DEVELOPMENT... { "data_id": "44574", "name": "arcene_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "arcene_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "753aae14-a597-42d1-9b39-c329ba2daa70", "description": "Subsampling of the dataset arcene (41157) 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": "David Wilson", "uploader_id": 32840, "visibility": "public", "creator": "\"Eddie Bergman\"", "contributor": null, "date": "2022-11-17 18:34:16", "update_comment": null, "last_update": "2022-11-17 18:34:16", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111336\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "arcene_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset arcene (41157) 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( c " ], "weight": 5 }, "qualities": { "NumberOfInstances": 100, "NumberOfFeatures": 101, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "PercentageOfSymbolicFeatures": 0.9900990099009901, "AutoCorrelation": 0.3939393939393939, "PercentageOfNumericFeatures": 99.00990099009901, "PercentageOfMissingValues": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfBinaryFeatures": 0.9900990099009901, "NumberOfBinaryFeatures": 1, "MinorityClassSize": 44, "MinorityClassPercentage": 44, "MajorityClassSize": 56, "MajorityClassPercentage": 56.00000000000001, "Dimensionality": 1.01 }, "tags": [], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "56", "0" ], [ "0", "44" ] ] ] }, { "name": "V198", "index": "0", "type": "numeric", "distinct": "71", "missing": "0", "min": "0", "max": "218", "mean": "84", "stdev": "46" }, { "name": "V274", "index": "1", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "82", "mean": "26", "stdev": "27" }, { "name": "V346", "index": "2", "type": "numeric", "distinct": "92", "missing": "0", "min": "0", "max": "634", "mean": "293", "stdev": "171" }, { "name": "V395", "index": "3", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "312", "mean": "118", "stdev": "85" }, { "name": "V542", "index": "4", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "59", "mean": "5", "stdev": "11" }, { "name": "V617", "index": "5", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "90", "mean": "7", "stdev": "18" }, { "name": "V623", "index": "6", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "501", "mean": "276", "stdev": "135" }, { "name": "V851", "index": "7", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "177", "mean": "29", "stdev": "41" }, { "name": "V917", "index": "8", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "303", "mean": "98", "stdev": "97" }, { "name": "V1155", "index": "9", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "99", "mean": "7", "stdev": "21" }, { "name": "V1164", "index": "10", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "172", "mean": "44", "stdev": "38" }, { "name": "V1231", "index": "11", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "309", "mean": "101", "stdev": "82" }, { "name": "V1236", "index": "12", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "711", "mean": "99", "stdev": "118" }, { "name": "V1332", "index": "13", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "87", "mean": "8", "stdev": "16" }, { "name": "V1429", "index": "14", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "142", "mean": "27", "stdev": "40" }, { "name": "V1479", "index": "15", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "297", "mean": "12", "stdev": "37" }, { "name": "V1600", "index": "16", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "42", "mean": "1", "stdev": "5" }, { "name": "V2022", "index": "17", "type": "numeric", "distinct": "61", "missing": "0", "min": "0", "max": "561", "mean": "279", "stdev": "196" }, { "name": "V2146", "index": "18", "type": "numeric", "distinct": "87", "missing": "0", "min": "54", "max": "505", "mean": "339", "stdev": "157" }, { "name": "V2470", "index": "19", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "206", "mean": "18", "stdev": "43" }, { "name": "V2549", "index": "20", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "116", "mean": "17", "stdev": "29" }, { "name": "V2598", "index": "21", "type": "numeric", "distinct": "83", "missing": "0", "min": "0", "max": "552", "mean": "249", "stdev": "183" }, { "name": "V2608", "index": "22", "type": "numeric", "distinct": "86", "missing": "0", "min": "0", "max": "713", "mean": "255", "stdev": "173" }, { "name": "V2708", "index": "23", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "23", "mean": "0", "stdev": "3" }, { "name": "V2757", "index": "24", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "71", "mean": "4", "stdev": "12" }, { "name": "V2789", "index": "25", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "301", "mean": "92", "stdev": "80" }, { "name