{ "data_id": "44752", "name": "guillermo_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "guillermo_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "db8377bf-7818-49e6-9d5a-884106ee61d9", "description": "Subsampling of the dataset guillermo (41159) with\n\nseed=4\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 18:48:13", "update_comment": null, "last_update": "2022-11-17 18:48:13", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111514\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "guillermo_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset guillermo (41159) with seed=4 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, "AutoCorrelation": 0.5277638819409705, "PercentageOfMissingValues": 0, "Dimensionality": 0.0505, "PercentageOfNumericFeatures": 99.00990099009901, "MajorityClassPercentage": 60, "PercentageOfSymbolicFeatures": 0.9900990099009901, "MajorityClassSize": 1200, "MinorityClassPercentage": 40, "MinorityClassSize": 800, "NumberOfBinaryFeatures": 1 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Mathematics" } ], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "1200", "0" ], [ "0", "800" ] ] ] }, { "name": "V115", "index": "0", "type": "numeric", "distinct": "550", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V150", "index": "1", "type": "numeric", "distinct": "335", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "V256", "index": "2", "type": "numeric", "distinct": "809", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V338", "index": "3", "type": "numeric", "distinct": "698", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V340", "index": "4", "type": "numeric", "distinct": "464", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "V383", "index": "5", "type": "numeric", "distinct": "540", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V493", "index": "6", "type": "numeric", "distinct": "620", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V549", "index": "7", "type": "numeric", "distinct": "194", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V567", "index": "8", "type": "numeric", "distinct": "720", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V589", "index": "9", "type": "numeric", "distinct": "588", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V702", "index": "10", "type": "numeric", "distinct": "382", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "V733", "index": "11", "type": "numeric", "distinct": "581", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V736", "index": "12", "type": "numeric", "distinct": "990", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V753", "index": "13", "type": "numeric", "distinct": "681", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V770", "index": "14", "type": "numeric", "distinct": "833", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "V817", "index": "15", "type": "numeric", "distinct": "327", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "0" }, { "name": "V855", "index": "16", "type": "numeric", "distinct": "915", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V882", "index": "17", "type": "numeric", "distinct": "299", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V926", "index": "18", "type": "numeric", "distinct": "481", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V928", "index": "19", "type": "numeric", "distinct": "614", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V950", "index": "20", "type": "numeric", "distinct": "601", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V953", "index": "21", "type": "numeric", "distinct": "431", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V1143", "index": "22", "type": "numeric", "distinct": "728", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "V1192", "index": "23", "type": "numeric", "distinct": "730", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V1288", "index": "24", "type": "numeric", "distinct": "414", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V1427", "index": "25", "type": "numeric", "distinct": "691", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "1" }, { "name": "V1489", "index": "26", "type": "numeric", "distinct": "755", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V1548", "index": "27", "type": "numeric", "distinct": "783", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V1551", "index": "28", "type": "numeric", "distinct": "799", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V1564", "index": "29", "type": "numeric", "distinct": "818", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V1572", "index": "30", "type": "numeric", "distinct": "243", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "V1585", "index": "31", "type": "numeric", "distinct": "600", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V1643", "index": "32", "type": "numeric", "distinct": "633", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V1731", "index": "33", "type": "numeric", "distinct": "474", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "V1818", "index": "34", "type": "numeric", "distinct": "681", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V1908", "index": "35", "type": "numeric", "distinct": "188", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "V1966", "index": "36", "type": "numeric", "distinct": "156", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "0" }, { "name": "V1971", "index": "37", "type": "numeric", "distinct": "877", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "V2014", "index": "38", "type": "numeric", "distinct": "654", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V2035", "index": "39", "type": "numeric", "distinct": "815", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V2053", "index": "40", "type": "numeric", "distinct": "438", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V2097", "index": "41", "type": "numeric", "distinct": "684", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V2100", "index": "42", "type": "numeric", "distinct": "666", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V2114", "index": "43", "type": "numeric", "distinct": "643", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V2117", "index": "44", "type": "numeric", "distinct": "500", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V2126", "index": "45", "type": "numeric", "distinct": "631", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "V2127", "index": "46", "type": "numeric", "distinct": "166", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "V2148", "index": "47", "type": "numeric", "distinct": "731", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V2213", "index": "48", "type": "numeric", "distinct": "586", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V2224", "index": "49", "type": "numeric", "distinct": "780", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "V2278", "index": "50", "type": "numeric", "distinct": "791", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V2294", "index": "51", "type": "numeric", "distinct": "418", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V2304", "index": "52", "type": "numeric", "distinct": "725", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V2427", "index": "53", "type": "numeric", "distinct": "610", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V2447", "index": "54", "type": "numeric", "distinct": "927", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V2453", "index": "55", "type": "numeric", "distinct": "771", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V2482", "index": "56", "type": "numeric", "distinct": "317", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "V2495", "index": "57", "type": "numeric", "distinct": "871", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V2555", "index": "58", "type": "numeric", "distinct": "478", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V2580", "index": "59", "type": "numeric", "distinct": "621", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V2639", "index": "60", "type": "numeric", "distinct": "789", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "1" }, { "name": "V2732", "index": "61", "type": "numeric", "distinct": "712", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V2824", "index": "62", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V2833", "index": "63", "type": "numeric", "distinct": "719", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V2848", "index": "64", "type": "numeric", "distinct": "768", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V2888", "index": "65", "type": "numeric", "distinct": "951", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V2963", "index": "66", "type": "numeric", "distinct": "341", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "V2988", "index": "67", "type": "numeric", "distinct": "582", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V3049", "index": "68", "type": "numeric", "distinct": "732", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V3099", "index": "69", "type": "numeric", "distinct": "365", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V3299", "index": "70", "type": "numeric", "distinct": "524", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "V3333", "index": "71", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V3377", "index": "72", "type": "numeric", "distinct": "509", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "V3452", "index": "73", "type": "numeric", "distinct": "812", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V3464", "index": "74", "type": "numeric", "distinct": "834", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V3636", "index": "75", "type": "numeric", "distinct": "535", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V3674", "index": "76", "type": "numeric", "distinct": "395", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V3701", "index": "77", "type": "numeric", "distinct": "731", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "V3760", "index": "78", "type": "numeric", "distinct": "325", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "V3789", "index": "79", "type": "numeric", "distinct": "579", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V3797", "index": "80", "type": "numeric", "distinct": "626", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V3806", "index": "81", "type": "numeric", "distinct": "578", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "V3831", "index": "82", "type": "numeric", "distinct": "393", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "V3931", "index": "83", "type": "numeric", "distinct": "579", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V3932", "index": "84", "type": "numeric", "distinct": "611", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V3951", "index": "85", "type": "numeric", "distinct": "742", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V3959", "index": "86", "type": "numeric", "distinct": "935", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V3969", "index": "87", "type": "numeric", "distinct": "615", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V3998", "index": "88", "type": "numeric", "distinct": "349", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V4003", "index": "89", "type": "numeric", "distinct": "380", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "V4075", "index": "90", "type": "numeric", "distinct": "754", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "V4076", "index": "91", "type": "numeric", "distinct": "753", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "V4079", "index": "92", "type": "numeric", "distinct": "686", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "V4099", "index": "93", "type": "numeric", "distinct": "1233", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V4103", "index": "94", "type": "numeric", "distinct": "1234", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V4132", "index": "95", "type": "numeric", "distinct": "1230", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V4160", "index": "96", "type": "numeric", "distinct": "1225", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V4175", "index": "97", "type": "numeric", "distinct": "1232", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V4253", "index": "98", "type": "numeric", "distinct": "1231", "missing": "0", "min": "-1", "max": "2", "mean": "0", "stdev": "0" }, { "name": "V4272", "index": "99", "type": "numeric", "distinct": "1235", "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 }