DEVELOPMENT... { "data_id": "44576", "name": "arcene_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "arcene_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "c292d30a-b3d5-4e2e-a352-40fe7f8c4cb0", "description": "Subsampling of the dataset arcene (41157) 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 18:34:25", "update_comment": null, "last_update": "2022-11-17 18:34:25", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111338\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "arcene_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset arcene (41157) 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( 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": "V15", "index": "0", "type": "numeric", "distinct": "87", "missing": "0", "min": "127", "max": "509", "mean": "321", "stdev": "83" }, { "name": "V48", "index": "1", "type": "numeric", "distinct": "59", "missing": "0", "min": "0", "max": "376", "mean": "39", "stdev": "52" }, { "name": "V303", "index": "2", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "80", "mean": "3", "stdev": "10" }, { "name": "V325", "index": "3", "type": "numeric", "distinct": "81", "missing": "0", "min": "0", "max": "326", "mean": "116", "stdev": "94" }, { "name": "V391", "index": "4", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "63", "mean": "4", "stdev": "10" }, { "name": "V429", "index": "5", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "289", "mean": "81", "stdev": "80" }, { "name": "V765", "index": "6", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "205", "mean": "57", "stdev": "40" }, { "name": "V849", "index": "7", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "85", "mean": "3", "stdev": "10" }, { "name": "V906", "index": "8", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "66", "mean": "10", "stdev": "18" }, { "name": "V933", "index": "9", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "387", "mean": "88", "stdev": "100" }, { "name": "V1023", "index": "10", "type": "numeric", "distinct": "83", "missing": "0", "min": "185", "max": "592", "mean": "427", "stdev": "87" }, { "name": "V1128", "index": "11", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "164", "mean": "11", "stdev": "25" }, { "name": "V1386", "index": "12", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "210", "mean": "31", "stdev": "47" }, { "name": "V1584", "index": "13", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "125", "mean": "16", "stdev": "29" }, { "name": "V1717", "index": "14", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "117", "mean": "28", "stdev": "23" }, { "name": "V1778", "index": "15", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "332", "mean": "33", "stdev": "59" }, { "name": "V1797", "index": "16", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "137", "mean": "5", "stdev": "19" }, { "name": "V1895", "index": "17", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "339", "mean": "52", "stdev": "43" }, { "name": "V2066", "index": "18", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "267", "mean": "41", "stdev": "68" }, { "name": "V2183", "index": "19", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "33", "mean": "0", "stdev": "3" }, { "name": "V2249", "index": "20", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "283", "mean": "45", "stdev": "46" }, { "name": "V2346", "index": "21", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "519", "mean": "254", "stdev": "160" }, { "name": "V2436", "index": "22", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "264", "mean": "27", "stdev": "46" }, { "name": "V2473", "index": "23", "type": "numeric", "distinct": "82", "missing": "0", "min": "14", "max": "834", "mean": "273", "stdev": "201" }, { "name": "V2528", "index": "24", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "344", "mean": "64", "stdev": "76" }, { "name": "V2534", "index": "25", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "331", "mean": "67", "stdev": "82" }, { "name": "V2626", "index": "26", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "44", "mean": "4", "stdev": "10" }, { "name": "V2824", "index": "27", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "183", "mean": "37", "stdev": "42" }, { "name": "V2910", "index": "28", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "142", "mean": "10", "stdev": "23" }, { "name": "V2919", "index": "29", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "203", "mean": "47", "stdev": "57" }, { "name": "V2968", "index": "30", "type": "numeric", "distinct": "79", "missing": "0", "min": "58", "max": "549", "mean": "259", "stdev": "125" }, { "name": "V2974", "index": "31", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "179", "mean": "23", "stdev": "38" }, { "name": "V3124", "index": "32", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "117", "mean": "10", "stdev": "24" }, { "name": "V3180", "index": "33", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "189", "mean": "35", "stdev": "44" }, { "name": "V3254", "index": "34", "type": "numeric", "distinct": "55", "missing": "0", "min": "0", "max": "291", "mean": "100", "stdev": "93" }, { "name": "V3293", "index": "35", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "95", "mean": "21", "stdev": "30" }, { "name": "V3729", "index": "36", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "76", "mean": "5", "stdev": "12" }, { "name": "V3844", "index": "37", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "185", "mean": "3", "stdev": "19" }, { "name": "V3871", "index": "38", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "103", "mean": "29", "stdev": "31" }, { "name": "V3882", "index": "39", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "248", "mean": "63", "stdev": "59" }, { "name": "V3940", "index": "40", "type": "numeric", "distinct": "79", "missing": "0", "min": "161", "max": "480", "mean": "281", "stdev": "67" }, { "name": "V4170", "index": "41", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "65", "mean": "5", "stdev": "13" }, { "name": "V4275", "index": "42", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "331", "mean": "50", "stdev": "61" }, { "name": "V4282", "index": "43", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "87", "mean": "6", "stdev": "17" }, { "name": "V4294", "index": "44", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "97", "mean": "10", "stdev": "22" }, { "name": "V4486", "index": "45", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "119", "mean": "8", "stdev": "22" }, { "name": "V4692", "index": "46", "type": "numeric", "distinct": "79", "missing": "0", "min": "44", "max": "505", "mean": "311", "stdev": "91" }, { "name": "V4725", "index": "47", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "110", "mean": "23", "stdev": "24" }, { "name": "V4750", "index": "48", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "82", "mean": "20", "stdev": "25" }, { "name": "V4861", "index": "49", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "87", "mean": "8", "stdev": "17" }, { "name": "V5129", "index": "50", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "101", "mean": "8", "stdev": "20" }, { "name": "V5177", "index": "51", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "66", "mean": "5", "stdev": "12" }, { "name": "V5185", "index": "52", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "229", "mean": "70", "stdev": "44" }, { "name": "V5769", "index": "53", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "163", "mean": "20", "stdev": "29" }, { "name": "V5824", "index": "54", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "108", "mean": "12", "stdev": "25" }, { "name": "V5826", "index": "55", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "113", "mean": "5", "stdev": "18" }, { "name": "V5933", "index": "56", "type": "numeric", "distinct": "65", "missing": "0", "min": "0", "max": "382", "mean": "65", "stdev": "81" }, { "name": "V6064", "index": "57", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "394", "mean": "126", "stdev": "124" }, { "name": "V6065", "index": "58", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "123", "mean": "10", "stdev": "19" }, { "name": "V6159", "index": "59", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "96", "mean": "17", "stdev": "23" }, { "name": "V6284", "index": "60", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "296", "mean": "90", "stdev": "65" }, { "name": "V6444", "index": "61", "type": "numeric", "distinct": "65", "missing": "0", "min": "0", "max": "331", "mean": "114", "stdev": "110" }, { "name": "V6463", "index": "62", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "24", "mean": "0", "stdev": "2" }, { "name": "V6524", "index": "63", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "400", "mean": "72", "stdev": "108" }, { "name": "V6564", "index": "64", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "97", "mean": "10", "stdev": "23" }, { "name": "V6566", "index": "65", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "26", "mean": "0", "stdev": "3" }, { "name": "V6583", "index": "66", "type": "numeric", "distinct": "93", "missing": "0", "min": "15", "max": "787", "mean": "359", "stdev": "204" }, { "name": "V6595", "index": "67", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "125", "mean": "9", "stdev": "20" }, { "name": "V6615", "index": "68", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "153", "mean": "27", "stdev": "36" }, { "name": "V6819", "index": "69", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "202", "mean": "55", "stdev": "57" }, { "name": "V6857", "index": "70", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "160", "mean": "21", "stdev": "38" }, { "name": "V6919", "index": "71", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "702", "mean": "102", "stdev": "119" }, { "name": "V7042", "index": "72", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "155", "mean": "24", "stdev": "38" }, { "name": "V7206", "index": "73", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "130", "mean": "30", "stdev": "34" }, { "name": "V7286", "index": "74", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "209", "mean": "50", "stdev": "42" }, { "name": "V7327", "index": "75", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "142", "mean": "4", "stdev": "17" }, { "name": "V7400", "index": "76", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "122", "mean": "13", "stdev": "23" }, { "name": "V7516", "index": "77", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "127", "mean": "33", "stdev": "35" }, { "name": "V7581", "index": "78", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "46", "mean": "2", "stdev": "7" }, { "name": "V7699", "index": "79", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "202", "mean": "16", "stdev": "28" }, { "name": "V7810", "index": "80", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V7938", "index": "81", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "254", "mean": "12", "stdev": "33" }, { "name": "V8035", "index": "82", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "100", "mean": "6", "stdev": "17" }, { "name": "V8191", "index": "83", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "76", "mean": "4", "stdev": "12" }, { "name": "V8284", "index": "84", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "211", "mean": "7", "stdev": "24" }, { "name": "V8413", "index": "85", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "34", "mean": "1", "stdev": "4" }, { "name": "V8496", "index": "86", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "76", "mean": "16", "stdev": "22" }, { "name": "V8612", "index": "87", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "123", "mean": "28", "stdev": "33" }, { "name": "V8640", "index": "88", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "291", "mean": "31", "stdev": "59" }, { "name": "V8780", "index": "89", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "265", "mean": "24", "stdev": "44" }, { "name": "V8810", "index": "90", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "448", "mean": "221", "stdev": "168" }, { "name": "V8873", "index": "91", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "88", "mean": "4", "stdev": "15" }, { "name": "V9127", "index": "92", "type": "numeric", "distinct": "80", "missing": "0", "min": "85", "max": "500", "mean": "206", "stdev": "105" }, { "name": "V9251", "index": "93", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "238", "mean": "15", "stdev": "39" }, { "name": "V9285", "index": "94", "type": "numeric", "distinct": "67", "missing": "0", "min": "0", "max": "238", "mean": "87", "stdev": "71" }, { "name": "V9333", "index": "95", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V9387", "index": "96", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "77", "mean": "6", "stdev": "14" }, { "name": "V9498", "index": "97", "type": "numeric", "distinct": "80", "missing": "0", "min": "0", "max": "556", "mean": "264", "stdev": "196" }, { "name": "V9562", "index": "98", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "155", "mean": "47", "stdev": "47" }, { "name": "V9681", "index": "99", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "100", "mean": "5", "stdev": "15" } ], "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 }