": "V2918", "index": "26", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "177", "mean": "29", "stdev": "40" }, { "name": "V2919", "index": "27", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "203", "mean": "47", "stdev": "57" }, { "name": "V3011", "index": "28", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "96", "mean": "8", "stdev": "16" }, { "name": "V3091", "index": "29", "type": "numeric", "distinct": "89", "missing": "0", "min": "26", "max": "495", "mean": "177", "stdev": "120" }, { "name": "V3213", "index": "30", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "191", "mean": "34", "stdev": "49" }, { "name": "V3273", "index": "31", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "64", "mean": "5", "stdev": "12" }, { "name": "V3443", "index": "32", "type": "numeric", "distinct": "81", "missing": "0", "min": "40", "max": "466", "mean": "230", "stdev": "94" }, { "name": "V3618", "index": "33", "type": "numeric", "distinct": "57", "missing": "0", "min": "0", "max": "475", "mean": "155", "stdev": "155" }, { "name": "V3674", "index": "34", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "244", "mean": "30", "stdev": "51" }, { "name": "V3809", "index": "35", "type": "numeric", "distinct": "88", "missing": "0", "min": "104", "max": "770", "mean": "351", "stdev": "168" }, { "name": "V4006", "index": "36", "type": "numeric", "distinct": "80", "missing": "0", "min": "36", "max": "346", "mean": "171", "stdev": "82" }, { "name": "V4058", "index": "37", "type": "numeric", "distinct": "86", "missing": "0", "min": "11", "max": "446", "mean": "176", "stdev": "116" }, { "name": "V4195", "index": "38", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "80", "mean": "10", "stdev": "18" }, { "name": "V4197", "index": "39", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "36", "mean": "3", "stdev": "8" }, { "name": "V4232", "index": "40", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "89", "mean": "12", "stdev": "18" }, { "name": "V4262", "index": "41", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "57", "mean": "3", "stdev": "9" }, { "name": "V4494", "index": "42", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "238", "mean": "41", "stdev": "41" }, { "name": "V4505", "index": "43", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "94", "mean": "28", "stdev": "25" }, { "name": "V4541", "index": "44", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "21", "mean": "0", "stdev": "3" }, { "name": "V4564", "index": "45", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "244", "mean": "29", "stdev": "45" }, { "name": "V4584", "index": "46", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "274", "mean": "56", "stdev": "59" }, { "name": "V4686", "index": "47", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "16", "mean": "0", "stdev": "2" }, { "name": "V4826", "index": "48", "type": "numeric", "distinct": "61", "missing": "0", "min": "0", "max": "328", "mean": "107", "stdev": "81" }, { "name": "V4956", "index": "49", "type": "numeric", "distinct": "86", "missing": "0", "min": "0", "max": "457", "mean": "238", "stdev": "152" }, { "name": "V4992", "index": "50", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "320", "mean": "42", "stdev": "60" }, { "name": "V5069", "index": "51", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "132", "mean": "17", "stdev": "31" }, { "name": "V5091", "index": "52", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "199", "mean": "28", "stdev": "36" }, { "name": "V5106", "index": "53", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "150", "mean": "35", "stdev": "51" }, { "name": "V5142", "index": "54", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "213", "mean": "86", "stdev": "61" }, { "name": "V5274", "index": "55", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "157", "mean": "18", "stdev": "33" }, { "name": "V5341", "index": "56", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "68", "mean": "11", "stdev": "19" }, { "name": "V5388", "index": "57", "type": "numeric", "distinct": "61", "missing": "0", "min": "0", "max": "234", "mean": "58", "stdev": "58" }, { "name": "V5451", "index": "58", "type": "numeric", "distinct": "84", "missing": "0", "min": "16", "max": "462", "mean": "205", "stdev": "109" }, { "name": "V5811", "index": "59", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "325", "mean": "64", "stdev": "73" }, { "name": "V5922", "index": "60", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "641", "mean": "253", "stdev": "186" }, { "name": "V6112", "index": "61", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "80", "mean": "13", "stdev": "19" }, { "name": "V6214", "index": "62", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "445", "mean": "31", "stdev": "66" }, { "name": "V6385", "index": "63", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "384", "mean": "189", "stdev": "134" }, { "name": "V6402", "index": "64", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "185", "mean": "32", "stdev": "47" }, { "name": "V6733", "index": "65", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "37", "mean": "2", "stdev": "7" }, { "name": "V7168", "index": "66", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "115", "mean": "9", "stdev": "19" }, { "name": "V7214", "index": "67", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "116", "mean": "17", "stdev": "27" }, { "name": "V7228", "index": "68", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "137", "mean": "10", "stdev": "23" }, { "name": "V7453", "index": "69", "type": "numeric", "distinct": "80", "missing": "0", "min": "0", "max": "560", "mean": "111", "stdev": "89" }, { "name": "V7461", "index": "70", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "69", "mean": "1", "stdev": "7" }, { "name": "V7477", "index": "71", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "575", "mean": "144", "stdev": "146" }, { "name": "V7479", "index": "72", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "276", "mean": "94", "stdev": "80" }, { "name": "V7528", "index": "73", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "323", "mean": "30", "stdev": "63" }, { "name": "V7688", "index": "74", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "443", "mean": "31", "stdev": "70" }, { "name": "V7706", "index": "75", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "147", "mean": "10", "stdev": "23" }, { "name": "V7742", "index": "76", "type": "numeric", "distinct": "81", "missing": "0", "min": "39", "max": "420", "mean": "215", "stdev": "92" }, { "name": "V7828", "index": "77", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "88", "mean": "10", "stdev": "19" }, { "name": "V8034", "index": "78", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "475", "mean": "131", "stdev": "107" }, { "name": "V8115", "index": "79", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "219", "mean": "46", "stdev": "62" }, { "name": "V8153", "index": "80", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "72", "mean": "9", "stdev": "17" }, { "name": "V8197", "index": "81", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "345", "mean": "13", "stdev": "48" }, { "name": "V8206", "index": "82", "type": "numeric", "distinct": "59", "missing": "0", "min": "0", "max": "332", "mean": "108", "stdev": "86" }, { "name": "V8315", "index": "83", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "162", "mean": "9", "stdev": "25" }, { "name": "V8391", "index": "84", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "22", "mean": "0", "stdev": "2" }, { "name": "V8513", "index": "85", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "434", "mean": "23", "stdev": "54" }, { "name": "V8588", "index": "86", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "314", "mean": "23", "stdev": "43" }, { "name": "V8613", "index": "87", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "83", "mean": "8", "stdev": "16" }, { "name": "V8701", "index": "88", "type": "numeric", "distinct": "85", "missing": "0", "min": "67", "max": "888", "mean": "403", "stdev": "248" }, { "name": "V8982", "index": "89", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "141", "mean": "3", "stdev": "15" }, { "name": "V9148", "index": "90", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "439", "mean": "95", "stdev": "117" }, { "name": "V9208", "index": "91", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "343", "mean": "69", "stdev": "87" }, { "name": "V9400", "index": "92", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "146", "mean": "24", "stdev": "36" }, { "name": "V9414", "index": "93", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "86", "mean": "6", "stdev": "17" }, { "name": "V9569", "index": "94", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "108", "mean": "25", "stdev": "34" }, { "name": "V9661", "index": "95", "type": "numeric", "distinct": "57", "missing": "0", "min": "0", "max": "379", "mean": "127", "stdev": "118" }, { "name": "V9704", "index": "96", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "153", "mean": "18", "stdev": "31" }, { "name": "V9757", "index": "97", "type": "numeric", "distinct": "49", "missing": "0", "min": "0", "max": "184", "mean": "30", "stdev": "38" }, { "name": "V9805", "index": "98", "type": "numeric", "distinct": "89", "missing": "0", "min": "43", "max": "490", "mean": "253", "stdev": "81" }, { "name": "V9999", "index": "99", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "392", "mean": "89", "stdev": "110" } ], "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 }