{ "data_id": "44699", "name": "Fashion-MNIST_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "Fashion-MNIST_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "b6d117bb-bbc0-46bf-af80-1cb6aaaeb5cb", "description": "Subsampling of the dataset Fashion-MNIST (40996) 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 18:43:57", "update_comment": null, "last_update": "2022-11-17 18:43:57", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111461\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "Fashion-MNIST_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset Fashion-MNIST (40996) 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.ch " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 101, "NumberOfClasses": 10, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.0975487743871936, "PercentageOfMissingValues": 0, "Dimensionality": 0.0505, "PercentageOfNumericFeatures": 99.00990099009901, "MajorityClassPercentage": 10, "PercentageOfSymbolicFeatures": 0.9900990099009901, "MajorityClassSize": 200, "MinorityClassPercentage": 10, "MinorityClassSize": 200, "NumberOfBinaryFeatures": 0 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Mathematics" } ], "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": "pixel15", "index": "0", "type": "numeric", "distinct": "229", "missing": "0", "min": "0", "max": "255", "mean": "50", "stdev": "67" }, { "name": "pixel20", "index": "1", "type": "numeric", "distinct": "148", "missing": "0", "min": "0", "max": "250", "mean": "11", "stdev": "33" }, { "name": "pixel25", "index": "2", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "181", "mean": "1", "stdev": "8" }, { "name": "pixel31", "index": "3", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "108", "mean": "0", "stdev": "2" }, { "name": "pixel43", "index": "4", "type": "numeric", "distinct": "234", "missing": "0", "min": "0", "max": "255", "mean": "108", "stdev": "103" }, { "name": "pixel46", "index": "5", "type": "numeric", "distinct": "247", "missing": "0", "min": "0", "max": "255", "mean": "90", "stdev": "96" }, { "name": "pixel48", "index": "6", "type": "numeric", "distinct": "233", "missing": "0", "min": "0", "max": "255", "mean": "43", "stdev": "73" }, { "name": "pixel61", "index": "7", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "231", "mean": "2", "stdev": "16" }, { "name": "pixel68", "index": "8", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "255", "mean": "99", "stdev": "93" }, { "name": "pixel86", "index": "9", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "51", "mean": "0", "stdev": "1" }, { "name": "pixel87", "index": "10", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "181", "mean": "0", "stdev": "6" }, { "name": "pixel89", "index": "11", "type": "numeric", "distinct": "99", "missing": "0", "min": "0", "max": "247", "mean": "6", "stdev": "26" }, { "name": "pixel97", "index": "12", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "103", "stdev": "94" }, { "name": "pixel100", "index": "13", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "105", "stdev": "94" }, { "name": "pixel116", "index": "14", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "248", "mean": "2", "stdev": "18" }, { "name": "pixel120", "index": "15", "type": "numeric", "distinct": "241", "missing": "0", "min": "0", "max": "255", "mean": "59", "stdev": "83" }, { "name": "pixel147", "index": "16", "type": "numeric", "distinct": "229", "missing": "0", "min": "0", "max": "255", "mean": "53", "stdev": "81" }, { "name": "pixel166", "index": "17", "type": "numeric", "distinct": "149", "missing": "0", "min": "0", "max": "255", "mean": "12", "stdev": "43" }, { "name": "pixel173", "index": "18", "type": "numeric", "distinct": "195", "missing": "0", "min": "0", "max": "252", "mean": "21", "stdev": "54" }, { "name": "pixel180", "index": "19", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "255", "mean": "103", "stdev": "90" }, { "name": "pixel190", "index": "20", "type": "numeric", "distinct": "245", "missing": "0", "min": "0", "max": "255", "mean": "81", "stdev": "90" }, { "name": "pixel191", "index": "21", "type": "numeric", "distinct": "242", "missing": "0", "min": "0", "max": "255", "mean": "68", "stdev": "86" }, { "name": "pixel201", "index": "22", "type": "numeric", "distinct": "208", "missing": "0", "min": "0", "max": "255", "mean": "25", "stdev": "59" }, { "name": "pixel205", "index": "23", "type": "numeric", "distinct": "244", "missing": "0", "min": "0", "max": "255", "mean": "83", "stdev": "91" }, { "name": "pixel217", "index": "24", "type": "numeric", "distinct": "253", "missing": "0", "min": "0", "max": "255", "mean": "100", "stdev": "91" }, { "name": "pixel219", "index": "25", "type": "numeric", "distinct": "245", "missing": "0", "min": "0", "max": "255", "mean": "79", "stdev": "90" }, { "name": "pixel235", "index": "26", "type": "numeric", "distinct": "247", "missing": "0", "min": "0", "max": "255", "mean": "104", "stdev": "91" }, { "name": "pixel240", "index": "27", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "129", "stdev": "85" }, { "name": "pixel267", "index": "28", "type": "numeric", "distinct": "253", "missing": "0", "min": "0", "max": "255", "mean": "120", "stdev": "82" }, { "name": "pixel274", "index": "29", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "255", "mean": "105", "stdev": "94" }, { "name": "pixel276", "index": "30", "type": "numeric", "distinct": "247", "missing": "0", "min": "0", "max": "255", "mean": "73", "stdev": "88" }, { "name": "pixel281", "index": "31", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "234", "mean": "1", "stdev": "12" }, { "name": "pixel287", "index": "32", "type": "numeric", "distinct": "234", "missing": "0", "min": "0", "max": "255", "mean": "70", "stdev": "90" }, { "name": "pixel291", "index": "33", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "109", "stdev": "90" }, { "name": "pixel295", "index": "34", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "128", "stdev": "80" }, { "name": "pixel314", "index": "35", "type": "numeric", "distinct": "237", "missing": "0", "min": "0", "max": "255", "mean": "57", "stdev": "85" }, { "name": "pixel319", "index": "36", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "117", "stdev": "88" }, { "name": "pixel322", "index": "37", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "134", "stdev": "80" }, { "name": "pixel324", "index": "38", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "151", "stdev": "73" }, { "name": "pixel325", "index": "39", "type": "numeric", "distinct": "247", "missing": "0", "min": "0", "max": "255", "mean": "153", "stdev": "71" }, { "name": "pixel343", "index": "40", "type": "numeric", "distinct": "243", "missing": "0", "min": "0", "max": "255", "mean": "68", "stdev": "90" }, { "name": "pixel350", "index": "41", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "255", "mean": "139", "stdev": "77" }, { "name": "pixel351", "index": "42", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "136", "stdev": "78" }, { "name": "pixel352", "index": "43", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "153", "stdev": "72" }, { "name": "pixel355", "index": "44", "type": "numeric", "distinct": "255", "missing": "0", "min": "0", "max": "255", "mean": "149", "stdev": "75" }, { "name": "pixel364", "index": "45", "type": "numeric", "distinct": "130", "missing": "0", "min": "0", "max": "215", "mean": "8", "stdev": "27" }, { "name": "pixel382", "index": "46", "type": "numeric", "distinct": "245", "missing": "0", "min": "0", "max": "255", "mean": "156", "stdev": "69" }, { "name": "pixel385", "index": "47", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "255", "mean": "126", "stdev": "90" }, { "name": "pixel386", "index": "48", "type": "numeric", "distinct": "247", "missing": "0", "min": "0", "max": "255", "mean": "119", "stdev": "94" }, { "name": "pixel396", "index": "49", "type": "numeric", "distinct": "203", "missing": "0", "min": "0", "max": "255", "mean": "25", "stdev": "59" }, { "name": "pixel398", "index": "50", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "255", "mean": "70", "stdev": "89" }, { "name": "pixel400", "index": "51", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "255", "mean": "93", "stdev": "94" }, { "name": "pixel402", "index": "52", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "121", "stdev": "85" }, { "name": "pixel427", "index": "53", "type": "numeric", "distinct": "245", "missing": "0", "min": "0", "max": "255", "mean": "86", "stdev": "92" }, { "name": "pixel451", "index": "54", "type": "numeric", "distinct": "218", "missing": "0", "min": "0", "max": "255", "mean": "26", "stdev": "60" }, { "name": "pixel452", "index": "55", "type": "numeric", "distinct": "226", "missing": "0", "min": "0", "max": "255", "mean": "37", "stdev": "68" }, { "name": "pixel457", "index": "56", "type": "numeric", "distinct": "254", "missing": "0", "min": "0", "max": "255", "mean": "114", "stdev": "87" }, { "name": "pixel463", "index": "57", "type": "numeric", "distinct": "247", "missing": "0", "min": "0", "max": "255", "mean": "143", "stdev": "78" }, { "name": "pixel468", "index": "58", "type": "numeric", "distinct": "253", "missing": "0", "min": "0", "max": "255", "mean": "139", "stdev": "80" }, { "name": "pixel492", "index": "59", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "255", "mean": "155", "stdev": "71" }, { "name": "pixel519", "index": "60", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "139", "stdev": "81" }, { "name": "pixel524", "index": "61", "type": "numeric", "distinct": "256", "missing": "0", "min": "0", "max": "255", "mean": "130", "stdev": "85" }, { "name": "pixel532", "index": "62", "type": "numeric", "distinct": "156", "missing": "0", "min": "0", "max": "225", "mean": "15", "stdev": "35" }, { "name": "pixel534", "index": "63", "type": "numeric", "distinct": "188", "missing": "0", "min": "0", "max": "255", "mean": "25", "stdev": "61" }, { "name": "pixel538", "index": "64", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "85", "stdev": "91" }, { "name": "pixel545", "index": "65", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "153", "stdev": "75" }, { "name": "pixel546", "index": "66", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "255", "mean": "143", "stdev": "79" }, { "name": "pixel550", "index": "67", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "152", "stdev": "74" }, { "name": "pixel562", "index": "68", "type": "numeric", "distinct": "189", "missing": "0", "min": "0", "max": "255", "mean": "24", "stdev": "59" }, { "name": "pixel569", "index": "69", "type": "numeric", "distinct": "256", "missing": "0", "min": "0", "max": "255", "mean": "111", "stdev": "88" }, { "name": "pixel578", "index": "70", "type": "numeric", "distinct": "253", "missing": "0", "min": "0", "max": "255", "mean": "142", "stdev": "81" }, { "name": "pixel580", "index": "71", "type": "numeric", "distinct": "256", "missing": "0", "min": "0", "max": "255", "mean": "118", "stdev": "89" }, { "name": "pixel584", "index": "72", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "255", "mean": "81", "stdev": "91" }, { "name": "pixel585", "index": "73", "type": "numeric", "distinct": "247", "missing": "0", "min": "0", "max": "255", "mean": "62", "stdev": "83" }, { "name": "pixel588", "index": "74", "type": "numeric", "distinct": "129", "missing": "0", "min": "0", "max": "220", "mean": "8", "stdev": "26" }, { "name": "pixel591", "index": "75", "type": "numeric", "distinct": "207", "missing": "0", "min": "0", "max": "255", "mean": "26", "stdev": "61" }, { "name": "pixel593", "index": "76", "type": "numeric", "distinct": "243", "missing": "0", "min": "0", "max": "255", "mean": "62", "stdev": "83" }, { "name": "pixel604", "index": "77", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "255", "mean": "132", "stdev": "86" }, { "name": "pixel611", "index": "78", "type": "numeric", "distinct": "242", "missing": "0", "min": "0", "max": "255", "mean": "83", "stdev": "96" }, { "name": "pixel621", "index": "79", "type": "numeric", "distinct": "243", "missing": "0", "min": "0", "max": "255", "mean": "57", "stdev": "82" }, { "name": "pixel643", "index": "80", "type": "numeric", "distinct": "182", "missing": "0", "min": "0", "max": "255", "mean": "22", "stdev": "59" }, { "name": "pixel651", "index": "81", "type": "numeric", "distinct": "243", "missing": "0", "min": "0", "max": "255", "mean": "73", "stdev": "93" }, { "name": "pixel652", "index": "82", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "255", "mean": "72", "stdev": "87" }, { "name": "pixel654", "index": "83", "type": "numeric", "distinct": "243", "missing": "0", "min": "0", "max": "255", "mean": "111", "stdev": "93" }, { "name": "pixel655", "index": "84", "type": "numeric", "distinct": "247", "missing": "0", "min": "0", "max": "255", "mean": "123", "stdev": "91" }, { "name": "pixel657", "index": "85", "type": "numeric", "distinct": "247", "missing": "0", "min": "0", "max": "255", "mean": "127", "stdev": "92" }, { "name": "pixel664", "index": "86", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "255", "mean": "93", "stdev": "93" }, { "name": "pixel684", "index": "87", "type": "numeric", "distinct": "244", "missing": "0", "min": "0", "max": "255", "mean": "120", "stdev": "93" }, { "name": "pixel694", "index": "88", "type": "numeric", "distinct": "245", "missing": "0", "min": "0", "max": "255", "mean": "57", "stdev": "83" }, { "name": "pixel701", "index": "89", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "151", "mean": "1", "stdev": "8" }, { "name": "pixel706", "index": "90", "type": "numeric", "distinct": "225", "missing": "0", "min": "0", "max": "255", "mean": "52", "stdev": "84" }, { "name": "pixel714", "index": "91", "type": "numeric", "distinct": "244", "missing": "0", "min": "0", "max": "255", "mean": "94", "stdev": "94" }, { "name": "pixel715", "index": "92", "type": "numeric", "distinct": "240", "missing": "0", "min": "0", "max": "255", "mean": "86", "stdev": "93" }, { "name": "pixel716", "index": "93", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "92", "stdev": "94" }, { "name": "pixel718", "index": "94", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "255", "mean": "97", "stdev": "95" }, { "name": "pixel722", "index": "95", "type": "numeric", "distinct": "243", "missing": "0", "min": "0", "max": "255", "mean": "49", "stdev": "78" }, { "name": "pixel729", "index": "96", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "173", "mean": "0", "stdev": "5" }, { "name": "pixel737", "index": "97", "type": "numeric", "distinct": "242", "missing": "0", "min": "0", "max": "255", "mean": "59", "stdev": "87" }, { "name": "pixel740", "index": "98", "type": "numeric", "distinct": "235", "missing": "0", "min": "0", "max": "255", "mean": "98", "stdev": "101" }, { "name": "pixel765", "index": "99", "type": "numeric", "distinct": "201", "missing": "0", "min": "0", "max": "246", "mean": "23", "stdev": "50" } ], "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 }