{ "data_id": "44573", "name": "arcene_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "arcene_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "e3f12e0d-7e07-4590-81df-7ac3cf0488f4", "description": "Subsampling of the dataset arcene (41157) 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 18:34:12", "update_comment": null, "last_update": "2022-11-17 18:34:12", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111335\/dataset", "kaggle_url": null, "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "arcene_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset arcene (41157) 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": 100, "NumberOfFeatures": 101, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 0.9900990099009901, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "AutoCorrelation": 0.3939393939393939, "PercentageOfNumericFeatures": 99.00990099009901, "Dimensionality": 1.01, "PercentageOfSymbolicFeatures": 0.9900990099009901, "MajorityClassPercentage": 56.00000000000001, "MajorityClassSize": 56, "MinorityClassPercentage": 44, "MinorityClassSize": 44, "NumberOfBinaryFeatures": 1 }, "tags": [], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "56", "0" ], [ "0", "44" ] ] ] }, { "name": "V28", "index": "0", "type": "numeric", "distinct": "61", "missing": "0", "min": "0", "max": "345", "mean": "106", "stdev": "78" }, { "name": "V54", "index": "1", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "445", "mean": "151", "stdev": "143" }, { "name": "V83", "index": "2", "type": "numeric", "distinct": "92", "missing": "0", "min": "0", "max": "503", "mean": "209", "stdev": "162" }, { "name": "V164", "index": "3", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "23", "mean": "1", "stdev": "4" }, { "name": "V220", "index": "4", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "109", "mean": "5", "stdev": "15" }, { "name": "V282", "index": "5", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "174", "mean": "5", "stdev": "19" }, { "name": "V334", "index": "6", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "93", "mean": "14", "stdev": "25" }, { "name": "V406", "index": "7", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "242", "mean": "24", "stdev": "41" }, { "name": "V486", "index": "8", "type": "numeric", "distinct": "81", "missing": "0", "min": "95", "max": "498", "mean": "213", "stdev": "101" }, { "name": "V728", "index": "9", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "590", "mean": "75", "stdev": "110" }, { "name": "V746", "index": "10", "type": "numeric", "distinct": "75", "missing": "0", "min": "0", "max": "614", "mean": "161", "stdev": "165" }, { "name": "V799", "index": "11", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "372", "mean": "94", "stdev": "91" }, { "name": "V840", "index": "12", "type": "numeric", "distinct": "84", "missing": "0", "min": "80", "max": "565", "mean": "271", "stdev": "161" }, { "name": "V887", "index": "13", "type": "numeric", "distinct": "49", "missing": "0", "min": "0", "max": "342", "mean": "73", "stdev": "93" }, { "name": "V1236", "index": "14", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "711", "mean": "99", "stdev": "118" }, { "name": "V1347", "index": "15", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "119", "mean": "2", "stdev": "13" }, { "name": "V1737", "index": "16", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "270", "mean": "57", "stdev": "68" }, { "name": "V1745", "index": "17", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "501", "mean": "14", "stdev": "58" }, { "name": "V2271", "index": "18", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "77", "mean": "4", "stdev": "12" }, { "name": "V2542", "index": "19", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "678", "mean": "315", "stdev": "253" }, { "name": "V2560", "index": "20", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "362", "mean": "31", "stdev": "66" }, { "name": "V2638", "index": "21", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "349", "mean": "67", "stdev": "69" }, { "name": "V2672", "index": "22", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "160", "mean": "8", "stdev": "19" }, { "name": "V2752", "index": "23", "type": "numeric", "distinct": "89", "missing": "0", "min": "11", "max": "388", "mean": "219", "stdev": "118" }, { "name": "V2979", "index": "24", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "82", "mean": "20", "stdev": "25" }, { "name": "V3050", "index": "25", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "239", "mean": "51", "stdev": "49" }, { "name": "V3094", "index": "26", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "227", "mean": "37", "stdev": "64" }, { "name": "V3214", "index