{ "data_id": "44630", "name": "kc1_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "kc1_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "4931f5c1-c16a-4ad6-91fe-5d73553dfc1e", "description": "Subsampling of the dataset kc1 (1067) with\n\nseed=2\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 18:38:30", "update_comment": null, "last_update": "2022-11-17 18:38:30", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111392\/dataset", "kaggle_url": null, "default_target_attribute": "defects", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "kc1_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset kc1 (1067) with seed=2 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( class " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 22, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 21, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 4.545454545454546, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "AutoCorrelation": 0.7368684342171086, "PercentageOfNumericFeatures": 95.45454545454545, "Dimensionality": 0.011, "PercentageOfSymbolicFeatures": 4.545454545454546, "MajorityClassPercentage": 84.55, "MajorityClassSize": 1691, "MinorityClassPercentage": 15.45, "MinorityClassSize": 309, "NumberOfBinaryFeatures": 1 }, "tags": [], "features": [ { "name": "defects", "index": "21", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "True", "False" ], [ [ "309", "0" ], [ "0", "1691" ] ] ] }, { "name": "loc", "index": "0", "type": "numeric", "distinct": "136", "missing": "0", "min": "1", "max": "288", "mean": "20", "stdev": "30" }, { "name": "v(g)", "index": "1", "type": "numeric", "distinct": "31", "missing": "0", "min": "1", "max": "45", "mean": "3", "stdev": "4" }, { "name": "ev(g)", "index": "2", "type": "numeric", "distinct": "21", "missing": "0", "min": "1", "max": "26", "mean": "2", "stdev": "2" }, { "name": "iv(g)", "index": "3", "type": "numeric", "distinct": "26", "missing": "0", "min": "1", "max": "45", "mean": "3", "stdev": "3" }, { "name": "n", "index": "4", "type": "numeric", "distinct": "274", "missing": "0", "min": "0", "max": "1106", "mean": "50", "stdev": "83" }, { "name": "v", "index": "5", "type": "numeric", "distinct": "704", "missing": "0", "min": "0", "max": "7919", "mean": "259", "stdev": "515" }, { "name": "l", "index": "6", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "d", "index": "7", "type": "numeric", "distinct": "529", "missing": "0", "min": "0", "max": "54", "mean": "7", "stdev": "8" }, { "name": "i", "index": "8", "type": "numeric", "distinct": "867", "missing": "0", "min": "0", "max": "193", "mean": "21", "stdev": "21" }, { "name": "e", "index": "9", "type": "numeric", "distinct": "927", "missing": "0", "min": "0", "max": "324804", "mean": "5212", "stdev": "17289" }, { "name": "b", "index": "10", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "t", "index": "11", "type": "numeric", "distinct": "913", "missing": "0", "min": "0", "max": "18045", "mean": "290", "stdev": "961" }, { "name": "lOCode", "index": "12", "type": "numeric", "distinct": "118", "missing": "0", "min": "0", "max": "262", "mean": "15", "stdev": "24" }, { "name": "lOComment", "index": "13", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "44", "mean": "1", "stdev": "3" }, { "name": "lOBlank", "index": "14", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "58", "mean": "2", "stdev": "4" }, { "name": "locCodeAndComment", "index": "15", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "12", "mean": "0", "stdev": "1" }, { "name": "uniq_Op", "index": "16", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "37", "mean": "8", "stdev": "6" }, { "name": "uniq_Opnd", "index": "17", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "120", "mean": "10", "stdev": "12" }, { "name": "total_Op", "index": "18", "type": "numeric", "distinct": "205", "missing": "0", "min": "0", "max": "678", "mean": "31", "stdev": "52" }, { "name": "total_Opnd", "index": "19", "type": "numeric", "distinct": "151", "missing": "0", "min": "0", "max": "428", "mean": "19", "stdev": "32" }, { "name": "branchCount", "index": "20", "type": "numeric", "distinct": "44", "missing": "0", "min": "1", "max": "89", "mean": "5", "stdev": "8" } ], "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 }