DEVELOPMENT... { "data_id": "44545", "name": "gina_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "gina_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "3a66bafc-8958-4e27-a45b-9a0da4fb3ba3", "description": "Subsampling of the dataset gina (41158) 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 18:32:04", "update_comment": null, "last_update": "2022-11-17 18:32:04", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111307\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "gina_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset gina (41158) 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( cla " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 101, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "PercentageOfSymbolicFeatures": 0.9900990099009901, "AutoCorrelation": 0.4832416208104052, "PercentageOfNumericFeatures": 99.00990099009901, "PercentageOfMissingValues": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfBinaryFeatures": 0.9900990099009901, "NumberOfBinaryFeatures": 1, "MinorityClassSize": 983, "MinorityClassPercentage": 49.15, "MajorityClassSize": 1017, "MajorityClassPercentage": 50.849999999999994, "Dimensionality": 0.0505 }, "tags": [], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "1017", "0" ], [ "0", "983" ] ] ] }, { "name": "V37", "index": "0", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "255", "mean": "3", "stdev": "22" }, { "name": "V38", "index": "1", "type": "numeric", "distinct": "221", "missing": "0", "min": "0", "max": "255", "mean": "88", "stdev": "109" }, { "name": "V49", "index": "2", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "255", "mean": "3", "stdev": "25" }, { "name": "V55", "index": "3", "type": "numeric", "distinct": "186", "missing": "0", "min": "0", "max": "255", "mean": "47", "stdev": "89" }, { "name": "V74", "index": "4", "type": "numeric", "distinct": "225", "missing": "0", "min": "0", "max": "255", "mean": "87", "stdev": "108" }, { "name": "V81", "index": "5", "type": "numeric", "distinct": "232", "missing": "0", "min": "0", "max": "255", "mean": "101", "stdev": "109" }, { "name": "V93", "index": "6", "type": "numeric", "distinct": "195", "missing": "0", "min": "0", "max": "255", "mean": "50", "stdev": "91" }, { "name": "V96", "index": "7", "type": "numeric", "distinct": "219", "missing": "0", "min": "0", "max": "255", "mean": "64", "stdev": "98" }, { "name": "V98", "index": "8", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "255", "mean": "2", "stdev": "21" }, { "name": "V100", "index": "9", "type": "numeric", "distinct": "189", "missing": "0", "min": "0", "max": "255", "mean": "49", "stdev": "91" }, { "name": "V135", "index": "10", "type": "numeric", "distinct": "180", "missing": "0", "min": "0", "max": "255", "mean": "31", "stdev": "73" }, { "name": "V167", "index": "11", "type": "numeric", "distinct": "231", "missing": "0", "min": "0", "max": "255", "mean": "96", "stdev": "109" }, { "name": "V171", "index": "12", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "255", "mean": "12", "stdev": "47" }, { "name": "V180", "index": "13", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "255", "mean": "3", "stdev": "25" }, { "name": "V189", "index": "14", "type": "numeric", "distinct": "206", "missing": "0", "min": "0", "max": "255", "mean": "56", "stdev": "93" }, { "name": "V198", "index": "15", "type": "numeric", "distinct": "233", "missing": "0", "min": "0", "max": "255", "mean": "97", "stdev": "111" }, { "name": "V203", "index": "16", "type": "numeric", "distinct": "181", "missing": "0", "min": "0", "max": "255", "mean": "40", "stdev": "82" }, { "name": "V207", "index": "17", "type": "numeric", "distinct": "138", "missing": "0", "min": "0", "max": "255", "mean": "25", "stdev": "68" }, { "name": "V209", "index": "18", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "255", "mean