": "27", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "114", "mean": "2", "stdev": "12" }, { "name": "V3279", "index": "28", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V3376", "index": "29", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "71", "mean": "6", "stdev": "16" }, { "name": "V3571", "index": "30", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "558", "mean": "55", "stdev": "96" }, { "name": "V3744", "index": "31", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "125", "mean": "24", "stdev": "29" }, { "name": "V3772", "index": "32", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "65", "mean": "7", "stdev": "12" }, { "name": "V3779", "index": "33", "type": "numeric", "distinct": "65", "missing": "0", "min": "0", "max": "494", "mean": "152", "stdev": "122" }, { "name": "V3819", "index": "34", "type": "numeric", "distinct": "65", "missing": "0", "min": "0", "max": "327", "mean": "147", "stdev": "105" }, { "name": "V3876", "index": "35", "type": "numeric", "distinct": "81", "missing": "0", "min": "0", "max": "534", "mean": "86", "stdev": "82" }, { "name": "V3912", "index": "36", "type": "numeric", "distinct": "82", "missing": "0", "min": "0", "max": "470", "mean": "191", "stdev": "120" }, { "name": "V3913", "index": "37", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "776", "mean": "457", "stdev": "168" }, { "name": "V4009", "index": "38", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "57", "mean": "3", "stdev": "10" }, { "name": "V4202", "index": "39", "type": "numeric", "distinct": "83", "missing": "0", "min": "0", "max": "328", "mean": "117", "stdev": "79" }, { "name": "V4219", "index": "40", "type": "numeric", "distinct": "83", "missing": "0", "min": "0", "max": "797", "mean": "206", "stdev": "204" }, { "name": "V4588", "index": "41", "type": "numeric", "distinct": "91", "missing": "0", "min": "10", "max": "586", "mean": "188", "stdev": "100" }, { "name": "V4782", "index": "42", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "227", "mean": "35", "stdev": "45" }, { "name": "V4846", "index": "43", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "167", "mean": "27", "stdev": "39" }, { "name": "V4993", "index": "44", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "176", "mean": "24", "stdev": "38" }, { "name": "V5038", "index": "45", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "47", "mean": "2", "stdev": "8" }, { "name": "V5062", "index": "46", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "201", "mean": "50", "stdev": "67" }, { "name": "V5229", "index": "47", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "184", "mean": "9", "stdev": "26" }, { "name": "V5238", "index": "48", "type": "numeric", "distinct": "84", "missing": "0", "min": "0", "max": "570", "mean": "188", "stdev": "160" }, { "name": "V5303", "index": "49", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "406", "mean": "91", "stdev": "88" }, { "name": "V5380", "index": "50", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "660", "mean": "60", "stdev": "104" }, { "name": "V5392", "index": "51", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "196", "mean": "47", "stdev": "54" }, { "name": "V5503", "index": "52", "type": "numeric", "distinct": "82", "missing": "0", "min": "0", "max": "630", "mean": "190", "stdev": "181" }, { "name": "V5554", "index": "53", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "431", "mean": "108", "stdev": "89" }, { "name": "V5706", "index": "54", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "49", "mean": "4", "stdev": "8" }, { "name": "V5770", "index": "55", "type": "numeric", "distinct": "61", "missing": "0", "min": "0", "max": "293", "mean": "77", "stdev": "90" }, { "name": "V5935", "index": "56", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "595", "mean": "195", "stdev": "154" }, { "name": "V6015", "index": "57", "type": "numeric", "distinct": "49", "missing": "0", "min": "0", "max": "195", "mean": "32", "stdev": "39" }, { "name": "V6124", "index": "58", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "306", "mean": "32", "stdev": "58" }, { "name": "V6230", "index": "59", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "40", "mean": "1", "stdev": "5" }, { "name": "V6271", "index": "60", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "574", "mean": "233", "stdev": "202" }, { "name": "V6308", "index": "61", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "433", "mean": "102", "stdev": "119" }, { "name": "V6437", "index": "62", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "521", "mean": "283", "stdev": "155" }, { "name": "V6439", "index": "63", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "509", "mean