DEVELOPMENT... { "data_id": "44561", "name": "madeline_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "madeline_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "16193df4-f0df-445e-9881-bc69f7f386d8", "description": "Subsampling of the dataset madeline (41144) with\n\nseed=3\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 18:33:16", "update_comment": null, "last_update": "2022-11-17 18:33:16", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111323\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "madeline_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset madeline (41144) with seed=3 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, "PercentageOfSymbolicFeatures": 0.9900990099009901, "AutoCorrelation": 0.5002501250625313, "PercentageOfNumericFeatures": 99.00990099009901, "PercentageOfMissingValues": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfBinaryFeatures": 0.9900990099009901, "NumberOfBinaryFeatures": 1, "MinorityClassSize": 994, "MinorityClassPercentage": 49.7, "MajorityClassSize": 1006, "MajorityClassPercentage": 50.3, "Dimensionality": 0.0505 }, "tags": [], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "994", "0" ], [ "0", "1006" ] ] ] }, { "name": "V1", "index": "0", "type": "numeric", "distinct": "189", "missing": "0", "min": "379", "max": "611", "mean": "488", "stdev": "36" }, { "name": "V2", "index": "1", "type": "numeric", "distinct": "123", "missing": "0", "min": "421", "max": "570", "mean": "497", "stdev": "22" }, { "name": "V6", "index": "2", "type": "numeric", "distinct": "30", "missing": "0", "min": "465", "max": "494", "mean": "479", "stdev": "5" }, { "name": "V7", "index": "3", "type": "numeric", "distinct": "156", "missing": "0", "min": "400", "max": "594", "mean": "491", "stdev": "28" }, { "name": "V9", "index": "4", "type": "numeric", "distinct": "111", "missing": "0", "min": "431", "max": "566", "mean": "493", "stdev": "19" }, { "name": "V14", "index": "5", "type": "numeric", "distinct": "161", "missing": "0", "min": "385", "max": "603", "mean": "498", "stdev": "29" }, { "name": "V16", "index": "6", "type": "numeric", "distinct": "147", "missing": "0", "min": "415", "max": "580", "mean": "496", "stdev": "26" }, { "name": "V21", "index": "7", "type": "numeric", "distinct": "163", "missing": "0", "min": "401", "max": "605", "mean": "503", "stdev": "29" }, { "name": "V27", "index": "8", "type": "numeric", "distinct": "225", "missing": "0", "min": "332", "max": "641", "mean": "507", "stdev": "43" }, { "name": "V28", "index": "9", "type": "numeric", "distinct": "137", "missing": "0", "min": "406", "max": "585", "mean": "482", "stdev": "24" }, { "name": "V29", "index": "10", "type": "numeric", "distinct": "229", "missing": "0", "min": "362", "max": "670", "mean": "515", "stdev": "42" }, { "name": "V30", "index": "11", "type": "numeric", "distinct": "91", "missing": "0", "min": "441", "max": "542", "mean": "488", "stdev": "15" }, { "name": "V33", "index": "12", "type": "numeric", "distinct": "206", "missing": "0", "min": "347", "max": "613", "mean": "483", "stdev": "38" }, { "name": "V39", "index": "13", "type": "numeric", "distinct": "73", "missing": "0", "min": "440", "max": "517", "mean": "477", "stdev": "12" }, { "name": "V41", "index": "14", "type": "numeric", "distinct": "192", "missing": "0", "min": "385", "max": "641", "mean": "495", "stdev": "35" }, { "name": "V47", "index": "15", "type": "numeric", "distinct": "99", "missing": "0", "min": "413", "max": "545", "mean": "479", "stdev": "17" }, { "name": "V48", "index": "16", "type": "numeric", "distinct": "85", "missing": "0", "min": "444", "max": "533", "mean": "488", "stdev": "14" }, { "name": "V52", "index": "17", "type": "numeric", "distinct": "59", "missing": "0", "min": "450", "max": "512", "mean": "481", "stdev": "9" }, { "name": "V53", "index": "18", "type": "numeric", "distinct": "255", "missing": "0", "min": "346", "max": "661", "mean": "496", "stdev": "58" }, { "