{ "data_id": "44543", "name": "gina_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "gina_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "b4b087b5-9a3f-4ca7-8824-181c66870631", "description": "Subsampling of the dataset gina (41158) 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 18:31:55", "update_comment": null, "last_update": "2022-11-17 18:31:55", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111305\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "gina_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset gina (41158) 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( cla " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 101, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 0.9900990099009901, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.5022511255627814, "PercentageOfMissingValues": 0, "Dimensionality": 0.0505, "PercentageOfNumericFeatures": 99.00990099009901, "MajorityClassPercentage": 50.849999999999994, "PercentageOfSymbolicFeatures": 0.9900990099009901, "MajorityClassSize": 1017, "MinorityClassPercentage": 49.15, "MinorityClassSize": 983, "NumberOfBinaryFeatures": 1 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Statistics" } ], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "1017", "0" ], [ "0", "983" ] ] ] }, { "name": "V3", "index": "0", "type": "numeric", "distinct": "191", "missing": "0", "min": "0", "max": "255", "mean": "58", "stdev": "96" }, { "name": "V5", "index": "1", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "255", "mean": "9", "stdev": "41" }, { "name": "V8", "index": "2", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "255", "mean": "8", "stdev": "38" }, { "name": "V15", "index": "3", "type": "numeric", "distinct": "237", "missing": "0", "min": "0", "max": "255", "mean": "114", "stdev": "111" }, { "name": "V21", "index": "4", "type": "numeric", "distinct": "189", "missing": "0", "min": "0", "max": "255", "mean": "47", "stdev": "88" }, { "name": "V26", "index": "5", "type": "numeric", "distinct": "234", "missing": "0", "min": "0", "max": "255", "mean": "80", "stdev": "103" }, { "name": "V31", "index": "6", "type": "numeric", "distinct": "217", "missing": "0", "min": "0", "max": "255", "mean": "75", "stdev": "104" }, { "name": "V36", "index": "7", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "255", "mean": "13", "stdev": "51" }, { "name": "V47", "index": "8", "type": "numeric", "distinct": "233", "missing": "0", "min": "0", "max": "255", "mean": "127", "stdev": "112" }, { "name": "V66", "index": "9", "type": "numeric", "distinct": "235", "missing": "0", "min": "0", "max": "255", "mean": "128", "stdev": "111" }, { "name": "V70", "index": "10", "type": "numeric", "distinct": "239", "missing": "0", "min": "0", "max": "255", "mean": "121", "stdev": "111" }, { "name": "V73", "index": "11", "type": "numeric", "distinct": "228", "missing": "0", "min": "0", "max": "255", "mean": "100", "stdev": "111" }, { "name": "V81", "index": "12", "type": "numeric", "distinct": "229", "missing": "0", "min": "0", "max": "255", "mean": "102", "stdev": "110" }, { "name": "V82", "index": "13", "type": "numeric", "distinct": "225", "missing": "0", "min": "0", "max": "255", "mean": "94", "stdev": "110" }, { "name": "V114", "index": "14", "type": "numeric", "distinct": "216", "missing": "0", "min": "0", "max": "255", "mean": "89", "stdev": "109" }, { "name": "V127", "index": "15", "type": "numeric", "distinct": "237", "missing": "0", "min": "0", "max": "255", "mean": "124", "stdev": "113" }, { "name": "V155", "index": "16", "type": "numeric", "distinct": "211", "missing": "0", "min": "0", "max": "255", "mean": "90", "stdev": "110" }, { "name": "V159", "index": "17", "type": "numeric", "distinct": "228", "missing": "0", "min": "0", "max": "255", "mean": "84", "stdev": "105" }, { "name": "V219", "index": "18", "type": "numeric", "distinct": "236", "missing": "0", "min": "0", "max": "255", "mean": "93", "stdev": "109" }, { "name": "V236", "index": "19", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "255", "mean": "3", "stdev": "24" }, { "name": "V237", "index": "20", "type": "numeric", "distinct": "228", "missing": "0", "min": "0", "max": "255", "mean": "89", "stdev": "107" }, { "name": "V243", "index": "21", "type": "numeric", "distinct": "217", "missing": "0", "min": "0", "max": "255", "mean": "73", "stdev": "103" }, { "name": "V248", "index": "22", "type": "numeric", "distinct": "231", "missing": "0", "min": "0", "max": "255", "mean": "119", "stdev": "112" }, { "name": "V255", "index": "23", "type": "numeric", "distinct": "219", "missing": "0", "min": "0", "max": "255", "mean": "78", "stdev": "105" }, { "name": "V270", "index": "24", "type": "numeric", "distinct": "141", "missing": "0", "min": "0", "max": "255", "mean": "22", "stdev": "63" }, { "name": "V273", "index": "25", "type": "numeric", "distinct": "102", "missing": "0", "min": "0", "max": "255", "mean": "10", "stdev": "42" }, { "name": "V293", "index": "26", "type": "numeric", "distinct": "214", "missing": "0", "min": "0", "max": "255", "mean": "68", "stdev": "101" }, { "name": "V308", "index": "27", "type": "numeric", "distinct": "230", "missing": "0", "min": "0", "max": "255", "mean": "116", "stdev": "112" }, { "name": "V316", "index": "28", "type": "numeric", "distinct": "238", "missing": "0", "min": "0", "max": "255", "mean": "134", "stdev": "110" }, { "name": "V324", "index": "29", "type": "numeric", "distinct": "98", "missing": "0", "min": "0", "max": "255", "mean": "13", "stdev": "51" }, { "name": "V340", "index": "30", "type": "numeric", "distinct": "179", "missing": "0", "min": "0", "max": "255", "mean": "41", "stdev": "84" }, { "name": "V352", "index": "31", "type": "numeric", "distinct": "65", "missing": "0", "min": "0", "max": "255", "mean": "4", "stdev": "29" }, { "name": "V353", "index": "32", "type": "numeric", "distinct": "198", "missing": "0", "min": "0", "max": "255", "mean": "45", "stdev": "87" }, { "name": "V354", "index": "33", "type": "numeric", "distinct": "183", "missing": "0", "min": "0", "max": "255", "mean": "43", "stdev": "84" }, { "name": "V364", "index": "34", "type": "numeric", "distinct": "168", "missing": "0", "min": "0", "max": "255", "mean": "31", "stdev": "74" }, { "name": "V366", "index": "35", "type": "numeric", "distinct": "216", "missing": "0", "min": "0", "max": "255", "mean": "69", "stdev": "101" }, { "name": "V368", "index": "36", "type": "numeric", "distinct": "231", "missing": "0", "min": "0", "max": "255", "mean": "110", "stdev": "112" }, { "name": "V376", "index": "37", "type": "numeric", "distinct": "150", "missing": "0", "min": "0", "max": "255", "mean": "31", "stdev": "76" }, { "name": "V385", "index": "38", "type": "numeric", "distinct": "236", "missing": "0", "min": "0", "max": "255", "mean": "113", "stdev": "111" }, { "name": "V399", "index": "39", "type": "numeric", "distinct": "239", "missing": "0", "min": "0", "max": "255", "mean": "131", "stdev": "109" }, { "name": "V426", "index": "40", "type": "numeric", "distinct": "222", "missing": "0", "min": "0", "max": "255", "mean": "93", "stdev": "110" }, { "name": "V438", "index": "41", "type": "numeric", "distinct": "218", "missing": "0", "min": "0", "max": "255", "mean": "102", "stdev": "112" }, { "name": "V445", "index": "42", "type": "numeric", "distinct": "172", "missing": "0", "min": "0", "max": "255", "mean": "36", "stdev": "79" }, { "name": "V447", "index": "43", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "255", "mean": "2", "stdev": "16" }, { "name": "V459", "index": "44", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "254", "mean": "2", "stdev": "17" }, { "name": "V482", "index": "45", "type