{ "data_id": "44702", "name": "Fashion-MNIST_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "Fashion-MNIST_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "189c610c-a34f-4041-bf46-7703b1693885", "description": "Subsampling of the dataset Fashion-MNIST (40996) 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 18:44:12", "update_comment": null, "last_update": "2022-11-17 18:44:12", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111464\/dataset", "kaggle_url": null, "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "Fashion-MNIST_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset Fashion-MNIST (40996) 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.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": 0.10905452726363181, "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": "pixel21", "index": "0", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "226", "mean": "4", "stdev": "20" }, { "name": "pixel28", "index": "1", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "pixel43", "index": "2", "type": "numeric", "distinct": "238", "missing": "0", "min": "0", "max": "255", "mean": "109", "stdev": "103" }, { "name": "pixel56", "index": "3", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "0" }, { "name": "pixel60", "index": "4", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "215", "mean": "1", "stdev": "10" }, { "name": "pixel66", "index": "5", "type": "numeric", "distinct": "246", "missing": "0", "min": "0", "max": "255", "mean": "73", "stdev": "88" }, { "name": "pixel88", "index": "6", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "247", "mean": "1", "stdev": "14" }, { "name": "pixel98", "index": "7", "type": "numeric", "distinct": "243", "missing": "0", "min": "0", "max": "255", "mean": "106", "stdev": "96" }, { "name": "pixel100", "index": "8", "type": "numeric", "distinct": "245", "missing": "0", "min": "0", "max": "255", "mean": "107", "stdev": "94" }, { "name": "pixel123", "index": "9", "type": "numeric", "distinct": "246", "missing": "0", "min": "0", "max": "255", "mean": "102", "stdev": "94" }, { "name": "pixel129", "index": "10", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "112", "stdev": "91" }, { "name": "pixel133", "index": "11", "type": "numeric", "distinct": "245", "missing": "0", "min": "0", "max": "255", "mean": "76", "stdev": "89" }, { "name": "pixel138", "index": "12", "type": "numeric", "distinct": "114", "missing": "0", "min": "0", "max": "255", "mean": "8", "stdev": "35" }, { "name": "pixel147", "index": "13", "type": "numeric", "distinct": "237", "missing": "0", "min": "0", "max": "255", "mean": "57", "stdev": "84" }, { "name": "pixel150", "index": "14", "type": "numeric", "distinct": "246", "missing": "0", "min": "0", "max": "255", "mean": "94", "stdev": "92" }, { "name": "pixel152", "index": "15", "type": "numeric", "distinct": "242", "missing": "0", "min": "0", "max": "255", "mean": "104", "stdev": "91" }, { "name": "pixel155", "index": "16", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "111", "stdev": "92" }, { "name": "pixel166", "index": "17", "type": "numeric", "distinct": "150", "missing": "0", "min": "0", "max": "255", "mean": "14", "stdev": "46" }, { "name": "pixel167", "index": "18", "type": "numeric", "distinct": "115", "missing": "0", "min": "0", "max": "255", "mean": "7", "stdev": "33" }, { "name": "pixel173", "index": "19", "type": "numeric", "distinct": "197", "missing": "0", "min": "0", "max": "255", "mean": "24", "stdev": "58" }, { "name": "pixel197", "index": "20", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "210", "mean": "1", "stdev": "9" }, { "name": "pixel202", "index": "21", "type": "numeric", "distinct": "238", "missing": "0", "min": "0", "max": "255", "mean": "52", "stdev": "80" }, { "name": "pixel221", "index": "22", "type": "numeric", "distinct": "223", "missing": "0", "min": "0", "max": "255", "mean": "40", "stdev": "74" }, { "name": "pixel239", "index": "23", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "118", "stdev": "86" }, { "name": "pixel260", "index": "24", "type": "numeric", "distinct": "233", "missing": "0", "min": "0", "max": "255", "mean": "85", "stdev": "97" }, { "name": "pixel263", "index": "25", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "255", "mean": "107", "stdev": "90" }, { "name": "pixel265", "index": "26", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "255", "mean": "116", "stdev": "90" }, { "name": "pixel270", "index": "27", "type": "numeric", "distinct": "255", "missing": "0", "min": "0", "max": "255", "mean": "144", "stdev": "76" }, { "name": "pixel281", "index": "28", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "202", "mean": "2", "stdev": "14" }, { "name": "pixel297", "index": "29", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "152", "stdev": "72" }, { "name": "pixel300", "index": "30", "type": "numeric", "distinct": "254", "missing": "0", "min