{ "data_id": "44465", "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": "ddbff86d-6d6f-4860-b26a-9774c1aa0db0", "description": "Subsampling of the dataset KDDCup09_upselling (44186) 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 18:03:48", "update_comment": null, "last_update": "2022-11-17 18:03:48", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111227\/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 (44186) 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": 50, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 34, "NumberOfSymbolicFeatures": 16, "MinorityClassPercentage": 50, "MinorityClassSize": 1000, "NumberOfBinaryFeatures": 3, "PercentageOfBinaryFeatures": 6, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.49074537268634316, "PercentageOfMissingValues": 0, "Dimensionality": 0.025, "PercentageOfNumericFeatures": 68, "MajorityClassPercentage": 50, "PercentageOfSymbolicFeatures": 32, "MajorityClassSize": 1000 }, "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": "507", "missing": "0", "min": "0", "max": "103740", "mean": "1377", "stdev": "2897" }, { "name": "Var13", "index": "1", "type": "numeric", "distinct": "684", "missing": "0", "min": "0", "max": "41688", "mean": "1170", "stdev": "2526" }, { "name": "Var21", "index": "2", "type": "numeric", "distinct": "246", "missing": "0", "min": "4", "max": "5120", "mean": "240", "stdev": "359" }, { "name": "Var22", "index": "3", "type": "numeric", "distinct": "246", "missing": "0", "min": "5", "max": "6400", "mean": "299", "stdev": "449" }, { "name": "Var24", "index": "4", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "80", "mean": "5", "stdev": "8" }, { "name": "Var25", "index": "5", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "3136", "mean": "110", "stdev": "179" }, { "name": "Var28", "index": "6", "type": "numeric", "distinct": "489", "missing": "0", "min": "0", "max": "1260", "mean": "213", "stdev": "83" }, { "name": "Var35", "index": "7", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "40", "mean": "1", "stdev": "3" }, { "name": "Var38", "index": "8", "type": "numeric", "distinct": "1544", "missing": "0", "min": "0", "max": "16586160", "mean": "2415204", "stdev": "2986820" }, { "name": "Var57", "index": "9", "type": "numeric", "distinct": "1944", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "2" }, { "name": "Var65", "index": "10", "type": "numeric", "distinct": "9", "missing": "0", "min": "9", "max": "108", "mean": "15", "stdev": "10" }, { "name": "Var73", "index": "11", "type": "numeric", "distinct": "109", "missing": "0", "min": "12", "max": "264", "mean": "71", "stdev": "50" }, { "name": "Var74", "index": "12", "type": "numeric", "distinct": "127", "missing": "0", "min": "0", "max": "9919", "mean": "92", "stdev": "300" }, { "name": "Var76", "index": "13", "type": "numeric", "distinct": "1570", "missing": "0", "min": "0", "max": "19353600", "mean": "1500282", "stdev": "1826737" }, { "name": "Var78", "index": "14", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "33", "mean": "0", "stdev": "2" }, { "name": "Var81", "index": "15", "type": "numeric", "distinct": "1997", "missing": "0", "min": "372", "max": "868770", "mean": "93894", "stdev": "93597" }, { "name": "Var83", "index": "16", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "890", "mean": "18", "stdev": "43" }, { "name": "Var85", "index": "17", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "202", "mean": "9", "stdev": "15" }, { "name": "Var109", "index": "18", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "1248", "mean": "60", "stdev": "87" }, { "name": "Var112", "index": "19", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "1592", "mean": "71", "stdev": "111" }, { "name": "Var113", "index": "20", "type": "numeric", "distinct": "1999", "missing": "0", "min": "-2040380", "max": "4382400", "mean": "-13864", "stdev": "459936" }, { "name": "Var119", "index": "21", "type": "numeric", "distinct": "485", "missing": "0", "min": "10", "max": "90535", "mean": "963", "stdev": "2387" }, { "name": "Var123", "index": "22", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "1974", "mean": "55", "stdev": "118" }, { "name": "Var125", "index": "23", "type": "numeric", "distinct": "1287", "missing": "0", "min": "0", "max": "986400", "mean": "27553", "stdev": "64453" }, { "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": "13", "missing": "0", "min": "0", "max": "120", "mean": "3", "stdev": "10" }, { "name": "Var133", "index": "26", "type": "numeric", "distinct": "1854", "missing": "0", "min": "0", "max": "13236650", "mean": "2224400", "stdev": "2429302" }, { "name": "Var134", "index": "27", "type": "numeric", "distinct": "1717", "missing": "0", "min": "0", "max": "5735340", "mean": "436123", "stdev": "617505" }, { "name": "Var140", "index": "28", "type": "numeric", "distinct": "649", "missing": "0", "min": "0", "max": "38885", "mean": "1325", "stdev": "2843" }, { "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": "1102", "missing": "0", "min": "0", "max": "12700800", "mean": "294020", "stdev": "609226" }, { "name": "Var153", "index": "31", "type": "numeric", "distinct": "1977", "missing": "0", "min": "468", "max": "13167720", "mean": "5964350", "stdev": "4271014" }, { "name": "Var160", "index": "32", "type": "numeric", "distinct": "125", "missing": "0", "min": "0", "max": "1172", "mean": "40", "stdev": "73" }, { "name": "Var163", "index": "33", "type": "numeric", "distinct": "1299", "missing": "0", "min": "0", "max": "10886400", "mean": "469102", "stdev": "835935" }, { "name": "Var194", "index": "34", "type": "nominal", "distinct": "4", "missing": "0", "distr": [ [ "0", "1", "2", "3" ], [ [ "1", "1" ], [ "228", "268" ], [ "3", "4" ], [ "768", "727" ] ] ] }, { "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" ], [ [ "232", "273" ], [ "768", "727" ] ] ] }, { "name": "Var203", "index": "37", "type": "nominal", "distinct": "4", "missing": "0", "distr": [ [ "0", "1", "2", "5" ], [ [ "937", "913" ], [ "14", "26" ], [ "48", "58" ], [ "1", "3" ] ] ] }, { "name": "Var205", "index": "38", "type": "nominal", "distinct": "4", "missing": "0", "distr": [ [ "0", "1", "2", "3" ], [ [ "228", "250" ], [ "638", "643" ], [ "96", "70" ], [ "38", "37" ] ] ] }, { "name": "Var207", "index": "39", "type": "nominal", "distinct": "10", "missing": "0", "distr": [ [ "0", "1", "10", "13", "2", "3", "4", "5", "6", "7", "8", "9" ], [ [ "0", "0" ], [ "0", "0" ], [ "707", "646" ], [ "1", "1" ], [ "3", "2" ], [ "1", "2" ], [ "135", "163" ], [ "75", "85" ], [ "1", "2" ], [ "15", "22" ], [ "37", "40" ], [ "25", "37" ] ] ] }, { "name": "Var208", "index": "40", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "939", "928" ], [ "60", "69" ], [ "1", "3" ] ] ] }, { "name": "Var210", "index": "41", "type": "nominal", "distinct": "5", "missing": "0", "distr": [ [ "0", "1", "2", "3", "5" ], [ [ "1", "1" ], [ "7", "0" ], [ "0", "2" ], [ "21", "4" ], [ "971", "993" ] ] ] }, { "name": "Var211", "index": "42", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "746", "988" ], [ "254", "12" ] ] ] }, { "name": "Var218", "index": "43", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "484", "359" ], [ "505", "621" ], [ "11", "20" ] ] ] }, { "name": "Var221", "index": "44", "type": "nominal", "distinct": "7", "missing": "0", "distr": [ [ "0", "1", "2", "3", "4", "5", "6" ], [ [ "27", "43" ], [ "5", "6" ], [ "28", "45" ], [ "65", "75" ], [ "743", "690" ], [ "3", "1" ], [ "129", "140" ] ] ] }, { "name": "Var223", "index": "45", "type": "nominal", "distinct": "5", "missing": "0", "distr": [ [ "0", "1", "2", "3", "4" ], [ [ "769", "807" ], [ "32", "36" ], [ "2", "2" ], [ "110", "103" ], [ "87", "52" ] ] ] }, { "name": "Var225", "index": "46", "type": "nominal", "distinct": "4", "missing": "0", "distr": [ [ "0", "1", "2", "3" ], [ [ "228", "340" ], [ "196", "195" ], [ "36", "78" ], [ "540", "387" ] ] ] }, { "name": "Var227", "index": "47", "type": "nominal", "distinct": "7", "missing": "0", "distr": [ [ "0", "1", "2", "3", "4", "5", "6" ], [ [ "36", "44" ], [ "66", "81" ], [ "708", "648" ], [ "119", "138" ], [ "55", "65" ], [ "1", "2" ], [ "15", "22" ] ] ] }, { "name": "Var229", "index": "48", "type": "nominal", "distinct": "5", "missing": "0", "distr": [ [ "0", "1", "2", "3", "4" ], [ [ "234", "300" ], [ "185", "253" ], [ "1", "0" ], [ "2", "0" ], [ "578", "447" ] ] ] } ], "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 }