{ "data_id": "44523", "name": "jasmine_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "jasmine_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "6af8b798-c145-4ef1-a488-c07a622a9202", "description": "Subsampling of the dataset jasmine (41143) 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 18:25:14", "update_comment": null, "last_update": "2022-11-17 18:25:14", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111285\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "jasmine_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset jasmine (41143) 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( " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 101, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 6, "NumberOfSymbolicFeatures": 95, "PercentageOfBinaryFeatures": 94.05940594059405, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.5162581290645323, "PercentageOfMissingValues": 0, "Dimensionality": 0.0505, "PercentageOfNumericFeatures": 5.9405940594059405, "MajorityClassPercentage": 50, "PercentageOfSymbolicFeatures": 94.05940594059405, "MajorityClassSize": 1000, "MinorityClassPercentage": 50, "MinorityClassSize": 1000, "NumberOfBinaryFeatures": 95 }, "tags": [ { "uploader": "38960", "tag": "Statistics" } ], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "1000", "0" ], [ "0", "1000" ] ] ] }, { "name": "V1", "index": "0", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "978", "915" ], [ "22", "85" ] ] ] }, { "name": "V2", "index": "1", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "955", "941" ], [ "45", "59" ] ] ] }, { "name": "V3", "index": "2", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "981", "987" ], [ "19", "13" ] ] ] }, { "name": "V4", "index": "3", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "963", "968" ], [ "37", "32" ] ] ] }, { "name": "V7", "index": "4", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "792", "621" ], [ "208", "379" ] ] ] }, { "name": "V9", "index": "5", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "748", "763" ], [ "252", "237" ] ] ] }, { "name": "V10", "index": "6", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "926", "930" ], [ "74", "70" ] ] ] }, { "name": "V11", "index": "7", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "841", "447" ], [ "159", "553" ] ] ] }, { "name": "V12", "index": "8", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "862", "776" ], [ "138", "224" ] ] ] }, { "name": "V13", "index": "9", "type": "numeric", "distinct": "105", "missing": "0", "min": "-1", "max": "10", "mean": "-1", "stdev": "1" }, { "name": "V14", "index": "10", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "934", "820" ], [ "66", "180" ] ] ] }, { "name": "V15", "index": "11", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "933", "911" ], [ "67", "89" ] ] ] }, { "name": "V16", "index": "12", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "984", "982" ], [ "16", "18" ] ] ] }, { "name": "V19", "index": "13", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "831", "740" ], [ "169", "260" ] ] ] }, { "name": "V24", "index": "14", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "920", "949" ], [ "80", "51" ] ] ] }, { "name": "V25", "index": "15", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "895", "912" ], [ "105", "88" ] ] ] }, { "name": "V28", "index": "16", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "977", "974" ], [ "23", "26" ] ] ] }, { "name": "V29", "index": "17", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "993", "996" ], [ "7", "4" ] ] ] }, { "name": "V30", "index": "18", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "915", "906" ], [ "85", "94" ] ] ] }, { "name": "V32", "index": "19", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "991", "970" ], [ "9", "30" ] ] ] }, { "name": "V33", "index": "20", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "924", "766" ], [ "76", "234" ] ] ] }, { "name": "V34", "index": "21", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "788", "708" ], [ "212", "292" ] ] ] }, { "name": "V35", "index": "22", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "911", "893" ], [ "89", "107" ] ] ] }, { "name": "V36", "index": "23", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "892", "885" ], [ "108", "115" ] ] ] }, { "name": "V37", "index": "24", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "932", "917" ], [ "68", "83" ] ] ] }, { "name": "V39", "index": "25", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "668", "193" ], [ "332", "807" ] ] ] }, { "name": "V40", "index": "26", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "682", "190" ], [ "318", "810" ] ] ] }, { "name": "V42", "index": "27", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "963", "880" ], [ "37", "120" ] ] ] }, { "name": "V43", "index": "28", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "0" }, { "name": "V44", "index": "29", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "980", "988" ], [ "20", "12" ] ] ] }, { "name": "V45", "index": "30", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "16", "mean": "2", "stdev": "2" }, { "name": "V48", "index": "31", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "730", "753" ], [ "270", "247" ] ] ] }, { "name": "V50", "index": "32", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "975", "972" ], [ "25", "28" ] ] ] }, { "name": "V52", "index": "33", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "963", "947" ], [ "37", "53" ] ] ] }, { "name": "V53", "index": "34", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "621", "635" ], [ "379", "365" ] ] ] }, { "name": "V54", "index": "35", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "837", "848" ], [ "163", "152" ] ] ] }, { "name": "V56", "index": "36", "type": "numeric", "distinct": "1149", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "V58", "index": "37", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "935", "797" ], [ "65", "203" ] ] ] }, { "name": "V59", "index": "38", "type": "numeric", "distinct": "119", "missing": "0", "min": "-1", "max": "9", "mean": "-1", "stdev": "1" }, { "name": "V60", "index": "39", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "872", "671" ], [ "128", "329" ] ] ] }, { "name": "V61", "index": "40", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "982", "926" ], [ "18", "74" ] ] ] }, { "name": "V63", "index": "41", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "816", "828" ], [ "184", "172" ] ] ] }, { "name": "V64", "index": "42", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "1000", "999" ], [ "0", "1" ] ] ] }, { "name": "V65", "index": "43", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "1000", "999" ], [ "0", "1" ] ] ] }, { "name": "V66", "index": "44", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "990", "990" ], [ "10", "10" ] ] ] }, { "name": "V67", "index": "45", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "920", "843" ], [ "80", "157" ] ] ] }, { "name": "V68", "index": "46", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "988", "973" ], [ "12", "27" ] ] ] }, { "name": "V70", "index": "47", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "948", "859" ], [ "52", "141" ] ] ] }, { "name": "V72", "index": "48", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "919", "826" ], [ "81", "174" ] ] ] }, { "name": "V73", "index": "49", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "995", "985" ], [ "5", "15" ] ] ] }, { "name": "V74", "index": "50", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "939", "833" ], [ "61", "167" ] ] ] }, { "name": "V75", "index": "51", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "918", "898" ], [ "82", "102" ] ] ] }, { "name": "V76", "index": "52", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "962", "885" ], [ "38", "115" ] ] ] }, { "name": "V78", "index": "53", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "879", "562" ], [ "121", "438" ] ] ] }, { "name": "V80", "index": "54", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "424", "431" ], [ "576", "569" ] ] ] }, { "name": "V81", "index": "55", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "942", "956" ], [ "58", "44" ] ] ] }, { "name": "V82", "index": "56", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "809", "602" ], [ "191", "398" ] ] ] }, { "name": "V83", "index": "57", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "847", "857" ], [ "153", "143" ] ] ] }, { "name": "V84", "index": "58", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "728", "527" ], [ "272", "473" ] ] ] }, { "name": "V85", "index": "59", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "997", "998" ], [ "3", "2" ] ] ] }, { "name": "V86", "index": "60", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "877", "635" ], [ "123", "365" ] ] ] }, { "name": "V87", "index": "61", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "958", "959" ], [ "42", "41" ] ] ] }, { "name": "V88", "index": "62", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "936", "912" ], [ "64", "88" ] ] ] }, { "name": "V89", "index": "63", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "1000", "999" ], [ "0", "1" ] ] ] }, { "name": "V90", "index": "64", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "980", "928" ], [ "20", "72" ] ] ] }, { "name": "V92", "index": "65", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "718", "481" ], [ "282", "519" ] ] ] }, { "name": "V93", "index": "66", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "688", "678" ], [ "312", "322" ] ] ] }, { "name": "V94", "index": "67", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "999", "995" ], [ "1", "5" ] ] ] }, { "name": "V96", "index": "68", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "975", "977" ], [ "25", "23" ] ] ] }, { "name": "V97", "index": "69", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "525", "535" ], [ "475", "465" ] ] ] }, { "name": "V98", "index": "70", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "957", "947" ], [ "43", "53" ] ] ] }, { "name": "V99", "index": "71", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "812", "770" ], [ "188", "230" ] ] ] }, { "name": "V100", "index": "72", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "485", "921" ], [ "515", "79" ] ] ] }, { "name": "V101", "index": "73", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "968", "970" ], [ "32", "30" ] ] ] }, { "name": "V102", "index": "74", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "656", "265" ], [ "344", "735" ] ] ] }, { "name": "V103", "index": "75", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "861", "807" ], [ "139", "193" ] ] ] }, { "name": "V104", "index": "76", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "992", "972" ], [ "8", "28" ] ] ] }, { "name": "V105", "index": "77", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "566", "548" ], [ "434", "452" ] ] ] }, { "name": "V106", "index": "78", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "920", "747" ], [ "80", "253" ] ] ] }, { "name": "V107", "index": "79", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "612", "630" ], [ "388", "370" ] ] ] }, { "name": "V112", "index": "80", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "785", "465" ], [ "215", "535" ] ] ] }, { "name": "V113", "index": "81", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "935", "922" ], [ "65", "78" ] ] ] }, { "name": "V114", "index": "82", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "906", "922" ], [ "94", "78" ] ] ] }, { "name": "V115", "index": "83", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "991", "985" ], [ "9", "15" ] ] ] }, { "name": "V116", "index": "84", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "974", "958" ], [ "26", "42" ] ] ] }, { "name": "V118", "index": "85", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "797", "820" ], [ "203", "180" ] ] ] }, { "name": "V119", "index": "86", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "935", "944" ], [ "65", "56" ] ] ] }, { "name": "V120", "index": "87", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "698", "696" ], [ "302", "304" ] ] ] }, { "name": "V122", "index": "88", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "945", "954" ], [ "55", "46" ] ] ] }, { "name": "V124", "index": "89", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "978", "960" ], [ "22", "40" ] ] ] }, { "name": "V126", "index": "90", "type": "numeric", "distinct": "107", "missing": "0", "min": "-1", "max": "9", "mean": "-1", "stdev": "1" }, { "name": "V130", "index": "91", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "912", "922" ], [ "88", "78" ] ] ] }, { "name": "V132", "index": "92", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "575", "91" ], [ "425", "909" ] ] ] }, { "name": "V133", "index": "93", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "939", "937" ], [ "61", "63" ] ] ] }, { "name": "V135", "index": "94", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "907", "816" ], [ "93", "184" ] ] ] }, { "name": "V136", "index": "95", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "988", "996" ], [ "12", "4" ] ] ] }, { "name": "V137", "index": "96", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "911", "903" ], [ "89", "97" ] ] ] }, { "name": "V139", "index": "97", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "912", "746" ], [ "88", "254" ] ] ] }, { "name": "V141", "index": "98", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "612", "643" ], [ "388", "357" ] ] ] }, { "name": "V143", "index": "99", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "986", "987" ], [ "14", "13" ] ] ] } ], "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 }