": "13", "stdev": "49" }, { "name": "V229", "index": "19", "type": "numeric", "distinct": "231", "missing": "0", "min": "0", "max": "255", "mean": "103", "stdev": "111" }, { "name": "V233", "index": "20", "type": "numeric", "distinct": "235", "missing": "0", "min": "0", "max": "255", "mean": "94", "stdev": "108" }, { "name": "V245", "index": "21", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "255", "mean": "4", "stdev": "28" }, { "name": "V251", "index": "22", "type": "numeric", "distinct": "223", "missing": "0", "min": "0", "max": "255", "mean": "78", "stdev": "105" }, { "name": "V261", "index": "23", "type": "numeric", "distinct": "195", "missing": "0", "min": "0", "max": "255", "mean": "51", "stdev": "91" }, { "name": "V273", "index": "24", "type": "numeric", "distinct": "100", "missing": "0", "min": "0", "max": "255", "mean": "9", "stdev": "39" }, { "name": "V293", "index": "25", "type": "numeric", "distinct": "208", "missing": "0", "min": "0", "max": "255", "mean": "68", "stdev": "102" }, { "name": "V295", "index": "26", "type": "numeric", "distinct": "207", "missing": "0", "min": "0", "max": "255", "mean": "59", "stdev": "95" }, { "name": "V304", "index": "27", "type": "numeric", "distinct": "127", "missing": "0", "min": "0", "max": "255", "mean": "19", "stdev": "60" }, { "name": "V316", "index": "28", "type": "numeric", "distinct": "240", "missing": "0", "min": "0", "max": "255", "mean": "133", "stdev": "110" }, { "name": "V327", "index": "29", "type": "numeric", "distinct": "235", "missing": "0", "min": "0", "max": "255", "mean": "133", "stdev": "110" }, { "name": "V345", "index": "30", "type": "numeric", "distinct": "237", "missing": "0", "min": "0", "max": "255", "mean": "106", "stdev": "111" }, { "name": "V356", "index": "31", "type": "numeric", "distinct": "238", "missing": "0", "min": "0", "max": "255", "mean": "101", "stdev": "109" }, { "name": "V363", "index": "32", "type": "numeric", "distinct": "240", "missing": "0", "min": "0", "max": "255", "mean": "113", "stdev": "110" }, { "name": "V381", "index": "33", "type": "numeric", "distinct": "238", "missing": "0", "min": "0", "max": "255", "mean": "135", "stdev": "110" }, { "name": "V383", "index": "34", "type": "numeric", "distinct": "234", "missing": "0", "min": "0", "max": "255", "mean": "125", "stdev": "111" }, { "name": "V388", "index": "35", "type": "numeric", "distinct": "106", "missing": "0", "min": "0", "max": "255", "mean": "13", "stdev": "48" }, { "name": "V396", "index": "36", "type": "numeric", "distinct": "225", "missing": "0", "min": "0", "max": "255", "mean": "81", "stdev": "106" }, { "name": "V417", "index": "37", "type": "numeric", "distinct": "197", "missing": "0", "min": "0", "max": "255", "mean": "52", "stdev": "91" }, { "name": "V420", "index": "38", "type": "numeric", "distinct": "167", "missing": "0", "min": "0", "max": "255", "mean": "32", "stdev": "77" }, { "name": "V426", "index": "39", "type": "numeric", "distinct": "215", "missing": "0", "min": "0", "max": "255", "mean": "92", "stdev": "109" }, { "name": "V428", "index": "40", "type": "numeric", "distinct": "175", "missing": "0", "min": "0", "max": "255", "mean": "26", "stdev": "68" }, { "name": "V436", "index": "41", "type": "numeric", "distinct": "222", "missing": "0", "min": "0", "max": "255", "mean": "92", "stdev": "109" }, { "name": "V444", "index": "42", "type": "numeric", "distinct": "195", "missing": "0", "min": "0", "max": "255", "mean": "49", "stdev": "90" }, { "name": "V447", "index": "43", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "255", "mean": "2", "stdev": "19" }, { "name": "V463", "index": "44", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "255", "mean": "1", "stdev": "16" }, { "name": "V468", "index": "45", "type": "numeric", "distinct": "208", "missing": "0", "min": "0", "max": "255", "mean": "50", "stdev": "90