{ "data_id": "44461", "name": "compass_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "compass_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "c3a1a7a4-65d5-4de1-b8ed-f4ba03cf525f", "description": "Subsampling of the dataset compass (44162) 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 18:03:27", "update_comment": null, "last_update": "2022-11-17 18:03:27", "licence": "See source", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111223\/dataset", "default_target_attribute": "is_recid", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "compass_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset compass (44162) 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( " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 18, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 8, "NumberOfSymbolicFeatures": 10, "MinorityClassPercentage": 50, "MinorityClassSize": 1000, "NumberOfBinaryFeatures": 2, "PercentageOfBinaryFeatures": 11.11111111111111, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.5102551275637819, "PercentageOfMissingValues": 0, "Dimensionality": 0.009, "PercentageOfNumericFeatures": 44.44444444444444, "MajorityClassPercentage": 50, "PercentageOfSymbolicFeatures": 55.55555555555556, "MajorityClassSize": 1000 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Statistics" } ], "features": [ { "name": "is_recid", "index": "17", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "-1", "0" ], [ [ "1000", "0" ], [ "0", "1000" ] ] ] }, { "name": "sex", "index": "0", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "214", "158" ], [ "786", "842" ] ] ] }, { "name": "age", "index": "1", "type": "numeric", "distinct": "56", "missing": "0", "min": "18", "max": "77", "mean": "33", "stdev": "11" }, { "name": "age_cat", "index": "2", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "584", "546" ], [ "220", "130" ], [ "196", "324" ] ] ] }, { "name": "race", "index": "3", "type": "nominal", "distinct": "6", "missing": "0", "distr": [ [ "0", "1", "2", "3", "4", "5" ], [ [ "456", "602" ], [ "6", "1" ], [ "384", "314" ], [ "86", "45" ], [ "7", "4" ], [ "61", "34" ] ] ] }, { "name": "juv_fel_count", "index": "4", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "0" }, { "name": "juv_misd_count", "index": "5", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "0" }, { "name": "juv_other_count", "index": "6", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "11", "mean": "0", "stdev": "1" }, { "name": "priors_count", "index": "7", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "31", "mean": "4", "stdev": "5" }, { "name": "days_b_screening_arrest", "index": "8", "type": "numeric", "distinct": "220", "missing": "0", "min": "-499", "max": "805", "mean": "3", "stdev": "74" }, { "name": "c_days_from_compas", "index": "9", "type": "numeric", "distinct": "196", "missing": "0", "min": "0", "max": "6323", "mean": "46", "stdev": "298" }, { "name": "c_charge_degree", "index": "10", "type": "nominal", "distinct": "10", "missing": "0", "distr": [ [ "0", "1", "10", "11", "12", "2", "3", "4", "5", "6", "7", "8", "9" ], [ [ "0", "1" ], [ "27", "12" ], [ "1", "2" ], [ "0", "0" ], [ "0", "0" ], [ "95", "88" ], [ "554", "609" ], [ "0", "0" ], [ "1", "0" ], [ "12", "10" ], [ "222", "186" ], [ "81", "83" ], [ "7", "9" ] ] ] }, { "name": "decile_score.1", "index": "11", "type": "nominal", "distinct": "10", "missing": "0", "distr": [ [ "0", "1", "2", "3", "4", "5", "6", "7", "8", "9" ], [ [ "243", "66" ], [ "149", "82" ], [ "105", "83" ], [ "80", "105" ], [ "91", "90" ], [ "74", "95" ], [ "85", "119" ], [ "60", "119" ], [ "66", "133" ], [ "47", "108" ] ] ] }, { "name": "score_text", "index": "12", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "173", "360" ], [ "577", "336" ], [ "250", "304" ] ] ] }, { "name": "v_type_of_assessment", "index": "13", "type": "nominal", "distinct": "1", "missing": "0", "distr": [ [ "0" ], [ [ "1000", "1000" ] ] ] }, { "name": "v_decile_score", "index": "14", "type": "nominal", "distinct": "10", "missing": "0", "distr": [ [ "0", "1", "2", "3", "4", "5", "6", "7", "8", "9" ], [ [ "303", "123" ], [ "160", "111" ], [ "157", "131" ], [ "100", "111" ], [ "62", "130" ], [ "75", "101" ], [ "53", "102" ], [ "37", "82" ], [ "37", "71" ], [ "16", "38" ] ] ] }, { "name": "v_score_text", "index": "15", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "90", "191" ], [ "720", "476" ], [ "190", "333" ] ] ] }, { "name": "end", "index": "16", "type": "numeric", "distinct": "929", "missing": "0", "min": "4", "max": "1186", "mean": "610", "stdev": "334" } ], "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 }