{ "data_id": "44714", "name": "nomao_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "nomao_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "dfb2ea65-2de9-4fae-91d0-297deb8ccd90", "description": "Subsampling of the dataset nomao (1486) 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 18:45:10", "update_comment": null, "last_update": "2022-11-17 18:45:10", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111476\/dataset", "default_target_attribute": "Class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "nomao_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset nomao (1486) 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.choice( cla " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 101, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 77, "NumberOfSymbolicFeatures": 24, "PercentageOfBinaryFeatures": 2.9702970297029703, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.5952976488244122, "PercentageOfMissingValues": 0, "Dimensionality": 0.0505, "PercentageOfNumericFeatures": 76.23762376237624, "MajorityClassPercentage": 71.45, "PercentageOfSymbolicFeatures": 23.762376237623762, "MajorityClassSize": 1429, "MinorityClassPercentage": 28.549999999999997, "MinorityClassSize": 571, "NumberOfBinaryFeatures": 3 }, "tags": [ { "uploader": "38960", "tag": "Computer Systems" }, { "uploader": "38960", "tag": "Statistics" } ], "features": [ { "name": "Class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "1", "2" ], [ [ "571", "0" ], [ "0", "1429" ] ] ] }, { "name": "V1", "index": "0", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V2", "index": "1", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V4", "index": "2", "type": "numeric", "distinct": "340", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V6", "index": "3", "type": "numeric", "distinct": "420", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V7", "index": "4", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2" ], [ [ "529", "423" ], [ "42", "1006" ] ] ] }, { "name": "V8", "index": "5", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2" ], [ [ "547", "947" ], [ "24", "482" ] ] ] }, { "name": "V9", "index": "6", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V10", "index": "7", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V11", "index": "8", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V12", "index": "9", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V13", "index": "10", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V14", "index": "11", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V15", "index": "12", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "252", "1020" ], [ "57", "65" ], [ "262", "344" ] ] ] }, { "name": "V16", "index": "13", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "252", "1020" ], [ "62", "133" ], [ "257", "276" ] ] ] }, { "name": "V18", "index": "14", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V20", "index": "15", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V21", "index": "16", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V22", "index": "17", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V23", "index": "18", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "306", "1131" ], [ "86", "46" ], [ "179", "252" ] ] ] }, { "name": "V24", "index": "19", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "306", "1131" ], [ "87", "54" ], [ "178", "244" ] ] ] }, { "name": "V25", "index": "20", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V26", "index": "21", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V27", "index": "22", "type": "numeric", "distinct": "253", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V28", "index": "23", "type": "numeric", "distinct": "169", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V29", "index": "24", "type": "numeric", "distinct": "192", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V31", "index": "25", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "318", "1084" ], [ "226", "96" ], [ "27", "249" ] ] ] }, { "name": "V32", "index": "26", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "318", "1084" ], [ "235", "156" ], [ "18", "189" ] ] ] }, { "name": "V33", "index": "27", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V34", "index": "28", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V35", "index": "29", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V36", "index": "30", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V37", "index": "31", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V39", "index": "32", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "559", "1319" ], [ "11", "34" ], [ "1", "76" ] ] ] }, { "name": "V40", "index": "33", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "559", "1319" ], [ "11", "53" ], [ "1", "57" ] ] ] }, { "name": "V42", "index": "34", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V45", "index": "35", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V46", "index": "36", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V48", "index": "37", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "434", "1247" ], [ "8", "86" ], [ "129", "96" ] ] ] }, { "name": "V49", "index": "38", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V50", "index": "39", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V51", "index": "40", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V52", "index": "41", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V53", "index": "42", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V54", "index": "43", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V55", "index": "44", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "2", "22" ], [ "59", "51" ], [ "510", "1356" ] ] ] }, { "name": "V57", "index": "45", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V58", "index": "46", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V59", "index": "47", "type": "numeric", "distinct": "876", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V60", "index": "48", "type": "numeric", "distinct": "703", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V61", "index": "49", "type": "numeric", "distinct": "630", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V62", "index": "50", "type": "numeric", "distinct": "735", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V64", "index": "51", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "0", "3" ], [ "527", "1286" ], [ "44", "140" ] ] ] }, { "name": "V65", "index": "52", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V66", "index": "53", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V67", "index": "54", "type": "numeric", "distinct": "385", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V68", "index": "55", "type": "numeric", "distinct": "295", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V69", "index": "56", "type": "numeric", "distinct": "390", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V70", "index": "57", "type": "numeric", "distinct": "441", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V71", "index": "58", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "0", "0" ], [ "330", "260" ], [ "241", "1169" ] ] ] }, { "name": "V74", "index": "59", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V75", "index": "60", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V76", "index": "61", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V77", "index": "62", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V78", "index": "63", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V79", "index": "64", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "103", "156" ], [ "95", "69" ], [ "373", "1204" ] ] ] }, { "name": "V80", "index": "65", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "103", "156" ], [ "95", "80" ], [ "373", "1193" ] ] ] }, { "name": "V83", "index": "66", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V84", "index": "67", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V85", "index": "68", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V86", "index": "69", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V87", "index": "70", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "26", "59" ], [ "1", "0" ], [ "544", "1370" ] ] ] }, { "name": "V89", "index": "71", "type": "numeric", "distinct": "107", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V90", "index": "72", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V91", "index": "73", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V92", "index": "74", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "357", "789" ], [ "195", "102" ], [ "19", "538" ] ] ] }, { "name": "V93", "index": "75", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V94", "index": "76", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V95", "index": "77", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V96", "index": "78", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "545", "1394" ], [ "25", "6" ], [ "1", "29" ] ] ] }, { "name": "V97", "index": "79", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V98", "index": "80", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V99", "index": "81", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V100", "index": "82", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "30", "23" ], [ "504", "458" ], [ "37", "948" ] ] ] }, { "name": "V101", "index": "83", "type": "numeric", "distinct": "725", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V102", "index": "84", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V103", "index": "85", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V105", "index": "86", "type": "numeric", "distinct": "701", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V106", "index": "87", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V107", "index": "88", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V108", "index": "89", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "0", "0" ], [ "396", "721" ], [ "175", "708" ] ] ] }, { "name": "V109", "index": "90", "type": "numeric", "distinct": "597", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V110", "index": "91", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V111", "index": "92", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V112", "index": "93", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "280", "822" ], [ "277", "529" ], [ "14", "78" ] ] ] }, { "name": "V113", "index": "94", "type": "numeric", "distinct": "571", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V114", "index": "95", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V115", "index": "96", "type": "numeric", "distinct": "71", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V116", "index": "97", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "280", "822" ], [ "276", "540" ], [ "15", "67" ] ] ] }, { "name": "V117", "index": "98", "type": "numeric", "distinct": "332", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V118", "index": "99", "type": "numeric", "distinct": "231", "missing": "0", "min": "0", "max": "1", "mean": "1", "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 }