DEVELOPMENT... { "data_id": "44713", "name": "nomao_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "nomao_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "7ebc6f00-d0eb-4e67-923d-f12dc8284fc6", "description": "Subsampling of the dataset nomao (1486) with\n\nseed=0\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": "David Wilson", "uploader_id": 32840, "visibility": "public", "creator": "\"Eddie Bergman\"", "contributor": null, "date": "2022-11-17 18:45:05", "update_comment": null, "last_update": "2022-11-17 18:45:05", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111475\/dataset", "default_target_attribute": "Class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "nomao_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset nomao (1486) with seed=0 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": 75, "NumberOfSymbolicFeatures": 26, "PercentageOfSymbolicFeatures": 25.742574257425744, "AutoCorrelation": 0.5847923961980991, "PercentageOfNumericFeatures": 74.25742574257426, "PercentageOfMissingValues": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfBinaryFeatures": 2.9702970297029703, "NumberOfBinaryFeatures": 3, "MinorityClassSize": 571, "MinorityClassPercentage": 28.549999999999997, "MajorityClassSize": 1429, "MajorityClassPercentage": 71.45, "Dimensionality": 0.0505 }, "tags": [], "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": "18", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V2", "index": "1", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V5", "index": "2", "type": "numeric", "distinct": "363", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V6", "index": "3", "type": "numeric", "distinct": "411", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V7", "index": "4", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2" ], [ [ "532", "449" ], [ "39", "980" ] ] ] }, { "name": "V8", "index": "5", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2" ], [ [ "553", "950" ], [ "18", "479" ] ] ] }, { "name": "V9", "index": "6", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V10", "index": "7", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V11", "index": "8", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V12", "index": "9", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V13", "index": "10", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V16", "index": "11", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "260", "1037" ], [ "68", "96" ], [ "243", "296" ] ] ] }, { "name": "V17", "index": "12", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V18", "index": "13", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V19", "index": "14", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V20", "index": "15", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V21", "index": "16", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V23", "index": "17", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "324", "1149" ], [ "102", "40" ], [ "145", "240" ] ] ] }, { "name": "V24", "index": "18", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "324", "1149" ], [ "102", "46" ], [ "145", "234" ] ] ] }, { "name": "V25", "index": "19", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V26", "index": "20", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V27", "index": "21", "type": "numeric", "distinct": "246", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V28", "index": "22", "type": "numeric", "distinct": "149", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V29", "index": "23", "type": "numeric", "distinct": "192", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V30", "index": "24", "type": "numeric", "distinct": "191", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V32", "index": "25", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "324", "1102" ], [ "224", "140" ], [ "23", "187" ] ] ] }, { "name": "V33", "index": "26", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V34", "index": "27", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V35", "index": "28", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V36", "index": "29", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V38", "index": "30", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V39", "index": "31", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "561", "1297" ], [ "10", "44" ], [ "0", "88" ] ] ] }, { "name": "V40", "index": "32", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "561", "1297" ], [ "10", "59" ], [ "0", "73" ] ] ] }, { "name": "V41", "index": "33", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V42", "index": "34", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V43", "index": "35", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V44", "index": "36", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V45", "index": "37", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V46", "index": "38", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V47", "index": "39", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "419", "1261" ], [ "13", "64" ], [ "139", "104" ] ] ] }, { "name": "V48", "index": "40", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "419", "1261" ], [ "13", "64" ], [ "139", "104" ] ] ] }, { "name": "V49", "index": "41", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V50", "index": "42", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V51", "index": "43", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V52", "index": "44", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V53", "index": "45", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V55", "index": "46", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "1", "25" ], [ "67", "37" ], [ "503", "1367" ] ] ] }, { "name": "V56", "index": "47", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "1", "25" ], [ "70", "37" ], [ "500", "1367" ] ] ] }, { "name": "V57", "index": "48", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V58", "index": "49", "type": "numeric", "distinct": "57", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V59", "index": "50", "type": "numeric", "distinct": "881", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V60", "index": "51", "type": "numeric", "distinct": "689", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V61", "index": "52", "type": "numeric", "distinct": "622", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V62", "index": "53", "type": "numeric", "distinct": "724", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V63", "index": "54", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "0", "1" ], [ "467", "919" ], [ "104", "509" ] ] ] }, { "name": "V64", "index": "55", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "0", "1" ], [ "520", "1304" ], [ "51", "124" ] ] ] }, { "name": "V65", "index": "56", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V66", "index": "57", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V67", "index": "58", "type": "numeric", "distinct": "371", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V68", "index": "59", "type": "numeric", "distinct": "273", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V69", "index": "60", "type": "numeric", "distinct": "397", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V71", "index": "61", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "0", "0" ], [ "320", "255" ], [ "251", "1174" ] ] ] }, { "name": "V72", "index": "62", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "0", "0" ], [ "396", "472" ], [ "175", "957" ] ] ] }, { "name": "V73", "index": "63", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V74", "index": "64", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V75", "index": "65", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V76", "index": "66", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V78", "index": "67", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V80", "index": "68", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "127", "155" ], [ "102", "71" ], [ "342", "1203" ] ] ] }, { "name": "V81", "index": "69", "type": "numeric", "distinct": "2", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V82", "index": "70", "type": "numeric", "distinct": "2", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V83", "index": "71", "type": "numeric", "distinct": "2", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V84", "index": "72", "type": "numeric", "distinct": "2", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V86", "index": "73", "type": "numeric", "distinct": "2", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V87", "index": "74", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "14", "65" ], [ "0", "0" ], [ "557", "1364" ] ] ] }, { "name": "V88", "index": "75", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "14", "65" ], [ "0", "0" ], [ "557", "1364" ] ] ] }, { "name": "V90", "index": "76", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V91", "index": "77", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V92", "index": "78", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "378", "776" ], [ "185", "108" ], [ "8", "545" ] ] ] }, { "name": "V93", "index": "79", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V96", "index": "80", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "549", "1410" ], [ "22", "4" ], [ "0", "15" ] ] ] }, { "name": "V97", "index": "81", "type": "numeric", "distinct": "94", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V98", "index": "82", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V99", "index": "83", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V100", "index": "84", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "25", "24" ], [ "523", "448" ], [ "23", "957" ] ] ] }, { "name": "V101", "index": "85", "type": "numeric", "distinct": "717", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V102", "index": "86", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V104", "index": "87", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "0", "0" ], [ "386", "696" ], [ "185", "733" ] ] ] }, { "name": "V105", "index": "88", "type": "numeric", "distinct": "711", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V106", "index": "89", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V108", "index": "90", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "0", "0" ], [ "385", "695" ], [ "186", "734" ] ] ] }, { "name": "V109", "index": "91", "type": "numeric", "distinct": "589", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V110", "index": "92", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V111", "index": "93", "type": "numeric", "distinct": "67", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V112", "index": "94", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "280", "801" ], [ "278", "529" ], [ "13", "99" ] ] ] }, { "name": "V113", "index": "95", "type": "numeric", "distinct": "561", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V114", "index": "96", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V115", "index": "97", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V117", "index": "98", "type": "numeric", "distinct": "331", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V118", "index": "99", "type": "numeric", "distinct": "240", "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 }