name": "V55", "index": "19", "type": "numeric", "distinct": "202", "missing": "0", "min": "350", "max": "613", "mean": "493", "stdev": "36" }, { "name": "V56", "index": "20", "type": "numeric", "distinct": "205", "missing": "0", "min": "379", "max": "640", "mean": "514", "stdev": "39" }, { "name": "V57", "index": "21", "type": "numeric", "distinct": "86", "missing": "0", "min": "444", "max": "538", "mean": "489", "stdev": "14" }, { "name": "V58", "index": "22", "type": "numeric", "distinct": "121", "missing": "0", "min": "409", "max": "571", "mean": "494", "stdev": "21" }, { "name": "V59", "index": "23", "type": "numeric", "distinct": "167", "missing": "0", "min": "383", "max": "586", "mean": "489", "stdev": "31" }, { "name": "V62", "index": "24", "type": "numeric", "distinct": "158", "missing": "0", "min": "397", "max": "583", "mean": "488", "stdev": "29" }, { "name": "V63", "index": "25", "type": "numeric", "distinct": "204", "missing": "0", "min": "378", "max": "643", "mean": "501", "stdev": "38" }, { "name": "V65", "index": "26", "type": "numeric", "distinct": "222", "missing": "0", "min": "348", "max": "624", "mean": "489", "stdev": "42" }, { "name": "V70", "index": "27", "type": "numeric", "distinct": "156", "missing": "0", "min": "393", "max": "605", "mean": "484", "stdev": "28" }, { "name": "V71", "index": "28", "type": "numeric", "distinct": "217", "missing": "0", "min": "317", "max": "646", "mean": "479", "stdev": "50" }, { "name": "V75", "index": "29", "type": "numeric", "distinct": "214", "missing": "0", "min": "346", "max": "607", "mean": "487", "stdev": "46" }, { "name": "V78", "index": "30", "type": "numeric", "distinct": "127", "missing": "0", "min": "403", "max": "548", "mean": "479", "stdev": "22" }, { "name": "V80", "index": "31", "type": "numeric", "distinct": "50", "missing": "0", "min": "454", "max": "508", "mean": "480", "stdev": "8" }, { "name": "V82", "index": "32", "type": "numeric", "distinct": "149", "missing": "0", "min": "415", "max": "602", "mean": "500", "stdev": "26" }, { "name": "V83", "index": "33", "type": "numeric", "distinct": "165", "missing": "0", "min": "387", "max": "594", "mean": "493", "stdev": "30" }, { "name": "V94", "index": "34", "type": "numeric", "distinct": "188", "missing": "0", "min": "355", "max": "603", "mean": "481", "stdev": "35" }, { "name": "V95", "index": "35", "type": "numeric", "distinct": "123", "missing": "0", "min": "420", "max": "576", "mean": "497", "stdev": "22" }, { "name": "V98", "index": "36", "type": "numeric", "distinct": "96", "missing": "0", "min": "430", "max": "533", "mean": "484", "stdev": "16" }, { "name": "V101", "index": "37", "type": "numeric", "distinct": "50", "missing": "0", "min": "455", "max": "505", "mean": "479", "stdev": "7" }, { "name": "V103", "index": "38", "type": "numeric", "distinct": "229", "missing": "0", "min": "375", "max": "658", "mean": "512", "stdev": "43" }, { "name": "V107", "index": "39", "type": "numeric", "distinct": "223", "missing": "0", "min": "350", "max": "646", "mean": "499", "stdev": "43" }, { "name": "V110", "index": "40", "type": "numeric", "distinct": "20", "missing": "0", "min": "468", "max": "487", "mean": "476", "stdev": "3" }, { "name": "V115", "index": "41", "type": "numeric", "distinct": "125", "missing": "0", "min": "426", "max": "568", "mean": "494", "stdev": "22" }, { "name": "V118", "index": "42", "type": "numeric", "distinct": "83", "missing": "0", "min": "440", "max": "529", "mean": "479", "stdev": "14" }, { "name": "V122", "index": "43", "type": "numeric", "distinct": "128", "missing": "0", "min": "414", "max": "573", "mean": "485", "stdev": "22" }, { "name": "V124", "index": "44", "type": "numeric", "distinct": "73", "missing": "0", "min": "442", "max": "521", "mean": "479", "stdev": "11" }, { "name": "V127", "index": "45", "type": "numeric", "distinct": "140", "missing": "0", "min": "402", "max": "565", "mean": "480", "stdev": "25" }, { "name": "V128", "index": "46