "distinct": "468", "missing": "0", "min": "37", "max": "796", "mean": "309", "stdev": "110" }, { "name": "V855", "index": "55", "type": "numeric", "distinct": "568", "missing": "0", "min": "21", "max": "857", "mean": "455", "stdev": "159" }, { "name": "V861", "index": "56", "type": "numeric", "distinct": "318", "missing": "0", "min": "41", "max": "560", "mean": "204", "stdev": "68" }, { "name": "V892", "index": "57", "type": "numeric", "distinct": "278", "missing": "0", "min": "42", "max": "580", "mean": "193", "stdev": "57" }, { "name": "V947", "index": "58", "type": "numeric", "distinct": "347", "missing": "0", "min": "0", "max": "881", "mean": "364", "stdev": "145" }, { "name": "V962", "index": "59", "type": "numeric", "distinct": "467", "missing": "0", "min": "1", "max": "668", "mean": "184", "stdev": "119" }, { "name": "V985", "index": "60", "type": "numeric", "distinct": "139", "missing": "0", "min": "0", "max": "350", "mean": "12", "stdev": "32" }, { "name": "V999", "index": "61", "type": "numeric", "distinct": "465", "missing": "0", "min": "0", "max": "821", "mean": "242", "stdev": "110" }, { "name": "V1000", "index": "62", "type": "numeric", "distinct": "409", "missing": "0", "min": "79", "max": "789", "mean": "381", "stdev": "89" }, { "name": "V1038", "index": "63", "type": "numeric", "distinct": "418", "missing": "0", "min": "0", "max": "770", "mean": "189", "stdev": "121" }, { "name": "V1098", "index": "64", "type": "numeric", "distinct": "149", "missing": "0", "min": "14", "max": "286", "mean": "79", "stdev": "26" }, { "name": "V1151", "index": "65", "type": "numeric", "distinct": "157", "missing": "0", "min": "0", "max": "725", "mean": "124", "stdev": "116" }, { "name": "V1157", "index": "66", "type": "numeric", "distinct": "475", "missing": "0", "min": "0", "max": "852", "mean": "272", "stdev": "132" }, { "name": "V1158", "index": "67", "type": "numeric", "distinct": "275", "missing": "0", "min": "19", "max": "695", "mean": "142", "stdev": "62" }, { "name": "V1163", "index": "68", "type": "numeric", "distinct": "207", "missing": "0", "min": "0", "max": "814", "mean": "67", "stdev": "129" }, { "name": "V1174", "index": "69", "type": "numeric", "distinct": "374", "missing": "0", "min": "84", "max": "610", "mean": "302", "stdev": "83" }, { "name": "V1185", "index": "70", "type": "numeric", "distinct": "445", "missing": "0", "min": "0", "max": "716", "mean": "425", "stdev": "101" }, { "name": "V1188", "index": "71", "type": "numeric", "distinct": "335", "missing": "0", "min": "121", "max": "864", "mean": "636", "stdev": "96" }, { "name": "V1229", "index": "72", "type": "nominal", "distinct": "1", "missing": "0", "distr": [ [ "0" ], [ [ "1000", "1000" ] ] ] }, { "name": "V1234", "index": "73", "type": "numeric", "distinct": "240", "missing": "0", "min": "5", "max": "760", "mean": "65", "stdev": "78" }, { "name": "V1242", "index": "74", "type": "numeric", "distinct": "490", "missing": "0", "min": "48", "max": "789", "mean": "373", "stdev": "113" }, { "name": "V1246", "index": "75", "type": "numeric", "distinct": "422", "missing": "0", "min": "98", "max": "784", "mean": "295", "stdev": "98" }, { "name": "V1247", "index": "76", "type": "numeric", "distinct": "405", "missing": "0", "min": "0", "max": "849", "mean": "389", "stdev": "89" }, { "name": "V1270", "index": "77", "type": "numeric", "distinct": "435", "missing": "0", "min": "168", "max": "921", "mean": "586", "stdev": "98" }, { "name": "V1277", "index": "78", "type": "numeric", "distinct": "388", "missing": "0", "min": "55", "max": "790", "mean": "277", "stdev": "85" }, { "name": "V1283", "index": "79", "type": "numeric", "distinct": "255", "missing": "0", "min": "0", "max": "690", "mean": "136", "stdev": "132" }, { "name": "V1306", "index": "80", "type": "numeric", "distinct": "131", "missing": "0", "min": "0", "max": "615", "mean": "11", "stdev": "36" }, { "name": "V1307", "index": "81", "type": "numeric", "distinct": "482", "missing": "0", "min": "0", "max": "712", "mean": "312", "stdev": "115" }, { "name": "V1341", "index": "82", "type": "numeric", "distinct": "209", "missing": "0", "min": "39", "max": "356", "mean": "125", "stdev": "42" }, { "name": "V1345", "index": "83", "type": "numeric", "distinct": "360", "missing": "0", "min": "70", "max": "544", "mean": "288", "stdev": "78" }, { "name": "V1348", "index": "84", "type": "numeric", "distinct": "343", "missing": "0", "min": "48", "max": "587", "mean": "250", "stdev": "77" }, { "name": "V1366", "index": "85", "type": "numeric", "distinct": "198", "missing": "0", "min": "0", "max": "270", "mean": "72", "stdev": "42" }, { "name": "V1382", "index": "86", "type": "numeric", "distinct": "169", "missing": "0", "min": "0", "max": "349", "mean": "43", "stdev": "39" }, { "name": "V1407", "index": "87", "type": "numeric", "distinct": "267", "missing": "0", "min": "33", "max": "528", "mean": "136", "stdev": "55" }, { "name": "V1422", "index": "88", "type": "numeric", "distinct": "452", "missing": "0", "min": "32", "max": "916", "mean": "238", "stdev": "113" }, { "name": "V1464", "index": "89", "type": "numeric", "distinct": "293", "missing": "0", "min": "47", "max": "517", "mean": "189", "stdev": "62" }, { "name": "V1465", "index": "90", "type": "numeric", "distinct": "175", "missing": "0", "min": "0", "max": "660", "mean": "16", "stdev": "53" }, { "name": "V1472", "index": "91", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "333", "mean": "16", "stdev": "13" }, { "name": "V1476", "index": "92", "type": "numeric", "distinct": "299", "missing": "0", "min": "249", "max": "824", "mean": "380", "stdev": "64" }, { "name": "V1526", "index": "93", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "564", "mean": "17", "stdev": "22" }, { "name": "V1533", "index": "94", "type": "numeric", "distinct": "475", "missing": "0", "min": "0", "max": "999", "mean": "145", "stdev": "146" }, { "name": "V1549", "index": "95", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "V1554", "index": "96", "type": "numeric", "distinct": "232", "missing": "0", "min": "521", "max": "998", "mean": "960", "stdev": "62" }, { "name": "V1581", "index": "97", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "347", "mean": "5", "stdev": "23" }, { "name": "V1600", "index": "98", "type": "numeric", "distinct": "427", "missing": "0", "min": "18", "max": "751", "mean": "291", "stdev": "93" }, { "name": "V1631", "index": "99", "type": "numeric", "distinct": "250", "missing": "0", "min": "53", "max": "620", "mean": "165", "stdev": "52" } ], "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 }