": "47", "stdev": "92" }, { "name": "V6479", "index": "64", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "427", "mean": "54", "stdev": "70" }, { "name": "V6658", "index": "65", "type": "numeric", "distinct": "89", "missing": "0", "min": "47", "max": "827", "mean": "317", "stdev": "204" }, { "name": "V6671", "index": "66", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "86", "mean": "11", "stdev": "20" }, { "name": "V6715", "index": "67", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "175", "mean": "14", "stdev": "32" }, { "name": "V6827", "index": "68", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "324", "mean": "26", "stdev": "52" }, { "name": "V6859", "index": "69", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "98", "mean": "4", "stdev": "14" }, { "name": "V7014", "index": "70", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "25", "mean": "1", "stdev": "4" }, { "name": "V7139", "index": "71", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "145", "mean": "9", "stdev": "20" }, { "name": "V7171", "index": "72", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "178", "mean": "45", "stdev": "37" }, { "name": "V7185", "index": "73", "type": "numeric", "distinct": "84", "missing": "0", "min": "0", "max": "768", "mean": "437", "stdev": "162" }, { "name": "V7192", "index": "74", "type": "numeric", "distinct": "57", "missing": "0", "min": "0", "max": "273", "mean": "51", "stdev": "51" }, { "name": "V7234", "index": "75", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "120", "mean": "13", "stdev": "28" }, { "name": "V7246", "index": "76", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "105", "mean": "5", "stdev": "18" }, { "name": "V7595", "index": "77", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "65", "mean": "11", "stdev": "18" }, { "name": "V7599", "index": "78", "type": "numeric", "distinct": "61", "missing": "0", "min": "0", "max": "270", "mean": "43", "stdev": "50" }, { "name": "V7604", "index": "79", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "88", "mean": "9", "stdev": "16" }, { "name": "V8014", "index": "80", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "555", "mean": "74", "stdev": "103" }, { "name": "V8060", "index": "81", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "175", "mean": "19", "stdev": "32" }, { "name": "V8095", "index": "82", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "172", "mean": "41", "stdev": "42" }, { "name": "V8327", "index": "83", "type": "numeric", "distinct": "59", "missing": "0", "min": "0", "max": "240", "mean": "44", "stdev": "56" }, { "name": "V8371", "index": "84", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "125", "mean": "18", "stdev": "27" }, { "name": "V8408", "index": "85", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "56", "mean": "3", "stdev": "9" }, { "name": "V8423", "index": "86", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "489", "mean": "203", "stdev": "164" }, { "name": "V8429", "index": "87", "type": "numeric", "distinct": "49", "missing": "0", "min": "0", "max": "274", "mean": "39", "stdev": "53" }, { "name": "V8511", "index": "88", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "154", "mean": "23", "stdev": "37" }, { "name": "V8575", "index": "89", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "106", "mean": "14", "stdev": "25" }, { "name": "V8721", "index": "90", "type": "numeric", "distinct": "82", "missing": "0", "min": "96", "max": "545", "mean": "241", "stdev": "129" }, { "name": "V8874", "index": "91", "type": "numeric", "distinct": "49", "missing": "0", "min": "0", "max": "139", "mean": "33", "stdev": "38" }, { "name": "V8896", "index": "92", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "517", "mean": "193", "stdev": "172" }, { "name": "V9048", "index": "93", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "110", "mean": "33", "stdev": "28" }, { "name": "V9276", "index": "94", "type": "numeric", "distinct": "71", "missing": "0", "min": "0", "max": "275", "mean": "74", "stdev": "55" }, { "name": "V9320", "index": "95", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "132", "mean": "22", "stdev": "31" }, { "name": "V9463", "index": "96", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "519", "mean": "37", "stdev": "77" }, { "name": "V9625", "index": "97", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "126", "mean": "25", "stdev": "28" }, { "name": "V9766", "index": "98", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "159", "mean": "8", "stdev": "22" }, { "name": "V9927", "index": "99", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "43", "mean": "6", "stdev": "11" } ], "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 }