{ "data_id": "44791", "name": "KDDCup09-Upselling_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "KDDCup09-Upselling_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "94ee218e-e12c-43f4-b42b-453a5a736f8d", "description": "Subsampling of the dataset KDDCup09-Upselling (43072) with\n\nseed=3\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 19:05:55", "update_comment": null, "last_update": "2022-11-17 19:05:55", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111553\/dataset", "default_target_attribute": "upselling", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "KDDCup09-Upselling_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset KDDCup09-Upselling (43072) with seed=3 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": 101, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 0.9900990099009901, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "AutoCorrelation": 0.8639319659829915, "PercentageOfNumericFeatures": 99.00990099009901, "Dimensionality": 0.0505, "PercentageOfSymbolicFeatures": 0.9900990099009901, "MajorityClassPercentage": 92.65, "MajorityClassSize": 1853, "MinorityClassPercentage": 7.35, "MinorityClassSize": 147, "NumberOfBinaryFeatures": 1 }, "tags": [ { "uploader": "38960", "tag": "Chemistry" }, { "uploader": "38960", "tag": "Machine Learning" } ], "features": [ { "name": "upselling", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "-1", "1" ], [ [ "1853", "0" ], [ "0", "147" ] ] ] }, { "name": "Var23", "index": "0", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "0" }, { "name": "Var72", "index": "1", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var454", "index": "2", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "55", "mean": "0", "stdev": "1" }, { "name": "Var488", "index": "3", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "49", "mean": "0", "stdev": "1" }, { "name": "Var587", "index": "4", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "Var643", "index": "5", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "Var1145", "index": "6", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "Var1272", "index": "7", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var1355", "index": "8", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "Var1399", "index": "9", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "Var1529", "index": "10", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var1689", "index": "11", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "Var2072", "index": "12", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "Var2372", "index": "13", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "Var2569", "index": "14", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var2662", "index": "15", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var2691", "index": "16", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "160", "mean": "0", "stdev": "5" }, { "name": "Var2833", "index": "17", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var3087", "index": "18", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "126", "mean": "0", "stdev": "4" }, { "name": "Var3261", "index": "19", "type": "numeric", "distinct": "1938", "missing": "0", "min": "-9803600", "max": "8190520", "mean": "-222482", "stdev": "1070376" }, { "name": "Var3358", "index": "20", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "430", "mean": "0", "stdev": "10" }, { "name": "Var3513", "index": "21", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var3641", "index": "22", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var3695", "index": "23", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "9520", "mean": "74", "stdev": "277" }, { "name": "Var3777", "index": "24", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "32", "mean": "0", "stdev": "1" }, { "name": "Var3788", "index": "25", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "60", "mean": "0", "stdev": "2" }, { "name": "Var3930", "index": "26", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var4224", "index": "27", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "Var4353", "index": "28", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var4361", "index": "29", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "0" }, { "name": "Var4439", "index": "30", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "36", "mean": "0", "stdev": "1" }, { "name": "Var4444", "index": "31", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var4671", "index": "32", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var4756", "index": "33", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var4859", "index": "34", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "Var4930", "index": "35", "type": "numeric", "distinct": "1351", "missing": "0", "min": "0", "max": "4838400", "mean": "369109", "stdev": "403134" }, { "name": "Var5573", "index": "36", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var5739", "index": "37", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "140", "mean": "1", "stdev": "8" }, { "name": "Var5782", "index": "38", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var5810", "index": "39", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var5880", "index": "40", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "120", "mean": "1", "stdev": "8" }, { "name": "Var6240", "index": "41", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "17626", "mean": "9", "stdev": "394" }, { "name": "Var6393", "index": "42", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "15", "mean": "0", "stdev": "0" }, { "name": "Var6396", "index": "43", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "Var6427", "index": "44", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "0" }, { "name": "Var6712", "index": "45", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "Var7013", "index": "46", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "1325", "mean": "12", "stdev": "45" }, { "name": "Var7062", "index": "47", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "Var7109", "index": "48", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "39", "mean": "0", "stdev": "1" }, { "name": "Var7263", "index": "49", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "Var7675", "index": "50", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var7738", "index": "51", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "Var7749", "index": "52", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var8636", "index": "53", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var8706", "index": "54", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var8716", "index": "55", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "18", "mean": "0", "stdev": "0" }, { "name": "Var8855", "index": "56", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "55", "mean": "0", "stdev": "1" }, { "name": "Var9060", "index": "57", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "Var9063", "index": "58", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "0" }, { "name": "Var9218", "index": "59", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "30", "mean": "0", "stdev": "1" }, { "name": "Var9387", "index": "60", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "Var9638", "index": "61", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Var9665", "index": "62", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var9743", "index": "63", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "32", "mean": "0", "stdev": "1" }, { "name": "Var9795", "index": "64", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var9804", "index": "65", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var9835", "index": "66", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "99", "mean": "0", "stdev": "2" }, { "name": "Var9857", "index": "67", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var9895", "index": "68", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "Var10180", "index": "69", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var10261", "index": "70", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "0" }, { "name": "Var10347", "index": "71", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "3504", "mean": "3", "stdev": "90" }, { "name": "Var10522", "index": "72", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var10760", "index": "73", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "Var10902", "index": "74", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "Var10959", "index": "75", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "Var11051", "index": "76", "type": "numeric", "distinct": "550", "missing": "0", "min": "0", "max": "787635", "mean": "24042", "stdev": "63537" }, { "name": "Var11241", "index": "77", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "Var11316", "index": "78", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var11506", "index": "79", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var11682", "index": "80", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var11886", "index": "81", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "0" }, { "name": "Var12033", "index": "82", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "Var12232", "index": "83", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "60", "mean": "0", "stdev": "2" }, { "name": "Var12373", "index": "84", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var12564", "index": "85", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var12683", "index": "86", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "Var12894", "index": "87", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "Var12923", "index": "88", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "16", "mean": "0", "stdev": "0" }, { "name": "Var13108", "index": "89", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Var13184", "index": "90", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var13267", "index": "91", "type": "numeric", "distinct": "1554", "missing": "0", "min": "0", "max": "159579000", "mean": "3963883", "stdev": "12578180" }, { "name": "Var13629", "index": "92", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "Var13825", "index": "93", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "192", "mean": "0", "stdev": "7" }, { "name": "Var13876", "index": "94", "type": "numeric", "distinct": "118", "missing": "0", "min": "0", "max": "400", "mean": "5", "stdev": "26" }, { "name": "Var13959", "index": "95", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "81277", "mean": "44", "stdev": "1822" }, { "name": "Var14039", "index": "96", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var14212", "index": "97", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "28", "mean": "1", "stdev": "3" }, { "name": "Var14279", "index": "98", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "0" }, { "name": "Var14480", "index": "99", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" } ], "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 }