DEVELOPMENT... { "data_id": "44515", "name": "dilbert_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "dilbert_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "731555c4-3dd5-4889-b8d1-cf9eb885c748", "description": "Subsampling of the dataset dilbert (41163) 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": "David Wilson", "uploader_id": 32840, "visibility": "public", "creator": "\"Eddie Bergman\"", "contributor": null, "date": "2022-11-17 18:24:35", "update_comment": null, "last_update": "2022-11-17 18:24:35", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111277\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "dilbert_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset dilbert (41163) 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( " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 101, "NumberOfClasses": 5, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "PercentageOfSymbolicFeatures": 0.9900990099009901, "AutoCorrelation": 0.19559779889944973, "PercentageOfNumericFeatures": 99.00990099009901, "PercentageOfMissingValues": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfBinaryFeatures": 0, "NumberOfBinaryFeatures": 0, "MinorityClassSize": 382, "MinorityClassPercentage": 19.1, "MajorityClassSize": 410, "MajorityClassPercentage": 20.5, "Dimensionality": 0.0505 }, "tags": [], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "5", "missing": "0", "target": "1", "distr": [ [ "0", "1", "2", "3", "4" ], [ [ "398", "0", "0", "0", "0" ], [ "0", "410", "0", "0", "0" ], [ "0", "0", "382", "0", "0" ], [ "0", "0", "0", "409", "0" ], [ "0", "0", "0", "0", "401" ] ] ] }, { "name": "V78", "index": "0", "type": "numeric", "distinct": "1999", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V106", "index": "1", "type": "numeric", "distinct": "2000", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V114", "index": "2", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V152", "index": "3", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V176", "index": "4", "type": "numeric", "distinct": "1994", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V193", "index": "5", "type": "numeric", "distinct": "1999", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V202", "index": "6", "type": "numeric", "distinct": "1999", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V205", "index": "7", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V209", "index": "8", "type": "numeric", "distinct": "1998", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V210", "index": "9", "type": "numeric", "distinct": "1995", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V289", "index": "10", "type": "numeric", "distinct": "1999", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V360", "index": "11", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V364", "index": "12", "type": "numeric", "distinct": "1998", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V387", "index": "13", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V397", "index": "14", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V422", "index": "15", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V425", "index": "16", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V432", "index": "17", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V438", "index": "18", "type": "numeric", "distinct": "1999", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V498", "index": "19", "type": "numeric", "distinct": "1999", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V501", "index": "20", "type": "numeric", "distinct": "1999", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V517", "index": "21", "type": "numeric", "distinct": "2000", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V528", "index": "22", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "V569", "index": "23", "type": "numeric", "distinct": "2000", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "V588", "index": "24", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V621", "index": "25", "type": "numeric", "distinct": "1998", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V640", "index": "26", "type": "numeric", "distinct": "1998", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V647", "index": "27", "type": "numeric", "distinct": "2000", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V672", "index": "28", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V676", "index": "29", "type": "numeric", "distinct": "1999", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "V737", "index": "30", "type": "numeric", "distinct": "2000", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V759", "index": "31", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V789", "index": "32", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V802", "index": "33", "type": "numeric", "distinct": "1998", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V816", "index": "34", "type": "numeric", "distinct": "1995", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V834", "index": "35", "type": "numeric", "distinct": "1999", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V861", "index": "36", "type": "numeric", "distinct": "1995", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V868", "index": "37", "type": "numeric", "distinct": "1994", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V874", "index": "38", "type": "numeric", "distinct": "1991", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V882", "index": "39", "type": "numeric", "distinct": "1993", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V883", "index": "40", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V895", "index": "41", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V921", "index": "42", "type": "numeric", "distinct": "1995", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V933", "index": "43", "type": "numeric", "distinct": "1994", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V935", "index": "44", "type": "numeric", "distinct": "1992", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V964", "index": "45", "type": "numeric", "distinct": "1992", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V983", "index": "46", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V991", "index": "47", "type": "numeric", "distinct": "1989", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V994", "index": "48", "type": "numeric", "distinct": "1990", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1002", "index": "49", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1020", "index": "50", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1027", "index": "51", "type": "numeric", "distinct": "1992", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1043", "index": "52", "type": "numeric", "distinct": "1992", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1071", "index": "53", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1081", "index": "54", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1114", "index": "55", "type": "numeric", "distinct": "1995", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "V1127", "index": "56", "type": "numeric", "distinct": "1994", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1147", "index": "57", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "V1170", "index": "58", "type": "numeric", "distinct": "1994", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "V1172", "index": "59", "type": "numeric", "distinct": "1998", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "V1173", "index": "60", "type": "numeric", "distinct": "1995", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "V1218", "index": "61", "type": "numeric", "distinct": "1995", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1224", "index": "62", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1261", "index": "63", "type": "numeric", "distinct": "2000", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "V1263", "index": "64", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "V1270", "index": "65", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "V1291", "index": "66", "type": "numeric", "distinct": "1998", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "V1308", "index": "67", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1323", "index": "68", "type": "numeric", "distinct": "1994", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "V1337", "index": "69", "type": "numeric", "distinct": "1994", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1347", "index": "70", "type": "numeric", "distinct": "1994", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "V1357", "index": "71", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "V1371", "index": "72", "type": "numeric", "distinct": "1994", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "V1379", "index": "73", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "V1394", "index": "74", "type": "numeric", "distinct": "1992", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1443", "index": "75", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "V1511", "index": "76", "type": "numeric", "distinct": "1992", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1533", "index": "77", "type": "numeric", "distinct": "1994", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1551", "index": "78", "type": "numeric", "distinct": "1998", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "V1552", "index": "79", "type": "numeric", "distinct": "1992", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "V1555", "index": "80", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "V1593", "index": "81", "type": "numeric", "distinct": "1995", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V1648", "index": "82", "type": "numeric", "distinct": "1991", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V1672", "index": "83", "type": "numeric", "distinct": "1989", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V1680", "index": "84", "type": "numeric", "distinct": "1992", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V1686", "index": "85", "type": "numeric", "distinct": "1995", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "V1706", "index": "86", "type": "numeric", "distinct": "1993", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V1708", "index": "87", "type": "numeric", "distinct": "1992", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1735", "index": "88", "type": "numeric", "distinct": "1995", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1738", "index": "89", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "V1769", "index": "90", "type": "numeric", "distinct": "1998", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V1771", "index": "91", "type": "numeric", "distinct": "1998", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "V1805", "index": "92", "type": "numeric", "distinct": "1999", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1808", "index": "93", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V1824", "index": "94", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V1872", "index": "95", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V1879", "index": "96", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V1900", "index": "97", "type": "numeric", "distinct": "1999", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V1904", "index": "98", "type": "numeric", "distinct": "1999", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V2000", "index": "99", "type": "numeric", "distinct": "1998", "missing": "0", "min": "0", "max": "2", "mean": "0", "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 }

A PHP Error was encountered

Severity: Core Warning

Message: Module 'mysqli' already loaded

Filename: Unknown

Line Number: 0

Backtrace: