{ "data_id": "44467", "name": "KDDCup09_upselling_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "KDDCup09_upselling_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "783ce7a7-b811-4ba4-b725-d6d08c41235a", "description": "Subsampling of the dataset KDDCup09_upselling (44186) with\n\nseed=4\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 18:03:58", "update_comment": null, "last_update": "2022-11-17 18:03:58", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111229\/dataset", "default_target_attribute": "UPSELLING", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "KDDCup09_upselling_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset KDDCup09_upselling (44186) with seed=4 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 = r " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 50, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 34, "NumberOfSymbolicFeatures": 16, "AutoCorrelation": 0.5217608804402201, "PercentageOfMissingValues": 0, "Dimensionality": 0.025, "PercentageOfNumericFeatures": 68, "MajorityClassPercentage": 50, "PercentageOfSymbolicFeatures": 32, "MajorityClassSize": 1000, "MinorityClassPercentage": 50, "MinorityClassSize": 1000, "NumberOfBinaryFeatures": 3, "PercentageOfBinaryFeatures": 6, "PercentageOfInstancesWithMissingValues": 0 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Mathematics" } ], "features": [ { "name": "UPSELLING", "index": "49", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "-1", "1" ], [ [ "1000", "0" ], [ "0", "1000" ] ] ] }, { "name": "Var6", "index": "0", "type": "numeric", "distinct": "502", "missing": "0", "min": "0", "max": "32620", "mean": "1338", "stdev": "2005" }, { "name": "Var13", "index": "1", "type": "numeric", "distinct": "687", "missing": "0", "min": "0", "max": "38872", "mean": "1215", "stdev": "2456" }, { "name": "Var21", "index": "2", "type": "numeric", "distinct": "222", "missing": "0", "min": "4", "max": "5828", "mean": "230", "stdev": "337" }, { "name": "Var22", "index": "3", "type": "numeric", "distinct": "222", "missing": "0", "min": "5", "max": "7285", "mean": "287", "stdev": "421" }, { "name": "Var24", "index": "4", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "188", "mean": "5", "stdev": "9" }, { "name": "Var25", "index": "5", "type": "numeric", "distinct": "98", "missing": "0", "min": "0", "max": "3560", "mean": "104", "stdev": "171" }, { "name": "Var28", "index": "6", "type": "numeric", "distinct": "444", "missing": "0", "min": "0", "max": "908", "mean": "211", "stdev": "76" }, { "name": "Var35", "index": "7", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "110", "mean": "1", "stdev": "4" }, { "name": "Var38", "index": "8", "type": "numeric", "distinct": "1556", "missing": "0", "min": "0", "max": "14515200", "mean": "2446932", "stdev": "2952326" }, { "name": "Var57", "index": "9", "type": "numeric", "distinct": "1943", "missing": "0", "min": "0", "max": "7", "mean": "3", "stdev": "2" }, { "name": "Var65", "index": "10", "type": "numeric", "distinct": "9", "missing": "0", "min": "9", "max": "99", "mean": "14", "stdev": "10" }, { "name": "Var73", "index": "11", "type": "numeric", "distinct": "111", "missing": "0", "min": "12", "max": "264", "mean": "74", "stdev": "51" }, { "name": "Var74", "index": "12", "type": "numeric", "distinct": "134", "missing": "0", "min": "0", "max": "4928", "mean": "101", "stdev": "273" }, { "name": "Var76", "index": "13", "type": "numeric", "distinct": "1546", "missing": "0", "min": "0", "max": "19353600", "mean": "1484139", "stdev": "1894701" }, { "name": "Var78", "index": "14", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "33", "mean": "1", "stdev": "2" }, { "name": "Var81", "index": "15", "type": "numeric", "distinct": "1999", "missing": "0", "min": "426", "max": "938238", "mean": "92783", "stdev": "96195" }, { "name": "Var83", "index": "16", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "780", "mean": "18", "stdev": "43" }, { "name": "Var85", "index": "17", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "254", "mean": "9", "stdev": "16" }, { "name": "Var109", "index": "18", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "1712", "mean": "61", "stdev": "97" }, { "name": "Var112", "index": "19", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "5704", "mean": "72", "stdev": "162" }, { "name": "Var113", "index": "20", "type": "numeric", "distinct": "1997", "missing": "0", "min": "-2121772", "max": "4137440", "mean": "-12786", "stdev": "459772" }, { "name": "Var119", "index": "21", "type": "numeric", "distinct": "468", "missing": "0", "min": "5", "max": "39670", "mean": "917", "stdev": "1527" }, { "name": "Var123", "index": "22", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "1758", "mean": "51", "stdev": "95" }, { "name": "Var125", "index": "23", "type": "numeric", "distinct": "1323", "missing": "0", "min": "0", "max": "4707558", "mean": "31669", "stdev": "149949" }, { "name": "Var126", "index": "24", "type": "numeric", "distinct": "51", "missing": "0", "min": "-32", "max": "68", "mean": "-5", "stdev": "25" }, { "name": "Var132", "index": "25", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "184", "mean": "3", "stdev": "11" }, { "name": "Var133", "index": "26", "type": "numeric", "distinct": "1861", "missing": "0", "min": "0", "max": "12096000", "mean": "2212637", "stdev": "2393301" }, { "name": "Var134", "index": "27", "type": "numeric", "distinct": "1710", "missing": "0", "min": "0", "max": "5735340", "mean": "415588", "stdev": "587425" }, { "name": "Var140", "index": "28", "type": "numeric", "distinct": "664", "missing": "0", "min": "0", "max": "37760", "mean": "1366", "stdev": "2801" }, { "name": "Var144", "index": "29", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "63", "mean": "11", "stdev": "11" }, { "name": "Var149", "index": "30", "type": "numeric", "distinct": "1056", "missing": "0", "min": "0", "max": "16934400", "mean": "279770", "stdev": "749847" }, { "name": "Var153", "index": "31", "type": "numeric", "distinct": "1980", "missing": "0", "min": "468", "max": "12015760", "mean": "5945929", "stdev": "4263468" }, { "name": "Var160", "index": "32", "type": "numeric", "distinct": "120", "missing": "0", "min": "0", "max": "1024", "mean": "38", "stdev": "59" }, { "name": "Var163", "index": "33", "type": "numeric", "distinct": "1278", "missing": "0", "min": "0", "max": "10886400", "mean": "468787", "stdev": "883204" }, { "name": "Var194", "index": "34", "type": "nominal", "distinct": "4", "missing": "0", "distr": [ [ "0", "1", "2", "3" ], [ [ "2", "1" ], [ "262", "260" ], [ "7", "6" ], [ "729", "733" ] ] ] }, { "name": "Var196", "index": "35", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1", "3" ], [ [ "999", "992" ], [ "0", "0" ], [ "1", "8" ] ] ] }, { "name": "Var201", "index": "36", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2" ], [ [ "271", "267" ], [ "729", "733" ] ] ] }, { "name": "Var203", "index": "37", "type": "nominal", "distinct": "4", "missing": "0", "distr": [ [ "0", "1", "2", "5" ], [ [ "929", "916" ], [ "21", "13" ], [ "48", "71" ], [ "2", "0" ] ] ] }, { "name": "Var205", "index": "38", "type": "nominal", "distinct": "4", "missing": "0", "distr": [ [ "0", "1", "2", "3" ], [ [ "232", "263" ], [ "660", "617" ], [ "81", "76" ], [ "27", "44" ] ] ] }, { "name": "Var207", "index": "39", "type": "nominal", "distinct": "9", "missing": "0", "distr": [ [ "0", "1", "10", "13", "2", "3", "4", "5", "6", "7", "8", "9" ], [ [ "0", "0" ], [ "0", "0" ], [ "701", "654" ], [ "0", "0" ], [ "4", "3" ], [ "3", "3" ], [ "132", "161" ], [ "62", "74" ], [ "1", "2" ], [ "18", "23" ], [ "44", "48" ], [ "35", "32" ] ] ] }, { "name": "Var208", "index": "40", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "936", "921" ], [ "62", "79" ], [ "2", "0" ] ] ] }, { "name": "Var210", "index": "41", "type": "nominal", "distinct": "5", "missing": "0", "distr": [ [ "0", "1", "2", "3", "5" ], [ [ "2", "0" ], [ "5", "0" ], [ "2", "2" ], [ "26", "3" ], [ "965", "995" ] ] ] }, { "name": "Var211", "index": "42", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "763", "993" ], [ "237", "7" ] ] ] }, { "name": "Var218", "index": "43", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "498", "375" ], [ "497", "604" ], [ "5", "21" ] ] ] }, { "name": "Var221", "index": "44", "type": "nominal", "distinct": "7", "missing": "0", "distr": [ [ "0", "1", "2", "3", "4", "5", "6" ], [ [ "33", "42" ], [ "3", "2" ], [ "29", "41" ], [ "54", "60" ], [ "734", "697" ], [ "4", "2" ], [ "143", "156" ] ] ] }, { "name": "Var223", "index": "45", "type": "nominal", "distinct": "5", "missing": "0", "distr": [ [ "0", "1", "2", "3", "4" ], [ [ "756", "779" ], [ "38", "35" ], [ "4", "2" ], [ "114", "108" ], [ "88", "76" ] ] ] }, { "name": "Var225", "index": "46", "type": "nominal", "distinct": "4", "missing": "0", "distr": [ [ "0", "1", "2", "3" ], [ [ "221", "339" ], [ "225", "189" ], [ "46", "78" ], [ "508", "394" ] ] ] }, { "name": "Var227", "index": "47", "type": "nominal", "distinct": "7", "missing": "0", "distr": [ [ "0", "1", "2", "3", "4", "5", "6" ], [ [ "35", "48" ], [ "87", "86" ], [ "701", "654" ], [ "118", "145" ], [ "46", "51" ], [ "0", "1" ], [ "13", "15" ] ] ] }, { "name": "Var229", "index": "48", "type": "nominal", "distinct": "5", "missing": "0", "distr": [ [ "0", "1", "2", "3", "4" ], [ [ "249", "291" ], [ "199", "237" ], [ "1", "2" ], [ "1", "2" ], [ "550", "468" ] ] ] } ], "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 }