" }, { "name": "V478", "index": "46", "type": "numeric", "distinct": "232", "missing": "0", "min": "0", "max": "255", "mean": "106", "stdev": "112" }, { "name": "V486", "index": "47", "type": "numeric", "distinct": "104", "missing": "0", "min": "0", "max": "255", "mean": "14", "stdev": "52" }, { "name": "V488", "index": "48", "type": "numeric", "distinct": "161", "missing": "0", "min": "0", "max": "255", "mean": "31", "stdev": "75" }, { "name": "V489", "index": "49", "type": "numeric", "distinct": "226", "missing": "0", "min": "0", "max": "255", "mean": "72", "stdev": "100" }, { "name": "V496", "index": "50", "type": "numeric", "distinct": "215", "missing": "0", "min": "0", "max": "255", "mean": "53", "stdev": "92" }, { "name": "V502", "index": "51", "type": "numeric", "distinct": "160", "missing": "0", "min": "0", "max": "255", "mean": "36", "stdev": "81" }, { "name": "V505", "index": "52", "type": "numeric", "distinct": "94", "missing": "0", "min": "0", "max": "255", "mean": "12", "stdev": "48" }, { "name": "V527", "index": "53", "type": "numeric", "distinct": "236", "missing": "0", "min": "0", "max": "255", "mean": "99", "stdev": "109" }, { "name": "V529", "index": "54", "type": "numeric", "distinct": "155", "missing": "0", "min": "0", "max": "255", "mean": "34", "stdev": "80" }, { "name": "V530", "index": "55", "type": "numeric", "distinct": "199", "missing": "0", "min": "0", "max": "255", "mean": "41", "stdev": "84" }, { "name": "V558", "index": "56", "type": "numeric", "distinct": "190", "missing": "0", "min": "0", "max": "255", "mean": "42", "stdev": "84" }, { "name": "V560", "index": "57", "type": "numeric", "distinct": "228", "missing": "0", "min": "0", "max": "255", "mean": "131", "stdev": "114" }, { "name": "V562", "index": "58", "type": "numeric", "distinct": "238", "missing": "0", "min": "0", "max": "255", "mean": "131", "stdev": "110" }, { "name": "V572", "index": "59", "type": "numeric", "distinct": "216", "missing": "0", "min": "0", "max": "255", "mean": "80", "stdev": "107" }, { "name": "V586", "index": "60", "type": "numeric", "distinct": "227", "missing": "0", "min": "0", "max": "255", "mean": "89", "stdev": "109" }, { "name": "V602", "index": "61", "type": "numeric", "distinct": "124", "missing": "0", "min": "0", "max": "255", "mean": "16", "stdev": "54" }, { "name": "V606", "index": "62", "type": "numeric", "distinct": "227", "missing": "0", "min": "0", "max": "255", "mean": "94", "stdev": "109" }, { "name": "V609", "index": "63", "type": "numeric", "distinct": "89", "missing": "0", "min": "0", "max": "255", "mean": "8", "stdev": "37" }, { "name": "V619", "index": "64", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "254", "mean": "4", "stdev": "28" }, { "name": "V634", "index": "65", "type": "numeric", "distinct": "236", "missing": "0", "min": "0", "max": "255", "mean": "123", "stdev": "112" }, { "name": "V637", "index": "66", "type": "numeric", "distinct": "228", "missing": "0", "min": "0", "max": "255", "mean": "101", "stdev": "111" }, { "name": "V643", "index": "67", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "255", "mean": "12", "stdev": "48" }, { "name": "V650", "index": "68", "type": "numeric", "distinct": "205", "missing": "0", "min": "0", "max": "255", "mean": "76", "stdev": "106" }, { "name": "V665", "index": "69", "type": "numeric", "distinct": "59", "missing": "0", "min": "0", "max": "254", "mean": "4", "stdev": "28" }, { "name": "V671", "index": "70", "type": "numeric", "distinct": "239", "missing": "0", "min": "0", "max": "255", "mean": "94", "stdev": "108" }, { "name": "V712", "index": "71", "type": "numeric", "distinct": "228", "missing": "0", "min": "0", "max": "255", "mean": "91", "stdev": "108" }, { "name": "V714", "index": "72", "type": "numeric", "distinct": "209", "missing": "0", "min": "0", "max": "255", "mean": "68", "stdev": "102" }