{ "data_id": "44728", "name": "helena_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "helena_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "47f3cdba-7b6b-4178-bfe9-9bc93b0f8bf8", "description": "Subsampling of the dataset helena (41169) 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": "Eddie Bergman", "uploader_id": 32840, "visibility": "public", "creator": "\"Eddie Bergman\"", "contributor": null, "date": "2022-11-17 18:46:13", "update_comment": null, "last_update": "2022-11-17 18:46:13", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111490\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "helena_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset helena (41169) 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( c " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 28, "NumberOfClasses": 100, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 27, "NumberOfSymbolicFeatures": 1, "PercentageOfNumericFeatures": 96.42857142857143, "Dimensionality": 0.014, "PercentageOfSymbolicFeatures": 3.571428571428571, "MajorityClassPercentage": 6.15, "MajorityClassSize": 123, "MinorityClassPercentage": 0.15, "MinorityClassSize": 3, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "AutoCorrelation": 0.0240120060030015 }, "tags": [ { "uploader": "38960", "tag": "Statistics" } ], "features": [ { "name": "class", "index": "27", "type": "nominal", "distinct": "100", "missing": "0", "target": "1", "distr": [] }, { "name": "V1", "index": "0", "type": "numeric", "distinct": "1959", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V2", "index": "1", "type": "numeric", "distinct": "553", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V3", "index": "2", "type": "numeric", "distinct": "606", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V4", "index": "3", "type": "numeric", "distinct": "1998", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V5", "index": "4", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V6", "index": "5", "type": "numeric", "distinct": "1993", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V7", "index": "6", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V8", "index": "7", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V9", "index": "8", "type": "numeric", "distinct": "1993", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V10", "index": "9", "type": "numeric", "distinct": "1987", "missing": "0", "min": "1", "max": "255", "mean": "126", "stdev": "53" }, { "name": "V11", "index": "10", "type": "numeric", "distinct": "1992", "missing": "0", "min": "1", "max": "255", "mean": "119", "stdev": "54" }, { "name": "V12", "index": "11", "type": "numeric", "distinct": "1992", "missing": "0", "min": "0", "max": "255", "mean": "113", "stdev": "61" }, { "name": "V13", "index": "12", "type": "numeric", "distinct": "1998", "missing": "0", "min": "1", "max": "96", "mean": "37", "stdev": "19" }, { "name": "V14", "index": "13", "type": "numeric", "distinct": "1998", "missing": "0", "min": "0", "max": "96", "mean": "35", "stdev": "19" }, { "name": "V15", "index": "14", "type": "numeric", "distinct": "2000", "missing": "0", "min": "0", "max": "93", "mean": "34", "stdev": "19" }, { "name": "V16", "index": "15", "type": "numeric", "distinct": "1999", "missing": "0", "min": "-56", "max": "49", "mean": "0", "stdev": "3" }, { "name": "V17", "index": "16", "type": "numeric", "distinct": "1998", "missing": "0", "min": "-58", "max": "40", "mean": "0", "stdev": "3" }, { "name": "V18", "index": "17", "type": "numeric", "distinct": "1998", "missing": "0", "min": "-51", "max": "38", "mean": "0", "stdev": "3" }, { "name": "V19", "index": "18", "type": "numeric", "distinct": "1994", "missing": "0", "min": "7", "max": "100", "mean": "70", "stdev": "15" }, { "name": "V20", "index": "19", "type": "numeric", "distinct": "1999", "missing": "0", "min": "-32", "max": "52", "mean": "1", "stdev": "6" }, { "name": "V21", "index": "20", "type": "numeric", "distinct": "1998", "missing": "0", "min": "-40", "max": "58", "mean": "5", "stdev": "11" }, { "name": "V22", "index": "21", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "33", "mean": "10", "stdev": "6" }, { "name": "V23", "index": "22", "type": "numeric", "distinct": "1998", "missing": "0", "min": "0", "max": "33", "mean": "4", "stdev": "4" }, { "name": "V24", "index": "23", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "28", "mean": "6", "stdev": "4" }, { "name": "V25", "index": "24", "type": "numeric", "distinct": "1999", "missing": "0", "min": "-65", "max": "5", "mean": "-1", "stdev": "3" }, { "name": "V26", "index": "25", "type": "numeric", "distinct": "2000", "missing": "0", "min": "-16", "max": "37", "mean": "1", "stdev": "2" }, { "name": "V27", "index": "26", "type": "numeric", "distinct": "1999", "missing": "0", "min": "-11", "max": "20", "mean": "0", "stdev": "2" } ], "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 }