{ "data_id": "44701", "name": "Fashion-MNIST_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "Fashion-MNIST_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "a4c6e942-88ed-43c2-b6c6-1e97848193ea", "description": "Subsampling of the dataset Fashion-MNIST (40996) 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": "Eddie Bergman", "uploader_id": 32840, "visibility": "public", "creator": "\"Eddie Bergman\"", "contributor": null, "date": "2022-11-17 18:44:07", "update_comment": null, "last_update": "2022-11-17 18:44:07", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111463\/dataset", "kaggle_url": null, "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "Fashion-MNIST_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset Fashion-MNIST (40996) 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.ch " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 101, "NumberOfClasses": 10, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "AutoCorrelation": 0.09704852426213106, "PercentageOfNumericFeatures": 99.00990099009901, "Dimensionality": 0.0505, "PercentageOfSymbolicFeatures": 0.9900990099009901, "MajorityClassPercentage": 10, "MajorityClassSize": 200, "MinorityClassPercentage": 10, "MinorityClassSize": 200, "NumberOfBinaryFeatures": 0 }, "tags": [], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "10", "missing": "0", "target": "1", "distr": [ [ "0", "1", "2", "3", "4", "5", "6", "7", "8", "9" ], [ [ "200", "0", "0", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "200", "0", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "200", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "200", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "200", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "200", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "200", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "200", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "0", "200", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "0", "0", "200" ] ] ] }, { "name": "pixel2", "index": "0", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "0" }, { "name": "pixel4", "index": "1", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "56", "mean": "0", "stdev": "1" }, { "name": "pixel23", "index": "2", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "207", "mean": "1", "stdev": "10" }, { "name": "pixel28", "index": "3", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "pixel32", "index": "4", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "130", "mean": "0", "stdev": "5" }, { "name": "pixel56", "index": "5", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "36", "mean": "0", "stdev": "1" }, { "name": "pixel59", "index": "6", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "137", "mean": "0", "stdev": "5" }, { "name": "pixel66", "index": "7", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "71", "stdev": "87" }, { "name": "pixel68", "index": "8", "type": "numeric", "distinct": "241", "missing": "0", "min": "0", "max": "255", "mean": "102", "stdev": "94" }, { "name": "pixel80", "index": "9", "type": "numeric", "distinct": "117", "missing": "0", "min": "0", "max": "255", "mean": "8", "stdev": "35" }, { "name": "pixel81", "index": "10", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "252", "mean": "5", "stdev": "28" }, { "name": "pixel102", "index": "11", "type": "numeric", "distinct": "246", "missing": "0", "min": "0", "max": "255", "mean": "107", "stdev": "92" }, { "name": "pixel112", "index": "12", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "149", "mean": "1", "stdev": "8" }, { "name": "pixel124", "index": "13", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "255", "mean": "105", "stdev": "92" }, { "name": "pixel125", "index": "14", "type": "numeric", "distinct": "246", "missing": "0", "min": "0", "max": "255", "mean": "105", "stdev": "93" }, { "name": "pixel141", "index": "15", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "153", "mean": "0", "stdev": "7" }, { "name": "pixel157", "index": "16", "type": "numeric", "distinct": "241", "missing": "0", "min": "0", "max": "255", "mean": "114", "stdev": "88" }, { "name": "pixel163", "index": "17", "type": "numeric", "distinct": "246", "missing": "0", "min": "0", "max": "255", "mean": "59", "stdev": "84" }, { "name": "pixel168", "index": "18", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "219", "mean": "2", "stdev": "13" }, { "name": "pixel174", "index": "19", "type": "numeric", "distinct": "231", "missing": "0", "min": "0", "max": "255", "mean": "44", "stdev": "76" }, { "name": "pixel181", "index": "20", "type": "numeric", "distinct": "242", "missing": "0", "min": "0", "max": "255", "mean": "106", "stdev": "90" }, { "name": "pixel186", "index": "21", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "255", "mean": "120", "stdev": "87" }, { "name": "pixel188", "index": "22", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "109", "stdev": "89" }, { "name": "pixel190", "index": "23", "type": "numeric", "distinct": "246", "missing": "0", "min": "0", "max": "255", "mean": "84", "stdev": "90" }, { "name": "pixel205", "index": "24", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "85", "stdev": "92" }, { "name": "pixel212", "index": "25", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "255", "mean": "124", "stdev": "88" }, { "name": "pixel218", "index": "26", "type": "numeric", "distinct": "245", "missing": "0", "min": "0", "max": "255", "mean": "95", "stdev": "93" }, { "name": "pixel223", "index": "27", "type": "numeric", "distinct": "160", "missing": "0", "min": "0", "max": "255", "mean": "14", "stdev": "45" }, { "name": "pixel227", "index": "28", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "241", "mean": "7", "stdev": "31" }, { "name": "pixel230", "index": "29", "type": "numeric", "distinct": "235", "missing": "0", "min": "0", "max": "255", "mean": "54", "stdev": "82" }, { "name": "pixel231", "index": "30", "type": "numeric", "distinct": "236", "missing": "0", "min": "0", "max": "255", "mean": "71", "stdev": "91" }, { "name": "pixel253", "index": "31", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "217", "mean": "1", "stdev": "13" }, { "name": "pixel277", "index": "32", "type": "numeric", "distinct": "240", "missing": "0", "min": "0", "max": "255", "mean": "56", "stdev": "83" }, { "name": "pixel280", "index": "33", "type": "numeric", "distinct": "89", "missing": "0", "min": "0", "max": "178", "mean": "4", "stdev": "19" }, { "name": "pixel297", "index": "34", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "151", "stdev": "72" }, { "name": "pixel298", "index": "35", "type": "numeric", "distinct": "247", "missing": "0", "min": "0", "max": "255", "mean": "150", "stdev": "73" }, { "name": "pixel300", "index": "36", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "125", "stdev": "87" }, { "name": "pixel302", "index": "37", "type": "numeric", "distinct": "244", "missing": "0", "min": "0", "max": "255", "mean": "111", "stdev": "94" }, { "name": "pixel306", "index": "38", "type": "numeric", "distinct": "236", "missing": "0", "min": "0", "max": "255", "mean": "50", "stdev": "81" }, { "name": "pixel309", "index": "39", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "253", "mean": "2", "stdev": "16" }, { "name": "pixel319", "index": "40", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "120", "stdev": "88" }, { "name": "pixel332", "index": "41", "type": "numeric", "distinct": "253", "missing": "0", "min": "0", "max": "255", "mean": "85", "stdev": "91" }, { "name": "pixel335", "index": "42", "type": "numeric", "distinct": "224", "missing": "0", "min": "0", "max": "255", "mean": "36", "stdev": "71" }, { "name": "pixel348", "index": "43", "type": "numeric", "distinct": "245", "missing": "0", "min": "0", "max": "255", "mean": "135", "stdev": "81" }, { "name": "pixel352", "index": "44", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "255", "mean": "155", "stdev": "72" }, { "name": "pixel366", "index": "45", "type": "numeric", "distinct": "100", "missing": "0", "min": "0", "max": "255", "mean": "8", "stdev": "36" }, { "name": "pixel370", "index": "46", "type": "numeric", "distinct": "243", "missing": "0", "min": "0", "max": "255", "mean": "63", "stdev": "87" }, { "name": "pixel388", "index": "47", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "91", "stdev": "93" }, { "name": "pixel391", "index": "48", "type": "numeric", "distinct": "227", "missing": "0", "min": "0", "max": "255", "mean": "46", "stdev": "82" }, { "name": "pixel403", "index": "49", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "255", "mean": "141", "stdev": "79" }, { "name": "pixel418", "index": "50", "type": "numeric", "distinct": "227", "missing": "0", "min": "0", "max": "255", "mean": "61", "stdev": "88" }, { "name": "pixel431", "index": "51", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "255", "mean": "147", "stdev": "76" }, { "name": "pixel433", "index": "52", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "255", "mean": "154", "stdev": "70" }, { "name": "pixel456", "index": "53", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "100", "stdev": "93" }, { "name": "pixel460", "index": "54", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "155", "stdev": "68" }, { "name": "pixel464", "index": "55", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "157", "stdev": "71" }, { "name": "pixel467", "index": "56", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "255", "mean": "159", "stdev": "70" }, { "name": "pixel469", "index": "57", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "122", "stdev": "90" }, { "name": "pixel474", "index": "58", "type": "numeric", "distinct": "225", "missing": "0", "min": "0", "max": "255", "mean": "62", "stdev": "87" }, { "name": "pixel477", "index": "59", "type": "numeric", "distinct": "143", "missing": "0", "min": "0", "max": "236", "mean": "10", "stdev": "31" }, { "name": "pixel485", "index": "60", "type": "numeric", "distinct": "256", "missing": "0", "min": "0", "max": "255", "mean": "117", "stdev": "86" }, { "name": "pixel488", "index": "61", "type": "numeric", "distinct": "247", "missing": "0", "min": "0", "max": "255", "mean": "158", "stdev": "67" }, { "name": "pixel496", "index": "62", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "135", "stdev": "82" }, { "name": "pixel499", "index": "63", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "107", "stdev": "95" }, { "name": "pixel503", "index": "64", "type": "numeric", "distinct": "236", "missing": "0", "min": "0", "max": "255", "mean": "53", "stdev": "85" }, { "name": "pixel506", "index": "65", "type": "numeric", "distinct": "212", "missing": "0", "min": "0", "max": "255", "mean": "25", "stdev": "57" }, { "name": "pixel514", "index": "66", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "144", "stdev": "78" }, { "name": "pixel516", "index": "67", "type": "numeric", "distinct": "254", "missing": "0", "min": "0", "max": "255", "mean": "158", "stdev": "68" }, { "name": "pixel526", "index": "68", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "255", "mean": "108", "stdev": "95" }, { "name": "pixel527", "index": "69", "type": "numeric", "distinct": "246", "missing": "0", "min": "0", "max": "255", "mean": "103", "stdev": "95" }, { "name": "pixel542", "index": "70", "type": "numeric", "distinct": "253", "missing": "0", "min": "0", "max": "255", "mean": "142", "stdev": "80" }, { "name": "pixel551", "index": "71", "type": "numeric", "distinct": "254", "missing": "0", "min": "0", "max": "255", "mean": "144", "stdev": "79" }, { "name": "pixel553", "index": "72", "type": "numeric", "distinct": "253", "missing": "0", "min": "0", "max": "255", "mean": "106", "stdev": "90" }, { "name": "pixel556", "index": "73", "type": "numeric", "distinct": "243", "missing": "0", "min": "0", "max": "255", "mean": "85", "stdev": "91" }, { "name": "pixel564", "index": "74", "type": "numeric", "distinct": "234", "missing": "0", "min": "0", "max": "255", "mean": "41", "stdev": "71" }, { "name": "pixel573", "index": "75", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "148", "stdev": "78" }, { "name": "pixel589", "index": "76", "type": "numeric", "distinct": "108", "missing": "0", "min": "0", "max": "206", "mean": "6", "stdev": "24" }, { "name": "pixel601", "index": "77", "type": "numeric", "distinct": "243", "missing": "0", "min": "0", "max": "255", "mean": "142", "stdev": "84" }, { "name": "pixel628", "index": "78", "type": "numeric", "distinct": "240", "missing": "0", "min": "0", "max": "255", "mean": "139", "stdev": "86" }, { "name": "pixel629", "index": "79", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "255", "mean": "136", "stdev": "87" }, { "name": "pixel634", "index": "80", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "255", "mean": "125", "stdev": "90" }, { "name": "pixel636", "index": "81", "type": "numeric", "distinct": "253", "missing": "0", "min": "0", "max": "255", "mean": "102", "stdev": "93" }, { "name": "pixel647", "index": "82", "type": "numeric", "distinct": "166", "missing": "0", "min": "0", "max": "255", "mean": "17", "stdev": "50" }, { "name": "pixel655", "index": "83", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "125", "stdev": "91" }, { "name": "pixel665", "index": "84", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "74", "stdev": "88" }, { "name": "pixel681", "index": "85", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "255", "mean": "87", "stdev": "92" }, { "name": "pixel684", "index": "86", "type": "numeric", "distinct": "245", "missing": "0", "min": "0", "max": "255", "mean": "122", "stdev": "93" }, { "name": "pixel685", "index": "87", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "255", "mean": "120", "stdev": "94" }, { "name": "pixel689", "index": "88", "type": "numeric", "distinct": "245", "missing": "0", "min": "0", "max": "255", "mean": "111", "stdev": "96" }, { "name": "pixel699", "index": "89", "type": "numeric", "distinct": "134", "missing": "0", "min": "0", "max": "255", "mean": "11", "stdev": "43" }, { "name": "pixel701", "index": "90", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "131", "mean": "1", "stdev": "7" }, { "name": "pixel707", "index": "91", "type": "numeric", "distinct": "229", "missing": "0", "min": "0", "max": "255", "mean": "57", "stdev": "85" }, { "name": "pixel709", "index": "92", "type": "numeric", "distinct": "243", "missing": "0", "min": "0", "max": "255", "mean": "76", "stdev": "91" }, { "name": "pixel713", "index": "93", "type": "numeric", "distinct": "243", "missing": "0", "min": "0", "max": "255", "mean": "107", "stdev": "96" }, { "name": "pixel719", "index": "94", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "255", "mean": "89", "stdev": "93" }, { "name": "pixel742", "index": "95", "type": "numeric", "distinct": "245", "missing": "0", "min": "0", "max": "255", "mean": "89", "stdev": "101" }, { "name": "pixel747", "index": "96", "type": "numeric", "distinct": "240", "missing": "0", "min": "0", "max": "255", "mean": "82", "stdev": "97" }, { "name": "pixel760", "index": "97", "type": "numeric", "distinct": "83", "missing": "0", "min": "0", "max": "219", "mean": "4", "stdev": "20" }, { "name": "pixel770", "index": "98", "type": "numeric", "distinct": "230", "missing": "0", "min": "0", "max": "255", "mean": "47", "stdev": "68" }, { "name": "pixel775", "index": "99", "type": "numeric", "distinct": "221", "missing": "0", "min": "0", "max": "243", "mean": "36", "stdev": "59" } ], "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 }