, { "name": "V717", "index": "73", "type": "numeric", "distinct": "194", "missing": "0", "min": "0", "max": "255", "mean": "48", "stdev": "88" }, { "name": "V730", "index": "74", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "255", "mean": "5", "stdev": "31" }, { "name": "V741", "index": "75", "type": "numeric", "distinct": "106", "missing": "0", "min": "0", "max": "255", "mean": "10", "stdev": "42" }, { "name": "V742", "index": "76", "type": "numeric", "distinct": "209", "missing": "0", "min": "0", "max": "255", "mean": "70", "stdev": "102" }, { "name": "V780", "index": "77", "type": "numeric", "distinct": "204", "missing": "0", "min": "0", "max": "255", "mean": "50", "stdev": "89" }, { "name": "V786", "index": "78", "type": "numeric", "distinct": "221", "missing": "0", "min": "0", "max": "255", "mean": "87", "stdev": "108" }, { "name": "V793", "index": "79", "type": "numeric", "distinct": "209", "missing": "0", "min": "0", "max": "255", "mean": "49", "stdev": "89" }, { "name": "V797", "index": "80", "type": "numeric", "distinct": "184", "missing": "0", "min": "0", "max": "255", "mean": "43", "stdev": "87" }, { "name": "V805", "index": "81", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "255", "mean": "9", "stdev": "42" }, { "name": "V817", "index": "82", "type": "numeric", "distinct": "225", "missing": "0", "min": "0", "max": "255", "mean": "84", "stdev": "107" }, { "name": "V818", "index": "83", "type": "numeric", "distinct": "188", "missing": "0", "min": "0", "max": "255", "mean": "35", "stdev": "77" }, { "name": "V827", "index": "84", "type": "numeric", "distinct": "160", "missing": "0", "min": "0", "max": "255", "mean": "22", "stdev": "63" }, { "name": "V836", "index": "85", "type": "numeric", "distinct": "117", "missing": "0", "min": "0", "max": "255", "mean": "13", "stdev": "49" }, { "name": "V845", "index": "86", "type": "numeric", "distinct": "86", "missing": "0", "min": "0", "max": "255", "mean": "7", "stdev": "36" }, { "name": "V850", "index": "87", "type": "numeric", "distinct": "155", "missing": "0", "min": "0", "max": "255", "mean": "23", "stdev": "65" }, { "name": "V853", "index": "88", "type": "numeric", "distinct": "231", "missing": "0", "min": "0", "max": "255", "mean": "123", "stdev": "112" }, { "name": "V875", "index": "89", "type": "numeric", "distinct": "126", "missing": "0", "min": "0", "max": "255", "mean": "17", "stdev": "57" }, { "name": "V877", "index": "90", "type": "numeric", "distinct": "239", "missing": "0", "min": "0", "max": "255", "mean": "133", "stdev": "111" }, { "name": "V892", "index": "91", "type": "numeric", "distinct": "128", "missing": "0", "min": "0", "max": "255", "mean": "12", "stdev": "45" }, { "name": "V898", "index": "92", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "255", "mean": "2", "stdev": "20" }, { "name": "V926", "index": "93", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "254", "mean": "2", "stdev": "16" }, { "name": "V937", "index": "94", "type": "numeric", "distinct": "187", "missing": "0", "min": "0", "max": "255", "mean": "45", "stdev": "86" }, { "name": "V952", "index": "95", "type": "numeric", "distinct": "112", "missing": "0", "min": "0", "max": "255", "mean": "14", "stdev": "51" }, { "name": "V953", "index": "96", "type": "numeric", "distinct": "81", "missing": "0", "min": "0", "max": "255", "mean": "6", "stdev": "31" }, { "name": "V954", "index": "97", "type": "numeric", "distinct": "227", "missing": "0", "min": "0", "max": "255", "mean": "82", "stdev": "106" }, { "name": "V961", "index": "98", "type": "numeric", "distinct": "231", "missing": "0", "min": "0", "max": "255", "mean": "104", "stdev": "111" }, { "name": "V968", "index": "99", "type": "numeric", "distinct": "65", "missing": "0", "min": "0", "max": "255", "mean": "7", "stdev": "36" } ], "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 }