{ "data_id": "44726", "name": "adult_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "adult_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "18168a6a-1a45-4cd5-8fad-c5e5cda2daf0", "description": "Subsampling of the dataset adult (1590) 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 18:46:04", "update_comment": null, "last_update": "2022-11-17 18:46:04", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111488\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "adult_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset adult (1590) 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.choice( cla " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 15, "NumberOfClasses": 2, "NumberOfMissingValues": 254, "NumberOfInstancesWithMissingValues": 144, "NumberOfNumericFeatures": 6, "NumberOfSymbolicFeatures": 9, "PercentageOfBinaryFeatures": 13.333333333333334, "PercentageOfInstancesWithMissingValues": 7.199999999999999, "PercentageOfMissingValues": 0.8466666666666668, "AutoCorrelation": 0.6488244122061031, "PercentageOfNumericFeatures": 40, "Dimensionality": 0.0075, "PercentageOfSymbolicFeatures": 60, "MajorityClassPercentage": 76.05, "MajorityClassSize": 1521, "MinorityClassPercentage": 23.95, "MinorityClassSize": 479, "NumberOfBinaryFeatures": 2 }, "tags": [ { "uploader": "38960", "tag": "Statistics" } ], "features": [ { "name": "class", "index": "14", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ ">50K", "<=50K" ], [ [ "479", "0" ], [ "0", "1521" ] ] ] }, { "name": "age", "index": "0", "type": "numeric", "distinct": "65", "missing": "0", "min": "17", "max": "90", "mean": "38", "stdev": "13" }, { "name": "workclass", "index": "1", "type": "nominal", "distinct": "8", "missing": "110", "distr": [ [ "Private", "Self-emp-not-inc", "Self-emp-inc", "Federal-gov", "Local-gov", "State-gov", "Without-pay", "Never-worked" ], [ [ "308", "1096" ], [ "41", "106" ], [ "37", "23" ], [ "25", "41" ], [ "36", "97" ], [ "18", "58" ], [ "1", "1" ], [ "0", "2" ] ] ] }, { "name": "fnlwgt", "index": "2", "type": "numeric", "distinct": "1924", "missing": "0", "min": "18827", "max": "1268339", "mean": "192503", "stdev": "108822" }, { "name": "education", "index": "3", "type": "nominal", "distinct": "16", "missing": "0", "distr": [ [ "Bachelors", "Some-college", "11th", "HS-grad", "Prof-school", "Assoc-acdm", "Assoc-voc", "9th", "7th-8th", "12th", "Masters", "1st-4th", "10th", "Doctorate", "5th-6th", "Preschool" ], [ [ "154", "179" ], [ "89", "348" ], [ "3", "61" ], [ "93", "563" ], [ "24", "10" ], [ "18", "43" ], [ "18", "66" ], [ "3", "39" ], [ "0", "39" ], [ "3", "23" ], [ "56", "66" ], [ "0", "6" ], [ "3", "48" ], [ "12", "4" ], [ "3", "25" ], [ "0", "1" ] ] ] }, { "name": "education-num", "index": "4", "type": "numeric", "distinct": "16", "missing": "0", "min": "1", "max": "16", "mean": "10", "stdev": "3" }, { "name": "marital-status", "index": "5", "type": "nominal", "distinct": "7", "missing": "0", "distr": [ [ "Married-civ-spouse", "Divorced", "Never-married", "Separated", "Widowed", "Married-spouse-absent", "Married-AF-spouse" ], [ [ "413", "503" ], [ "21", "228" ], [ "37", "646" ], [ "2", "60" ], [ "3", "59" ], [ "2", "24" ], [ "1", "1" ] ] ] }, { "name": "occupation", "index": "6", "type": "nominal", "distinct": "13", "missing": "112", "distr": [ [ "Tech-support", "Craft-repair", "Other-service", "Sales", "Exec-managerial", "Prof-specialty", "Handlers-cleaners", "Machine-op-inspct", "Adm-clerical", "Farming-fishing", "Transport-moving", "Priv-house-serv", "Protective-serv", "Armed-Forces" ], [ [ "18", "46" ], [ "77", "180" ], [ "6", "205" ], [ "65", "183" ], [ "112", "115" ], [ "105", "149" ], [ "2", "79" ], [ "17", "120" ], [ "31", "177" ], [ "6", "50" ], [ "19", "79" ], [ "0", "16" ], [ "8", "23" ], [ "0", "0" ] ] ] }, { "name": "relationship", "index": "7", "type": "nominal", "distinct": "6", "missing": "0", "distr": [ [ "Wife", "Own-child", "Husband", "Not-in-family", "Other-relative", "Unmarried" ], [ [ "51", "59" ], [ "5", "315" ], [ "360", "432" ], [ "53", "464" ], [ "1", "67" ], [ "9", "184" ] ] ] }, { "name": "race", "index": "8", "type": "nominal", "distinct": "5", "missing": "0", "distr": [ [ "White", "Asian-Pac-Islander", "Amer-Indian-Eskimo", "Other", "Black" ], [ [ "431", "1292" ], [ "18", "41" ], [ "3", "11" ], [ "1", "11" ], [ "26", "166" ] ] ] }, { "name": "sex", "index": "9", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "Female", "Male" ], [ [ "80", "608" ], [ "399", "913" ] ] ] }, { "name": "capital-gain", "index": "10", "type": "numeric", "distinct": "55", "missing": "0", "min": "0", "max": "99999", "mean": "986", "stdev": "7096" }, { "name": "capital-loss", "index": "11", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "2824", "mean": "91", "stdev": "405" }, { "name": "hours-per-week", "index": "12", "type": "numeric", "distinct": "69", "missing": "0", "min": "2", "max": "99", "mean": "41", "stdev": "13" }, { "name": "native-country", "index": "13", "type": "nominal", "distinct": "37", "missing": "32", "distr": [ [ "United-States", "Cambodia", "England", "Puerto-Rico", "Canada", "Germany", "Outlying-US(Guam-USVI-etc)", "India", "Japan", "Greece", "South", "China", "Cuba", "Iran", "Honduras", "Philippines", "Italy", "Poland", "Jamaica", "Vietnam", "Mexico", "Portugal", "Ireland", "France", "Dominican-Republic", "Laos", "Ecuador", "Taiwan", "Haiti", "Columbia", "Hungary", "Guatemala", "Nicaragua", "Scotland", "Thailand", "Yugoslavia", "El-Salvador", "Trinadad&Tobago", "Peru", "Hong", "Holand-Netherlands" ], [ [ "441", "1346" ], [ "1", "2" ], [ "2", "2" ], [ "2", "10" ], [ "2", "7" ], [ "2", "7" ], [ "0", "0" ], [ "2", "5" ], [ "0", "3" ], [ "0", "1" ], [ "2", "2" ], [ "2", "3" ], [ "2", "2" ], [ "0", "3" ], [ "0", "1" ], [ "2", "8" ], [ "1", "3" ], [ "0", "3" ], [ "0", "5" ], [ "0", "6" ], [ "2", "45" ], [ "1", "1" ], [ "0", "1" ], [ "2", "1" ], [ "1", "3" ], [ "1", "0" ], [ "1", "2" ], [ "0", "1" ], [ "0", "4" ], [ "1", "4" ], [ "0", "2" ], [ "0", "3" ], [ "0", "1" ], [ "0", "0" ], [ "0", "2" ], [ "1", "0" ], [ "1", "4" ], [ "0", "0" ], [ "0", "0" ], [ "0", "2" ], [ "0", "1" ] ] ] } ], "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 }