": "numeric", "distinct": "202", "missing": "0", "min": "0", "max": "255", "mean": "58", "stdev": "95" }, { "name": "V483", "index": "46", "type": "numeric", "distinct": "230", "missing": "0", "min": "0", "max": "255", "mean": "74", "stdev": "101" }, { "name": "V491", "index": "47", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "255", "mean": "3", "stdev": "21" }, { "name": "V494", "index": "48", "type": "numeric", "distinct": "221", "missing": "0", "min": "0", "max": "255", "mean": "69", "stdev": "101" }, { "name": "V498", "index": "49", "type": "numeric", "distinct": "232", "missing": "0", "min": "0", "max": "255", "mean": "138", "stdev": "113" }, { "name": "V505", "index": "50", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "255", "mean": "12", "stdev": "48" }, { "name": "V537", "index": "51", "type": "numeric", "distinct": "163", "missing": "0", "min": "0", "max": "255", "mean": "30", "stdev": "74" }, { "name": "V543", "index": "52", "type": "numeric", "distinct": "227", "missing": "0", "min": "0", "max": "255", "mean": "97", "stdev": "109" }, { "name": "V545", "index": "53", "type": "numeric", "distinct": "171", "missing": "0", "min": "0", "max": "255", "mean": "30", "stdev": "73" }, { "name": "V556", "index": "54", "type": "numeric", "distinct": "226", "missing": "0", "min": "0", "max": "255", "mean": "118", "stdev": "114" }, { "name": "V561", "index": "55", "type": "numeric", "distinct": "241", "missing": "0", "min": "0", "max": "255", "mean": "132", "stdev": "111" }, { "name": "V567", "index": "56", "type": "numeric", "distinct": "238", "missing": "0", "min": "0", "max": "255", "mean": "130", "stdev": "111" }, { "name": "V569", "index": "57", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "255", "mean": "2", "stdev": "20" }, { "name": "V573", "index": "58", "type": "numeric", "distinct": "240", "missing": "0", "min": "0", "max": "255", "mean": "114", "stdev": "110" }, { "name": "V595", "index": "59", "type": "numeric", "distinct": "71", "missing": "0", "min": "0", "max": "255", "mean": "8", "stdev": "39" }, { "name": "V600", "index": "60", "type": "numeric", "distinct": "160", "missing": "0", "min": "0", "max": "255", "mean": "25", "stdev": "67" }, { "name": "V602", "index": "61", "type": "numeric", "distinct": "116", "missing": "0", "min": "0", "max": "255", "mean": "14", "stdev": "51" }, { "name": "V605", "index": "62", "type": "numeric", "distinct": "230", "missing": "0", "min": "0", "max": "255", "mean": "94", "stdev": "108" }, { "name": "V615", "index": "63", "type": "numeric", "distinct": "123", "missing": "0", "min": "0", "max": "255", "mean": "14", "stdev": "51" }, { "name": "V637", "index": "64", "type": "numeric", "distinct": "234", "missing": "0", "min": "0", "max": "255", "mean": "102", "stdev": "111" }, { "name": "V640", "index": "65", "type": "numeric", "distinct": "239", "missing": "0", "min": "0", "max": "255", "mean": "113", "stdev": "111" }, { "name": "V642", "index": "66", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "255", "mean": "7", "stdev": "38" }, { "name": "V647", "index": "67", "type": "numeric", "distinct": "132", "missing": "0", "min": "0", "max": "255", "mean": "23", "stdev": "66" }, { "name": "V657", "index": "68", "type": "numeric", "distinct": "127", "missing": "0", "min": "0", "max": "255", "mean": "21", "stdev": "63" }, { "name": "V677", "index": "69", "type": "numeric", "distinct": "216", "missing": "0", "min": "0", "max": "255", "mean": "86", "stdev": "107" }, { "name": "V680", "index": "70", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "253", "mean": "3", "stdev": "23" }, { "name": "V688", "index": "71", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "255", "mean": "8", "stdev": "39" }, { "name": "V690", "index": "72", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "255", "mean": "7", "stdev": "36" }, { "name": "V704", "index": "73", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "255", "mean": "4", "stdev": "26" }, { "name": "V716", "index": "74", "type": "numeric", "distinct": "210", "missing": "0", "min": "0", "max": "255", "mean": "72", "stdev": "103" }, { "name": "V728", "index": "75", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "255", "mean": "12", "stdev": "48" }, { "name": "V730", "index": "76", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "255", "mean": "5", "stdev": "30" }, { "name": "V741", "index": "77", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "255", "mean": "9", "stdev": "41" }, { "name": "V745", "index": "78", "type": "numeric", "distinct": "238", "missing": "0", "min": "0", "max": "255", "mean": "134", "stdev": "109" }, { "name": "V763", "index": "79", "type": "numeric", "distinct": "189", "missing": "0", "min": "0", "max": "255", "mean": "36", "stdev": "78" }, { "name": "V769", "index": "80", "type": "numeric", "distinct": "237", "missing": "0", "min": "0", "max": "255", "mean": "114", "stdev": "110" }, { "name": "V781", "index": "81", "type": "numeric", "distinct": "157", "missing": "0", "min": "0", "max": "255", "mean": "30", "stdev": "74" }, { "name": "V783", "index": "82", "type": "numeric", "distinct": "241", "missing": "0", "min": "0", "max": "255", "mean": "100", "stdev": "109" }, { "name": "V794", "index": "83", "type": "numeric", "distinct": "227", "missing": "0", "min": "0", "max": "255", "mean": "108", "stdev": "111" }, { "name": "V806", "index": "84", "type": "numeric", "distinct": "94", "missing": "0", "min": "0", "max": "255", "mean": "10", "stdev": "43" }, { "name": "V808", "index": "85", "type": "numeric", "distinct": "235", "missing": "0", "min": "0", "max": "255", "mean": "106", "stdev": "109" }, { "name": "V819", "index": "86", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "255", "mean": "4", "stdev": "26" }, { "name": "V833", "index": "87", "type": "numeric", "distinct": "235", "missing": "0", "min": "0", "max": "255", "mean": "118", "stdev": "112" }, { "name": "V842", "index": "88", "type": "numeric", "distinct": "187", "missing": "0", "min": "0", "max": "255", "mean": "49", "stdev": "91" }, { "name": "V857", "index": "89", "type": "numeric", "distinct": "225", "missing": "0", "min": "0", "max": "255", "mean": "95", "stdev": "110" }, { "name": "V860", "index": "90", "type": "numeric", "distinct": "205", "missing": "0", "min": "0", "max": "255", "mean": "57", "stdev": "94" }, { "name": "V883", "index": "91", "type": "numeric", "distinct": "141", "missing": "0", "min": "0", "max": "255", "mean": "20", "stdev": "61" }, { "name": "V886", "index": "92", "type": "numeric", "distinct": "224", "missing": "0", "min": "0", "max": "255", "mean": "100", "stdev": "110" }, { "name": "V897", "index": "93", "type": "numeric", "distinct": "187", "missing": "0", "min": "0", "max": "255", "mean": "46", "stdev": "88" }, { "name": "V909", "index": "94", "type": "numeric", "distinct": "234", "missing": "0", "min": "0", "max": "255", "mean": "118", "stdev": "112" }, { "name": "V922", "index": "95", "type": "numeric", "distinct": "231", "missing": "0", "min": "0", "max": "255", "mean": "91", "stdev": "108" }, { "name": "V933", "index": "96", "type": "numeric", "distinct": "141", "missing": "0", "min": "0", "max": "255", "mean": "22", "stdev": "63" }, { "name": "V941", "index": "97", "type": "numeric", "distinct": "219", "missing": "0", "min": "0", "max": "255", "mean": "82", "stdev": "107" }, { "name": "V955", "index": "98", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "255", "mean": "5", "stdev": "31" }, { "name": "V957", "index": "99", "type": "numeric", "distinct": "242", "missing": "0", "min": "0", "max": "255", "mean": "103", "stdev": "109" } ], "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 }