{ "data_id": "44560", "name": "madeline_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "madeline_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "eea4351c-c43f-4dac-8de8-2a67de1e3b39", "description": "Subsampling of the dataset madeline (41144) with\n\nseed=2\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 18:33:11", "update_comment": null, "last_update": "2022-11-17 18:33:11", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111322\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "madeline_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset madeline (41144) with seed=2 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, "PercentageOfMissingValues": 0, "AutoCorrelation": 0.48924462231115556, "Dimensionality": 0.0505, "PercentageOfNumericFeatures": 99.00990099009901, "MajorityClassPercentage": 50.3, "PercentageOfSymbolicFeatures": 0.9900990099009901, "MajorityClassSize": 1006, "MinorityClassPercentage": 49.7, "MinorityClassSize": 994, "NumberOfBinaryFeatures": 1, "PercentageOfBinaryFeatures": 0.9900990099009901, "PercentageOfInstancesWithMissingValues": 0 }, "tags": [ { "uploader": "38960", "tag": "Statistics" } ], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "994", "0" ], [ "0", "1006" ] ] ] }, { "name": "V8", "index": "0", "type": "numeric", "distinct": "75", "missing": "0", "min": "439", "max": "527", "mean": "485", "stdev": "12" }, { "name": "V10", "index": "1", "type": "numeric", "distinct": "12", "missing": "0", "min": "472", "max": "483", "mean": "477", "stdev": "2" }, { "name": "V15", "index": "2", "type": "numeric", "distinct": "119", "missing": "0", "min": "423", "max": "558", "mean": "490", "stdev": "20" }, { "name": "V16", "index": "3", "type": "numeric", "distinct": "146", "missing": "0", "min": "407", "max": "582", "mean": "496", "stdev": "26" }, { "name": "V18", "index": "4", "type": "numeric", "distinct": "134", "missing": "0", "min": "406", "max": "550", "mean": "478", "stdev": "24" }, { "name": "V19", "index": "5", "type": "numeric", "distinct": "185", "missing": "0", "min": "406", "max": "670", "mean": "512", "stdev": "35" }, { "name": "V23", "index": "6", "type": "numeric", "distinct": "100", "missing": "0", "min": "424", "max": "548", "mean": "481", "stdev": "17" }, { "name": "V24", "index": "7", "type": "numeric", "distinct": "66", "missing": "0", "min": "445", "max": "522", "mean": "479", "stdev": "10" }, { "name": "V26", "index": "8", "type": "numeric", "distinct": "157", "missing": "0", "min": "401", "max": "618", "mean": "500", "stdev": "27" }, { "name": "V28", "index": "9", "type": "numeric", "distinct": "134", "missing": "0", "min": "406", "max": "585", "mean": "481", "stdev": "24" }, { "name": "V33", "index": "10", "type": "numeric", "distinct": "206", "missing": "0", "min": "356", "max": "613", "mean": "483", "stdev": "38" }, { "name": "V36", "index": "11", "type": "numeric", "distinct": "200", "missing": "0", "min": "382", "max": "641", "mean": "505", "stdev": "37" }, { "name": "V38", "index": "12", "type": "numeric", "distinct": "51", "missing": "0", "min": "452", "max": "505", "mean": "477", "stdev": "9" }, { "name": "V42", "index": "13", "type": "numeric", "distinct": "224", "missing": "0", "min": "288", "max": "644", "mean": "480", "stdev": "43" }, { "name": "V43", "index": "14", "type": "numeric", "distinct": "73", "missing": "0", "min": "441", "max": "518", "mean": "478", "stdev": "12" }, { "name": "V45", "index": "15", "type": "numeric", "distinct": "193", "missing": "0", "min": "388", "max": "641", "mean": "504", "stdev": "36" }, { "name": "V48", "index": "16", "type": "numeric", "distinct": "86", "missing": "0", "min": "444", "max": "542", "mean": "488", "stdev": "14" }, { "name": "V49", "index": "17", "type": "numeric", "distinct": "181", "missing": "0", "min": "391", "max": "628", "mean": "503", "stdev": "32" }, { "name": "V51", "index": "18", "type": "numeric", "distinct": "228", "missing": "0", "min": "350", "max": "680", "mean": "513", "stdev": "44" }, { "name": "V56", "index": "19", "type": "numeric", "distinct": "206", "missing": "0", "min": "379", "max": "640", "mean": "513", "stdev": "39" }, { "name": "V57", "index": "20", "type": "numeric", "distinct": "83", "missing": "0", "min": "433", "max": "538", "mean": "490", "stdev": "14" }, { "name": "V67", "index": "21", "type": "numeric", "distinct": "199", "missing": "0", "min": "371", "max": "642", "mean": "508", "stdev": "37" }, { "name": "V68", "index": "22", "type": "numeric", "distinct": "138", "missing": "0", "min": "387", "max": "597", "mean": "499", "stdev": "24" }, { "name": "V70", "index": "23", "type": "numeric", "distinct": "152", "missing": "0", "min": "393", "max": "587", "mean": "484", "stdev": "28" }, { "name": "V75", "index": "24", "type": "numeric", "distinct": "208", "missing": "0", "min": "358", "max": "607", "mean": "485", "stdev": "45" }, { "name": "V78", "index": "25", "type": "numeric", "distinct": "130", "missing": "0", "min": "403", "max": "551", "mean": "478", "stdev": "22" }, { "name": "V80", "index": "26", "type": "numeric", "distinct": "50", "missing": "0", "min": "454", "max": "508", "mean": "481", "stdev": "8" }, { "name": "V81", "index": "27", "type": "numeric", "distinct": "48", "missing": "0", "min": "457", "max": "506", "mean": "481", "stdev": "7" }, { "name": "V86", "index": "28", "type": "numeric", "distinct": "422", "missing": "0", "min": "207", "max": "829", "mean": "502", "stdev": "96" }, { "name": "V94", "index": "29", "type": "numeric", "distinct": "192", "missing": "0", "min": "355", "max": "603", "mean": "481", "stdev": "35" }, { "name": "V99", "index": "30", "type": "numeric", "distinct": "36", "missing": "0", "min": "462", "max": "499", "mean": "481", "stdev": "5" }, { "name": "V100", "index": "31", "type": "numeric", "distinct": "224", "missing": "0", "min": "368", "max": "649", "mean": "503", "stdev": "42" }, { "name": "V101", "index": "32", "type": "numeric", "distinct": "48", "missing": "0", "min": "455", "max": "503", "mean": "479", "stdev": "7" }, { "name": "V102", "index": "33", "type": "numeric", "distinct": "136", "missing": "0", "min": "414", "max": "609", "mean": "488", "stdev": "24" }, { "name": "V104", "index": "34", "type": "numeric", "distinct": "38", "missing": "0", "min": "462", "max": "500", "mean": "480", "stdev": "5" }, { "name": "V105", "index": "35", "type": "numeric", "distinct": "222", "missing": "0", "min": "361", "max": "637", "mean": "495", "stdev": "41" }, { "name": "V107", "index": "36", "type": "numeric", "distinct": "218", "missing": "0", "min": "367", "max": "641", "mean": "498", "stdev": "42" }, { "name": "V110", "index": "37", "type": "numeric", "distinct": "20", "missing": "0", "min": "468", "max": "487", "mean": "476", "stdev": "3" }, { "name": "V112", "index": "38", "type": "numeric", "distinct": "203", "missing": "0", "min": "352", "max": "633", "mean": "485", "stdev": "37" }, { "name": "V113", "index": "39", "type": "numeric", "distinct": "47", "missing": "0", "min": "456", "max": "505", "mean": "480", "stdev": "7" }, { "name": "V117", "index": "40", "type": "numeric", "distinct": "216", "missing": "0", "min": "378", "max": "656", "mean": "505", "stdev": "41" }, { "name": "V118", "index": "41", "type": "numeric", "distinct": "84", "missing": "0", "min": "427", "max": "529", "mean": "479", "stdev": "13" }, { "name": "V121", "index": "42", "type": "numeric", "distinct": "192", "missing": "0", "min": "387", "max": "635", "mean": "497", "stdev": "35" }, { "name": "V122", "index": "43", "type": "numeric", "distinct": "131", "missing": "0", "min": "414", "max": "573", "mean": "485", "stdev": "22" }, { "name": "V124", "index": "44", "type": "numeric", "distinct": "70", "missing": "0", "min": "442", "max": "519", "mean": "479", "stdev": "11" }, { "name": "V125", "index": "45", "type": "numeric", "distinct": "214", "missing": "0", "min": "325", "max": "639", "mean": "498", "stdev": "42" }, { "name": "V126", "index": "46", "type": "numeric", "distinct": "24", "missing": "0", "min": "463", "max": "487", "mean": "476", "stdev": "3" }, { "name": "V127", "index": "47", "type": "numeric", "distinct": "137", "missing": "0", "min": "406", "max": "565", "mean": "481", "stdev": "25" }, { "name": "V130", "index": "48", "type": "numeric", "distinct": "209", "missing": "0", "min": "346", "max": "623", "mean": "501", "stdev": "39" }, { "name": "V133", "index": "49", "type": "numeric", "distinct": "161", "missing": "0", "min": "391", "max": "593", "mean": "494", "stdev": "29" }, { "name": "V134", "index": "50", "type": "numeric", "distinct": "158", "missing": "0", "min": "373", "max": "571", "mean": "483", "stdev": "29" }, { "name": "V135", "index": "51", "type": "numeric", "distinct": "31", "missing": "0", "min": "461", "max": "493", "mean": "477", "stdev": "4" }, { "name": "V136", "index": "52", "type": "numeric", "distinct": "193", "missing": "0", "min": "367", "max": "614", "mean": "484", "stdev": "42" }, { "name": "V138", "index": "53", "type": "numeric", "distinct": "118", "missing": "0", "min": "414", "max": "554", "mean": "486", "stdev": "20" }, { "name": "V139", "index": "54", "type": "numeric", "distinct": "12", "missing": "0", "min": "470", "max": "481", "mean": "476", "stdev": "2" }, { "name": "V140", "index": "55", "type": "numeric", "distinct": "185", "missing": "0", "min": "379", "max": "603", "mean": "481", "stdev": "34" }, { "name": "V142", "index": "56", "type": "numeric", "distinct": "44", "missing": "0", "min": "457", "max": "500", "mean": "480", "stdev": "6" }, { "name": "V148", "index": "57", "type": "numeric", "distinct": "47", "missing": "0", "min": "457", "max": "504", "mean": "480", "stdev": "7" }, { "name": "V150", "index": "58", "type": "numeric", "distinct": "69", "missing": "0", "min": "445", "max": "518", "mean": "482", "stdev": "11" }, { "name": "V152", "index": "59", "type": "numeric", "distinct": "30", "missing": "0", "min": "461", "max": "491", "mean": "477", "stdev": "4" }, { "name": "V153", "index": "60", "type": "numeric", "distinct": "64", "missing": "0", "min": "450", "max": "520", "mean": "485", "stdev": "11" }, { "name": "V154", "index": "61", "type": "numeric", "distinct": "94", "missing": "0", "min": "433", "max": "539", "mean": "488", "stdev": "15" }, { "name": "V159", "index": "62", "type": "numeric", "distinct": "220", "missing": "0", "min": "342", "max": "650", "mean": "487", "stdev": "42" }, { "name": "V161", "index": "63", "type": "numeric", "distinct": "119", "missing": "0", "min": "426", "max": "572", "mean": "490", "stdev": "20" }, { "name": "V165", "index": "64", "type": "numeric", "distinct": "100", "missing": "0", "min": "433", "max": "548", "mean": "488", "stdev": "17" }, { "name": "V169", "index": "65", "type": "numeric", "distinct": "42", "missing": "0", "min": "461", "max": "504", "mean": "481", "stdev": "6" }, { "name": "V171", "index": "66", "type": "numeric", "distinct": "182", "missing": "0", "min": "379", "max": "613", "mean": "495", "stdev": "33" }, { "name": "V173", "index": "67", "type": "numeric", "distinct": "128", "missing": "0", "min": "410", "max": "571", "mean": "495", "stdev": "22" }, { "name": "V177", "index": "68", "type": "numeric", "distinct": "63", "missing": "0", "min": "442", "max": "513", "mean": "477", "stdev": "10" }, { "name": "V178", "index": "69", "type": "numeric", "distinct": "144", "missing": "0", "min": "395", "max": "595", "mean": "500", "stdev": "26" }, { "name": "V180", "index": "70", "type": "numeric", "distinct": "182", "missing": "0", "min": "372", "max": "679", "mean": "500", "stdev": "33" }, { "name": "V181", "index": "71", "type": "numeric", "distinct": "82", "missing": "0", "min": "430", "max": "530", "mean": "482", "stdev": "13" }, { "name": "V183", "index": "72", "type": "numeric", "distinct": "135", "missing": "0", "min": "403", "max": "571", "mean": "497", "stdev": "24" }, { "name": "V184", "index": "73", "type": "numeric", "distinct": "549", "missing": "0", "min": "37", "max": "999", "mean": "499", "stdev": "134" }, { "name": "V187", "index": "74", "type": "numeric", "distinct": "95", "missing": "0", "min": "421", "max": "540", "mean": "484", "stdev": "15" }, { "name": "V191", "index": "75", "type": "numeric", "distinct": "174", "missing": "0", "min": "393", "max": "609", "mean": "487", "stdev": "30" }, { "name": "V193", "index": "76", "type": "numeric", "distinct": "35", "missing": "0", "min": "464", "max": "502", "mean": "480", "stdev": "5" }, { "name": "V194", "index": "77", "type": "numeric", "distinct": "127", "missing": "0", "min": "407", "max": "577", "mean": "485", "stdev": "22" }, { "name": "V196", "index": "78", "type": "numeric", "distinct": "230", "missing": "0", "min": "361", "max": "668", "mean": "510", "stdev": "43" }, { "name": "V198", "index": "79", "type": "numeric", "distinct": "484", "missing": "0", "min": "84", "max": "780", "mean": "483", "stdev": "113" }, { "name": "V202", "index": "80", "type": "numeric", "distinct": "67", "missing": "0", "min": "438", "max": "516", "mean": "481", "stdev": "12" }, { "name": "V204", "index": "81", "type": "numeric", "distinct": "146", "missing": "0", "min": "388", "max": "571", "mean": "480", "stdev": "25" }, { "name": "V205", "index": "82", "type": "numeric", "distinct": "36", "missing": "0", "min": "462", "max": "499", "mean": "481", "stdev": "5" }, { "name": "V206", "index": "83", "type": "numeric", "distinct": "30", "missing": "0", "min": "465", "max": "500", "mean": "479", "stdev": "4" }, { "name": "V209", "index": "84", "type": "numeric", "distinct": "80", "missing": "0", "min": "444", "max": "525", "mean": "486", "stdev": "13" }, { "name": "V211", "index": "85", "type": "numeric", "distinct": "202", "missing": "0", "min": "353", "max": "616", "mean": "478", "stdev": "37" }, { "name": "V212", "index": "86", "type": "numeric", "distinct": "122", "missing": "0", "min": "409", "max": "557", "mean": "488", "stdev": "21" }, { "name": "V216", "index": "87", "type": "numeric", "distinct": "147", "missing": "0", "min": "417", "max": "611", "mean": "492", "stdev": "25" }, { "name": "V218", "index": "88", "type": "numeric", "distinct": "214", "missing": "0", "min": "307", "max": "626", "mean": "491", "stdev": "41" }, { "name": "V220", "index": "89", "type": "numeric", "distinct": "177", "missing": "0", "min": "363", "max": "619", "mean": "490", "stdev": "32" }, { "name": "V232", "index": "90", "type": "numeric", "distinct": "202", "missing": "0", "min": "347", "max": "602", "mean": "484", "stdev": "38" }, { "name": "V233", "index": "91", "type": "numeric", "distinct": "293", "missing": "0", "min": "263", "max": "719", "mean": "499", "stdev": "68" }, { "name": "V239", "index": "92", "type": "numeric", "distinct": "184", "missing": "0", "min": "368", "max": "615", "mean": "493", "stdev": "35" }, { "name": "V240", "index": "93", "type": "numeric", "distinct": "73", "missing": "0", "min": "438", "max": "520", "mean": "480", "stdev": "14" }, { "name": "V243", "index": "94", "type": "numeric", "distinct": "196", "missing": "0", "min": "352", "max": "632", "mean": "496", "stdev": "36" }, { "name": "V245", "index": "95", "type": "numeric", "distinct": "218", "missing": "0", "min": "370", "max": "639", "mean": "503", "stdev": "40" }, { "name": "V248", "index": "96", "type": "numeric", "distinct": "126", "missing": "0", "min": "398", "max": "569", "mean": "479", "stdev": "22" }, { "name": "V255", "index": "97", "type": "numeric", "distinct": "224", "missing": "0", "min": "330", "max": "647", "mean": "491", "stdev": "42" }, { "name": "V256", "index": "98", "type": "numeric", "distinct": "171", "missing": "0", "min": "388", "max": "615", "mean": "497", "stdev": "31" }, { "name": "V259", "index": "99", "type": "numeric", "distinct": "62", "missing": "0", "min": "448", "max": "510", "mean": "478", "stdev": "10" } ], "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 }