", "type": "numeric", "distinct": "217", "missing": "0", "min": "342", "max": "622", "mean": "489", "stdev": "41" }, { "name": "V130", "index": "47", "type": "numeric", "distinct": "211", "missing": "0", "min": "346", "max": "623", "mean": "501", "stdev": "40" }, { "name": "V131", "index": "48", "type": "numeric", "distinct": "9", "missing": "0", "min": "473", "max": "481", "mean": "477", "stdev": "1" }, { "name": "V133", "index": "49", "type": "numeric", "distinct": "166", "missing": "0", "min": "379", "max": "593", "mean": "494", "stdev": "30" }, { "name": "V137", "index": "50", "type": "numeric", "distinct": "191", "missing": "0", "min": "384", "max": "623", "mean": "498", "stdev": "35" }, { "name": "V138", "index": "51", "type": "numeric", "distinct": "113", "missing": "0", "min": "426", "max": "554", "mean": "486", "stdev": "20" }, { "name": "V140", "index": "52", "type": "numeric", "distinct": "182", "missing": "0", "min": "345", "max": "596", "mean": "481", "stdev": "34" }, { "name": "V144", "index": "53", "type": "numeric", "distinct": "188", "missing": "0", "min": "376", "max": "639", "mean": "503", "stdev": "35" }, { "name": "V145", "index": "54", "type": "numeric", "distinct": "80", "missing": "0", "min": "430", "max": "527", "mean": "482", "stdev": "13" }, { "name": "V146", "index": "55", "type": "numeric", "distinct": "203", "missing": "0", "min": "375", "max": "634", "mean": "506", "stdev": "39" }, { "name": "V149", "index": "56", "type": "numeric", "distinct": "211", "missing": "0", "min": "328", "max": "621", "mean": "499", "stdev": "40" }, { "name": "V151", "index": "57", "type": "numeric", "distinct": "112", "missing": "0", "min": "433", "max": "558", "mean": "491", "stdev": "19" }, { "name": "V152", "index": "58", "type": "numeric", "distinct": "30", "missing": "0", "min": "461", "max": "491", "mean": "477", "stdev": "4" }, { "name": "V155", "index": "59", "type": "numeric", "distinct": "55", "missing": "0", "min": "452", "max": "512", "mean": "483", "stdev": "9" }, { "name": "V156", "index": "60", "type": "numeric", "distinct": "9", "missing": "0", "min": "473", "max": "481", "mean": "477", "stdev": "1" }, { "name": "V160", "index": "61", "type": "numeric", "distinct": "91", "missing": "0", "min": "436", "max": "542", "mean": "490", "stdev": "15" }, { "name": "V162", "index": "62", "type": "numeric", "distinct": "42", "missing": "0", "min": "458", "max": "505", "mean": "479", "stdev": "7" }, { "name": "V164", "index": "63", "type": "numeric", "distinct": "330", "missing": "0", "min": "265", "max": "735", "mean": "501", "stdev": "78" }, { "name": "V167", "index": "64", "type": "numeric", "distinct": "193", "missing": "0", "min": "369", "max": "624", "mean": "497", "stdev": "36" }, { "name": "V168", "index": "65", "type": "numeric", "distinct": "47", "missing": "0", "min": "459", "max": "507", "mean": "481", "stdev": "7" }, { "name": "V170", "index": "66", "type": "numeric", "distinct": "57", "missing": "0", "min": "448", "max": "510", "mean": "481", "stdev": "9" }, { "name": "V172", "index": "67", "type": "numeric", "distinct": "64", "missing": "0", "min": "439", "max": "509", "mean": "477", "stdev": "10" }, { "name": "V173", "index": "68", "type": "numeric", "distinct": "124", "missing": "0", "min": "428", "max": "569", "mean": "494", "stdev": "22" }, { "name": "V175", "index": "69", "type": "numeric", "distinct": "71", "missing": "0", "min": "443", "max": "515", "mean": "478", "stdev": "12" }, { "name": "V183", "index": "70", "type": "numeric", "distinct": "137", "missing": "0", "min": "406", "max": "578", "mean": "497", "stdev": "24" }, { "name": "V187", "index": "71", "type": "numeric", "distinct": "93", "missing": "0", "min": "436", "max": "540", "mean": "484", "stdev": "15" }, { "name": "V188", "index": "72", "type": "numeric", "distinct": "105", "missing": "0", "min": "424", "max": "540", "mean": "485", "stdev": "17" }, { "name": "V191", "index": "73", "type": "numeric