{ "data_id": "44749", "name": "guillermo_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "guillermo_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "3d70f7a3-74e8-49b0-bebb-d1486a3b450a", "description": "Subsampling of the dataset guillermo (41159) 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 18:47:56", "update_comment": null, "last_update": "2022-11-17 18:47:56", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111511\/dataset", "kaggle_url": null, "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "guillermo_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset guillermo (41159) 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": 100, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 0.9900990099009901, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "AutoCorrelation": 0.5177588794397199, "PercentageOfNumericFeatures": 99.00990099009901, "Dimensionality": 0.0505, "PercentageOfSymbolicFeatures": 0.9900990099009901, "MajorityClassPercentage": 60, "MajorityClassSize": 1200, "MinorityClassPercentage": 40, "MinorityClassSize": 800, "NumberOfBinaryFeatures": 1 }, "tags": [], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "1200", "0" ], [ "0", "800" ] ] ] }, { "name": "V84", "index": "0", "type": "numeric", "distinct": "782", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V117", "index": "1", "type": "numeric", "distinct": "488", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V147", "index": "2", "type": "numeric", "distinct": "239", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "V170", "index": "3", "type": "numeric", "distinct": "180", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "V233", "index": "4", "type": "numeric", "distinct": "540", "missing": "0", "min": "0", "max": "11", "mean": "0", "stdev": "1" }, { "name": "V263", "index": "5", "type": "numeric", "distinct": "603", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V267", "index": "6", "type": "numeric", "distinct": "613", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V362", "index": "7", "type": "numeric", "distinct": "628", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V392", "index": "8", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V494", "index": "9", "type": "numeric", "distinct": "678", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V497", "index": "10", "type": "numeric", "distinct": "662", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V524", "index": "11", "type": "numeric", "distinct": "367", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "V526", "index": "12", "type": "numeric", "distinct": "454", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V567", "index": "13", "type": "numeric", "distinct": "697", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V606", "index": "14", "type": "numeric", "distinct": "680", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V636", "index": "15", "type": "numeric", "distinct": "267", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "0" }, { "name": "V684", "index": "16", "type": "numeric", "distinct": "507", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V862", "index": "17", "type": "numeric", "distinct": "676", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V920", "index": "18", "type": "numeric", "distinct": "306", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V1049", "index": "19", "type": "numeric", "distinct": "406", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V1083", "index": "20", "type": "numeric", "distinct": "412", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V1112", "index": "21", "type": "numeric", "distinct": "329", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "V1115", "index": "22", "type": "numeric", "distinct": "718", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "V1150", "index": "23", "type": "numeric", "distinct": "499", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V1178", "index": "24", "type": "numeric", "distinct": "357", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V1189", "index": "25", "type": "numeric", "distinct": "178", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "V1246", "index": "26", "type": "numeric", "distinct": "350", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V1248", "index": "27", "type": "numeric", "distinct": "548", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V1282", "index": "28", "type": "numeric", "distinct": "391", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "V1312", "index": "29", "type": "numeric", "distinct": "738", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V1373", "index": "30", "type": "numeric", "distinct": "474", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "V1393", "index": "31", "type": "numeric", "distinct": "903", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V1477", "index": "32", "type": "numeric", "distinct": "551", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V1548", "index": "33", "type": "numeric", "distinct": "772", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V1574", "index": "34", "type": "numeric", "distinct": "731", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V1622", "index": "35", "type": "numeric", "distinct": "338", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "0" }, { "name": "V1706", "index": "36", "type": "numeric", "distinct": "359", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "V1724", "index": "37", "type": "numeric", "distinct": "646", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V1782", "index": "38", "type": "numeric", "distinct": "700", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V1793", "index": "39", "type": "numeric", "distinct": "674", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V1810", "index": "40", "type": "numeric", "distinct": "606", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V1825", "index": "41", "type": "numeric", "distinct": "712", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V1912", "index": "42", "type": "numeric", "distinct": "574", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V1918", "index": "43", "type": "numeric", "distinct": "534", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V1943", "index": "44", "type": "numeric", "distinct": "546", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V1956", "index": "45", "type": "numeric", "distinct": "586", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V1964", "index": "46", "type": "numeric", "distinct": "959", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V1986", "index": "47", "type": "numeric", "distinct": "781", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V2059", "index": "48", "type": "numeric", "distinct": "619", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V2114", "index": "49", "type": "numeric", "distinct": "639", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V2128", "index": "50", "type": "numeric", "distinct": "464", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V2149", "index": "51", "type": "numeric", "distinct": "834", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V2185", "index": "52", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V2192", "index": "53", "type": "numeric", "distinct": "864", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V2198", "index": "54", "type": "numeric", "distinct": "808", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V2259", "index": "55", "type": "numeric", "distinct": "139", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "V2271", "index": "56", "type": "numeric", "distinct": "641", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V2301", "index": "57", "type": "numeric", "distinct": "271", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "V2316", "index": "58", "type": "numeric", "distinct": "195", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "0" }, { "name": "V2342", "index": "59", "type": "numeric", "distinct": "653", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V2494", "index": "60", "type": "numeric", "distinct": "737", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V2539", "index": "61", "type": "numeric", "distinct": "465", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V2616", "index": "62", "type": "numeric", "distinct": "588", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "V2658", "index": "63", "type": "numeric", "distinct": "478", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V2713", "index": "64", "type": "numeric", "distinct": "577", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V2744", "index": "65", "type": "numeric", "distinct": "437", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "V2890", "index": "66", "type": "numeric", "distinct": "470", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V3069", "index": "67", "type": "numeric", "distinct": "268", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V3079", "index": "68", "type": "numeric", "distinct": "353", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "V3088", "index": "69", "type": "numeric", "distinct": "732", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V3171", "index": "70", "type": "numeric", "distinct": "292", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "V3179", "index": "71", "type": "numeric", "distinct": "589", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V3180", "index": "72", "type": "numeric", "distinct": "839", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V3181", "index": "73", "type": "numeric", "distinct": "801", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V3233", "index": "74", "type": "numeric", "distinct": "755", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "V3296", "index": "75", "type": "numeric", "distinct": "189", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "V3298", "index": "76", "type": "numeric", "distinct": "330", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "0" }, { "name": "V3312", "index": "77", "type": "numeric", "distinct": "757", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V3331", "index": "78", "type": "numeric", "distinct": "815", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V3446", "index": "79", "type": "numeric", "distinct": "465", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V3451", "index": "80", "type": "numeric", "distinct": "698", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "1" }, { "name": "V3459", "index": "81", "type": "numeric", "distinct": "857", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "V3485", "index": "82", "type": "numeric", "distinct": "882", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V3522", "index": "83", "type": "numeric", "distinct": "618", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V3536", "index": "84", "type": "numeric", "distinct": "799", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "1" }, { "name": "V3600", "index": "85", "type": "numeric", "distinct": "804", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "1" }, { "name": "V3650", "index": "86", "type": "numeric", "distinct": "555", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V3651", "index": "87", "type": "numeric", "distinct": "537", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V3656", "index": "88", "type": "numeric", "distinct": "435", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V3727", "index": "89", "type": "numeric", "distinct": "585", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V3827", "index": "90", "type": "numeric", "distinct": "411", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "V3916", "index": "91", "type": "numeric", "distinct": "366", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "V3932", "index": "92", "type": "numeric", "distinct": "647", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V3989", "index": "93", "type": "numeric", "distinct": "347", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "V3992", "index": "94", "type": "numeric", "distinct": "762", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V4084", "index": "95", "type": "numeric", "distinct": "627", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V4129", "index": "96", "type": "numeric", "distinct": "1240", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V4132", "index": "97", "type": "numeric", "distinct": "1243", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V4163", "index": "98", "type": "numeric", "distinct": "1238", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V4210", "index": "99", "type": "numeric", "distinct": "1240", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" } ], "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 }