{ "data_id": "44788", "name": "KDDCup09-Upselling_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "KDDCup09-Upselling_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "fa8f1574-bf6e-46eb-9510-78742a832399", "description": "Subsampling of the dataset KDDCup09-Upselling (43072) 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 19:05:38", "update_comment": null, "last_update": "2022-11-17 19:05:38", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111550\/dataset", "default_target_attribute": "upselling", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "KDDCup09-Upselling_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset KDDCup09-Upselling (43072) 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 = r " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 101, "NumberOfClasses": 2, "NumberOfMissingValues": 3570, "NumberOfInstancesWithMissingValues": 2000, "NumberOfNumericFeatures": 99, "NumberOfSymbolicFeatures": 2, "PercentageOfBinaryFeatures": 1.9801980198019802, "PercentageOfInstancesWithMissingValues": 100, "AutoCorrelation": 0.8659329664832416, "PercentageOfMissingValues": 1.7673267326732671, "Dimensionality": 0.0505, "PercentageOfNumericFeatures": 98.01980198019803, "MajorityClassPercentage": 92.65, "PercentageOfSymbolicFeatures": 1.9801980198019802, "MajorityClassSize": 1853, "MinorityClassPercentage": 7.35, "MinorityClassSize": 147, "NumberOfBinaryFeatures": 2 }, "tags": [ { "uploader": "38960", "tag": "Statistics" } ], "features": [ { "name": "upselling", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "-1", "1" ], [ [ "1853", "0" ], [ "0", "147" ] ] ] }, { "name": "Var41", "index": "0", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var81", "index": "1", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "Var124", "index": "2", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "Var247", "index": "3", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "Var331", "index": "4", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "Var424", "index": "5", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "Var501", "index": "6", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "35094", "mean": "39", "stdev": "1094" }, { "name": "Var610", "index": "7", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var726", "index": "8", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "Var1088", "index": "9", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var1118", "index": "10", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "Var1197", "index": "11", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "2" }, { "name": "Var1255", "index": "12", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var1329", "index": "13", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "28950", "mean": "64", "stdev": "910" }, { "name": "Var1849", "index": "14", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "Var2013", "index": "15", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "63", "mean": "6", "stdev": "12" }, { "name": "Var2601", "index": "16", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var2611", "index": "17", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "115", "mean": "1", "stdev": "10" }, { "name": "Var3390", "index": "18", "type": "numeric", "distinct": "1320", "missing": "194", "min": "0", "max": "7257600", "mean": "685979", "stdev": "830962" }, { "name": "Var3797", "index": "19", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "125", "mean": "2", "stdev": "13" }, { "name": "Var3828", "index": "20", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var3938", "index": "21", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "0" }, { "name": "Var4001", "index": "22", "type": "numeric", "distinct": "1566", "missing": "0", "min": "0", "max": "16808760", "mean": "1518625", "stdev": "1964896" }, { "name": "Var4118", "index": "23", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var4456", "index": "24", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "0" }, { "name": "Var4566", "index": "25", "type": "numeric", "distinct": "295", "missing": "0", "min": "0", "max": "251", "mean": "3", "stdev": "15" }, { "name": "Var4623", "index": "26", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "140", "mean": "0", "stdev": "4" }, { "name": "Var4800", "index": "27", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var4896", "index": "28", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "Var5040", "index": "29", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "Var5335", "index": "30", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "Var5594", "index": "31", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "46", "mean": "0", "stdev": "1" }, { "name": "Var5630", "index": "32", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "81", "mean": "0", "stdev": "2" }, { "name": "Var5650", "index": "33", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var5709", "index": "34", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "513", "mean": "16", "stdev": "42" }, { "name": "Var5792", "index": "35", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "154", "mean": "0", "stdev": "5" }, { "name": "Var5842", "index": "36", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "35", "mean": "0", "stdev": "1" }, { "name": "Var5854", "index": "37", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var5995", "index": "38", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "0" }, { "name": "Var6284", "index": "39", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "Var6302", "index": "40", "type": "numeric", "distinct": "1", "missing": "1941", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var6857", "index": "41", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "Var7152", "index": "42", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "0" }, { "name": "Var7240", "index": "43", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "75", "mean": "0", "stdev": "3" }, { "name": "Var7475", "index": "44", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "Var7524", "index": "45", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "28", "mean": "0", "stdev": "1" }, { "name": "Var7581", "index": "46", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "0" }, { "name": "Var7819", "index": "47", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "340", "mean": "13", "stdev": "20" }, { "name": "Var7827", "index": "48", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var7922", "index": "49", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var8049", "index": "50", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "2" }, { "name": "Var8071", "index": "51", "type": "numeric", "distinct": "68", "missing": "0", "min": "0", "max": "560", "mean": "14", "stdev": "30" }, { "name": "Var8234", "index": "52", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var8313", "index": "53", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var8521", "index": "54", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var8622", "index": "55", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "Var8862", "index": "56", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "0" }, { "name": "Var9002", "index": "57", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "Var9154", "index": "58", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "125", "mean": "0", "stdev": "5" }, { "name": "Var9299", "index": "59", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "Var9384", "index": "60", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var9444", "index": "61", "type": "numeric", "distinct": "1600", "missing": "0", "min": "0", "max": "51719120", "mean": "5261011", "stdev": "5686357" }, { "name": "Var9625", "index": "62", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "207", "mean": "5", "stdev": "23" }, { "name": "Var9634", "index": "63", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "Var9681", "index": "64", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "16", "mean": "0", "stdev": "1" }, { "name": "Var9961", "index": "65", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var9973", "index": "66", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var10027", "index": "67", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "50", "mean": "0", "stdev": "3" }, { "name": "Var10202", "index": "68", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "12036", "mean": "16", "stdev": "364" }, { "name": "Var10248", "index": "69", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "Var10480", "index": "70", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "207", "mean": "0", "stdev": "9" }, { "name": "Var10654", "index": "71", "type": "numeric", "distinct": "1747", "missing": "0", "min": "0", "max": "2147483647", "mean": "11282432", "stdev": "241969065" }, { "name": "Var10709", "index": "72", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "0" }, { "name": "Var10726", "index": "73", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "84", "mean": "0", "stdev": "2" }, { "name": "Var10743", "index": "74", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "98", "mean": "0", "stdev": "4" }, { "name": "Var10825", "index": "75", "type": "numeric", "distinct": "65", "missing": "0", "min": "0", "max": "221", "mean": "1", "stdev": "9" }, { "name": "Var10838", "index": "76", "type": "numeric", "distinct": "460", "missing": "0", "min": "0", "max": "2244", "mean": "269", "stdev": "287" }, { "name": "Var11343", "index": "77", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var11360", "index": "78", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "46", "mean": "0", "stdev": "1" }, { "name": "Var11365", "index": "79", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "Var11980", "index": "80", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Var12067", "index": "81", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "0" }, { "name": "Var12115", "index": "82", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var12429", "index": "83", "type": "numeric", "distinct": "61", "missing": "0", "min": "0", "max": "204", "mean": "2", "stdev": "11" }, { "name": "Var12511", "index": "84", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var12578", "index": "85", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "Var12594", "index": "86", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "18408", "mean": "10", "stdev": "413" }, { "name": "Var12613", "index": "87", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "0" }, { "name": "Var12735", "index": "88", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "3762", "mean": "2", "stdev": "84" }, { "name": "Var12828", "index": "89", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "Var13033", "index": "90", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "Var13258", "index": "91", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "57", "mean": "0", "stdev": "1" }, { "name": "Var13283", "index": "92", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var13546", "index": "93", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var13885", "index": "94", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var13924", "index": "95", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var14145", "index": "96", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var14411", "index": "97", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "2538", "mean": "25", "stdev": "116" }, { "name": "Var14601", "index": "98", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "46", "mean": "0", "stdev": "2" }, { "name": "Var14874", "index": "99", "type": "nominal", "distinct": "2", "missing": "1435", "distr": [ [ "WvqeQBy", "ooli" ], [ [ "2", "0" ], [ "526", "37" ] ] ] } ], "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 }