": "0", "max": "255", "mean": "126", "stdev": "86" }, { "name": "pixel306", "index": "31", "type": "numeric", "distinct": "234", "missing": "0", "min": "0", "max": "255", "mean": "52", "stdev": "82" }, { "name": "pixel315", "index": "32", "type": "numeric", "distinct": "227", "missing": "0", "min": "0", "max": "255", "mean": "72", "stdev": "91" }, { "name": "pixel336", "index": "33", "type": "numeric", "distinct": "118", "missing": "0", "min": "0", "max": "255", "mean": "7", "stdev": "28" }, { "name": "pixel338", "index": "34", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "255", "mean": "7", "stdev": "35" }, { "name": "pixel352", "index": "35", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "255", "mean": "155", "stdev": "71" }, { "name": "pixel356", "index": "36", "type": "numeric", "distinct": "255", "missing": "0", "min": "0", "max": "255", "mean": "136", "stdev": "83" }, { "name": "pixel363", "index": "37", "type": "numeric", "distinct": "230", "missing": "0", "min": "0", "max": "255", "mean": "42", "stdev": "77" }, { "name": "pixel364", "index": "38", "type": "numeric", "distinct": "133", "missing": "0", "min": "0", "max": "234", "mean": "8", "stdev": "29" }, { "name": "pixel366", "index": "39", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "255", "mean": "8", "stdev": "38" }, { "name": "pixel367", "index": "40", "type": "numeric", "distinct": "125", "missing": "0", "min": "0", "max": "253", "mean": "10", "stdev": "39" }, { "name": "pixel370", "index": "41", "type": "numeric", "distinct": "242", "missing": "0", "min": "0", "max": "255", "mean": "62", "stdev": "87" }, { "name": "pixel371", "index": "42", "type": "numeric", "distinct": "245", "missing": "0", "min": "0", "max": "255", "mean": "77", "stdev": "93" }, { "name": "pixel373", "index": "43", "type": "numeric", "distinct": "254", "missing": "0", "min": "0", "max": "255", "mean": "103", "stdev": "91" }, { "name": "pixel378", "index": "44", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "255", "mean": "145", "stdev": "76" }, { "name": "pixel383", "index": "45", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "255", "mean": "153", "stdev": "73" }, { "name": "pixel390", "index": "46", "type": "numeric", "distinct": "220", "missing": "0", "min": "0", "max": "255", "mean": "59", "stdev": "87" }, { "name": "pixel402", "index": "47", "type": "numeric", "distinct": "255", "missing": "0", "min": "0", "max": "255", "mean": "125", "stdev": "86" }, { "name": "pixel407", "index": "48", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "255", "mean": "142", "stdev": "79" }, { "name": "pixel413", "index": "49", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "255", "mean": "125", "stdev": "90" }, { "name": "pixel414", "index": "50", "type": "numeric", "distinct": "242", "missing": "0", "min": "0", "max": "255", "mean": "118", "stdev": "94" }, { "name": "pixel422", "index": "51", "type": "numeric", "distinct": "158", "missing": "0", "min": "0", "max": "255", "mean": "18", "stdev": "52" }, { "name": "pixel425", "index": "52", "type": "numeric", "distinct": "241", "missing": "0", "min": "0", "max": "255", "mean": "54", "stdev": "78" }, { "name": "pixel431", "index": "53", "type": "numeric", "distinct": "254", "missing": "0", "min": "0", "max": "255", "mean": "147", "stdev": "76" }, { "name": "pixel437", "index": "54", "type": "numeric", "distinct": "245", "missing": "0", "min": "0", "max": "255", "mean": "162", "stdev": "67" }, { "name": "pixel438", "index": "55", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "161", "stdev": "67" }, { "name": "pixel441", "index": "56", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "255", "mean": "126", "stdev": "89" }, { "name": "pixel474", "index": "57", "type": "numeric", "distinct": "233", "missing": "0", "min": "0", "max": "255", "mean": "63", "stdev": "87" }, { "name": "pixel480", "index": "58", "type": "numeric", "distinct": "232", "missing": "0", "min": "0", "max": "255", "mean": "43", "stdev": "72" }, { "name": "pixel486", "index": "59", "type": "numeric", "distinct": "253", "missing": "0", "min": "0", "max": "255", "mean": "142", "stdev": "80" }, { "name": "pixel498", "index": "60", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "255", "mean": "111", "stdev": "95" }, { "name": "pixel510", "index": "61", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "255", "mean": "85", "stdev": "91" }, { "name": "pixel512", "index": "62", "type": "numeric", "distinct": "254", "missing": "0", "min": "0", "max": "255", "mean": "100", "stdev": "90" }, { "name": "pixel514", "index": "63", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "255", "mean": "143", "stdev": "80" }, { "name": "pixel526", "index": "64", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "255", "mean": "107", "stdev": "95" }, { "name": "pixel531", "index": "65", "type": "numeric", "distinct": "236", "missing": "0", "min": "0", "max": "255", "mean": "49", "stdev": "82" }, { "name": "pixel560", "index": "66", "type": "numeric", "distinct": "132", "missing": "0", "min": "0", "max": "189", "mean": "9", "stdev": "27" }, { "name": "pixel562", "index": "67", "type": "numeric", "distinct": "185", "missing": "0", "min": "0", "max": "255", "mean": "22", "stdev": "57" }, { "name": "pixel592", "index": "68", "type": "numeric", "distinct": "225", "missing": "0", "min": "0", "max": "255", "mean": "40", "stdev": "71" }, { "name": "pixel606", "index": "69", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "255", "mean": "135", "stdev": "87" }, { "name": "pixel612", "index": "70", "type": "numeric", "distinct": "242", "missing": "0", "min": "0", "max": "255", "mean": "73", "stdev": "89" }, { "name": "pixel620", "index": "71", "type": "numeric", "distinct": "221", "missing": "0", "min": "0", "max": "255", "mean": "35", "stdev": "69" }, { "name": "pixel627", "index": "72", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "255", "mean": "132", "stdev": "86" }, { "name": "pixel631", "index": "73", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "255", "mean": "118", "stdev": "91" }, { "name": "pixel637", "index": "74", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "255", "mean": "80", "stdev": "88" }, { "name": "pixel647", "index": "75", "type": "numeric", "distinct": "166", "missing": "0", "min": "0", "max": "255", "mean": "18", "stdev": "52" }, { "name": "pixel648", "index": "76", "type": "numeric", "distinct": "212", "missing": "0", "min": "0", "max": "255", "mean": "30", "stdev": "65" }, { "name": "pixel655", "index": "77", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "124", "stdev": "90" }, { "name": "pixel665", "index": "78", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "255", "mean": "72", "stdev": "88" }, { "name": "pixel669", "index": "79", "type": "numeric", "distinct": "236", "missing": "0", "min": "0", "max": "255", "mean": "41", "stdev": "73" }, { "name": "pixel671", "index": "80", "type": "numeric", "distinct": "171", "missing": "0", "min": "0", "max": "255", "mean": "17", "stdev": "53" }, { "name": "pixel674", "index": "81", "type": "numeric", "distinct": "95", "missing": "0", "min": "0", "max": "255", "mean": "7", "stdev": "33" }, { "name": "pixel687", "index": "82", "type": "numeric", "distinct": "243", "missing": "0", "min": "0", "max": "255", "mean": "99", "stdev": "94" }, { "name": "pixel688", "index": "83", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "255", "mean": "104", "stdev": "94" }, { "name": "pixel692", "index": "84", "type": "numeric", "distinct": "246", "missing": "0", "min": "0", "max": "255", "mean": "83", "stdev": "93" }, { "name": "pixel696", "index": "85", "type": "numeric", "distinct": "230", "missing": "0", "min": "0", "max": "255", "mean": "53", "stdev": "82" }, { "name": "pixel703", "index": "86", "type": "numeric", "distinct": "111", "missing": "0", "min": "0", "max": "255", "mean": "9", "stdev": "36" }, { "name": "pixel705", "index": "87", "type": "numeric", "distinct": "217", "missing": "0", "min": "0", "max": "255", "mean": "38", "stdev": "71" }, { "name": "pixel709", "index": "88", "type": "numeric", "distinct": "240", "missing": "0", "min": "0", "max": "255", "mean": "72", "stdev": "91" }, { "name": "pixel710", "index": "89", "type": "numeric", "distinct": "240", "missing": "0", "min": "0", "max": "255", "mean": "87", "stdev": "94" }, { "name": "pixel733", "index": "90", "type": "numeric", "distinct": "215", "missing": "0", "min": "0", "max": "255", "mean": "33", "stdev": "68" }, { "name": "pixel745", "index": "91", "type": "numeric", "distinct": "232", "missing": "0", "min": "0", "max": "255", "mean": "92", "stdev": "101" }, { "name": "pixel749", "index": "92", "type": "numeric", "distinct": "239", "missing": "0", "min": "0", "max": "255", "mean": "45", "stdev": "78" }, { "name": "pixel751", "index": "93", "type": "numeric", "distinct": "225", "missing": "0", "min": "0", "max": "255", "mean": "47", "stdev": "83" }, { "name": "pixel753", "index": "94", "type": "numeric", "distinct": "198", "missing": "0", "min": "0", "max": "255", "mean": "22", "stdev": "55" }, { "name": "pixel755", "index": "95", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "255", "mean": "4", "stdev": "24" }, { "name": "pixel756", "index": "96", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "189", "mean": "1", "stdev": "8" }, { "name": "pixel774", "index": "97", "type": "numeric", "distinct": "222", "missing": "0", "min": "0", "max": "255", "mean": "47", "stdev": "66" }, { "name": "pixel777", "index": "98", "type": "numeric", "distinct": "171", "missing": "0", "min": "0", "max": "246", "mean": "17", "stdev": "43" }, { "name": "pixel781", "index": "99", "type": "numeric", "distinct": "127", "missing": "0", "min": "0", "max": "226", "mean": "8", "stdev": "29" } ], "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 }