", "distinct": "167", "missing": "0", "min": "393", "max": "609", "mean": "487", "stdev": "30" }, { "name": "V193", "index": "74", "type": "numeric", "distinct": "36", "missing": "0", "min": "464", "max": "502", "mean": "480", "stdev": "5" }, { "name": "V198", "index": "75", "type": "numeric", "distinct": "480", "missing": "0", "min": "84", "max": "785", "mean": "482", "stdev": "113" }, { "name": "V201", "index": "76", "type": "numeric", "distinct": "190", "missing": "0", "min": "371", "max": "641", "mean": "496", "stdev": "36" }, { "name": "V202", "index": "77", "type": "numeric", "distinct": "71", "missing": "0", "min": "443", "max": "518", "mean": "481", "stdev": "12" }, { "name": "V203", "index": "78", "type": "numeric", "distinct": "189", "missing": "0", "min": "387", "max": "643", "mean": "508", "stdev": "34" }, { "name": "V204", "index": "79", "type": "numeric", "distinct": "141", "missing": "0", "min": "388", "max": "558", "mean": "479", "stdev": "25" }, { "name": "V210", "index": "80", "type": "numeric", "distinct": "119", "missing": "0", "min": "408", "max": "554", "mean": "478", "stdev": "21" }, { "name": "V211", "index": "81", "type": "numeric", "distinct": "198", "missing": "0", "min": "353", "max": "610", "mean": "478", "stdev": "37" }, { "name": "V212", "index": "82", "type": "numeric", "distinct": "120", "missing": "0", "min": "409", "max": "557", "mean": "488", "stdev": "21" }, { "name": "V217", "index": "83", "type": "numeric", "distinct": "226", "missing": "0", "min": "364", "max": "661", "mean": "507", "stdev": "42" }, { "name": "V219", "index": "84", "type": "numeric", "distinct": "192", "missing": "0", "min": "376", "max": "632", "mean": "501", "stdev": "36" }, { "name": "V221", "index": "85", "type": "numeric", "distinct": "9", "missing": "0", "min": "473", "max": "481", "mean": "477", "stdev": "1" }, { "name": "V222", "index": "86", "type": "numeric", "distinct": "210", "missing": "0", "min": "362", "max": "632", "mean": "489", "stdev": "40" }, { "name": "V223", "index": "87", "type": "numeric", "distinct": "116", "missing": "0", "min": "412", "max": "555", "mean": "494", "stdev": "20" }, { "name": "V227", "index": "88", "type": "numeric", "distinct": "220", "missing": "0", "min": "359", "max": "651", "mean": "498", "stdev": "42" }, { "name": "V228", "index": "89", "type": "numeric", "distinct": "64", "missing": "0", "min": "440", "max": "517", "mean": "479", "stdev": "10" }, { "name": "V230", "index": "90", "type": "numeric", "distinct": "228", "missing": "0", "min": "342", "max": "640", "mean": "498", "stdev": "44" }, { "name": "V234", "index": "91", "type": "numeric", "distinct": "173", "missing": "0", "min": "391", "max": "587", "mean": "490", "stdev": "32" }, { "name": "V236", "index": "92", "type": "numeric", "distinct": "94", "missing": "0", "min": "408", "max": "531", "mean": "477", "stdev": "15" }, { "name": "V240", "index": "93", "type": "numeric", "distinct": "75", "missing": "0", "min": "438", "max": "520", "mean": "481", "stdev": "15" }, { "name": "V246", "index": "94", "type": "numeric", "distinct": "69", "missing": "0", "min": "437", "max": "518", "mean": "482", "stdev": "11" }, { "name": "V249", "index": "95", "type": "numeric", "distinct": "84", "missing": "0", "min": "441", "max": "534", "mean": "484", "stdev": "13" }, { "name": "V252", "index": "96", "type": "numeric", "distinct": "214", "missing": "0", "min": "319", "max": "613", "mean": "482", "stdev": "41" }, { "name": "V253", "index": "97", "type": "numeric", "distinct": "405", "missing": "0", "min": "245", "max": "786", "mean": "499", "stdev": "90" }, { "name": "V254", "index": "98", "type": "numeric", "distinct": "217", "missing": "0", "min": "325", "max": "612", "mean": "487", "stdev": "41" }, { "name": "V259", "index": "99", "type": "numeric", "distinct": "63", "missing": "0", "min": "447", "max": "510", "mean": "477", "stdev": "10" } ], "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 }