{ "data_id": "44790", "name": "KDDCup09-Upselling_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "KDDCup09-Upselling_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "4ecfc538-6362-47e2-8231-1752d963c2f3", "description": "Subsampling of the dataset KDDCup09-Upselling (43072) with\n\nseed=2\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 19:05:50", "update_comment": null, "last_update": "2022-11-17 19:05:50", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111552\/dataset", "default_target_attribute": "upselling", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "KDDCup09-Upselling_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset KDDCup09-Upselling (43072) with seed=2 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": 5914, "NumberOfInstancesWithMissingValues": 2000, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 0.9900990099009901, "PercentageOfInstancesWithMissingValues": 100, "PercentageOfMissingValues": 2.927722772277228, "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": "Agriculture" }, { "uploader": "38960", "tag": "Life Science" } ], "features": [ { "name": "upselling", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "-1", "1" ], [ [ "1853", "0" ], [ "0", "147" ] ] ] }, { "name": "Var578", "index": "0", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "0" }, { "name": "Var593", "index": "1", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var820", "index": "2", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var850", "index": "3", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "Var1143", "index": "4", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var1366", "index": "5", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "Var1445", "index": "6", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "0" }, { "name": "Var1505", "index": "7", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var1558", "index": "8", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "49", "mean": "2", "stdev": "7" }, { "name": "Var1597", "index": "9", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var1623", "index": "10", "type": "numeric", "distinct": "1424", "missing": "0", "min": "0", "max": "6048000", "mean": "500674", "stdev": "564068" }, { "name": "Var2230", "index": "11", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "1638", "mean": "8", "stdev": "51" }, { "name": "Var2785", "index": "12", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "245", "mean": "9", "stdev": "21" }, { "name": "Var2789", "index": "13", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "100", "mean": "1", "stdev": "6" }, { "name": "Var2990", "index": "14", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "441", "mean": "2", "stdev": "15" }, { "name": "Var3006", "index": "15", "type": "numeric", "distinct": "1961", "missing": "0", "min": "0", "max": "89695530", "mean": "14567128", "stdev": "10854490" }, { "name": "Var3177", "index": "16", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var3227", "index": "17", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "Var3265", "index": "18", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "16", "mean": "0", "stdev": "0" }, { "name": "Var3330", "index": "19", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "56", "mean": "0", "stdev": "2" }, { "name": "Var3862", "index": "20", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var3864", "index": "21", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "99", "mean": "0", "stdev": "2" }, { "name": "Var3880", "index": "22", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "0" }, { "name": "Var4082", "index": "23", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Var4428", "index": "24", "type": "numeric", "distinct": "365", "missing": "0", "min": "0", "max": "51964", "mean": "1139", "stdev": "3900" }, { "name": "Var4540", "index": "25", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "Var4733", "index": "26", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "Var4951", "index": "27", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var4969", "index": "28", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "1648", "mean": "29", "stdev": "70" }, { "name": "Var5058", "index": "29", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "5535", "mean": "76", "stdev": "202" }, { "name": "Var5145", "index": "30", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var5652", "index": "31", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var5822", "index": "32", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "22", "mean": "0", "stdev": "1" }, { "name": "Var6057", "index": "33", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var6137", "index": "34", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var6282", "index": "35", "type": "numeric", "distinct": "180", "missing": "0", "min": "0", "max": "455010", "mean": "704", "stdev": "10774" }, { "name": "Var6426", "index": "36", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var6532", "index": "37", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "0" }, { "name": "Var6565", "index": "38", "type": "numeric", "distinct": "650", "missing": "0", "min": "0", "max": "325", "mean": "58", "stdev": "22" }, { "name": "Var6627", "index": "39", "type": "numeric", "distinct": "2", "missing": "1978", "min": "0", "max": "32", "mean": "1", "stdev": "7" }, { "name": "Var6686", "index": "40", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "21", "mean": "0", "stdev": "1" }, { "name": "Var6693", "index": "41", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "0" }, { "name": "Var6761", "index": "42", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "60", "mean": "0", "stdev": "3" }, { "name": "Var7007", "index": "43", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "Var7030", "index": "44", "type": "numeric", "distinct": "23", "missing": "1958", "min": "0", "max": "500", "mean": "89", "stdev": "128" }, { "name": "Var7099", "index": "45", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "2" }, { "name": "Var7249", "index": "46", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "30", "mean": "1", "stdev": "3" }, { "name": "Var7430", "index": "47", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var7438", "index": "48", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var7481", "index": "49", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "Var7601", "index": "50", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "240", "mean": "1", "stdev": "6" }, { "name": "Var7698", "index": "51", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "1107", "mean": "2", "stdev": "43" }, { "name": "Var7778", "index": "52", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var7802", "index": "53", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "17", "mean": "0", "stdev": "1" }, { "name": "Var8287", "index": "54", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "Var8349", "index": "55", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "0" }, { "name": "Var8474", "index": "56", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var8620", "index": "57", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var8843", "index": "58", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var8844", "index": "59", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var8847", "index": "60", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "Var8903", "index": "61", "type": "numeric", "distinct": "1", "missing": "1978", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var9151", "index": "62", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var9407", "index": "63", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "114", "mean": "0", "stdev": "4" }, { "name": "Var9441", "index": "64", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "126", "mean": "0", "stdev": "5" }, { "name": "Var9598", "index": "65", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var9759", "index": "66", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var9941", "index": "67", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "7", "mean": "0", "stdev": "1" }, { "name": "Var10080", "index": "68", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "Var10122", "index": "69", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "3311", "mean": "52", "stdev": "119" }, { "name": "Var10150", "index": "70", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var10296", "index": "71", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var10323", "index": "72", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "42", "mean": "3", "stdev": "8" }, { "name": "Var10328", "index": "73", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Var10421", "index": "74", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "176", "mean": "0", "stdev": "7" }, { "name": "Var10808", "index": "75", "type": "numeric", "distinct": "1955", "missing": "0", "min": "0", "max": "2147483647", "mean": "88274410", "stdev": "970163644" }, { "name": "Var11123", "index": "76", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "Var11473", "index": "77", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "Var11535", "index": "78", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "0" }, { "name": "Var11695", "index": "79", "type": "numeric", "distinct": "55", "missing": "0", "min": "0", "max": "506", "mean": "10", "stdev": "33" }, { "name": "Var12066", "index": "80", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var12078", "index": "81", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "80", "mean": "0", "stdev": "3" }, { "name": "Var12369", "index": "82", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "120", "mean": "0", "stdev": "3" }, { "name": "Var12420", "index": "83", "type": "numeric", "distinct": "1482", "missing": "0", "min": "0", "max": "12096000", "mean": "1221082", "stdev": "1502963" }, { "name": "Var12649", "index": "84", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var12850", "index": "85", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "88", "mean": "0", "stdev": "3" }, { "name": "Var12899", "index": "86", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var13045", "index": "87", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "Var13064", "index": "88", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var13170", "index": "89", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var13256", "index": "90", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "80", "mean": "1", "stdev": "4" }, { "name": "Var13305", "index": "91", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "Var13503", "index": "92", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var13753", "index": "93", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var13895", "index": "94", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var14044", "index": "95", "type": "numeric", "distinct": "420", "missing": "0", "min": "0", "max": "448128", "mean": "12351", "stdev": "36737" }, { "name": "Var14263", "index": "96", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "0" }, { "name": "Var14381", "index": "97", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var14531", "index": "98", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Var14737", "index": "99", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "504", "mean": "1", "stdev": "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 }